Tootfinder

This https://arxiv.org/abs/2410.03483 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

A Versatile Neural Network Configuration Space Planning and Control Strategy for Modular Soft Robot Arms
Modular soft robot arms (MSRAs) are composed of multiple modules connected in a sequence, and they can bend at different angles in various directions. This capability allows MSRAs to perform more intricate tasks than single-module robots. However, the modular structure also induces challenges in accurate planning and control. Nonlinearity and hysteresis complicate the physical model, while the modular structure and increased DOFs further lead to cumulative errors along the sequence. To address …

Dynamic Chunking for End-to-End Hierarchical Sequence Modeling
Sukjun Hwang, Brandon Wang, Albert Gu
https://arxiv.org/abs/2507.07955 https://arxiv.org/pdf/2507.07955 https://arxiv.org/html/2507.07955
arXiv:2507.07955v1 Announce Type: new
Abstract: Despite incredible progress in language models (LMs) in recent years, largely resulting from moving away from specialized models designed for specific tasks to general models based on powerful architectures (e.g. the Transformer) that learn everything from raw data, pre-processing steps such as tokenization remain a barrier to true end-to-end foundation models. We introduce a collection of new techniques that enable a dynamic chunking mechanism which automatically learns content -- and context -- dependent segmentation strategies learned jointly with the rest of the model. Incorporating this into an explicit hierarchical network (H-Net) allows replacing the (implicitly hierarchical) tokenization-LM-detokenization pipeline with a single model learned fully end-to-end. When compute- and data- matched, an H-Net with one stage of hierarchy operating at the byte level outperforms a strong Transformer language model operating over BPE tokens. Iterating the hierarchy to multiple stages further increases its performance by modeling multiple levels of abstraction, demonstrating significantly better scaling with data and matching a token-based Transformer of twice its size. H-Nets pretrained on English show significantly increased character-level robustness, and qualitatively learn meaningful data-dependent chunking strategies without any heuristics or explicit supervision. Finally, the H-Net's improvement over tokenized pipelines is further increased in languages and modalities with weaker tokenization heuristics, such as Chinese and code, or DNA sequences (nearly 4x improvement in data efficiency over baselines), showing the potential of true end-to-end models that learn and scale better from unprocessed data.
toXiv_bot_toot

Structured State Space Model Dynamics and Parametrization for Spiking Neural Networks
Maxime Fabre, Lyubov Dudchenko, Emre Neftci
https://arxiv.org/abs/2506.06374

Structured State Space Model Dynamics and Parametrization for Spiking Neural Networks
Multi-state spiking neurons such as the adaptive leaky integrate-and-fire (AdLIF) neuron offer compelling alternatives to conventional deep learning models thanks to their sparse binary activations, second-order nonlinear recurrent dynamics, and efficient hardware realizations. However, such internal dynamics can cause instabilities during inference and training, often limiting performance and scalability. Meanwhile, state space models (SSMs) excel in long sequence processing using linear state…

This https://arxiv.org/abs/2502.16626 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_…

Hyper-active repeating fast radio bursts from rotation modulated starquakes on magnetars
The non-detection of periodicity related to rotation challenges magnetar models for fast radio bursts (FRBs) with FRB emission from close to the magnetar surface. Moreover, a bimodal distribution of the burst waiting times is widely observed in hyper-active FRBs, a significant deviation from the exponential distribution expected from stationary Poisson processes. By combining the epidemic-type aftershock sequence (ETAS) earthquake model and the rotating vector model (RVM) involving the rotation…

This https://arxiv.org/abs/2412.07911 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIT_…

Turbo Receiver Design with Joint Detection and Demapping for Coded Differential PSK in Bursty Impulsive Noise Channels
It has been recognized that the impulsive noise (IN) generated by power devices poses significant challenges to wireless receivers. In this paper, we comprehensively assess the achievable information rate (AIR) for the well-established Markov-Middleton IN model with a phase-shift keying (PSK) input sequence across various channel conditions, including matched and mismatched decoding scenarios. Upon determining information-theoretic bounds, we propose an optimal turbo-DPSK-IN receiver design bas…

WhisQ: Cross-Modal Representation Learning for Text-to-Music MOS Prediction
Jakaria Islam Emon, Kazi Tamanna Alam, Md. Abu Salek
https://arxiv.org/abs/2506.05899

WhisQ: Cross-Modal Representation Learning for Text-to-Music MOS Prediction
Mean Opinion Score (MOS) prediction for text to music systems requires evaluating both overall musical quality and text prompt alignment. This paper introduces WhisQ, a multimodal architecture that addresses this dual-assessment challenge through sequence level co-attention and optimal transport regularization. WhisQ employs the Whisper Base pretrained model for temporal audio encoding and Qwen 3, a 0.6B Small Language Model (SLM), for text encoding, with both maintaining sequence structure for…

This https://arxiv.org/abs/2409.10283 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

ASMA: An Adaptive Safety Margin Algorithm for Vision-Language Drone Navigation via Scene-Aware Control Barrier Functions
In the rapidly evolving field of vision-language navigation (VLN), ensuring safety for physical agents remains an open challenge. For a human-in-the-loop language-operated drone to navigate safely, it must understand natural language commands, perceive the environment, and simultaneously avoid hazards in real time. Control Barrier Functions (CBFs) are formal methods that enforce safe operating conditions. Model Predictive Control (MPC) is an optimization framework that plans a sequence of futur…

HITSZ's End-To-End Speech Translation Systems Combining Sequence-to-Sequence Auto Speech Recognition Model and Indic Large Language Model for IWSLT 2025 in Indic Track
Xuchen Wei, Yangxin Wu, Yaoyin Zhang, Henglyu Liu, Kehai Chen, Xuefeng Bai, Min Zhang
https://arxiv.org/abs/2507.19616

HITSZ's End-To-End Speech Translation Systems Combining Sequence-to-Sequence Auto Speech Recognition Model and Indic Large Language Model for IWSLT 2025 in Indic Track
This paper presents HITSZ's submission for the IWSLT 2025 Indic track, focusing on speech-to-text translation (ST) for English-to-Indic and Indic-to-English language pairs. To enhance translation quality in this low-resource scenario, we propose an end-to-end system integrating the pre-trained Whisper automated speech recognition (ASR) model with Krutrim, an Indic-specialized large language model (LLM). Experimental results demonstrate that our end-to-end system achieved average BLEU scores of …

Nonstationary Distribution Estimation via Wasserstein Probability Flows
Edward J. Anderson, Dominic S. T. Keehan
https://arxiv.org/abs/2507.05893 https://

Nonstationary Distribution Estimation via Wasserstein Probability Flows
We study the problem of estimating a sequence of evolving probability distributions from historical data, where the underlying distribution changes over time in a nonstationary and nonparametric manner. To capture gradual changes, we introduce a model that penalises large deviations between consecutive distributions using the Wasserstein distance. This leads to a method in which we estimate the underlying series of distributions by maximizing the log-likelihood of the observations with a penalt…

Fibonacci Numbers and Model-Complete Axiomatization of Presburger Arithmetic Expanded with a Beatty Sequence
Mohsen Khani, Ali N. Valizadeh, Afshin Zarei
https://arxiv.org/abs/2508.02303

Fibonacci Numbers and Model-Complete Axiomatization of Presburger Arithmetic Expanded with a Beatty Sequence
We introduce a recursive theory that completely axiomatizes the structure $\langle \mathbb{Z},<, +,f,0\rangle$ where $f$ is the function that maps each $x$ to the integer part of $φx $, with $φ$ the golden ratio. We prove that our axiomatization is model-complete in a language expanded with a function which we call the Fibonacci floor function, as defined in the introduction. We also present an improvement of the axiomatization of the structure $\langle \mathbb{Z}, +, f,0\rangle$ already stud…

Greedy Dynamic Matching
Nick Arnosti, Felipe Simon
https://arxiv.org/abs/2507.04551 https://arxiv.org/pdf/2507.04551

Greedy Dynamic Matching
We study a foundational model of dynamic matching market with abandonment. This model has been studied by Collina et al (2020) and Aouad and Saritac (2022), and many other papers have considered special cases. We compare the performance of greedy policies -- which identify a set of "acceptable" matches up front, and perform these matches as soon as possible -- to that of an omniscient benchmark which knows the full arrival and departure sequence. We use a novel family of linear programs ($LP^…

Generating Long Semantic IDs in Parallel for Recommendation
Yupeng Hou, Jiacheng Li, Ashley Shin, Jinsung Jeon, Abhishek Santhanam, Wei Shao, Kaveh Hassani, Ning Yao, Julian McAuley
https://arxiv.org/abs/2506.05781

Generating Long Semantic IDs in Parallel for Recommendation
Semantic ID-based recommendation models tokenize each item into a small number of discrete tokens that preserve specific semantics, leading to better performance, scalability, and memory efficiency. While recent models adopt a generative approach, they often suffer from inefficient inference due to the reliance on resource-intensive beam search and multiple forward passes through the neural sequence model. As a result, the length of semantic IDs is typically restricted (e.g. to just 4 tokens), …

MCeT: Behavioral Model Correctness Evaluation using Large Language Models
Khaled Ahmed, Jialing Song, Boqi Chen, Ou Wei, Bingzhou Zheng
https://arxiv.org/abs/2508.00630 https://…

MCeT: Behavioral Model Correctness Evaluation using Large Language Models
Behavioral model diagrams, e.g., sequence diagrams, are an essential form of documentation that are typically designed by system engineers from requirements documentation, either fully manually or assisted by design tools. With the growing use of Large Language Models (LLM) as AI modeling assistants, more automation will be involved in generating diagrams. This necessitates the advancement of automatic model correctness evaluation tools. Such a tool can be used to evaluate both manually and AI …

Omega-regular Verification and Control for Distributional Specifications in MDPs
S. Akshay (Dept of CSE, Indian Institute of Technology Bombay), Ouldouz Neysari (Singapore Management University, University of Tehran), {\DJ}or{\dj}e \v{Z}ikeli\'c (Singapore Management University)
https://arxiv.org/abs/2507.04286

Omega-regular Verification and Control for Distributional Specifications in MDPs
A classical approach to studying Markov decision processes (MDPs) is to view them as state transformers. However, MDPs can also be viewed as distribution transformers, where an MDP under a strategy generates a sequence of probability distributions over MDP states. This view arises in several applications, even as the probabilistic model checking problem becomes much harder compared to the classical state transformer counterpart. It is known that even distributional reachability and safety probl…

Elementary Steps of Energy Conversion in Strongly Correlated Systems: Beyond Single Quasiparticles and Rigid Bands
V. Moshnyaga, Ch. Jooss P. E. Bl\"ochl, V. Bruchmann-Bamberg, A. Dehning, L. Allen-Rump, C. Hausmann, M. Kr\"uger, A. Rathnakaran, S. Rajpurohit, D. Steil, C. Flathmann, J. Hoffmann, M. Seibt, C. Volkert
https://

Elementary Steps of Energy Conversion in Strongly Correlated Systems: Beyond Single Quasiparticles and Rigid Bands
Energy conversion in materials can be considered as a sequence of elementary steps initiated by a primary excitation. While these steps are quite well understood in classical semiconductors in terms of quasiparticle (QP) excitations and interactions, their understanding in strongly correlated materials is still elusive. Here, we review the progress which has been achieved over recent years by studies of manganite perovskite oxides as a model system for materials with strong correlations. They s…

⛓️‍💥 Broken Tokens? Your Language Model can Secretly Handle Non-Canonical Tokenizations
#ai #llm

Broken Tokens? Your Language Model can Secretly Handle Non-Canonical Tokenizations
Modern tokenizers employ deterministic algorithms to map text into a single "canonical" token sequence, yet the same string can be encoded as many non-canonical tokenizations using the tokenizer vocabulary. In this work, we investigate the robustness of LMs to text encoded with non-canonical tokenizations entirely unseen during training. Surprisingly, when evaluated across 20 benchmarks, we find that instruction-tuned models retain up to 93.4% of their original performance when given a randomly…

Probing the statistics of sequence-dependent DNA conformations in solution using SAXS
Heidar J. Koning, Anuradha Pullakhandam, Andrew E. Whitten, Charles S. Bond, Michel Peyrard
https://arxiv.org/abs/2508.04358

Probing the statistics of sequence-dependent DNA conformations in solution using SAXS
SAXS studies of four 60 base-pair DNA duplexes with sequences closely related to part of the GAGE6 (G-antigen 6) promoter have been performed to study the role of DNA conformations in solution and their potential relationship to DNA-protein binding. We show that the SAXS data can be analysed using a simple polymer model which nevertheless quantitatively describes the average persistence length and torsional rigidity of the DNA double helix to determine the statistical distribution o…

First Contact: Data-driven Friction-Stir Process Control
James Koch, Ethan King, WoongJo Choi, Megan Ebers, David Garcia, Ken Ross, Keerti Kappagantula
https://arxiv.org/abs/2507.03177

First Contact: Data-driven Friction-Stir Process Control
This study validates the use of Neural Lumped Parameter Differential Equations for open-loop setpoint control of the plunge sequence in Friction Stir Processing (FSP). The approach integrates a data-driven framework with classical heat transfer techniques to predict tool temperatures, informing control strategies. By utilizing a trained Neural Lumped Parameter Differential Equation model, we translate theoretical predictions into practical set-point control, facilitating rapid attainment of des…

Input-Sensitive Reconfiguration of Sliding Cubes
Hugo Akitaya, Matias Korman, Frederick Stock
https://arxiv.org/abs/2507.04170 https://

Input-Sensitive Reconfiguration of Sliding Cubes
A configuration of $n$ unit-cube-shaped \textit{modules} (or \textit{robots}) is a lattice-aligned placement of the $n$ modules so that their union is face-connected. The reconfiguration problem aims at finding a sequence of moves that reconfigures the modules from one given configuration to another. The sliding cube model (in which modules are allowed to slide over the face or edge of neighboring modules) is one of the most studied theoretical models for modular robots. In the sliding cubes …

TrinityDNA: A Bio-Inspired Foundational Model for Efficient Long-Sequence DNA Modeling
Qirong Yang, Yucheng Guo, Zicheng Liu, Yujie Yang, Qijin Yin, Siyuan Li, Shaomin Ji, Linlin Chao, Xiaoming Zhang, Stan Z. Li
https://arxiv.org/abs/2507.19229

TrinityDNA: A Bio-Inspired Foundational Model for Efficient Long-Sequence DNA Modeling
The modeling of genomic sequences presents unique challenges due to their length and structural complexity. Traditional sequence models struggle to capture long-range dependencies and biological features inherent in DNA. In this work, we propose TrinityDNA, a novel DNA foundational model designed to address these challenges. The model integrates biologically informed components, including Groove Fusion for capturing DNA's structural features and Gated Reverse Complement (GRC) to handle the inhe…

hqQUBO: A Hybrid-querying Quantum Optimization Model Validated with 16-qubits on an Ion Trap Quantum Computer for Life Science Applications
Rong Chen, Quan-Xin Mei, Wen-Ding Zhao, Lin Yao, Hao-Xiang Yang, Shun-Yao Zhang, Jiao Chen, Hong-Lin Li
https://arxiv.org/abs/2506.01559

hqQUBO: A Hybrid-querying Quantum Optimization Model Validated with 16-qubits on an Ion Trap Quantum Computer for Life Science Applications
AlphaFold has achieved groundbreaking advancements in protein structure prediction, exerting profound influence across biology, medicine, and drug discovery. However, its reliance on multiple sequence alignment (MSA) is inherently time-consuming due to the NP-hard nature of constructing MSAs. Quantum computing emerges as a promising alternative, compared to classical computers, offering the potentials for exponential speedup and improved accuracy on such complex optimization challenges. This wo…

This https://arxiv.org/abs/2409.03833 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_grqc_…

Sequence modeling of higher-order wave modes of binary black hole mergers
Higher-order gravitational wave modes from quasi-circular, spinning, non-precessing binary black hole mergers encode key information about these systems' nonlinear dynamics. We model these waveforms using transformer architectures, targeting the evolution from late inspiral through ringdown. Our data is derived from the \texttt{NRHybSur3dq8} surrogate model, which includes spherical harmonic modes up to $\ell \leq 4$ (excluding $(4,0)$, $(4,\pm1)$ and including $(5,5)$ modes). These waveforms s…

This https://arxiv.org/abs/2505.24293 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Large Language Models are Locally Linear Mappings
We demonstrate that the inference operations of several open-weight large language models (LLMs) can be mapped to an exactly equivalent linear system for an input sequence without modifying the model weights or altering output predictions. Extending techniques from image diffusion models that exhibit local or piecewise linearity, we strategically alter the gradient computation with respect to a given input sequence for a next-token prediction such that the Jacobian of the model nearly exactly r…

This https://arxiv.org/abs/2501.18626 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

The TIP of the Iceberg: Revealing a Hidden Class of Task-in-Prompt Adversarial Attacks on LLMs
We present a novel class of jailbreak adversarial attacks on LLMs, termed Task-in-Prompt (TIP) attacks. Our approach embeds sequence-to-sequence tasks (e.g., cipher decoding, riddles, code execution) into the model's prompt to indirectly generate prohibited inputs. To systematically assess the effectiveness of these attacks, we introduce the PHRYGE benchmark. We demonstrate that our techniques successfully circumvent safeguards in six state-of-the-art language models, including GPT-4o and LLaMA…

Testing parametric additive time-varying GARCH models
Niklas Ahlgren, Alexander Back, Timo Ter\"asvirta
https://arxiv.org/abs/2506.23821 https://

Testing parametric additive time-varying GARCH models
We develop misspecification tests for building additive time-varying (ATV-)GARCH models. In the model, the volatility equation of the GARCH model is augmented by a deterministic time-varying intercept modeled as a linear combination of logistic transition functions. The intercept is specified by a sequence of tests, moving from specific to general. The first test is the test of the standard stationary GARCH model against an ATV-GARCH model with one transition. The alternative model is unidentif…

Performance of the image persistence model for Euclid infrared detectors
B. Kubik, R. Barbier, G. Smadja, S. Ferriol, Y. Conseil, Y. Copin, W. Gillard, S. Dusini, K. Jahnke, E. Prieto, N. Auricchio, E. Balbi, A. Balestra, P. Battaglia, V. Capobianco, R. Chary, L. Corcione, F. Cogato, G. Delucchi, E. Franceschi, L. Gabarra, F. Gianotti, F. Grupp, E. Lentini, S. Ligori, E. Medinaceli, G. Morgante, K. Paterson, E. Romelli, L. Sauniere, M. Schirmer, C. Sirignano G. Testera, M. Trifoglio, A. Troja, L. Valenziano, M. Frailis, M. Scodeggio, J. -C. Barriere, M. Berthe, C. Bodendorf, A. Caillat, M. Carle, R. Casas, H. Cho, A. Costille, F. Ducret, B. Garilli, W. Holmes, F. Hormuth, A. Hornstrup, M. Jhabvala, R. Kohley, D. Le Mignant, P. B. Lilje, I. Lloro, C. Padilla, G. Polenta, J. -C. Salvignol, G. Seidel, B. Serra, A. Secroun, L. Stanco, R. Toledo-Moreo, S. Anselmi, E. Borsato, L. Caillat, C. Colodro-Conde, V. Conforti, J. E. Davies, A. Renzi, F. Dal Corso, S. Davini, A. Derosa, J. J. Diaz, S. Di Domizio, D. Di Ferdinando, R. Farinelli, A. G. Ferrari, F. Fornari, F. Giacomini, O. Krause, F. Laudisio, J. Macias-Perez, J. Marpaud, N. Mauri, R. da Silva, M. Niclas, F. Passalacqua, I. Risso, P. Lagier, A. N. Sorensen, P. Stassi, J. Steinwagner, M. Tenti, C. Thizy, S. Tosi, R. Travaglini, O. Tubio, C. Valieri, S. Ventura, C. Vescovi, J. Zoubian
#toXiv_bot_toot

AI Accelerators for Large Language Model In-ference: Architecture Analysis and Scaling Strategies
Amit Sharma
https://arxiv.org/abs/2506.00008 https://

AI Accelerators for Large Language Model In-ference: Architecture Analysis and Scaling Strategies
The rapid growth of large-language models (LLMs) is driving a new wave of specialized hardware for inference. This paper presents the first workload-centric, cross-architectural performance study of commercial AI accelerators, spanning GPU-based chips, hybrid packages, and wafer-scale engines. We compare memory hierarchies, compute fabrics, and on-chip interconnects, and observe up to 3.7x performance variation across architectures as batch size and sequence length change. Four scaling techniqu…

Guiding an Automatic Speech Recognition Decoder Using Large Language Models
Eyal Cohen (Technion - Israel Institute of Technology), Bhiksha Raj (Carnegie Mellon University), Joseph Keshet (Technion - Israel Institute of Technology)
https://arxiv.org/abs/2508.02228

Guiding an Automatic Speech Recognition Decoder Using Large Language Models
Automatic Speech Recognition (ASR) consists of an acoustic model (AM) and a language model (LM). The AM estimates the probability of an acoustic signal based on a sequence of linguistic units, typically phones, characters, or tokens, while the LM assesses the likelihood of a specific sequence of words or tokens. Although Large Language Models (LLMs) have demonstrated significant potential across various tasks, integrating them into ASR remains an open challenge. By decomposing the maximum a pos…

Counting Distinct Square Substrings in Sublinear Time
Panagiotis Charalampopoulos, Manal Mohamed, Jakub Radoszewski, Wojciech Rytter, Tomasz Wale\'n, Wiktor Zuba
https://arxiv.org/abs/2508.03930

Counting Distinct Square Substrings in Sublinear Time
We show that the number of distinct squares in a packed string of length $n$ over an alphabet of size $σ$ can be computed in $O(n/\log_σn)$ time in the word-RAM model. This paper is the first to introduce a sublinear-time algorithm for counting squares in the packed setting. The packed representation of a string of length $n$ over an alphabet of size $σ$ is given as a sequence of $O(n/\log_σn)$ machine words in the word-RAM model (a machine word consists of $ω\ge \log_2 n$ bits). Previousl…

Monitoring Robustness and Individual Fairness
Ashutosh Gupta, Thomas A. Henzinger, Konstantin Kueffner, Kaushik Mallik, David Pape
https://arxiv.org/abs/2506.00496

Monitoring Robustness and Individual Fairness
Input-output robustness appears in various different forms in the literature, such as robustness of AI models to adversarial or semantic perturbations and individual fairness of AI models that make decisions about humans. We propose runtime monitoring of input-output robustness of deployed, black-box AI models, where the goal is to design monitors that would observe one long execution sequence of the model, and would raise an alarm whenever it is detected that two similar inputs from the past…

In our #ISE2025 lecture last Wednesday, we learned how in n-gram language models via Markov assumption and maximum likelihood estimation we can predict the probability of the occurrence of a word given a specific context (i.e. n words previous in the sequence of words).
#NLP

Bridging Expressivity and Scalability with Adaptive Unitary SSMs
Arjun Karuvally, Franz Nowak, Anderson T. Keller, Carmen Amo Alonso, Terrence J. Sejnowski, Hava T. Siegelmann
https://arxiv.org/abs/2507.05238

Bridging Expressivity and Scalability with Adaptive Unitary SSMs
Recent work has revealed that state space models (SSMs), while efficient for long-sequence processing, are fundamentally limited in their ability to represent formal languages particularly due to time-invariant and real-valued recurrence structures. In this work, we draw inspiration from adaptive and structured dynamics observed in biological neural systems and introduce the Adaptive Unitary State Space Model (AUSSM)- a novel class of SSMs that leverages skew-symmetric, input-dependent recurren…

Sequence-Only Prediction of Binding Affinity Changes: A Robust and Interpretable Model for Antibody Engineering
Chen Liu, Mingchen Li, Yang Tan, Wenrui Gou, Guisheng Fan, Bingxin Zhou
https://arxiv.org/abs/2505.20301

Sequence-Only Prediction of Binding Affinity Changes: A Robust and Interpretable Model for Antibody Engineering
A pivotal area of research in antibody engineering is to find effective modifications that enhance antibody-antigen binding affinity. Traditional wet-lab experiments assess mutants in a costly and time-consuming manner. Emerging deep learning solutions offer an alternative by modeling antibody structures to predict binding affinity changes. However, they heavily depend on high-quality complex structures, which are frequently unavailable in practice. Therefore, we propose ProtAttBA, a deep learn…

Error estimates of linear decoupled structure-preserving incremental viscosity splitting methods for the Cahn--Hilliard--Navier--Stokes system
Baolin Kuang, Hongfei Fu, Xiaoli Li
https://arxiv.org/abs/2508.01141

Error estimates of linear decoupled structure-preserving incremental viscosity splitting methods for the Cahn--Hilliard--Navier--Stokes system
We propose first- and second-order time discretization schemes for the coupled Cahn--Hilliard--Navier--Stokes model, leveraging the incremental viscosity splitting (IVS) method. The schemes combine the scalar auxiliary variable method and the zero-energy-contribution approach, resulting in a linear, decoupled numerical framework. At each time step, they only require to solve a sequence of constant-coefficient equations, along with a linear equation with one unknown, making the algorithms comput…

Effect of Matter Accretion on Lithium Enhancement of Giants
Xuefeng Li, Jianrong Shi, Yan Li, Hongliang Yan, Jinghua Zhang, Fei Guo
https://arxiv.org/abs/2508.00405 https://

Effect of Matter Accretion on Lithium Enhancement of Giants
A subset of low-mass giants ($<2.2\,M_{\odot}$) exhibit anomalous lithium enhancement behavior, which is still an open topic. Given that more massive giants retain more surface lithium, increasing mass by accreting circumstellar matter could be a channel to enrich lithium. We evaluate this process in the current work. Using MESA, we construct a model of matter accretion, including mass loss, that evolves a star from the main sequence turnoff to the red giant branch tip. The mean accretion rate …

Gaussian Sequence Model: Sample Complexities of Testing, Estimation and LFHT
Zeyu Jia, Yury Polyanskiy
https://arxiv.org/abs/2507.16734 https://

Gaussian Sequence Model: Sample Complexities of Testing, Estimation and LFHT
We study the Gaussian sequence model, i.e. $X \sim N(\mathbfθ, I_\infty)$, where $\mathbfθ \in Γ\subset \ell_2$ is assumed to be convex and compact. We show that goodness-of-fit testing sample complexity is lower bounded by the square-root of the estimation complexity, whenever $Γ$ is orthosymmetric. We show that the lower bound is tight when $Γ$ is also quadratically convex, thus significantly extending validity of the testing-estimation relationship from [GP24]. Using similar methods, we…

Dispersion models on a circle: universal properties and asymptotic results
Jean-Fran\c{c}ois Marckert, Zo\'e Varin
https://arxiv.org/abs/2507.00737 htt…

Dispersion models on a circle: universal properties and asymptotic results
Consider a sequence of masses $m_0,m_1,...$ arriving uniformly at random at some points $u_0,u_1,...$ on the unit circle $\mathbb{R}/\mathbb{Z}$ (or on $\mathbb{Z}/n\mathbb{Z}$, in the discrete version). Upon arrival, each mass undergoes a relaxation phase during which it is dispersed, possibly also at random. This process can model many physical phenomena, such as the diffusion of liquid in a porous medium. In the discrete case, it can model parking (related to additive coalescence and hashing…

Geometry Meets Incentives: Sample-Efficient Incentivized Exploration with Linear Contexts
Benjamin Schiffer, Mark Sellke
https://arxiv.org/abs/2506.01685 h…

Geometry Meets Incentives: Sample-Efficient Incentivized Exploration with Linear Contexts
In the incentivized exploration model, a principal aims to explore and learn over time by interacting with a sequence of self-interested agents. It has been recently understood that the main challenge in designing incentive-compatible algorithms for this problem is to gather a moderate amount of initial data, after which one can obtain near-optimal regret via posterior sampling. With high-dimensional contexts, however, this \emph{initial exploration} phase requires exponential sample complexity…

Latent-X: An Atom-level Frontier Model for De Novo Protein Binder Design
Latent Labs Team, Alex Bridgland, Jonathan Crabb\'e, Henry Kenlay, Daniella Pretorius, Sebastian M. Schmon, Agrin Hilmkil, Rebecca Bartke-Croughan, Robin Rombach, Michael Flashman, Tomas Matteson, Simon Mathis, Alexander W. R. Nelson, David Yuan, Annette Obika, Simon A. A. Kohl
https:/…

Latent-X: An Atom-level Frontier Model for De Novo Protein Binder Design
Traditional drug discovery relies on rounds of screening millions of candidate molecules with low success rates, making drug discovery time and resource intensive. To overcome this screening bottleneck, we introduce Latent-X, an all-atom protein design model that enables a new paradigm of precision AI design. Given a target protein epitope, Latent-X jointly generates the all atom structure and sequence of the protein binder and target, directly modelling the non-covalent interactions essential …

DeSamba: Decoupled Spectral Adaptive Framework for 3D Multi-Sequence MRI Lesion Classification
Dezhen Wang, Sheng Miao, Rongxin Chai, Jiufa Cui
https://arxiv.org/abs/2507.15487

DeSamba: Decoupled Spectral Adaptive Framework for 3D Multi-Sequence MRI Lesion Classification
Magnetic Resonance Imaging (MRI) sequences provide rich spatial and frequency domain information, which is crucial for accurate lesion classification in medical imaging. However, effectively integrating multi-sequence MRI data for robust 3D lesion classification remains a challenge. In this paper, we propose DeSamba (Decoupled Spectral Adaptive Network and Mamba-Based Model), a novel framework designed to extract decoupled representations and adaptively fuse spatial and spectral features for le…

Persuasion in the Long Run: When history matters
Hyeonggyun Ko
https://arxiv.org/abs/2508.01662 https://arxiv.org/pdf/2508.01662

Persuasion in the Long Run: When history matters
We study a long-run persuasion problem where a long-lived Sender repeatedly interacts with a sequence of short-lived Receivers who may adopt a misspecified model for belief updating. The Sender commits to a stationary information structure, but suspicious Receivers compare it to an uninformative alternative and may switch based on the Bayes factor rule. We characterize when the one-shot Bayesian Persuasion-optimal (BP-optimal) structure remains optimal in the long run despite this switching ris…

An nth-cousin mating model and the n-anacci numbers
Elisa Heinrich Mora, Noah A. Rosenberg
https://arxiv.org/abs/2506.16577 https://a…

An nth-cousin mating model and the n-anacci numbers
In seeking to understand the size of inbred pedigrees, J. Lachance (J. Theor. Biol. 261, 238-247, 2009) studied a population model in which, for a fixed value of $n$, each mating occurs between $n$th cousins. We explain a connection between the second-cousin case of the model ($n=2$) and the Fibonacci sequence, and more generally, between the $n$th-cousin case and the $n$-anacci sequence $(n \geq 2)$. For a model with $n$th-cousin mating $(n \geq 1)$, we obtain the generating function describin…

StruMamba3D: Exploring Structural Mamba for Self-supervised Point Cloud Representation Learning
Chuxin Wang, Yixin Zha, Wenfei Yang, Tianzhu Zhang
https://arxiv.org/abs/2506.21541

StruMamba3D: Exploring Structural Mamba for Self-supervised Point Cloud Representation Learning
Recently, Mamba-based methods have demonstrated impressive performance in point cloud representation learning by leveraging State Space Model (SSM) with the efficient context modeling ability and linear complexity. However, these methods still face two key issues that limit the potential of SSM: Destroying the adjacency of 3D points during SSM processing and failing to retain long-sequence memory as the input length increases in downstream tasks. To address these issues, we propose StruMamba3D,…

SPACE: Your Genomic Profile Predictor is a Powerful DNA Foundation Model
Zhao Yang, Jiwei Zhu, Bing Su
https://arxiv.org/abs/2506.01833 https://

SPACE: Your Genomic Profile Predictor is a Powerful DNA Foundation Model
Inspired by the success of unsupervised pre-training paradigms, researchers have applied these approaches to DNA pre-training. However, we argue that these approaches alone yield suboptimal results because pure DNA sequences lack sufficient information, since their functions are regulated by genomic profiles like chromatin accessibility. Here, we demonstrate that supervised training for genomic profile prediction serves as a more effective alternative to pure sequence pre-training. Furthermore,…

The Kuramoto model on the Sierpinski Gasket
Georgi S. Medvedev, Matthew S. Mizuhara
https://arxiv.org/abs/2506.12940 https://arxiv.or…

The Kuramoto model on the Sierpinski Gasket
We study the Kuramoto model (KM) of coupled phase oscillators on graphs approximating the Sierpinski gasket (SG). As the size of the graph tends to infinity, the limit points of the sequence of stable equilibria in the KM correspond to the minima of the Dirichlet energy, i.e., to harmonic maps from the SG to the circle. We provide a complete description of the stable equilibria of the continuum limit of the KM on graphs approximating the SG, under both Dirichlet and free boundary conditions. We…

Reducing Quantum Circuit Synthesis to #SAT
Dekel Zak, Jingyi Mei, Jean-Marie Lagniez, Alfons Laarman
https://arxiv.org/abs/2508.00416

Reducing Quantum Circuit Synthesis to #SAT
Quantum circuit synthesis is the task of decomposing a given quantum operator into a sequence of elementary quantum gates. Since the finite target gate set cannot exactly implement any given operator, approximation is often necessary. Model counting, or #SAT, has recently been demonstrated as a promising new approach for tackling core problems in quantum circuit analysis. In this work, we show for the first time that the universal quantum circuit synthesis problem can be reduced to maximum mode…

Dissociating model architectures from inference computations
Noor Sajid, Johan Medrano
https://arxiv.org/abs/2507.15776 https://arxiv…

Dissociating model architectures from inference computations
Parr et al., 2025 examines how auto-regressive and deep temporal models differ in their treatment of non-Markovian sequence modelling. Building on this, we highlight the need for dissociating model architectures, i.e., how the predictive distribution factorises, from the computations invoked at inference. We demonstrate that deep temporal computations are mimicked by autoregressive models by structuring context access during iterative inference. Using a transformer trained on next-token predict…

This https://arxiv.org/abs/2503.14328 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

Risk-Sensitive Model Predictive Control for Interaction-Aware Planning -- A Sequential Convexification Algorithm
This paper considers risk-sensitive model predictive control for stochastic systems with a decision-dependent distribution. This class of systems is commonly found in human-robot interaction scenarios. We derive computationally tractable convex upper bounds to both the objective function, and to frequently used penalty terms for collision avoidance, allowing us to efficiently solve the generally nonconvex optimal control problem as a sequence of convex problems. Simulations of a robot navigatin…

Hybrid Tokenization Strategy for DNA Language Model using Byte Pair Encoding and K-MER Methods
Ganesh Sapkota, Md Hasibur Rahman
https://arxiv.org/abs/2507.18570 https://…

Hybrid Tokenization Strategy for DNA Language Model using Byte Pair Encoding and K-MER Methods
This paper presents a novel hybrid tokenization strategy that enhances the performance of DNA Language Models (DLMs) by combining 6-mer tokenization with Byte Pair Encoding (BPE-600). Traditional k-mer tokenization is effective at capturing local DNA sequence structures but often faces challenges, including uneven token distribution and a limited understanding of global sequence context. To address these limitations, we propose merging unique 6mer tokens with optimally selected BPE tokens gener…

Integrating LLM-Derived Multi-Semantic Intent into Graph Model for Session-based Recommendation
Shuo Zhang, Xiao Li, Jiayi Wu, Fan Yang, Xiang Li, Ming Gao
https://arxiv.org/abs/2507.20147

Integrating LLM-Derived Multi-Semantic Intent into Graph Model for Session-based Recommendation
Session-based recommendation (SBR) is mainly based on anonymous user interaction sequences to recommend the items that the next user is most likely to click. Currently, the most popular and high-performing SBR methods primarily leverage graph neural networks (GNNs), which model session sequences as graph-structured data to effectively capture user intent. However, most GNNs-based SBR methods primarily focus on modeling the ID sequence information of session sequences, while neglecting the rich …

A Minimum Distance Estimator Approach for Misspecified Ergodic Processes
Jaroslav I. Borodavka, Sebastian Krumscheid, Grigorios A. Pavliotis
https://arxiv.org/abs/2506.12432

A Minimum Distance Estimator Approach for Misspecified Ergodic Processes
We propose a minimum distance estimator (MDE) for parameter identification in misspecified models characterized by a sequence of ergodic stochastic processes that converge weakly to the model of interest. The data is generated by the sequence of processes, and we are interested in inferring parameters for the limiting processes. We define a general statistical setting for parameter estimation under such model misspecification and prove the robustness of the MDE. Furthermore, we prove the asympt…

Beat and Downbeat Tracking in Performance MIDI Using an End-to-End Transformer Architecture
Sebastian Murgul, Michael Heizmann
https://arxiv.org/abs/2507.00466

Beat and Downbeat Tracking in Performance MIDI Using an End-to-End Transformer Architecture
Beat tracking in musical performance MIDI is a challenging and important task for notation-level music transcription and rhythmical analysis, yet existing methods primarily focus on audio-based approaches. This paper proposes an end-to-end transformer-based model for beat and downbeat tracking in performance MIDI, leveraging an encoder-decoder architecture for sequence-to-sequence translation of MIDI input to beat annotations. Our approach introduces novel data preprocessing techniques, includi…

eccDNAMamba: A Pre-Trained Model for Ultra-Long eccDNA Sequence Analysis
Zhenke Liu, Jien Li, Ziqi Zhang
https://arxiv.org/abs/2506.18940 https://

eccDNAMamba: A Pre-Trained Model for Ultra-Long eccDNA Sequence Analysis
Extrachromosomal circular DNA (eccDNA) plays key regulatory roles and contributes to oncogene overexpression in cancer through high-copy amplification and long-range interactions. Despite advances in modeling, no pre-trained models currently support full-length circular eccDNA for downstream analysis. Existing genomic models are either limited to single-nucleotide resolution or hindered by the inefficiency of the quadratic attention mechanism. Here, we introduce eccDNAMamba, the first bidirecti…

Pendulum Model of Spiking Neurons
Joy Bose
https://arxiv.org/abs/2507.22146 https://arxiv.org/pdf/2507.22146

Pendulum Model of Spiking Neurons
We propose a biologically inspired model of spiking neurons based on the dynamics of a damped, driven pendulum. Unlike traditional models such as the Leaky Integrate-and-Fire (LIF) neurons, the pendulum neuron incorporates second-order, nonlinear dynamics that naturally give rise to oscillatory behavior and phase-based spike encoding. This model captures richer temporal features and supports timing-sensitive computations critical for sequence processing and symbolic learning. We present an anal…

Hybrid Approach for Electricity Price Forecasting using AlexNet and LSTM
Bosubabu Sambana, Kotamsetty Geethika Devi, Bandi Rajeswara Reddy, Galeti Mohammad Hussain, Gownivalla Siddartha
https://arxiv.org/abs/2506.23504

Hybrid Approach for Electricity Price Forecasting using AlexNet and LSTM
The recent development of advanced machine learning methods for hybrid models has greatly addressed the need for the correct prediction of electrical prices. This method combines AlexNet and LSTM algorithms, which are used to introduce a new model with higher accuracy in price forecasting. Despite RNN and ANN being effective, they often fail to deal with forex time sequence data. The traditional methods do not accurately forecast the prices. These traditional methods only focus on demand and pr…

Transformers as Multi-task Learners: Decoupling Features in Hidden Markov Models
Yifan Hao, Chenlu Ye, Chi Han, Tong Zhang
https://arxiv.org/abs/2506.01919

Transformers as Multi-task Learners: Decoupling Features in Hidden Markov Models
Transformer based models have shown remarkable capabilities in sequence learning across a wide range of tasks, often performing well on specific task by leveraging input-output examples. Despite their empirical success, a comprehensive theoretical understanding of this phenomenon remains limited. In this work, we investigate the layerwise behavior of Transformers to uncover the mechanisms underlying their multi-task generalization ability. Taking explorations on a typical sequence model, i.e, H…

FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space
Black Forest Labs, Stephen Batifol, Andreas Blattmann, Frederic Boesel, Saksham Consul, Cyril Diagne, Tim Dockhorn, Jack English, Zion English, Patrick Esser, Sumith Kulal, Kyle Lacey, Yam Levi, Cheng Li, Dominik Lorenz, Jonas M\"uller, Dustin Podell, Robin Rombach, Harry Saini, Axel Sauer, Luke Smith

FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space
We present evaluation results for FLUX.1 Kontext, a generative flow matching model that unifies image generation and editing. The model generates novel output views by incorporating semantic context from text and image inputs. Using a simple sequence concatenation approach, FLUX.1 Kontext handles both local editing and generative in-context tasks within a single unified architecture. Compared to current editing models that exhibit degradation in character consistency and stability across multip…

Critical Metallicity of Cool Supergiant Formation. II. Physical Origin
Po-Sheng Ou, Ke-Jung Chen
https://arxiv.org/abs/2506.01753 https://

Critical Metallicity of Cool Supergiant Formation. II. Physical Origin
This study investigates the physical origin of the critical metallicity ($Z_{\rm c}\sim 0.001$) required for the formation of cool supergiants, as revealed by stellar evolution models. Using model grids that vary in mass, metallicity, opacity, and nuclear reaction rates, we identify a threshold terminal-age main-sequence (TAMS) radius ($R_{\rm T}$) that determines whether a star of a given mass can evolve into the red supergiant (RSG) phase. Through stellar models and homology relations, we sho…

Topological crystals and soliton lattices in a Gross-Neveu model with Hilbert-space fragmentation
Sergio Cerezo-Roquebr\'un, Simon Hands, Alejandro Bermudez
https://arxiv.org/abs/2506.18675

Topological crystals and soliton lattices in a Gross-Neveu model with Hilbert-space fragmentation
We explore the finite-density phase diagram of the single-flavour Gross-Neveu-Wilson (GNW) model using matrix product state (MPS) simulations. At zero temperature and along the symmetry line of the phase diagram, we find a sequence of inhomogeneous ground states that arise through a real-space version of the mechanism of Hilbert-space fragmentation. For weak interactions, doping the symmetry-protected topological (SPT) phase of the GNW model leads to localized charges or holes at periodic arran…

Inverse scattering transform via affine map: applications to high-speed nonlinear optical communications
Ilia Kuk, Ildar R. Gabitov
https://arxiv.org/abs/2507.20470 https://

Inverse scattering transform via affine map: applications to high-speed nonlinear optical communications
This work present an affine map approximation for solving the inverse scattering problem related to the nonlinear Schrödinger model of signal propagation in high-speed coherent optical communication. Numerical simulations indicate that accurate recovery of the transmitted bit sequence can be achieved using only the continuous part of the Lax spectrum at the fiber output, thereby allowing the discrete (soliton) spectrum to be disregarded. We observed that the numerically evaluated rank of the r…

This https://arxiv.org/abs/2501.00256 has been replaced.
initial toot: https://mastoxiv.page/@arX…

Rapid, High-resolution and Distortion-free $R_{2}^{*}$ Mapping of Fetal Brain using Multi-echo Radial FLASH and Model-based Reconstruction
Purpose: To develop a rapid, high-resolution and distortion-free technique for simultaneous water-fat separation, $R_{2}^{*}$ and $B_{0}$ mapping of the fetal brain at 3T. Methods: A 2D multi-echo radial FLASH sequence with blip gradients is adapted for data acquisition during maternal free breathing. A calibrationless model-based reconstruction with sparsity constraints is developed to jointly estimate water, fat, $R_{2}^{*}$ and $B_{0}$ field maps directly from k-space. This approach was va…

Aptamer-protein interaction prediction model based on transformer
Zhichao Yan, Yue Kang, Buyong Ma
https://arxiv.org/abs/2506.16084 https://

Aptamer-protein interaction prediction model based on transformer
Aptamers are single-stranded DNA/RNAs or short peptides with unique tertiary structures that selectively bind to specific targets. They have great potential in the detection and medical fields. Here, we present SelfTrans-Ensemble, a deep learning model that integrates sequence information models and structural information models to extract multi-scale features for predicting aptamer-protein interactions (APIs). The model employs two pre-trained models, ProtBert and RNA-FM, to encode protein and…

Alice and the Caterpillar: A more descriptive null model for assessing data mining results
Giulia Preti, Gianmarco De Francisci Morales, Matteo Riondato
https://arxiv.org/abs/2506.09764

Alice and the Caterpillar: A more descriptive null model for assessing data mining results
We introduce novel null models for assessing the results obtained from observed binary transactional and sequence datasets, using statistical hypothesis testing. Our null models maintain more properties of the observed dataset than existing ones. Specifically, they preserve the Bipartite Joint Degree Matrix of the bipartite (multi-)graph corresponding to the dataset, which ensures that the number of caterpillars, i.e., paths of length three, is preserved, in addition to other properties conside…

Role of bubble positioning in force induced melting of DNA
Bidisha Mukherjee, Amit Raj Singh, Garima Mishra
https://arxiv.org/abs/2506.18821 https://

Role of bubble positioning in force induced melting of DNA
We investigate the role of bubble positioning in the force-induced melting of double-stranded DNA using two distinct approaches: Brownian Dynamics simulations and the Gaussian Network Model. We isolate the effect of bubble positioning by using DNA molecules with 50% AT - 50% GC base-pair composition which ensures constant enthalpy. Our results reveal that it is not just the sequence itself, but its specific arrangement that influences DNA stability. We examine two types of DNA sequences contain…

General Proximal Quasi-Newton Methods based on model functions for nonsmooth nonconvex problems
Xiaoxi Jia, Peter Ochs
https://arxiv.org/abs/2507.18363 https://

General Proximal Quasi-Newton Methods based on model functions for nonsmooth nonconvex problems
In this manuscript, we propose a general proximal quasi-Newton method tailored for nonconvex and nonsmooth optimization problems, where we do not require the sequence of the variable metric (or Hessian approximation) to be uniformly bounded as a prerequisite, instead, the variable metric is updated by a continuous matrix generator. From the respective of the algorithm, the objective function is approximated by the so-called local model function and subproblems aim to exploit the proximal point(…

STEP Planner: Constructing cross-hierarchical subgoal tree as an embodied long-horizon task planner
Zhou Tianxing, Wang Zhirui, Ao Haojia, Chen Guangyan, Xing Boyang, Cheng Jingwen, Yang Yi, Yue Yufeng
https://arxiv.org/abs/2506.21030

STEP Planner: Constructing cross-hierarchical subgoal tree as an embodied long-horizon task planner
The ability to perform reliable long-horizon task planning is crucial for deploying robots in real-world environments. However, directly employing Large Language Models (LLMs) as action sequence generators often results in low success rates due to their limited reasoning ability for long-horizon embodied tasks. In the STEP framework, we construct a subgoal tree through a pair of closed-loop models: a subgoal decomposition model and a leaf node termination model. Within this framework, we develo…

Captain Cinema: Towards Short Movie Generation
Junfei Xiao, Ceyuan Yang, Lvmin Zhang, Shengqu Cai, Yang Zhao, Yuwei Guo, Gordon Wetzstein, Maneesh Agrawala, Alan Yuille, Lu Jiang
https://arxiv.org/abs/2507.18634

Captain Cinema: Towards Short Movie Generation
We present Captain Cinema, a generation framework for short movie generation. Given a detailed textual description of a movie storyline, our approach firstly generates a sequence of keyframes that outline the entire narrative, which ensures long-range coherence in both the storyline and visual appearance (e.g., scenes and characters). We refer to this step as top-down keyframe planning. These keyframes then serve as conditioning signals for a video synthesis model, which supports long context l…

This https://arxiv.org/abs/2504.10545 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

HSTU-BLaIR: Lightweight Contrastive Text Embedding for Generative Recommender
Recent advances in recommender systems have underscored the complementary strengths of generative modeling and pretrained language models. We propose HSTU-BLaIR, a hybrid framework that augments the Hierarchical Sequential Transduction Unit (HSTU)-based generative recommender with BLaIR, a lightweight contrastive text embedding model. This integration enriches item representations with semantic signals from textual metadata while preserving HSTU's powerful sequence modeling capabilities. We e…

Dark energy era with a resolution of Hubble tension in generalized entropic cosmology
Priyanka Adhikary, Sudipta Das, Sergei D. Odintsov, Tanmoy Paul
https://arxiv.org/abs/2507.15273

Dark energy era with a resolution of Hubble tension in generalized entropic cosmology
We propose a new dark energy (DE) model from four parameter generalized entropy function of apparent horizon in a spatially flat universe. Such kind of generalized entropy is able to generalize all the known entropies proposed so far, for suitable representations of the entropic parameters. It turns out that the scenario can describe the correct thermal history of the universe, with the sequence of matter and dark energy epochs. Comparing with the $Λ$CDM model, the proposed generalized entropi…

Misspecified Bayesianism
Pooya Molavi
https://arxiv.org/abs/2507.22775 https://arxiv.org/pdf/2507.22775

Misspecified Bayesianism
An agent is a misspecified Bayesian if she updates her belief using Bayes' rule given a subjective, possibly misspecified model of her signals. This paper shows that a belief sequence is consistent with misspecified Bayesianism if the prior contains a grain of the average posterior, i.e., is a mixture of the average posterior and another distribution. A partition-based variant of the grain condition is both necessary and sufficient. Under correct specification, the grain condition reduces to th…

Uncertainty-Aware Genomic Classification of Alzheimer's Disease: A Transformer-Based Ensemble Approach with Monte Carlo Dropout
Taeho Jo, Eun Hye Lee, Alzheimer's Disease Sequencing Project
https://arxiv.org/abs/2506.00662

Uncertainty-Aware Genomic Classification of Alzheimer's Disease: A Transformer-Based Ensemble Approach with Monte Carlo Dropout
INTRODUCTION: Alzheimer's disease (AD) is genetically complex, complicating robust classification from genomic data. METHODS: We developed a transformer-based ensemble model (TrUE-Net) using Monte Carlo Dropout for uncertainty estimation in AD classification from whole-genome sequencing (WGS). We combined a transformer that preserves single-nucleotide polymorphism (SNP) sequence structure with a concurrent random forest using flattened genotypes. An uncertainty threshold separated samples into …

Pimba: A Processing-in-Memory Acceleration for Post-Transformer Large Language Model Serving
Wonung Kim, Yubin Lee, Yoonsung Kim, Jinwoo Hwang, Seongryong Oh, Jiyong Jung, Aziz Huseynov, Woong Gyu Park, Chang Hyun Park, Divya Mahajan, Jongse Park
https://arxiv.org/abs/2507.10178

Pimba: A Processing-in-Memory Acceleration for Post-Transformer Large Language Model Serving
Transformers are the driving force behind today's Large Language Models (LLMs), serving as the foundation for their performance and versatility. Yet, their compute and memory costs grow with sequence length, posing scalability challenges for long-context inferencing. In response, the algorithm community is exploring alternative architectures, such as state space models (SSMs), linear attention, and recurrent neural networks (RNNs), which we refer to as post-transformers. This shift presents a k…

Speeding up thermalization and quantum state preparation through engineered quantum collisions
Sofia Sgroi, Salvatore Lorenzo, Luca Innocenti, Paolo A. Erdman, G. Massimo Palma, Mauro Paternostro
https://arxiv.org/abs/2506.20625

Speeding up thermalization and quantum state preparation through engineered quantum collisions
We realize fast thermalization and state preparation of a single mode cavity field using a collision model-like approach, where a sequence of qubits or three level system ancillae, sequentially interacting with the field, is engineered with a genetic algorithm approach. In contrast to optimal control techniques, there is no time-dependent system Hamiltonian control deployed and, in contrast to reservoir engineering, the engineered full system-environment dynamics is optimized, and the target is…

A Stackelberg Game of Demand Response from the Aggregator's Perspective
Seangleng Khe, Parin Chaipunya, Athikom Bangviwat
https://arxiv.org/abs/2507.12708

A Stackelberg Game of Demand Response from the Aggregator's Perspective
In this paper, we investigate on the modeling of demand response activities between the single aggregator and multiple participating consumers. The model incorporates the bilevel structure that naturally occurs in the information structure and decision sequence, where the aggregator assumes the role of a leader and the participating consumers play the role of followers. The proposed model is demonstrated to be effective in load control, helping the aggregator to meet the target reduction while …

A MILP-Based Solution to Multi-Agent Motion Planning and Collision Avoidance in Constrained Environments
Akshay Jaitly, Jack Cline, Siavash Farzan
https://arxiv.org/abs/2506.21982

A MILP-Based Solution to Multi-Agent Motion Planning and Collision Avoidance in Constrained Environments
We propose a mixed-integer linear program (MILP) for multi-agent motion planning that embeds Polytopic Action-based Motion Planning (PAAMP) into a sequence-then-solve pipeline. Region sequences confine each agent to adjacent convex polytopes, while a big-M hyperplane model enforces inter-agent separation. Collision constraints are applied only to agents sharing or neighboring a region, which reduces binary variables exponentially compared with naive formulations. An L1 path-length-plus-accelera…

Dynamic Parameter Memory: Temporary LoRA-Enhanced LLM for Long-Sequence Emotion Recognition in Conversation
Jialong Mai, Xiaofen Xing, Yawei Li, Zhipeng Li, Jingyuan Xing, Xiangmin Xu
https://arxiv.org/abs/2507.09076

Dynamic Parameter Memory: Temporary LoRA-Enhanced LLM for Long-Sequence Emotion Recognition in Conversation
Recent research has focused on applying speech large language model (SLLM) to improve speech emotion recognition (SER). However, the inherently high frame rate in speech modality severely limits the signal processing and understanding capabilities of SLLM. For example, a SLLM with a 4K context window can only process 80 seconds of audio at 50Hz feature sampling rate before reaching its capacity limit. Input token compression methods used in SLLM overlook the continuity and inertia of emotions a…

The BRS Cohomology of the Wess Zumino Chiral Scalar supersymmetric model with exotic pairs and exotic triplets (E2)
John A. Dixon
https://arxiv.org/abs/2507.14174 https://

The BRS Cohomology of the Wess Zumino Chiral Scalar supersymmetric model with exotic pairs and exotic triplets (E2)
Using the spectral sequence method, this paper advances some of the construction of the BRS cohomology of the Wess Zumino supersymmetric action. An important missing part was the inclusion of the sources for the variations of the fields. In this paper, these sources are called pseudofields. Since the most interesting part of the result contains unsaturated spinor indices, we include a constant spinor to saturate those indices. At dimension zero, this gives rise to a new set of invariants and a …

Bounds of Shannon entropy and Extropy and their application in exploring the extreme value behavior of a large set of data
Konstantinos Zografos
https://arxiv.org/abs/2507.13656

Bounds of Shannon entropy and Extropy and their application in exploring the extreme value behavior of a large set of data
This paper derives bounds for two omnipresent information theoretic measures, the Shannon entropy and its complementary dual, the extropy. Based on a large size data set from a logconcave model, the said bounds are obtained for the entropy and the extropy of the distribution of the largest order statistic and the respective normalized sequence, in the extreme value theory setting. A characterization of the exponential distribution is provided as the model that maximizes the Shannon entropy and …

AmpLyze: A Deep Learning Model for Predicting the Hemolytic Concentration
Peng Qiu, Hanqi Feng, Barnabas Poczos
https://arxiv.org/abs/2507.08162 https://…

AmpLyze: A Deep Learning Model for Predicting the Hemolytic Concentration
Red-blood-cell lysis (HC50) is the principal safety barrier for antimicrobial-peptide (AMP) therapeutics, yet existing models only say "toxic" or "non-toxic." AmpLyze closes this gap by predicting the actual HC50 value from sequence alone and explaining the residues that drive toxicity. The model couples residue-level ProtT5/ESM2 embeddings with sequence-level descriptors in dual local and global branches, aligned by a cross-attention module and trained with log-cosh loss for robustness to assa…

Stereo sound event localization and detection based on PSELDnet pretraining and BiMamba sequence modeling
Wenmiao Gao, Yang Xiao
https://arxiv.org/abs/2506.13455

Stereo sound event localization and detection based on PSELDnet pretraining and BiMamba sequence modeling
Pre-training methods have achieved significant performance improvements in sound event localization and detection (SELD) tasks, but existing Transformer-based models suffer from high computational complexity. In this work, we propose a stereo sound event localization and detection system based on pre-trained PSELDnet and bidirectional Mamba sequence modeling. We replace the Conformer module with a BiMamba module and introduce asymmetric convolutions to more effectively model the spatiotemporal …

Unsupervised deep learning model for fast energy layer pre-selection of delivery-efficient proton arc therapy plan optimization of nasopharyngeal carcinoma
Bohan Yang, Gang Liu, Rirao Dao, Yujia Qian, Ke Shi, Anke Tang, Yong Luo, Jingnan Liu
https://arxiv.org/abs/2506.15803

Unsupervised deep learning model for fast energy layer pre-selection of delivery-efficient proton arc therapy plan optimization of nasopharyngeal carcinoma
Objective. Proton arc therapy (PAT) is an emerging and promising modality in radiotherapy, offering several advantages over conventional intensitymodulated proton therapy (IMPT). However, identifying the optimal energy layer (EL) sequence remains computationally intensive due to the large number of possible energy layer transitions. This study proposes an unsupervised deep learning framework for fast and effective EL pre-selection, aiming to minimize energy layer switch time while preserving hi…

Covariance Decomposition for Distance Based Species Tree Estimation
Georgios Aliatimis, Ruriko Yoshida, Burak Boyak, James Grant
https://arxiv.org/abs/2506.16425

Covariance Decomposition for Distance Based Species Tree Estimation
In phylogenomics, species-tree methods must contend with two major sources of noise; stochastic gene-tree variation under the multispecies coalescent model (MSC) and finite-sequence substitutional noise. Fast agglomerative methods such as GLASS, STEAC, and METAL combine multi-locus information via distance-based clustering. We derive the exact covariance matrix of these pairwise distance estimates under a joint MSC-plus-substitution model and leverage it for reliable confidence estimation, and …

A framework for modeling the evolution of young stellar objects
Theo Richardson, Adam Ginsburg, Erik Rosolowsky, Joshua Peltonen, R\'emy Indebetouw
https://arxiv.org/abs/2507.16944

A framework for modeling the evolution of young stellar objects
Measuring properties of young stellar objects (YSOs) is necessary for probing the pre-main-sequence evolution of stars. As YSOs exhibit complex geometry, measurement generally entails comparing observed radiation to template populations of radiative-transfer model YSO spectral energy distributions (SEDs). Due to uncertainty on the precise mechanics of star formation, the properties inferred for YSOs using these models often depend strongly on the assumed accretion history. We develop a framewor…

Sequence Modeling for Time-Optimal Quadrotor Trajectory Optimization with Sampling-based Robustness Analysis
Katherine Mao, Hongzhan Yu, Ruipeng Zhang, Igor Spasojevic, M Ani Hsieh, Sicun Gao, Vijay Kumar
https://arxiv.org/abs/2506.13915

Sequence Modeling for Time-Optimal Quadrotor Trajectory Optimization with Sampling-based Robustness Analysis
Time-optimal trajectories drive quadrotors to their dynamic limits, but computing such trajectories involves solving non-convex problems via iterative nonlinear optimization, making them prohibitively costly for real-time applications. In this work, we investigate learning-based models that imitate a model-based time-optimal trajectory planner to accelerate trajectory generation. Given a dataset of collision-free geometric paths, we show that modeling architectures can effectively learn the pat…

Nonparametric predictive inference for discrete data via Metropolis-adjusted Dirichlet sequences
Davide Agnoletto, Tommaso Rigon, David B. Dunson
https://arxiv.org/abs/2507.08629 …

Nonparametric predictive inference for discrete data via Metropolis-adjusted Dirichlet sequences
This article is motivated by challenges in conducting Bayesian inferences on unknown discrete distributions, with a particular focus on count data. To avoid the computational disadvantages of traditional mixture models, we develop a novel Bayesian predictive approach. In particular, our Metropolis-adjusted Dirichlet (MAD) sequence model characterizes the predictive measure as a mixture of a base measure and Metropolis-Hastings kernels centered on previous data points. The resulting MAD sequence…

Predicting function of evolutionarily implausible DNA sequences
Shiyu Jiang, Xuyin Liu, Zitong Jerry Wang
https://arxiv.org/abs/2506.10271 https://

Predicting function of evolutionarily implausible DNA sequences
Genomic language models (gLMs) show potential for generating novel, functional DNA sequences for synthetic biology, but doing so requires them to learn not just evolutionary plausibility, but also sequence-to-function relationships. We introduce a set of prediction tasks called Nullsettes, which assesses a model's ability to predict loss-of-function mutations created by translocating key control elements in synthetic expression cassettes. Across 12 state-of-the-art models, we find that mutation…

RNAMunin: A Deep Machine Learning Model for Non-coding RNA Discovery
Lauren Lui, Torben Nielsen
https://arxiv.org/abs/2507.11950 https://

RNAMunin: A Deep Machine Learning Model for Non-coding RNA Discovery
Functional annotation of microbial genomes is often biased toward protein-coding genes, leaving a vast, unexplored landscape of non-coding RNAs (ncRNAs) that are critical for regulating bacterial and archaeal physiology, stress response and metabolism. Identifying ncRNAs directly from genomic sequence is a paramount challenge in bioinformatics and biology, essential for understanding the complete regulatory potential of an organism. This paper presents RNAMunin, a machine learning (ML) model th…

Mixture of Raytraced Experts
Andrea Perin, Giacomo Lagomarsini, Claudio Gallicchio, Giuseppe Nuti
https://arxiv.org/abs/2507.12419 https://

Mixture of Raytraced Experts
We introduce a Mixture of Raytraced Experts, a stacked Mixture of Experts (MoE) architecture which can dynamically select sequences of experts, producing computational graphs of variable width and depth. Existing MoE architectures generally require a fixed amount of computation for a given sample. Our approach, in contrast, yields predictions with increasing accuracy as the computation cycles through the experts' sequence. We train our model by iteratively sampling from a set of candidate exper…

Simulation-trained conditional normalizing flows for likelihood approximation: a case study in stress regulation kinetics in yeast
Pedro Pessoa, Juan Andres Martinez, Vincent Vandenbroucke, Frank Delvigne, Steve Press\'e
https://arxiv.org/abs/2506.09374

Simulation-trained conditional normalizing flows for likelihood approximation: a case study in stress regulation kinetics in yeast
Physics-inspired inference often hinges on the ability to construct a likelihood, or the probability of observing a sequence of data given a model. These likelihoods can be directly maximized for parameter estimation, incorporated into Bayesian frameworks, or even used as loss functions in neural networks. Yet, many models, despite being conceptually simple, lack tractable likelihoods. A notable example arises in estimating protein production from snapshot measurements of actively dividing cell…

Dictionary Learning Based Regularization in Quantitative MRI: A Nested Alternating Optimization Framework
Guozhi Dong, Michael Hinterm\"uller, Clemens Sirotenko
https://arxiv.org/abs/2506.11977

Dictionary Learning Based Regularization in Quantitative MRI: A Nested Alternating Optimization Framework
In this article, we propose a novel regularization method for a class of nonlinear inverse problems that is inspired by an application in quantitative magnetic resonance imaging (qMRI). The latter is a special instance of a general dynamical image reconstruction technique, wherein a radio-frequency pulse sequence gives rise to a time-discrete physics-based mathematical model which acts as a side constraint in our inverse problem. To enhance reconstruction quality, we employ dictionary learning …

EnerBridge-DPO: Energy-Guided Protein Inverse Folding with Markov Bridges and Direct Preference Optimization
Dingyi Rong, Haotian Lu, Wenzhuo Zheng, Fan Zhang, Shuangjia Zheng, Ning Liu
https://arxiv.org/abs/2506.09496

EnerBridge-DPO: Energy-Guided Protein Inverse Folding with Markov Bridges and Direct Preference Optimization
Designing protein sequences with optimal energetic stability is a key challenge in protein inverse folding, as current deep learning methods are primarily trained by maximizing sequence recovery rates, often neglecting the energy of the generated sequences. This work aims to overcome this limitation by developing a model that directly generates low-energy, stable protein sequences. We propose EnerBridge-DPO, a novel inverse folding framework focused on generating low-energy, high-stability prot…

Enhancing Stereo Sound Event Detection with BiMamba and Pretrained PSELDnet
Wenmiao Gao, Han Yin
https://arxiv.org/abs/2507.09570 https://

Enhancing Stereo Sound Event Detection with BiMamba and Pretrained PSELDnet
Pre-training methods have greatly improved the performance of sound event localization and detection (SELD). However, existing Transformer-based models still face high computational cost. To solve this problem, we present a stereo SELD system using a pre-trained PSELDnet and a bidirectional Mamba sequence model. Specifically, we replace the Conformer module with a BiMamba module. We also use asymmetric convolutions to better capture the time and frequency relationships in the audio signal. Test…

Multimodal Modeling of CRISPR-Cas12 Activity Using Foundation Models and Chromatin Accessibility Data
Azim Dehghani Amirabad, Yanfei Zhang, Artem Moskalev, Sowmya Rajesh, Tommaso Mansi, Shuwei Li, Mangal Prakash, Rui Liao
https://arxiv.org/abs/2506.11182

Multimodal Modeling of CRISPR-Cas12 Activity Using Foundation Models and Chromatin Accessibility Data
Predicting guide RNA (gRNA) activity is critical for effective CRISPR-Cas12 genome editing but remains challenging due to limited data, variation across protospacer adjacent motifs (PAMs-short sequence requirements for Cas binding), and reliance on large-scale training. We investigate whether pre-trained biological foundation model originally trained on transcriptomic data can improve gRNA activity estimation even without domain-specific pre-training. Using embeddings from existing RNA foundati…