Tootfinder

Outcomes-over-outputs is one thing — but even outcomes aren't always impactful.
Investing in any outcome carries opportunity cost. Any effort you expend means not spending that effort elsewhere.
And when there's a bottleneck in the system, effort upstream of the bottleneck has diminishing returns. Typically, that bottleneck is your process.
Since the process is made up of people, technical solutions won't help.

All your problems are people problems (Don't Just Do Things, Part 2)
If you want to do strategy, you must be willing to do process transformation first.

Post-hoc Stochastic Concept Bottleneck Models
Wiktor Jan Hoffmann, Sonia Laguna, Moritz Vandenhirtz, Emanuele Palumbo, Julia E. Vogt
https://arxiv.org/abs/2510.08219 https://

Post-hoc Stochastic Concept Bottleneck Models
Concept Bottleneck Models (CBMs) are interpretable models that predict the target variable through high-level human-understandable concepts, allowing users to intervene on mispredicted concepts to adjust the final output. While recent work has shown that modeling dependencies between concepts can improve CBM performance, especially under interventions, such approaches typically require retraining the entire model, which may be infeasible when access to the original data or compute is limited. I…

Enhancing Concept Localization in CLIP-based Concept Bottleneck Models
R\'emi Kazmierczak, Steve Azzolin, Elo\"ise Berthier, Goran Frehse, Gianni Franchi
https://arxiv.org/abs/2510.07115

Enhancing Concept Localization in CLIP-based Concept Bottleneck Models
This paper addresses explainable AI (XAI) through the lens of Concept Bottleneck Models (CBMs) that do not require explicit concept annotations, relying instead on concepts extracted using CLIP in a zero-shot manner. We show that CLIP, which is central in these techniques, is prone to concept hallucination, incorrectly predicting the presence or absence of concepts within an image in scenarios used in numerous CBMs, hence undermining the faithfulness of explanations. To mitigate this issue, we …

Exponential Error Bounds for Information Bottleneck Source Coding Problems
Han Wu, Hamdi Joudeh
https://arxiv.org/abs/2510.08364 https://arxiv.org/pdf/2510…

Exponential Error Bounds for Information Bottleneck Source Coding Problems
We study the information bottleneck (IB) source coding problem, also known as remote lossy source coding under logarithmic loss. Based on a rate-limited description of noisy observations, the receiver produces a soft estimate for the remote source, i.e., a probability distribution, evaluated under the logarithmic loss. We focus on the excess distortion probability of IB source coding and investigate how fast it converges to 0 or 1, depending on whether the rate is above or below the rate-distor…

The Cognitive Bandwidth Bottleneck: Shifting Long-Horizon Agent from Planning with Actions to Planning with Schemas
Baixuan Xu, Tianshi Zheng, Zhaowei Wang, Hong Ting Tsang, Weiqi Wang, Tianqing Fang, Yangqiu Song
https://arxiv.org/abs/2510.07091

The Cognitive Bandwidth Bottleneck: Shifting Long-Horizon Agent from Planning with Actions to Planning with Schemas
Enabling LLMs to effectively operate long-horizon task which requires long-term planning and multiple interactions is essential for open-world autonomy. Conventional methods adopt planning with actions where a executable action list would be provided as reference. However, this action representation choice would be impractical when the environment action space is combinatorial exploded (e.g., open-ended real world). This naturally leads to a question: As environmental action space scales, what …

Israel-based RAAAM, whose "GCRAM" on-chip memory tech aims to deliver up to 10x power savings relative to high-density SRAM, raised a $17M Series A led by NXP (Meir Orbach/CTech)
https://www.calcalistech.com/ctechnews/article/sjjv3pp1bg

Chip giant NXP leads $17.5M Series A for Israeli startup tackling AI’s memory bottleneck
RAAAM Memory Technologies’ “GCRAM” promises denser, lower-power on-chip memory as the semiconductor industry races to support next-generation AI processors. 

Nystr\"om-Accelerated Primal LS-SVMs: Breaking the $O(an^3)$ Complexity Bottleneck for Scalable ODEs Learning
Weikuo Wang, Yue Liao, Huan Luo
https://arxiv.org/abs/2510.04094

Nyström-Accelerated Primal LS-SVMs: Breaking the $O(an^3)$ Complexity Bottleneck for Scalable ODEs Learning
A major problem of kernel-based methods (e.g., least squares support vector machines, LS-SVMs) for solving linear/nonlinear ordinary differential equations (ODEs) is the prohibitive $O(an^3)$ ($a=1$ for linear ODEs and 27 for nonlinear ODEs) part of their computational complexity with increasing temporal discretization points $n$. We propose a novel Nyström-accelerated LS-SVMs framework that breaks this bottleneck by reformulating ODEs as primal-space constraints. Specifically, we derive for t…

Quantum Strategies to Overcome Classical Multiplexing Limits
Tzula B. Propp, Bethany Davies, Jeroen Grimbergen, Emil R. Hellebek, Junior R. Gonzales-Ureta, Janice van Dam, Joshua A. Slater, Anders S. S{\o}rensen, Stephanie D. C. Wehner
https://arxiv.org/abs/2510.06099

Quantum Strategies to Overcome Classical Multiplexing Limits
Near-term quantum networks face a bottleneck due to low quantum communication rates. This degrades performance both by lowering operating speeds and increasing qubit storage time in noisy memories, making some quantum internet applications infeasible. One way to circumvent this bottleneck is multiplexing: combining multiple signals into a single signal to improve the overall rate. Standard multiplexing techniques are classical in that they do not make use of coherence between quantum channels n…

AMANDA: Agentic Medical Knowledge Augmentation for Data-Efficient Medical Visual Question Answering
Ziqing Wang, Chengsheng Mao, Xiaole Wen, Yuan Luo, Kaize Ding
https://arxiv.org/abs/2510.02328

AMANDA: Agentic Medical Knowledge Augmentation for Data-Efficient Medical Visual Question Answering
Medical Multimodal Large Language Models (Med-MLLMs) have shown great promise in medical visual question answering (Med-VQA). However, when deployed in low-resource settings where abundant labeled data are unavailable, existing Med-MLLMs commonly fail due to their medical reasoning capability bottlenecks: (i) the intrinsic reasoning bottleneck that ignores the details from the medical image; (ii) the extrinsic reasoning bottleneck that fails to incorporate specialized medical knowledge. To addr…

Quantifying the Accuracy-Interpretability Trade-Off in Concept-Based Sidechannel Models
David Debot, Giuseppe Marra
https://arxiv.org/abs/2510.05670 https://

Quantifying the Accuracy-Interpretability Trade-Off in Concept-Based Sidechannel Models
Concept Bottleneck Models (CBNMs) are deep learning models that provide interpretability by enforcing a bottleneck layer where predictions are based exclusively on human-understandable concepts. However, this constraint also restricts information flow and often results in reduced predictive accuracy. Concept Sidechannel Models (CSMs) address this limitation by introducing a sidechannel that bypasses the bottleneck and carry additional task-relevant information. While this improves accuracy, it …

Uncertainty-Aware Concept Bottleneck Models with Enhanced Interpretability
Haifei Zhang, Patrick Barry, Eduardo Brandao
https://arxiv.org/abs/2510.00773 https://

Uncertainty-Aware Concept Bottleneck Models with Enhanced Interpretability
In the context of image classification, Concept Bottleneck Models (CBMs) first embed images into a set of human-understandable concepts, followed by an intrinsically interpretable classifier that predicts labels based on these intermediate representations. While CBMs offer a semantically meaningful and interpretable classification pipeline, they often sacrifice predictive performance compared to end-to-end convolutional neural networks. Moreover, the propagation of uncertainty from concept pred…

Species invasions often create a "founder effect" that makes it hard to see effects of adaptation to the invaded habitat— genomic signals of a rapid post-bottleneck expansion look a lot like signals of adaptation. This study of European starlings teases those signals apart!
https://doi.org/10.1111/mec.17195

Placeit! A Framework for Learning Robot Object Placement Skills
Amina Ferrad, Johann Huber, Fran\c{c}ois H\'el\'enon, Julien Gleyze, Mahdi Khoramshahi, St\'ephane Doncieux
https://arxiv.org/abs/2510.09267

Placeit! A Framework for Learning Robot Object Placement Skills
Robotics research has made significant strides in learning, yet mastering basic skills like object placement remains a fundamental challenge. A key bottleneck is the acquisition of large-scale, high-quality data, which is often a manual and laborious process. Inspired by Graspit!, a foundational work that used simulation to automatically generate dexterous grasp poses, we introduce Placeit!, an evolutionary-computation framework for generating valid placement positions for rigid objects. Placei…

ISAAC: Intelligent, Scalable, Agile, and Accelerated CPU Verification via LLM-aided FPGA Parallelism
Jialin Sun, Yuchen Hu, Dean You, Yushu Du, Hui Wang, Xinwei Fang, Weiwei Shan, Nan Guan, Zhe Jiang
https://arxiv.org/abs/2510.10225

ISAAC: Intelligent, Scalable, Agile, and Accelerated CPU Verification via LLM-aided FPGA Parallelism
Functional verification is a critical bottleneck in integrated circuit development, with CPU verification being especially time-intensive and labour-consuming. Industrial practice relies on differential testing for CPU verification, yet faces bottlenecks at nearly each stage of the framework pipeline: front-end stimulus generation lacks micro-architectural awareness, yielding low-quality and redundant tests that impede coverage closure and miss corner cases. Meanwhile, back-end simulation infra…

Hierarchical Semantic RL: Tackling the Problem of Dynamic Action Space for RL-based Recommendations
Minmao Wang, Xingchen Liu, Shijie Yi, Likang Wu, Hongke Zhao, Fei Pan, Qingpeng Cai, Peng Jiang
https://arxiv.org/abs/2510.09167

Hierarchical Semantic RL: Tackling the Problem of Dynamic Action Space for RL-based Recommendations
Recommender Systems (RS) are fundamental to modern online services. While most existing approaches optimize for short-term engagement, recent work has begun to explore reinforcement learning (RL) to model long-term user value. However, these efforts face significant challenges due to the vast, dynamic action spaces inherent in recommendation, which hinder stable policy learning. To resolve this bottleneck, we introduce Hierarchical Semantic RL (HSRL), which reframes RL-based recommendation over…

MS2toImg: A Framework for Direct Bioactivity Prediction from Raw LC-MS/MS Data
Hansol Hong, Sangwon Lee, Jang-Ho Ha, Sung-June Chu, So-Hee An, Woo-Hyun Paek, Gyuhwa Chung, Kyoung Tai No
https://arxiv.org/abs/2510.09716

MS2toImg: A Framework for Direct Bioactivity Prediction from Raw LC-MS/MS Data
Untargeted metabolomics using LC-MS/MS offers the potential to comprehensively profile the chemical diversity of biological samples. However, the process is fundamentally limited by the "identification bottleneck," where only a small fraction of detected features can be annotated using existing spectral libraries, leaving the majority of data uncharacterized and unused. In addition, the inherently low reproducibility of LC-MS/MS instruments introduces alignment errors between runs, making featu…

Crosslisted article(s) found for cond-mat.stat-mech. https://arxiv.org/list/cond-mat.stat-mech/new
[1/1]:
- Combined Representation and Generation with Diffusive State Predictive Information Bottleneck
Richard John, Yunrui Qiu, Lukas Herron, Pratyush Tiwary

LOOPerSet: A Large-Scale Dataset for Data-Driven Polyhedral Compiler Optimization
Massinissa Merouani, Afif Boudaoud, Riyadh Baghdadi
https://arxiv.org/abs/2510.10209 https://…

LOOPerSet: A Large-Scale Dataset for Data-Driven Polyhedral Compiler Optimization
The advancement of machine learning for compiler optimization, particularly within the polyhedral model, is constrained by the scarcity of large-scale, public performance datasets. This data bottleneck forces researchers to undertake costly data generation campaigns, slowing down innovation and hindering reproducible research learned code optimization. To address this gap, we introduce LOOPerSet, a new public dataset containing 28 million labeled data points derived from 220,000 unique, synthet…

Replaced article(s) found for stat.ML. https://arxiv.org/list/stat.ML/new
[2/2]:
- A Deterministic Information Bottleneck Method for Clustering Mixed-Type Data
Efthymios Costa, Ioanna Papatsouma, Angelos Markos

Distributed Resource Selection for Self-Organising Cloud-Edge Systems
Quentin Renau, Amjad Ullah, Emma Hart
https://arxiv.org/abs/2510.08228 https://arxiv.…

Distributed Resource Selection for Self-Organising Cloud-Edge Systems
This paper presents a distributed resource selection mechanism for diverse cloud-edge environments, enabling dynamic and context-aware allocation of resources to meet the demands of complex distributed applications. By distributing the decision-making process, our approach ensures efficiency, scalability, and resilience in highly dynamic cloud-edge environments where centralised coordination becomes a bottleneck. The proposed mechanism aims to function as a core component of a broader, distribu…

Multi-Modal Multi-Task Semantic Communication: A Distributed Information Bottleneck Perspective
Yujie Zhou, Yiwei Liao, Cheng Peng, Yong Xiao, Yingyu Li
https://arxiv.org/abs/2510.04000

Multi-Modal Multi-Task Semantic Communication: A Distributed Information Bottleneck Perspective
Semantic communication (SemCom) shifts the focus from data transmission to meaning delivery, enabling efficient and intelligent communication. Existing AI-based coding schemes for multi-modal multi-task SemCom often require transmitters with full-modal data to participate in all receivers' tasks, which leads to redundant transmissions and conflicts with the physical limits of channel capacity and computational capability. In this paper, we propose PoM$^2$-DIB, a novel framework that extends…

Bootstrapping as a Morphism: An Arithmetic Geometry Approach to Asymptotically Faster Homomorphic Encryption
Dongfang Zhao
https://arxiv.org/abs/2510.02365 https://

Bootstrapping as a Morphism: An Arithmetic Geometry Approach to Asymptotically Faster Homomorphic Encryption
Fully Homomorphic Encryption (FHE) provides a powerful paradigm for secure computation, but its practical adoption is severely hindered by the prohibitive computational cost of its bootstrapping procedure. The complexity of all current bootstrapping methods is fundamentally tied to the multiplicative depth of the decryption circuit, denoted $L_{dec}$, making it the primary performance bottleneck. This paper introduces a new approach to bootstrapping that completely bypasses the traditional circ…

A large-scale, unsupervised pipeline for automatic corpus annotation using LLMs: variation and change in the English consider construction
Cameron Morin, Matti Marttinen Larsson
https://arxiv.org/abs/2510.12306

A large-scale, unsupervised pipeline for automatic corpus annotation using LLMs: variation and change in the English consider construction
As natural language corpora expand at an unprecedented rate, manual annotation remains a significant methodological bottleneck in corpus linguistic work. We address this challenge by presenting a scalable, unsupervised pipeline for automating grammatical annotation in voluminous corpora using large language models (LLMs). Unlike previous supervised and iterative approaches, our method employs a four-phase workflow: prompt engineering, pre-hoc evaluation, automated batch processing, and post-hoc…

GPU-Accelerated X-ray Pulse Profile Modeling
Tianzhe Zhou, Chun Huang
https://arxiv.org/abs/2510.07764 https://arxiv.org/pdf/2510.07764

GPU-Accelerated X-ray Pulse Profile Modeling
Pulse-profile modeling (PPM) of thermal X-ray emission from rotation-powered millisecond pulsars enables simultaneous constraints on the mass $M$, radius $R$, and hence the equation of state of cold, dense matter. However, Bayesian PPM has faced a hard accuracy-speed bottleneck: current production resolutions used to keep inference tractable can under-resolve extreme hotspot geometries and bias the waveform computation, whereas the higher resolutions that remove this bias push forward models to…

Replaced article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[5/14]:
- QUITO-X: A New Perspective on Context Compression from the Information Bottleneck Theory
Wang, Huang, Tian, Su, Yu, Liao, Fan, Guo, Cheng

Differentiable Model Predictive Control on the GPU
Emre Adabag, Marcus Greiff, John Subosits, Thomas Lew
https://arxiv.org/abs/2510.06179 https://arxiv.org…

Differentiable Model Predictive Control on the GPU
Differentiable model predictive control (MPC) offers a powerful framework for combining learning and control. However, its adoption has been limited by the inherently sequential nature of traditional optimization algorithms, which are challenging to parallelize on modern computing hardware like GPUs. In this work, we tackle this bottleneck by introducing a GPU-accelerated differentiable optimization tool for MPC. This solver leverages sequential quadratic programming and a custom preconditioned…

BrainIB : Leveraging Graph Neural Networks and Information Bottleneck for Functional Brain Biomarkers in Schizophrenia
Tianzheng Hu, Qiang Li, Shu Liu, Vince D. Calhoun, Guido van Wingen, Shujian Yu
https://arxiv.org/abs/2510.03004

BrainIB++: Leveraging Graph Neural Networks and Information Bottleneck for Functional Brain Biomarkers in Schizophrenia
The development of diagnostic models is gaining traction in the field of psychiatric disorders. Recently, machine learning classifiers based on resting-state functional magnetic resonance imaging (rs-fMRI) have been developed to identify brain biomarkers that differentiate psychiatric disorders from healthy controls. However, conventional machine learning-based diagnostic models often depend on extensive feature engineering, which introduces bias through manual intervention. While deep learning…

When Light Bends to the Collective Will: A Theory and Vision for Adaptive Photonic Scale-up Domains
Vamsi Addanki
https://arxiv.org/abs/2510.08072 https://…

When Light Bends to the Collective Will: A Theory and Vision for Adaptive Photonic Scale-up Domains
As chip-to-chip silicon photonics gain traction for their bandwidth and energy efficiency, collective communication has emerged as a critical bottleneck in scale-up systems. Programmable photonic interconnects offer a promising path forward: by dynamically reconfiguring the fabric, they can establish direct, high-bandwidth optical paths between communicating endpoints -- \emph{synchronously and guided by the structure of collective operations} (e.g., AllReduce). However, realizing this vision -…

WARP -- Web-Augmented Real-time Program Repairer: A Real-Time Compilation Error Resolution using LLMs and Web-Augmented Synthesis
Anderson de Lima Luiz
https://arxiv.org/abs/2509.25192

WARP -- Web-Augmented Real-time Program Repairer: A Real-Time Compilation Error Resolution using LLMs and Web-Augmented Synthesis
Compilation errors represent a significant bottleneck in software development productivity. This paper introduces WARP (Web-Augmented Real-time Program Repairer), a novel system that leverages Large Language Models (LLMs) and dynamic web-augmented synthesis for real-time resolution of these errors. WARP actively monitors developer terminals, intelligently detects compilation errors, and synergistically combines the understanding of a fine-tuned Code-LLM with relevant solutions, explanations, an…

FlowLensing: Simulating Gravitational Lensing with Flow Matching
Hamees Sayed, Pranath Reddy, Michael W. Toomey, Sergei Gleyzer
https://arxiv.org/abs/2510.07878 https://

FlowLensing: Simulating Gravitational Lensing with Flow Matching
Gravitational lensing is one of the most powerful probes of dark matter, yet creating high-fidelity lensed images at scale remains a bottleneck. Existing tools rely on ray-tracing or forward-modeling pipelines that, while precise, are prohibitively slow. We introduce FlowLensing, a Diffusion Transformer-based compact and efficient flow-matching model for strong gravitational lensing simulation. FlowLensing operates in both discrete and continuous regimes, handling classes such as different dark…

Can Large Language Models Autoformalize Kinematics?
Aditi Kabra, Jonathan Laurent, Sagar Bharadwaj, Ruben Martins, Stefan Mitsch, Andr\'e Platzer
https://arxiv.org/abs/2509.21840

Can Large Language Models Autoformalize Kinematics?
Autonomous cyber-physical systems like robots and self-driving cars could greatly benefit from using formal methods to reason reliably about their control decisions. However, before a problem can be solved it needs to be stated. This requires writing a formal physics model of the cyber-physical system, which is a complex task that traditionally requires human expertise and becomes a bottleneck. This paper experimentally studies whether Large Language Models (LLMs) can automate the formalizati…

Locality-Sensitive Hashing-Based Efficient Point Transformer for Charged Particle Reconstruction
Shitij Govil, Jack P. Rodgers, Yuan-Tang Chou, Siqi Miao, Amit Saha, Advaith Anand, Kilian Lieret, Gage DeZoort, Mia Liu, Javier Duarte, Pan Li, Shih-Chieh Hsu
https://arxiv.org/abs/2510.07594

Locality-Sensitive Hashing-Based Efficient Point Transformer for Charged Particle Reconstruction
Charged particle track reconstruction is a foundational task in collider experiments and the main computational bottleneck in particle reconstruction. Graph neural networks (GNNs) have shown strong performance for this problem, but costly graph construction, irregular computations, and random memory access patterns substantially limit their throughput. The recently proposed Hashing-based Efficient Point Transformer (HEPT) offers a theoretically guaranteed near-linear complexity for large point …

Voxel-scale quantum state control in nanorod ensembles using reconfigurable needle beams
G. A. Mantashian, D. B. Hayrapetyan, P. A. Mantashyan
https://arxiv.org/abs/2510.07767 h…

Voxel-scale quantum state control in nanorod ensembles using reconfigurable needle beams
Precisely addressing single nanostructures inside dense ensembles remains a bottleneck for scalable photonic and quantum information devices. Here we demonstrate, through comprehensive finite element and variational Monte-Carlo modelling, that a reconfigurable three-dimensional array of needle shaped beams can selectively switch the quantum optical response of individual InAs nanorods embedded in GaAs. By tuning the local non resonant intensity pattern the exciton and biexciton energies were ca…

Efficient Log-Rank Updates for Random Survival Forests
Erik Sverdrup, James Yang, Michael LeBlanc
https://arxiv.org/abs/2510.03665 https://arxiv.org/pdf/25…

Efficient Log-Rank Updates for Random Survival Forests
Random survival forests are widely used for estimating covariate-conditional survival functions under right-censoring. Their standard log-rank splitting criterion is typically recomputed at each candidate split. This O(M) cost per split, with M the number of distinct event times in a node, creates a bottleneck for large cohort datasets with long follow-up. We revisit approximations proposed by LeBlanc and Crowley (1995) and develop simple constant-time updates for the log-rank criterion. The me…

Measurement-Guided Consistency Model Sampling for Inverse Problems
Amirreza Tanevardi, Pooria Abbas Rad Moghadam, Sajjad Amini
https://arxiv.org/abs/2510.02208 https://

Measurement-Guided Consistency Model Sampling for Inverse Problems
Diffusion models have become powerful generative priors for solving inverse imaging problems, but their reliance on slow multi-step sampling limits practical deployment. Consistency models address this bottleneck by enabling high-quality generation in a single or only a few steps, yet their direct adaptation to inverse problems is underexplored. In this paper, we present a modified consistency sampling approach tailored for inverse problem reconstruction: the sampler's stochasticity is guided b…

Replaced article(s) found for math.CO. https://arxiv.org/list/math.CO/new
[2/2]:
- Gromov's Approximating Tree and the All-Pairs Bottleneck Paths Problem
Anders Cornect, Eduardo Mart\'inez-Pedroza

Unlocking Symbol-Level Precoding Efficiency Through Tensor Equivariant Neural Network
Jinshuo Zhang, Yafei Wang, Xinping Yi, Wenjin Wang, Shi Jin, Symeon Chatzinotas, Bj\"orn Ottersten
https://arxiv.org/abs/2510.02108

Unlocking Symbol-Level Precoding Efficiency Through Tensor Equivariant Neural Network
Although symbol-level precoding (SLP) based on constructive interference (CI) exploitation offers performance gains, its high complexity remains a bottleneck. This paper addresses this challenge with an end-to-end deep learning (DL) framework with low inference complexity that leverages the structure of the optimal SLP solution in the closed-form and its inherent tensor equivariance (TE), where TE denotes that a permutation of the input induces the corresponding permutation of the output. Build…

Temporal-Aware Iterative Speech Model for Dementia Detection
Chukwuemeka Ugwu, Oluwafemi Oyeleke
https://arxiv.org/abs/2510.00030 https://arxiv.org/pdf/251…

Temporal-Aware Iterative Speech Model for Dementia Detection
Deep learning systems often struggle with processing long sequences, where computational complexity can become a bottleneck. Current methods for automated dementia detection using speech frequently rely on static, time-agnostic features or aggregated linguistic content, lacking the flexibility to model the subtle, progressive deterioration inherent in speech production. These approaches often miss the dynamic temporal patterns that are critical early indicators of cognitive decline. In this pap…

Universal initial state preparation for first quantized quantum simulations
Jack S. Baker, Gaurav Saxena, Thi Ha Kyaw
https://arxiv.org/abs/2510.07278 https://

Universal initial state preparation for first quantized quantum simulations
Preparing symmetry-adapted initial states is a principal bottleneck in first-quantized quantum simulation. We present a universal approach that efficiently maps any polynomial-size superposition of occupation-number configurations to the first-quantized representation on a digital quantum computer. The method exploits the Jordan--Schwinger Lie algebra homomorphism, which identifies number-conserving second-quantized operators with their first-quantized action and induces an equivariant bijectio…

CodePlot-CoT: Mathematical Visual Reasoning by Thinking with Code-Driven Images
Chengqi Duan, Kaiyue Sun, Rongyao Fang, Manyuan Zhang, Yan Feng, Ying Luo, Yufang Liu, Ke Wang, Peng Pei, Xunliang Cai, Hongsheng Li, Yi Ma, Xihui Liu
https://arxiv.org/abs/2510.11718

CodePlot-CoT: Mathematical Visual Reasoning by Thinking with Code-Driven Images
Recent advances in Large Language Models (LLMs) and Vision Language Models (VLMs) have shown significant progress in mathematical reasoning, yet they still face a critical bottleneck with problems requiring visual assistance, such as drawing auxiliary lines or plotting functions to solve the problems. Most LLMs and VLMs are constrained to text-only reasoning chains, while multimodal unified models that can generate interleaved text and images lack the necessary precision and controllability for…

MoBiLE: Efficient Mixture-of-Experts Inference on Consumer GPU with Mixture of Big Little Experts
Yushu Zhao, Yubin Qin, Yang Wang, Xiaolong Yang, Huiming Han, Shaojun Wei, Yang Hu, Shouyi Yin
https://arxiv.org/abs/2510.12357

MoBiLE: Efficient Mixture-of-Experts Inference on Consumer GPU with Mixture of Big Little Experts
Mixture-of-Experts (MoE) models have recently demonstrated exceptional performance across a diverse range of applications. The principle of sparse activation in MoE models facilitates an offloading strategy, wherein active experts are maintained in GPU HBM, while inactive experts are stored in CPU DRAM. The efficacy of this approach, however, is fundamentally constrained by the limited bandwidth of the CPU-GPU interconnect. To mitigate this bottleneck, existing approaches have employed prefetch…

Replaced article(s) found for cs.CG. https://arxiv.org/list/cs.CG/new
[1/1]:
- Gromov's Approximating Tree and the All-Pairs Bottleneck Paths Problem
Anders Cornect, Eduardo Mart\'inez-Pedroza

gCAMB: A GPU-accelerated Boltzmann solver for next-generation cosmological surveys
L. Storchi, P. Campeti, M. Lattanzi, N. Antonini, E. Calore, P. Lubrano
https://arxiv.org/abs/2509.25110

gCAMB: A GPU-accelerated Boltzmann solver for next-generation cosmological surveys
Inferring cosmological parameters from Cosmic Microwave Background (CMB) data requires repeated and computationally expensive calculations of theoretical angular power spectra using Boltzmann solvers like CAMB. This creates a significant bottleneck, particularly for non-standard cosmological models and the high-accuracy demands of future surveys. While emulators based on deep neural networks can accelerate this process by several orders of magnitude, they first require large, pre-computed train…

Combined Exoplanet Mass and Atmospheric Characterization for Accelerated Exoplanetology
Julien de Wit, Sara Seager, Prajwal Niraula
https://arxiv.org/abs/2509.25323 https://

Combined Exoplanet Mass and Atmospheric Characterization for Accelerated Exoplanetology
Today's most detailed characterization of exoplanet atmospheres is accessible via transit spectroscopy (TS). Detecting transiting exoplanets only yields their size, and it is thus standard to measure a planet's mass before moving towards their atmospheric characterization, or even the publication of their discovery. This framework, however, can act as a bottleneck for high-throughput exoplanetology. Here, we review existing applications of an alternative approach deriving exoplanet masses in sm…

HumanoidExo: Scalable Whole-Body Humanoid Manipulation via Wearable Exoskeleton
Rui Zhong, Yizhe Sun, Junjie Wen, Jinming Li, Chuang Cheng, Wei Dai, Zhiwen Zeng, Huimin Lu, Yichen Zhu, Yi Xu
https://arxiv.org/abs/2510.03022

HumanoidExo: Scalable Whole-Body Humanoid Manipulation via Wearable Exoskeleton
A significant bottleneck in humanoid policy learning is the acquisition of large-scale, diverse datasets, as collecting reliable real-world data remains both difficult and cost-prohibitive. To address this limitation, we introduce HumanoidExo, a novel system that transfers human motion to whole-body humanoid data. HumanoidExo offers a high-efficiency solution that minimizes the embodiment gap between the human demonstrator and the robot, thereby tackling the scarcity of whole-body humanoid data…

Crosslisted article(s) found for q-bio.QM. https://arxiv.org/list/q-bio.QM/new
[1/1]:
- Combined Representation and Generation with Diffusive State Predictive Information Bottleneck
Richard John, Yunrui Qiu, Lukas Herron, Pratyush Tiwary

Replaced article(s) found for cs.DM. https://arxiv.org/list/cs.DM/new
[1/1]:
- Gromov's Approximating Tree and the All-Pairs Bottleneck Paths Problem
Anders Cornect, Eduardo Mart\'inez-Pedroza

Structured Sparsity and Weight-adaptive Pruning for Memory and Compute efficient Whisper models
Prasenjit K Mudi, Anshi Sachan, Dahlia Devapriya, Sheetal Kalyani
https://arxiv.org/abs/2510.12666

Structured Sparsity and Weight-adaptive Pruning for Memory and Compute efficient Whisper models
Whisper models have achieved remarkable progress in speech recognition; yet their large size remains a bottleneck for deployment on resource-constrained edge devices. This paper proposes a framework to design fine-tuned variants of Whisper which address the above problem. Structured sparsity is enforced via the Sparse Group LASSO penalty as a loss regularizer, to reduce the number of FLOating Point operations (FLOPs). Further, a weight statistics aware pruning algorithm is proposed. We also des…

FlashResearch: Real-time Agent Orchestration for Efficient Deep Research
Lunyiu Nie, Nedim Lipka, Ryan A. Rossi, Swarat Chaudhuri
https://arxiv.org/abs/2510.05145 https://

FlashResearch: Real-time Agent Orchestration for Efficient Deep Research
Deep research agents, which synthesize information across diverse sources, are significantly constrained by their sequential reasoning processes. This architectural bottleneck results in high latency, poor runtime adaptability, and inefficient resource allocation, making them impractical for interactive applications. To overcome this, we introduce FlashResearch, a novel framework for efficient deep research that transforms sequential processing into parallel, runtime orchestration by dynamicall…

A path towards AI-scale, interoperable biological data
Brian Aevermann, Andrea Califano, Chi-Li Chiu, Nathan Clack, William M. Clemons Jr., Jonah Cool Florence D. D'Orazi, Joseph L. DeRisi, Joshua E. Elias, Elizabeth Fahsbender, Scott E. Fraser, Carlos G. Gonzalez, Matthias Haury, Theofanis Karaletsos, Shana O. Kelley, Aly A. Khan, Alan R. Lowe, Emma Lundberg, Ryan A. McClure, Stephani Otte, Evan O. Paull, Lo\"ic A. Royer, Dana Sadgat, Sandra L. Schmid, Samantha Scovanner, Cat…

A path towards AI-scale, interoperable biological data
Biology is at the precipice of a new era where AI accelerates and amplifies the ability to study how cells operate, organize, and work as systems, revealing why disease happens and how to correct it. Organizations globally are prioritizing AI to accelerate basic research, drug discovery, personalized medicine, and synthetic biology. However, despite these opportunities, scientific data have proven a bottleneck, and progress has been slow and fragmented. Unless the scientific community takes a t…

EditReward: A Human-Aligned Reward Model for Instruction-Guided Image Editing
Keming Wu, Sicong Jiang, Max Ku, Ping Nie, Minghao Liu, Wenhu Chen
https://arxiv.org/abs/2509.26346

EditReward: A Human-Aligned Reward Model for Instruction-Guided Image Editing
Recently, we have witnessed great progress in image editing with natural language instructions. Several closed-source models like GPT-Image-1, Seedream, and Google-Nano-Banana have shown highly promising progress. However, the open-source models are still lagging. The main bottleneck is the lack of a reliable reward model to scale up high-quality synthetic training data. To address this critical bottleneck, we built \mname, trained with our new large-scale human preference dataset, meticulously…

Fully Parallel Multi-Agent Photonic Optimizer
Ghazi Sarwat Syed, Philipp Schmidt, Frank Br\"uckerhoff-Pl\"uckelmann, Jelle Dijkstra, Wolfram H. P Pernice, Abu Sebastian
https://arxiv.org/abs/2510.06424

Fully Parallel Multi-Agent Photonic Optimizer
Optimization problems are central to many important cross-disciplinary applications.In their conventional implementations, the sequential nature of operations imposes strict limitations on the computational efficiency. Here, we discuss how analog optical computing can overcome this fundamental bottleneck. We propose a photonic optimizer unit, together with supporting algorithms that uses in memory computation within a nature inspired, multi agent cooperative framework. The system performs a seq…

Unsupervised Representation Learning for 3D Mesh Parameterization with Semantic and Visibility Objectives
AmirHossein Zamani, Bruno Roy, Arianna Rampini
https://arxiv.org/abs/2509.25094

Unsupervised Representation Learning for 3D Mesh Parameterization with Semantic and Visibility Objectives
Recent 3D generative models produce high-quality textures for 3D mesh objects. However, they commonly rely on the heavy assumption that input 3D meshes are accompanied by manual mesh parameterization (UV mapping), a manual task that requires both technical precision and artistic judgment. Industry surveys show that this process often accounts for a significant share of asset creation, creating a major bottleneck for 3D content creators. Moreover, existing automatic methods often ignore two perc…

Predictor-corrector method based on dynamic mode decomposition for tensor-train nonequilibrium Green's function calculations
Maksymilian \'Sroda, Ken Inayoshi, Michael Sch\"uler, Hiroshi Shinaoka, Philipp Werner
https://arxiv.org/abs/2509.22177

Predictor-corrector method based on dynamic mode decomposition for tensor-train nonequilibrium Green's function calculations
The nonequilibrium Green's function (NEGF) formalism is a powerful tool to study the nonequilibrium dynamics of correlated lattice systems, but its applicability to realistic system sizes and long timescales is limited by unfavorable memory scaling. While compressed representations, such as the recently introduced quantics tensor train (QTT) format, alleviate the memory bottleneck, the efficiency of QTT-NEGF calculations is hindered by poor initializations and slow or unstable convergence of gl…

Towards Label-Free Biological Reasoning Synthetic Dataset Creation via Uncertainty Filtering
Josefa Lia Stoisser, Lawrence Phillips, Aditya Misra, Tom A. Lamb, Philip Torr, Marc Boubnovski Martell, Julien Fauqueur, Kaspar M\"artens
https://arxiv.org/abs/2510.05871

Towards Label-Free Biological Reasoning Synthetic Dataset Creation via Uncertainty Filtering
Synthetic chain-of-thought (CoT) traces are widely used to train large reasoning models (LRMs), improving generalization by providing step-level supervision. Yet most approaches require ground-truth labels to seed or filter these traces - an expensive bottleneck in domains like biology where wet-lab data are scarce. We propose a label-free alternative: uncertainty-based filtering, which uses a model's own confidence - quantified through established uncertainty metrics like self-consistency and …

Automating Sensor Characterization with Bayesian Optimization
J. Cuevas-Zepeda, C. Chavez, J. Estrada, J. Noonan, B. D. Nord, N. Saffold, M. Sofo-Haro, R. Spinola e Castro, S. Trivedi
https://arxiv.org/abs/2509.21661

Automating Sensor Characterization with Bayesian Optimization
The development of novel instrumentation requires an iterative cycle with three stages: design, prototyping, and testing. Recent advancements in simulation and nanofabrication techniques have significantly accelerated the design and prototyping phases. Nonetheless, detector characterization continues to be a major bottleneck in device development. During the testing phase, a significant time investment is required to characterize the device in different operating conditions and find optimal ope…

Symmetry-preserving random batch Ewald method for constant-potential simulation of electrochemical systems
Weihang Gao, Qi Zhou, Qianru Zhang, Zhenli Xu
https://arxiv.org/abs/2509.24742

Symmetry-preserving random batch Ewald method for constant-potential simulation of electrochemical systems
Constant potential molecular dynamics simulation plays important role for applications of electrochemical systems, yet the calculation of charge fluctuation on electrodes remains a computational bottleneck. We propose a highly scalable, symmetry-preserving random batch Ewald (SRBE) algorithm to address this challenge. The SRBE algorithm deterministically computes the low-frequency components along the direction perpendicular to electrodes, while efficiently approximating the remaining component…

Low Complexity Detector for XL-MIMO Uplink: A Cross Splitting Based Information Geometry Approach
Wenjun Zhang, An-An Lu, Xiqi Gao
https://arxiv.org/abs/2510.09039 https://

Low Complexity Detector for XL-MIMO Uplink: A Cross Splitting Based Information Geometry Approach
In this paper, we propose the cross splitting based information geometry approach (CS-IGA), a novel and low complexity iterative detector for uplink signal recovery in extralarge-scale MIMO (XL-MIMO) systems. Conventional iterative detectors, such as the approximate message passing (AMP) algorithm and the traditional information geometry algorithm (IGA), suffer from a per iteration complexity that scales with the number of base station (BS) antennas, creating a computational bottleneck. To over…

On Spectral Learning for Odeco Tensors: Perturbation, Initialization, and Algorithms
Arnab Auddy, Ming Yuan
https://arxiv.org/abs/2509.25126 https://arxiv.…

On Spectral Learning for Odeco Tensors: Perturbation, Initialization, and Algorithms
We study spectral learning for orthogonally decomposable (odeco) tensors, emphasizing the interplay between statistical limits, optimization geometry, and initialization. Unlike matrices, recovery for odeco tensors does not hinge on eigengaps, yielding improved robustness under noise. While iterative methods such as tensor power iterations can be statistically efficient, initialization emerges as the main computational bottleneck. We investigate perturbation bounds, non-convex optimization anal…

GLASS Flows: Transition Sampling for Alignment of Flow and Diffusion Models
Peter Holderrieth, Uriel Singer, Tommi Jaakkola, Ricky T. Q. Chen, Yaron Lipman, Brian Karrer
https://arxiv.org/abs/2509.25170

GLASS Flows: Transition Sampling for Alignment of Flow and Diffusion Models
The performance of flow matching and diffusion models can be greatly improved at inference time using reward alignment algorithms, yet efficiency remains a major limitation. While several algorithms were proposed, we demonstrate that a common bottleneck is the sampling method these algorithms rely on: many algorithms require to sample Markov transitions via SDE sampling, which is significantly less efficient and often less performant than ODE sampling. To remove this bottleneck, we introduce GL…

GSID: Generative Semantic Indexing for E-Commerce Product Understanding
Haiyang Yang, Qinye Xie, Qingheng Zhang, Liyu Chen, Huike Zou, Chengbao Lian, Shuguang Han, Fei Huang, Jufeng Chen, Bo Zheng
https://arxiv.org/abs/2509.23860

GSID: Generative Semantic Indexing for E-Commerce Product Understanding
Structured representation of product information is a major bottleneck for the efficiency of e-commerce platforms, especially in second-hand ecommerce platforms. Currently, most product information are organized based on manually curated product categories and attributes, which often fail to adequately cover long-tail products and do not align well with buyer preference. To address these problems, we propose \textbf{G}enerative \textbf{S}emantic \textbf{I}n\textbf{D}exings (GSID), a data-driven…

TCB-VIO: Tightly-Coupled Focal-Plane Binary-Enhanced Visual Inertial Odometry
Matthew Lisondra, Junseo Kim, Glenn Takashi Shimoda, Kourosh Zareinia, Sajad Saeedi
https://arxiv.org/abs/2510.03919

TCB-VIO: Tightly-Coupled Focal-Plane Binary-Enhanced Visual Inertial Odometry
Vision algorithms can be executed directly on the image sensor when implemented on the next-generation sensors known as focal-plane sensor-processor arrays (FPSP)s, where every pixel has a processor. FPSPs greatly improve latency, reducing the problems associated with the bottleneck of data transfer from a vision sensor to a processor. FPSPs accelerate vision-based algorithms such as visual-inertial odometry (VIO). However, VIO frameworks suffer from spatial drift due to the vision-based pose e…

Replaced article(s) found for cs.CL. https://arxiv.org/list/cs.CL/new
[3/7]:
- FlowNIB: An Information Bottleneck Analysis of Bidirectional vs. Unidirectional Language Models
Kowsher, Prottasha, Xu, Mohanto, Garibay, Yousefi, Chen

CapGeo: A Caption-Assisted Approach to Geometric Reasoning
Yuying Li, Siyi Qian, Hao Liang, Leqi Zheng, Ruichuan An, Yongzhen Guo, Wentao Zhang
https://arxiv.org/abs/2510.09302 …

CapGeo: A Caption-Assisted Approach to Geometric Reasoning
Geometric reasoning remains a core challenge for Multimodal Large Language Models (MLLMs). Even the most advanced closed-source systems, such as GPT-O3 and Gemini-2.5-Pro, still struggle to solve geometry problems reliably, despite exhibiting strong textual reasoning abilities on tasks like the International Mathematical Olympiad (IMO). This gap suggests that the bottleneck lies in understanding geometric diagrams rather than reasoning itself. Since geometric figures can often be faithfully des…

Orders in Chaos: Enhancing Large-Scale MoE LLM Serving with Data Movement Forecasting
Zhongkai Yu, Yue Guan, Zihao Yu, Chenyang Zhou, Shuyi Pei, Yangwook Kang, Yufei Ding, Po-An Tsai
https://arxiv.org/abs/2510.05497

Orders in Chaos: Enhancing Large-Scale MoE LLM Serving with Data Movement Forecasting
Large Language Models (LLMs) with Mixture of Experts (MoE) architectures achieve remarkable performance improvements, but their random expert selection mechanism introduces significant data movement overhead that becomes the dominant bottleneck in multi-unit serving systems. To forecast the patterns underlying this data movement, we conduct comprehensive data-movement-centric profiling across three state-of-the-art large-scale MoE models (200B- 671B) using over 24,000 requests spanning diverse …

\textit{No One-Size-Fits-All}: A Workload-Driven Characterization of Bit-Parallel vs. Bit-Serial Data Layouts for Processing-using-Memory
Jingyao Zhang, Elaheh Sadredini
https://arxiv.org/abs/2509.22980

\textit{No One-Size-Fits-All}: A Workload-Driven Characterization of Bit-Parallel vs. Bit-Serial Data Layouts for Processing-using-Memory
Processing-in-Memory (PIM) is a promising approach to overcoming the memory-wall bottleneck. However, the PIM community has largely treated its two fundamental data layouts, Bit-Parallel (BP) and Bit-Serial (BS), as if they were interchangeable. This implicit "one-layout-fits-all" assumption, often hard-coded into existing evaluation frameworks, creates a critical gap: architects lack systematic, workload-driven guidelines for choosing the optimal data layout for their target applications. To…

Unmute the Patch Tokens: Rethinking Probing in Multi-Label Audio Classification
Lukas Rauch, Ren\'e Heinrich, Houtan Ghaffari, Lukas Miklautz, Ilyass Moummad, Bernhard Sick, Christoph Scholz
https://arxiv.org/abs/2509.24901

Unmute the Patch Tokens: Rethinking Probing in Multi-Label Audio Classification
Although probing frozen models has become a standard evaluation paradigm, self-supervised learning in audio defaults to fine-tuning. A key reason is that global pooling creates an information bottleneck causing linear probes to misrepresent the embedding quality: The $\texttt{cls}$-token discards crucial token information about dispersed, localized events in multi-label audio. This weakness is rooted in the mismatch between the pretraining objective (operating globally) and the downstream task …

🇺🇦 #NowPlaying on #BBC6Music's #HuwStephens
Mercury Rev:
🎵 Delta Sun Bottleneck Stomp
#MercuryRev
https://open.spotify.com/track/2j4APtyKqOnp3BfuiBmuFV

Decoding the dark proteome: Deep learning-enabled discovery of druggable enzymes in Wuchereria bancrofti
Shawnak Shivakumar, Jefferson Hernandez
https://arxiv.org/abs/2510.07337

Decoding the dark proteome: Deep learning-enabled discovery of druggable enzymes in Wuchereria bancrofti
Wuchereria bancrofti, the parasitic roundworm responsible for lymphatic filariasis, permanently disables over 36 million people and places 657 million at risk across 39 countries. A major bottleneck for drug discovery is the lack of functional annotation for more than 90 percent of the W. bancrofti dark proteome, leaving many potential targets unidentified. In this work, we present a novel computational pipeline that converts W. bancrofti's unannotated amino acid sequence data into precise four…

Stab-QRAM: An All-Clifford Quantum Random Access Memory for Special Data
Guangyi Li, Yu Gan, Zeguan Wu, Xueyue Zhang, Zheshen Zhang, Junyu Liu
https://arxiv.org/abs/2509.26494 h…

Stab-QRAM: An All-Clifford Quantum Random Access Memory for Special Data
Quantum random access memories (QRAMs) are pivotal for data-intensive quantum algorithms, but existing general-purpose and domain-specific architectures are hampered by a critical bottleneck: a heavy reliance on non-Clifford gates (e.g., T-gates), which are prohibitively expensive to implement fault-tolerantly. To address this challenge, we introduce the Stabilizer-QRAM (Stab-QRAM), a domain-specific architecture tailored for data with an affine Boolean structure ($f(\mathbf{x}) = A\mathbf{x} +…

Automated Modeling with AAP-Imfit: Astrometry and Photometry via CASA
Alfredo Amador-Portes, Eva Palafox, V\'ictor M. Pati\~no-\'Alvarez, Vahram Chavushyan, Andrei P. Lobanov, Sergio A. Dzib
https://arxiv.org/abs/2510.00119

Automated Modeling with AAP-Imfit: Astrometry and Photometry via CASA
Very Long Baseline Interferometry (VLBI) provides the highest-resolution radio intensity maps, crucial for detailed studies of compact sources like active galactic nuclei (AGN) and their relativistic jets. Analyzing jet components in these maps traditionally involves manual Gaussian fitting, a time-consuming bottleneck for large datasets. To address this, we present an automated batch-processing tool, based on the Gaussian fitting capabilities of CASA, designed to streamline VLBI jet component …

Scalable Boltzmann Generators for equilibrium sampling of large-scale materials
Maximilian Schebek, Jutta Rogal
https://arxiv.org/abs/2509.25486 https://ar…

Scalable Boltzmann Generators for equilibrium sampling of large-scale materials
The use of generative models to sample equilibrium distributions of many-body systems, as first demonstrated by Boltzmann Generators, has attracted substantial interest due to their ability to produce unbiased and uncorrelated samples in `one shot'. Despite their promise and impressive results across the natural sciences, scaling these models to large systems remains a major challenge. In this work, we introduce a Boltzmann Generator architecture that addresses this scalability bottleneck with …

Scaling LLM Multi-turn RL with End-to-end Summarization-based Context Management
Miao Lu, Weiwei Sun, Weihua Du, Zhan Ling, Xuesong Yao, Kang Liu, Jiecao Chen
https://arxiv.org/abs/2510.06727

Scaling LLM Multi-turn RL with End-to-end Summarization-based Context Management
We study reinforcement learning (RL) fine-tuning of large language model (LLM) agents for long-horizon multi-turn tool use, where context length quickly becomes a fundamental bottleneck. Existing RL pipelines can suffer from degraded instruction following, excessive rollout costs, and most importantly, strict context limits. To address these challenges, we introduce summarization-based context management to training. In specific, it periodically compresses the tool using history by LLM-generate…

Chat to Chip: Large Language Model Based Design of Arbitrarily Shaped Metasurfaces
Huanshu Zhang, Lei Kang, Sawyer D. Campbell, Douglas H. Werner
https://arxiv.org/abs/2509.24196

Chat to Chip: Large Language Model Based Design of Arbitrarily Shaped Metasurfaces
Traditional metasurface design is limited by the computational cost of full-wave simulations, preventing thorough exploration of complex configurations. Data-driven approaches have emerged as a solution to this bottleneck, replacing costly simulations with rapid neural network evaluations and enabling near-instant design for meta-atoms. Despite advances, implementing a new optical function still requires building and training a task-specific network, along with exhaustive searches for suitable …

Draft, Verify, and Improve: Toward Training-Aware Speculative Decoding
Shrenik Bhansali, Larry Heck
https://arxiv.org/abs/2510.05421 https://arxiv.org/pdf/…

Draft, Verify, and Improve: Toward Training-Aware Speculative Decoding
Autoregressive (AR) decoding is a major latency bottleneck for large language models. Speculative decoding (SD) accelerates AR by letting a drafter propose multi-token blocks that a verifier accepts or rejects. However, many SD systems require heavy offline training or extra components. These choices raise data/compute cost and can yield brittle drafters under distribution drift. We introduce \emph{Draft, Verify, \& Improve (DVI)}, a training-aware self-speculative framework that combines infer…

D-Artemis: A Deliberative Cognitive Framework for Mobile GUI Multi-Agents
Hongze Mi, Yibo Feng, Wenjie Lu, Yuqi Wang, Jinyuan Li, Song Cao, He Cui, Tengfei Tian, Xuelin Zhang, Haotian Luo, Di Sun, Naiqiang Tan, Gang Pan
https://arxiv.org/abs/2509.21799

D-Artemis: A Deliberative Cognitive Framework for Mobile GUI Multi-Agents
Graphical User Interface (GUI) agents aim to automate a wide spectrum of human tasks by emulating user interaction. Despite rapid advancements, current approaches are hindered by several critical challenges: data bottleneck in end-to-end training, high cost of delayed error detection, and risk of contradictory guidance. Inspired by the human cognitive loop of Thinking, Alignment, and Reflection, we present D-Artemis -- a novel deliberative framework in this paper. D-Artemis leverages a fine-gra…

DeepPrune: Parallel Scaling without Inter-trace Redundancy
Shangqing Tu, Yaxuan Li, Yushi Bai, Lei Hou, Juanzi Li
https://arxiv.org/abs/2510.08483 https://…

DeepPrune: Parallel Scaling without Inter-trace Redundancy
Parallel scaling has emerged as a powerful paradigm to enhance reasoning capabilities in large language models (LLMs) by generating multiple Chain-of-Thought (CoT) traces simultaneously. However, this approach introduces significant computational inefficiency due to inter-trace redundancy -- our analysis reveals that over 80% of parallel reasoning traces yield identical final answers, representing substantial wasted computation. To address this critical efficiency bottleneck, we propose DeepPru…

Efficient Discriminative Joint Encoders for Large Scale Vision-Language Reranking
Mitchell Keren Taraday, Shahaf Wagner, Chaim Baskin
https://arxiv.org/abs/2510.06820 https://…

Efficient Discriminative Joint Encoders for Large Scale Vision-Language Reranking
Multimodal retrieval still leans on embedding-based models like CLIP for fast vector search over pre-computed image embeddings. Yet, unlike text retrieval, where joint-encoder rerankers are standard, comparable vision--language rerankers are largely absent. We find that seminal joint encoders such as BLIP are severely bottlenecked by an expensive visual feature-extraction stage, preventing practical deployment at scale. Motivated by this bottleneck, we introduce EDJE, an Efficient Discriminativ…

gLSTM: Mitigating Over-Squashing by Increasing Storage Capacity
Hugh Blayney, \'Alvaro Arroyo, Xiaowen Dong, Michael M. Bronstein
https://arxiv.org/abs/2510.08450 https://…

gLSTM: Mitigating Over-Squashing by Increasing Storage Capacity
Graph Neural Networks (GNNs) leverage the graph structure to transmit information between nodes, typically through the message-passing mechanism. While these models have found a wide variety of applications, they are known to suffer from over-squashing, where information from a large receptive field of node representations is collapsed into a single fixed sized vector, resulting in an information bottleneck. In this paper, we re-examine the over-squashing phenomenon through the lens of model st…

A Near-Cache Architectural Framework for Cryptographic Computing
Jingyao Zhang, Elaheh Sadredini
https://arxiv.org/abs/2509.23179 https://arxiv.org/pdf/250…

A Near-Cache Architectural Framework for Cryptographic Computing
Recent advancements in post-quantum cryptographic algorithms have led to their standardization by the National Institute of Standards and Technology (NIST) to safeguard information security in the post-quantum era. These algorithms, however, employ public keys and signatures that are 3 to 9$\times$ longer than those used in pre-quantum cryptography, resulting in significant performance and energy efficiency overheads. A critical bottleneck identified in our analysis is the cache bandwidth. This…

Efficient Construction of Large Search Spaces for Auto-Tuning
Floris-Jan Willemsen, Rob V. van Nieuwpoort, Ben van Werkhoven
https://arxiv.org/abs/2509.26253 https://

Efficient Construction of Large Search Spaces for Auto-Tuning
Automatic performance tuning, or auto-tuning, accelerates high-performance codes by exploring vast spaces of code variants. However, due to the large number of possible combinations and complex constraints, constructing these search spaces can be a major bottleneck. Real-world applications have been encountered where the search space construction takes minutes to hours or even days. Current state-of-the-art techniques for search space construction, such as chain-of-trees, lack a formal foundati…

EMMA: Generalizing Real-World Robot Manipulation via Generative Visual Transfer
Zhehao Dong, Xiaofeng Wang, Zheng Zhu, Yirui Wang, Yang Wang, Yukun Zhou, Boyuan Wang, Chaojun Ni, Runqi Ouyang, Wenkang Qin, Xinze Chen, Yun Ye, Guan Huang
https://arxiv.org/abs/2509.22407

EMMA: Generalizing Real-World Robot Manipulation via Generative Visual Transfer
Vision-language-action (VLA) models increasingly rely on diverse training data to achieve robust generalization. However, collecting large-scale real-world robot manipulation data across varied object appearances and environmental conditions remains prohibitively time-consuming and expensive. To overcome this bottleneck, we propose Embodied Manipulation Media Adaptation (EMMA), a VLA policy enhancement framework that integrates a generative data engine with an effective training pipeline. We in…

Improving GUI Grounding with Explicit Position-to-Coordinate Mapping
Suyuchen Wang, Tianyu Zhang, Ahmed Masry, Christopher Pal, Spandana Gella, Bang Liu, Perouz Taslakian
https://arxiv.org/abs/2510.03230

Improving GUI Grounding with Explicit Position-to-Coordinate Mapping
GUI grounding, the task of mapping natural-language instructions to pixel coordinates, is crucial for autonomous agents, yet remains difficult for current VLMs. The core bottleneck is reliable patch-to-pixel mapping, which breaks when extrapolating to high-resolution displays unseen during training. Current approaches generate coordinates as text tokens directly from visual features, forcing the model to infer complex position-to-pixel mappings implicitly; as a result, accuracy degrades and fai…

Low-probability Tokens Sustain Exploration in Reinforcement Learning with Verifiable Reward
Guanhua Huang, Tingqiang Xu, Mingze Wang, Qi Yi, Xue Gong, Siheng Li, Ruibin Xiong, Kejiao Li, Yuhao Jiang, Bo Zhou
https://arxiv.org/abs/2510.03222

Low-probability Tokens Sustain Exploration in Reinforcement Learning with Verifiable Reward
Reinforcement Learning with Verifiable Rewards (RLVR) has propelled Large Language Models in complex reasoning, yet its scalability is often hindered by a training bottleneck where performance plateaus as policy entropy collapses, signaling a loss of exploration. Previous methods typically address this by maintaining high policy entropy, yet the precise mechanisms that govern meaningful exploration have remained underexplored. Our analysis suggests that an unselective focus on entropy risks amp…

SparseServe: Unlocking Parallelism for Dynamic Sparse Attention in Long-Context LLM Serving
Qihui Zhou, Peiqi Yin, Pengfei Zuo, James Cheng
https://arxiv.org/abs/2509.24626 http…

SparseServe: Unlocking Parallelism for Dynamic Sparse Attention in Long-Context LLM Serving
Serving long-context LLMs is costly because attention computation grows linearly with context length. Dynamic sparse attention algorithms (DSAs) mitigate this by attending only to the key-value (KV) cache of critical tokens. However, with DSAs, the main performance bottleneck shifts from HBM bandwidth to HBM capacity: KV caches for unselected tokens must remain in HBM for low-latency decoding, constraining parallel batch size and stalling further throughput gains. Offloading these underutilized…

Crosslisted article(s) found for q-bio.OT. https://arxiv.org/list/q-bio.OT/new
[1/1]:
- Automated Genomic Interpretation via Concept Bottleneck Models for Medical Robotics
Zijun Li, Jinchang Zhang, Ming Zhang, Guoyu Lu

SemShareKV: Efficient KVCache Sharing for Semantically Similar Prompts via Token-Level LSH Matching
Xinye Zhao, Spyridon Mastorakis
https://arxiv.org/abs/2509.24832 https://

SemShareKV: Efficient KVCache Sharing for Semantically Similar Prompts via Token-Level LSH Matching
As large language models (LLMs) continue to scale, the memory footprint of key-value (KV) caches during inference has become a significant bottleneck. Existing approaches primarily focus on compressing KV caches within a single prompt or reusing shared prefixes or frequently ocurred text segments across prompts. However, such strategies are limited in scenarios where prompts are semantically similar but lexically different, which frequently occurs in tasks such as multi-document summarization a…

Distilled Protein Backbone Generation
Liyang Xie, Haoran Zhang, Zhendong Wang, Wesley Tansey, Mingyuan Zhou
https://arxiv.org/abs/2510.03095 https://arxiv.…

Distilled Protein Backbone Generation
Diffusion- and flow-based generative models have recently demonstrated strong performance in protein backbone generation tasks, offering unprecedented capabilities for de novo protein design. However, while achieving notable performance in generation quality, these models are limited by their generating speed, often requiring hundreds of iterative steps in the reverse-diffusion process. This computational bottleneck limits their practical utility in large-scale protein discovery, where thousand…

Autoproof: Automated Segmentation Proofreading for Connectomics
Gary B Huang, William M Katz, Stuart Berg, Louis Scheffer
https://arxiv.org/abs/2509.26585 https://

Autoproof: Automated Segmentation Proofreading for Connectomics
Producing connectomes from electron microscopy (EM) images has historically required a great deal of human proofreading effort. This manual annotation cost is the current bottleneck in scaling EM connectomics, for example, in making larger connectome reconstructions feasible, or in enabling comparative connectomics where multiple related reconstructions are produced. In this work, we propose using the available ground-truth data generated by this manual annotation effort to learn a machine lear…

Enhancing Communication Efficiency in FL with Adaptive Gradient Quantization and Communication Frequency Optimization
Asadullah Tariq, Tariq Qayyum, Mohamed Adel Serhani, Farag Sallabi, Ikbal Taleb, Ezedin S. Barka
https://arxiv.org/abs/2509.23419

Enhancing Communication Efficiency in FL with Adaptive Gradient Quantization and Communication Frequency Optimization
Federated Learning (FL) enables participant devices to collaboratively train deep learning models without sharing their data with the server or other devices, effectively addressing data privacy and computational concerns. However, FL faces a major bottleneck due to high communication overhead from frequent model updates between devices and the server, limiting deployment in resource-constrained wireless networks. In this paper, we propose a three-fold strategy. Firstly, an Adaptive Feature-Eli…

LABELING COPILOT: A Deep Research Agent for Automated Data Curation in Computer Vision
Debargha Ganguly, Sumit Kumar, Ishwar Balappanawar, Weicong Chen, Shashank Kambhatla, Srinivasan Iyengar, Shivkumar Kalyanaraman, Ponnurangam Kumaraguru, Vipin Chaudhary
https://arxiv.org/abs/2509.22631

LABELING COPILOT: A Deep Research Agent for Automated Data Curation in Computer Vision
Curating high-quality, domain-specific datasets is a major bottleneck for deploying robust vision systems, requiring complex trade-offs between data quality, diversity, and cost when researching vast, unlabeled data lakes. We introduce Labeling Copilot, the first data curation deep research agent for computer vision. A central orchestrator agent, powered by a large multimodal language model, uses multi-step reasoning to execute specialized tools across three core capabilities: (1) Calibrated Di…

DyMoDreamer: World Modeling with Dynamic Modulation
Boxuan Zhang, Runqing Wang, Wei Xiao, Weipu Zhang, Jian Sun, Gao Huang, Jie Chen, Gang Wang
https://arxiv.org/abs/2509.24804 …

DyMoDreamer: World Modeling with Dynamic Modulation
A critical bottleneck in deep reinforcement learning (DRL) is sample inefficiency, as training high-performance agents often demands extensive environmental interactions. Model-based reinforcement learning (MBRL) mitigates this by building world models that simulate environmental dynamics and generate synthetic experience, improving sample efficiency. However, conventional world models process observations holistically, failing to decouple dynamic objects and temporal features from static backg…

Looking Alike From Far to Near: Enhancing Cross-Resolution Re-Identification via Feature Vector Panning
Zanwu Liu, Chao Yuan, Bo Li, Xiaowei Zhang, Guanglin Niu
https://arxiv.org/abs/2510.00936

Looking Alike From Far to Near: Enhancing Cross-Resolution Re-Identification via Feature Vector Panning
In surveillance scenarios, varying camera distances cause significant differences among pedestrian image resolutions, making it hard to match low-resolution (LR) images with high-resolution (HR) counterparts, limiting the performance of Re-Identification (ReID) tasks. Most existing Cross-Resolution ReID (CR-ReID) methods rely on super-resolution (SR) or joint learning for feature compensation, which increases training and inference complexity and has reached a performance bottleneck in recent s…

ReLAM: Learning Anticipation Model for Rewarding Visual Robotic Manipulation
Nan Tang, Jing-Cheng Pang, Guanlin Li, Chao Qian, Yang Yu
https://arxiv.org/abs/2509.22402 https://

ReLAM: Learning Anticipation Model for Rewarding Visual Robotic Manipulation
Reward design remains a critical bottleneck in visual reinforcement learning (RL) for robotic manipulation. In simulated environments, rewards are conventionally designed based on the distance to a target position. However, such precise positional information is often unavailable in real-world visual settings due to sensory and perceptual limitations. In this study, we propose a method that implicitly infers spatial distances through keypoints extracted from images. Building on this, we introdu…

LUMA: Low-Dimension Unified Motion Alignment with Dual-Path Anchoring for Text-to-Motion Diffusion Model
Haozhe Jia, Wenshuo Chen, Yuqi Lin, Yang Yang, Lei Wang, Mang Ning, Bowen Tian, Songning Lai, Nanqian Jia, Yifan Chen, Yutao Yue
https://arxiv.org/abs/2509.25304

LUMA: Low-Dimension Unified Motion Alignment with Dual-Path Anchoring for Text-to-Motion Diffusion Model
While current diffusion-based models, typically built on U-Net architectures, have shown promising results on the text-to-motion generation task, they still suffer from semantic misalignment and kinematic artifacts. Through analysis, we identify severe gradient attenuation in the deep layers of the network as a key bottleneck, leading to insufficient learning of high-level features. To address this issue, we propose \textbf{LUMA} (\textit{\textbf{L}ow-dimension \textbf{U}nified \textbf{M}otion …

MARCOS: Deep Thinking by Markov Chain of Continuous Thoughts
Jiayu Liu, Zhenya Huang, Anya Sims, Enhong Chen, Yee Whye Teh, Ning Miao
https://arxiv.org/abs/2509.25020 https://…

MARCOS: Deep Thinking by Markov Chain of Continuous Thoughts
The current paradigm for reasoning in large language models (LLMs) involves models "thinking out loud" via a sequence of tokens, known as chain-of-thought (CoT). This approach, while effective, has several significant drawbacks. Firstly, inference requires autoregressive generation of often thousands of CoT tokens, which is slow and computationally expensive. Secondly, it constrains reasoning to the discrete space of tokens, creating an information bottleneck across reasoning steps. Thirdly, it…