Tootfinder

This https://arxiv.org/abs/2506.00202 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

What do professional software developers need to know to succeed in an age of Artificial Intelligence?
Generative AI is showing early evidence of productivity gains for software developers, but concerns persist regarding workforce disruption and deskilling. We describe our research with 21 developers at the cutting edge of using AI, summarizing 12 of their work goals we uncovered, together with 75 associated tasks and the skills & knowledge for each, illustrating how developers use AI at work. From all of these, we distilled our findings in the form of 5 insights. We found that the skills & know…

This https://arxiv.org/abs/2506.02308 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

MINT: Multimodal Instruction Tuning with Multimodal Interaction Grouping
Recent advances in multimodal foundation models have achieved state-of-the-art performance across a range of tasks. These breakthroughs are largely driven by new pre-training paradigms that leverage large-scale, unlabeled multimodal data, followed by instruction fine-tuning on curated labeled datasets and high-quality prompts. While there is growing interest in scaling instruction fine-tuning to ever-larger datasets in both quantity and scale, our findings reveal that simply increasing the numb…

This https://arxiv.org/abs/2503.01177 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csET_…

Scalable Connectivity for Ising Machines: Dense to Sparse
In recent years, hardware implementations of Ising machines have emerged as a viable alternative to quantum computing for solving hard optimization problems among other applications. Unlike quantum hardware, dense connectivity can be achieved in classical systems. However, we show that dense connectivity leads to severe frequency slowdowns and interconnect congestion scaling unfavorably with system sizes. As a scalable solution, we propose a systematic sparsification method for dense graphs by …

This https://arxiv.org/abs/2505.23891 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_hept…

A microscopic Normal Matrix Model for $(A)dS_2$
We describe the duality between the gravitating $c=1$ (compact) Sine-Gordon model and a normal matrix model. From a two-dimensional quantum gravity perspective and due to the periodic nature of the potential, this model admits both anti-de Sitter and de-Sitter saddles, similarly to simpler models of Sine-Dilaton gravity, as well as more complicated interpolating "wineglass wormhole" geometries. From a string theory perspective the Euclidean de-Sitter (genus zero) saddles are related to the pres…

[2025-06-04 Wed (UTC), 1 new article found for cs.PF Performance]
#toXiv_bot_toot

[2025-06-04 Wed (UTC), 31 new articles found for cs.DC Distributed, Parallel, and Cluster Computing]
#toXiv_bot_toot

On Some New Congruences For Biregular Overpartitions
Anakha V
https://arxiv.org/abs/2507.02720 https://arxiv.org/pdf/2507.02720

On Some New Congruences For Biregular Overpartitions
Inspired by the recent work by Nadji, Ahmia and Ramírez, we examined the arithmetic properties of $\bar{B}_{l_1,l_2} (n)$, the number of overpartitions of n whose parts are neither divisible by $l_1$ nor divisible by $l_2$. In particular, we establish some congruences modulo k in {4, 8, 6, 12} satisfied by $\bar{B}_{l_1,l_2} (n)$ where $l_1$ and $l_2$ take values as arbitrary powers of 2 and 3. Moreover, we extend certain results proved in [26] and [15] for $l_1$ and $l_2$ with random powers o…

[2025-06-04 Wed (UTC), 2 new articles found for cs.LO Logic in Computer Science]
#toXiv_bot_toot

This https://arxiv.org/abs/2506.01046 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

STATE-NAV: Stability-Aware Traversability Estimation for Bipedal Navigation on Rough Terrain
Bipedal robots have advantages in maneuvering human-centered environments, but face greater failure risk compared to other stable mobile plarforms such as wheeled or quadrupedal robots. While learning-based traversability has been widely studied for these platforms, bipedal traversability has instead relied on manually designed rules with limited consideration of locomotion stability on rough terrain. In this work, we present the first learning-based traversability estimation and risk-sensitive…

Replaced article(s) found for cs.CR. https://arxiv.org/list/cs.CR/new
[1/1]:
- OblivIO: Securing reactive programs by oblivious execution with bounded traffic overheads
Jeppe Fredsgaard Blaabjerg, Aslan Askarov

Replaced article(s) found for physics.ed-ph. https://arxiv.org/list/physics.ed-ph/new
[1/1]:
- Learning quantum properties with informationally redundant external representations: An eye-track...
Eva Rexigel, Linda Qerimi, Jonas Bley, Sarah Malone, Stefan K\"uchemann, J…

Replaced article(s) found for cond-mat.str-el. https://arxiv.org/list/cond-mat.str-el/new
[1/1]:
- Quantum Magnetic Skyrmions on Kondo-type Lattices
Zhen Zhao, Emil \"Ostberg, Ferdi Aryasetiawan, Claudio Verdozzi

This https://arxiv.org/abs/2405.11676 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

The High-Dimensional Asymptotics of Principal Component Regression
We study principal components regression (PCR) in an asymptotic high-dimensional regression setting, where the number of data points is proportional to the dimension. We derive exact limiting formulas for the estimation and prediction risks, which depend in a complicated manner on the eigenvalues of the population covariance, the alignment between the population PCs and the true signal, and the number of selected PCs. A key challenge in the high-dimensional setting stems from the fact that the …

This https://arxiv.org/abs/2411.05791 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_qfi…

Forecasting Company Fundamentals
Company fundamentals are key to assessing companies' financial and overall success and stability. Forecasting them is important in multiple fields, including investing and econometrics. While statistical and contemporary machine learning methods have been applied to many time series tasks, there is a lack of comparison of these approaches on this particularly challenging data regime. To this end, we try to bridge this gap and thoroughly evaluate the theoretical properties and practical performa…

This https://arxiv.org/abs/2505.17836 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_sta…

Robust Distributed Estimation: Extending Gossip Algorithms to Ranking and Trimmed Means
This paper addresses the problem of robust estimation in gossip algorithms over arbitrary communication graphs. Gossip algorithms are fully decentralized, relying only on local neighbor-to-neighbor communication, making them well-suited for situations where communication is constrained. A fundamental challenge in existing mean-based gossip algorithms is their vulnerability to malicious or corrupted nodes. In this paper, we show that an outlier-robust mean can be computed by globally estimating …

Replaced article(s) found for physics.comp-ph. https://arxiv.org/list/physics.comp-ph/new
[1/1]:
- Hybrid Quantum Physics-informed Neural Network: Towards Efficient Learning of High-speed Flows
Fong Yew Leong, Wei-Bin Ewe, Tran Si Bui Quang, Zhongyuan Zhang, Jun Yong Khoo

Replaced article(s) found for cond-mat.mes-hall. https://arxiv.org/list/cond-mat.mes-hall/new
[1/1]:
- Theory of Valley Splitting in Si/SiGe Spin-Qubits: Interplay of Strain, Resonances and Random All...
Abel Thayil, Lasse Ermoneit, Markus Kantner

[2025-06-05 Thu (UTC), no new articles found for math.CT Category Theory]
#toXiv_bot_toot

[2025-08-04 Mon (UTC), no new articles found for cs.OH Other Computer Science]
toXiv_bot_toot

Replaced article(s) found for cs.CY. https://arxiv.org/list/cs.CY/new
[1/1]:
- The Urban Impact of AI: Modeling Feedback Loops in Next-Venue Recommendation
Giovanni Mauro, Marco Minici, Luca Pappalardo

This https://arxiv.org/abs/2506.01297 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

MobCLIP: Learning General-purpose Geospatial Representation at Scale
Representation learning of geospatial locations remains a core challenge in achieving general geospatial intelligence. Current embedding methods often lack versatility, limiting their utility across diverse tasks in both human and natural domains. We present MobCLIP, the first nationwide general-purpose location encoder, integrating an unprecedented diversity of data modalities through effective and scalable multimodal fusion. Adopting a novel CLIP-based architecture, our framework aligns 100M+…

This https://arxiv.org/abs/2506.02965 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Memory-Efficient and Privacy-Preserving Collaborative Training for Mixture-of-Experts LLMs
Mixture-of-Experts (MoE) has been gaining popularity due to its successful adaptation to large language models (LLMs). In this work, we introduce Privacy-preserving Collaborative Mixture-of-Experts (PC-MoE), which leverages the sparsity of the MoE architecture for memory-efficient decentralized collaborative LLM training, enabling multiple parties with limited GPU-memory and data resources to collectively train more capable LLMs than they could achieve individually. At the same time, this appro…

This https://arxiv.org/abs/2502.12012 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csET_…

Evolving Hard Maximum Cut Instances for Quantum Approximate Optimization Algorithms
Variational quantum algorithms, such as the Recursive Quantum Approximate Optimization Algorithm (RQAOA), have become increasingly popular, offering promising avenues for employing Noisy Intermediate-Scale Quantum devices to address challenging combinatorial optimization tasks like the maximum cut problem. In this study, we utilize an evolutionary algorithm equipped with a unique fitness function. This approach targets hard maximum cut instances within the latent space of a Graph Autoencoder, i…

This https://arxiv.org/abs/2505.23199 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_hept…

Chaos in the holographic matrix models for meson and baryon
In recent years, the investigation of chaos has become a bridge connecting gravity theory and quantum field theory, especially within the framework of gauge-gravity duality. In this work, we study holographically the chaos in the matrix models for meson and baryon, which are derived from the $\mathrm{D4}/\mathrm{D6}/\overline{\mathrm{D6}}$ approach as a top-down holographic model for QCD. Since these matrix models can be simplified into coupled oscillator models with special parameters, we anal…

PII Jailbreaking in LLMs via Activation Steering Reveals Personal Information Leakage
Krishna Kanth Nakka, Xue Jiang, Xuebing Zhou
https://arxiv.org/abs/2507.02332

PII Jailbreaking in LLMs via Activation Steering Reveals Personal Information Leakage
This paper investigates privacy jailbreaking in LLMs via steering, focusing on whether manipulating activations can bypass LLM alignment and alter response behaviors to privacy related queries (e.g., a certain public figure's sexual orientation). We begin by identifying attention heads predictive of refusal behavior for private attributes (e.g., sexual orientation) using lightweight linear probes trained with privacy evaluator labels. Next, we steer the activations of a small subset of these at…

Replaced article(s) found for cs.PF. https://arxiv.org/list/cs.PF/new
[1/1]:
- Fast solvers for Tokamak fluid models with PETSC -- Part I
Mark F. Adams, Jin Chen, Benjamin Sturdevant

This https://arxiv.org/abs/2506.01056 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

MCP-Zero: Proactive Toolchain Construction for LLM Agents from Scratch
Function-calling has enabled large language models (LLMs) to act as tool-using agents, but injecting thousands of tool schemas into the prompt is costly and error-prone. We introduce MCP-Zero, a proactive agent framework that lets the LLM itself decide when and which external tools to retrieve, thereby assembling a task-specific toolchain from scratch. The framework is built upon three components: (1) Proactive Tool Request, where the model emits a structured $\left<\operatorname{tool\_assistan…

This https://arxiv.org/abs/2505.23240 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

Joint estimation of smooth graph signals from partial linear measurements
Given an undirected and connected graph $G$ on $T$ vertices, suppose each vertex $t$ has a latent signal $x_t \in \mathbb{R}^n$ associated to it. Given partial linear measurements of the signals, for a potentially small subset of the vertices, our goal is to estimate $x_t$'s. Assuming that the signals are smooth w.r.t $G$, in the sense that the quadratic variation of the signals over the graph is small, we obtain non-asymptotic bounds on the mean squared error for jointly recovering $x_t$'s, fo…

\'Etude statistique du facteur premier m\'edian, 4: somme des inverses
Jonathan Rotg\'e
https://arxiv.org/abs/2507.02739 https://

Étude statistique du facteur premier médian, 4: somme des inverses
We consider the sum of the reciprocals of the middle prime factor of an integer, defined according to multiplicity or not. We obtain an asymptotic expansion in the first case and an asymptotic formula involving an implicit parameter in the second. Both these results improve on previous estimates available in the literature.

[2025-07-04 Fri (UTC), 12 new articles found for cond-mat.str-el Strongly Correlated Electrons]
toXiv_bot_toot

This https://arxiv.org/abs/2506.01016 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Optimistic critics can empower small actors
Actor-critic methods have been central to many of the recent advances in deep reinforcement learning. The most common approach is to use symmetric architectures, whereby both actor and critic have the same network topology and number of parameters. However, recent works have argued for the advantages of asymmetric setups, specifically with the use of smaller actors. We perform broad empirical investigations and analyses to better understand the implications of this and find that, in general, sm…

This https://arxiv.org/abs/2506.00618 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

RiOSWorld: Benchmarking the Risk of Multimodal Compter-Use Agents
With the rapid development of multimodal large language models (MLLMs), they are increasingly deployed as autonomous computer-use agents capable of accomplishing complex computer tasks. However, a pressing issue arises: Can the safety risk principles designed and aligned for general MLLMs in dialogue scenarios be effectively transferred to real-world computer-use scenarios? Existing research on evaluating the safety risks of MLLM-based computer-use agents suffers from several limitations: it ei…

This https://arxiv.org/abs/2505.20459 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_hept…

Holographic Timelike c-function
The integration of high-energy degrees of freedom along the renormalization group (RG) flow in Poincaré-invariant theories can be captured by a monotonic c-function. For such theories, holographic monotonic c-functions have been constructed using entanglement entropy. However, in theories with broken Lorentz invariance, such constructions generally fail, reflecting both the violation of the entanglement RG monotonicity and its limitations in capturing certain properties of non-relativistic RG …

Replaced article(s) found for cs.ET. https://arxiv.org/list/cs.ET/new
[1/1]:
- Vertiport Terminal Scheduling and Throughput Analysis for Multiple Surface Directions
Ravi Raj Saxena, T. V. Prabhakar, Joy Kuri, Manogna Yadav

Replaced article(s) found for cs.PF. https://arxiv.org/list/cs.PF/new
[1/1]:
- Fast solvers for Tokamak fluid models with PETSC
Mark F. Adams, Jin Chen, Benjamin Sturdevant

This https://arxiv.org/abs/2504.08435 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

High-dimensional Gaussian and bootstrap approximations for robust means
Recent years have witnessed much progress on Gaussian and bootstrap approximations to the distribution of max-type statistics of sums of independent random vectors with dimension $d$ large relative to the sample size $n$. However, for any number of moments $m>2$ that the summands may possess, there exist distributions such that these approximations break down if $d$ grows faster than $n^{\frac{m}{2}-1}$. In this paper, we establish Gaussian and bootstrap approximations to the distributions of w…

The $\mu-$invariant of fine Selmer groups associated to general Drinfeld modules
Hang Chen
https://arxiv.org/abs/2507.02688 https://a…

The $μ-$invariant of fine Selmer groups associated to general Drinfeld modules
Let $F$ be a global function field over the finite field $\mathbb{F}_q$ where $q$ is a prime power and $A$ be the ring of elements in $F$ regular outside $\infty$. Let $ϕ$ be an arbitrary Drinfeld module over $F$ For a fixed non-zero prime ideal $\mathfrak{p}$ of $A$, we show that on the constant $\mathbb{Z}_{\textit{p}}-$extension $\mathfrak{F}$ of $F$, the Pontryagin dual of the fine Selmer group associated to the $\mathfrak{p}-$primary torsion of $ϕ$ over $\mathfrak{F}$ is a finitely gener…

This https://arxiv.org/abs/2506.00691 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Optimizing Sensory Neurons: Nonlinear Attention Mechanisms for Accelerated Convergence in Permutation-Invariant Neural Networks for Reinforcement Learning
Training reinforcement learning (RL) agents often requires significant computational resources and extended training times. To address this, we build upon the foundation laid by Google Brain's Sensory Neuron, which introduced a novel neural architecture for reinforcement learning tasks that maintained permutation in-variance in the sensory neuron system. While the baseline model demonstrated significant performance improvements over traditional approaches, we identified opportunities to enhance…

This https://arxiv.org/abs/2506.00140 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

Balancing Profit and Fairness in Risk-Based Pricing Markets
Dynamic, risk-based pricing can systematically exclude vulnerable consumer groups from essential resources such as health insurance and consumer credit. We show that a regulator can realign private incentives with social objectives through a learned, interpretable tax schedule. First, we provide a formal proposition that bounding each firm's \emph{local} demographic gap implicitly bounds the \emph{global} opt-out disparity, motivating firm-level penalties. Building on this insight we introduce …

This https://arxiv.org/abs/2505.19412 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_hept…

2d Cardy-Rabinovici model with the modified Villain lattice: Exact dualities and symmetries
The Cardy-Rabinovici model is a toy model of the lattice $U(1)$ gauge theories to study various oblique confinement states associated with the nonzero $θ$ angles. We reformulate the $2$d version of this model using the modified Villain lattice formalism, and we establish the exact $θ$ periodicity for the Witten effect and the strong-weak duality at the finite lattice spacings. We then study the phase structure of this model based on the duality, symmetry and anomaly, and the perturbative reno…

This https://arxiv.org/abs/2505.23703 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

Let's Reason Formally: Natural-Formal Hybrid Reasoning Enhances LLM's Math Capability
Enhancing the mathematical reasoning capabilities of LLMs has garnered significant attention in both the mathematical and computer science communities. Recent works have made substantial progress in both Natural Language (NL) reasoning and Formal Language (FL) reasoning by leveraging the potential of pure Reinforcement Learning (RL) methods on base models. However, RL approaches struggle to impart new capabilities not presented in the base model, highlighting the need to integrate more knowledg…

This https://arxiv.org/abs/2411.11824 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

Theoretical Foundations of Conformal Prediction
This book is about conformal prediction and related inferential techniques that build on permutation tests and exchangeability. These techniques are useful in a diverse array of tasks, including hypothesis testing and providing uncertainty quantification guarantees for machine learning systems. Much of the current interest in conformal prediction is due to its ability to integrate into complex machine learning workflows, solving the problem of forming prediction sets without any assumptions on …

Energy Efficiency Analysis of Active RIS-enhanced Wireless Network under Power-Sum Constraint
Jingdie Xin, Yan Wang, Feng Shu, Feng Zhao, Yifan Zhao, Hao Jiang
https://arxiv.org/abs/2506.02823

Energy Efficiency Analysis of Active RIS-enhanced Wireless Network under Power-Sum Constraint
Recently, as a green wireless technology, active reconfigurable intelligent surface (RIS) attracts numerous research activities due to its amplifying ability to combat the double-fading effect compared to passive one. How about its energy efficiency (EE) over passive one? Below, the EE of active RIS-aided wireless network in Rayleigh fading channels is analyzed. Using the law of large numbers, EE is derived as a function of five factors: power allocation factor, the number (N) of RIS elements, …

This https://arxiv.org/abs/2506.00486 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

It Takes a Good Model to Train a Good Model: Generalized Gaussian Priors for Optimized LLMs
Despite rapid advancements in the research and deployment of large language models (LLMs), the statistical distribution of model parameters, as well as their influence on initialization, training dynamics, and downstream efficiency, has received surprisingly little attention. A recent work introduced BackSlash, a training-time compression algorithm. It first demonstrated that pre-trained LLM parameters follow generalized Gaussian distributions (GGDs) better. By optimizing GG priors during train…

Monodromy groups and exceptional Hodge classes, II: Sato-Tate groups
Andrea Gallese, Heidi Goodson, Davide Lombardo
https://arxiv.org/abs/2507.02535 https:…

Monodromy groups and exceptional Hodge classes, II: Sato-Tate groups
Denote by $J_m$ the Jacobian variety of the hyperelliptic curve defined by the affine equation $y^2=x^m+1$ over $\mathbb{Q}$, where $m \geq 3$ is a fixed positive integer. In this paper, we compute the Sato-Tate group of $J_m$. Currently, there is no general algorithm that computes this invariant. We also describe the Sato-Tate group of an abelian variety, generalizing existing results that apply only to non-degenerate varieties, and prove an extension of a well-known formula of Gross-Koblitz t…

[2025-06-04 Wed (UTC), 1 new article found for cs.ET Emerging Technologies]
#toXiv_bot_toot

This https://arxiv.org/abs/2505.06369 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_hept…

Yang-Lee Quantum Criticality in Various Dimensions
The Yang-Lee universality class arises when imaginary magnetic field is tuned to its critical value in the paramagnetic phase of the $d<6$ Ising model. In $d=2$, this non-unitary Conformal Field Theory (CFT) is exactly solvable via the $M(2,5)$ minimal model. As found long ago by von Gehlen using Exact Diagonalization, the corresponding real-time, quantum critical behavior arises in the periodic Ising spin chain when the imaginary longitudinal magnetic field is tuned to its critical value from …

This https://arxiv.org/abs/2505.22990 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

MenTeR: A fully-automated Multi-agenT workflow for end-to-end RF/Analog Circuits Netlist Design
RF/Analog design is essential for bridging digital technologies with real-world signals, ensuring the functionality and reliability of a wide range of electronic systems. However, analog design procedures are often intricate, time-consuming and reliant on expert intuition, and hinder the time and cost efficiency of circuit development. To overcome the limitations of the manual circuit design, we introduce MenTeR - a multiagent workflow integrated into an end-to-end analog design framework. By e…

This https://arxiv.org/abs/2505.24603 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

The Gaussian Mixing Mechanism: Renyi Differential Privacy via Gaussian Sketches
Gaussian sketching, which consists of pre-multiplying the data with a random Gaussian matrix, is a widely used technique for multiple problems in data science and machine learning, with applications spanning computationally efficient optimization, coded computing, and federated learning. This operation also provides differential privacy guarantees due to its inherent randomness. In this work, we revisit this operation through the lens of Renyi Differential Privacy (RDP), providing a refined pri…

This https://arxiv.org/abs/2409.08928 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

Self-Organizing State-Space Models with Artificial Dynamics
We consider the problem of performing parameter and state inference in a state-space model (SSM) parametrized by a static parameter $θ$. A popular idea to address this problem consists of incorporating $θ$ in the state of the system and allowing its time evolution, modelled as a Markov chain $(θ_t)_{t\geq 1}$. This proxy model defines a so-called self-organizing SSM (SO-SSM) to which one may apply standard particle filters. However, the practical implementation of this idea in a theoreticall…

This https://arxiv.org/abs/2505.21427 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

Policy Induction: Predicting Startup Success via Explainable Memory-Augmented In-Context Learning
Early-stage startup investment is a high-risk endeavor characterized by scarce data and uncertain outcomes. Traditional machine learning approaches often require large, labeled datasets and extensive fine-tuning, yet remain opaque and difficult for domain experts to interpret or improve. In this paper, we propose a transparent and data-efficient investment decision framework powered by memory-augmented large language models (LLMs) using in-context learning (ICL). Central to our method is a natu…

Cusp forms of weight 1/2 and pairs of quadratic forms
Andr\'as Bir\'o
https://arxiv.org/abs/2507.02522 https://arxiv.org/pdf/…

Cusp forms of weight 1/2 and pairs of quadratic forms
We prove a spectral summation formula for the product of four Fourier coefficients of half-integral weight cusp forms in Kohnen's subspace. The other side of the formula involves certain generalized class numbers of pairs of quadratic forms with integer coefficients.

[2025-06-05 Thu (UTC), 2 new articles found for cs.PF Performance]
#toXiv_bot_toot

[2025-06-05 Thu (UTC), no new articles found for cs.ET Emerging Technologies]
#toXiv_bot_toot

This https://arxiv.org/abs/2504.20227 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_hept…

On the CFT dual of superstring on AdS$_3$
In this work, we study the proposed duality between superstring on AdS$_3\times$S$^3\times\mathbb{T}^4$ with pure NS-NS flux and a deformed symmetric orbifold CFT. We extract the residues of 3-point string correlators at their next-to-leading poles, which can be expressed as integrals. Because of picture changing, the integrand is not unique. We make an ansatz for its proper form which linearly combines three different picture choices. On the CFT side, we obtain the corresponding residues by do…

This https://arxiv.org/abs/2505.24492 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Object Centric Concept Bottlenecks
Developing high-performing, yet interpretable models remains a critical challenge in modern AI. Concept-based models (CBMs) attempt to address this by extracting human-understandable concepts from a global encoding (e.g., image encoding) and then applying a linear classifier on the resulting concept activations, enabling transparent decision-making. However, their reliance on holistic image encodings limits their expressiveness in object-centric real-world settings and thus hinders their abilit…

This https://arxiv.org/abs/2505.19641 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond
Recent advances such as OpenAI-o1 and DeepSeek R1 have demonstrated the potential of Reinforcement Learning (RL) to enhance reasoning abilities in Large Language Models (LLMs). While open-source replication efforts have primarily focused on mathematical and coding domains, methods and resources for developing general reasoning capabilities remain underexplored. This gap is partly due to the challenge of collecting diverse and verifiable reasoning data suitable for RL. We hypothesize that logica…

This https://arxiv.org/abs/2504.08612 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_hept…

Scalar subleading soft theorems from an infinite tower of charges
We investigate the emergence of infinite-dimensional symmetries in the absence of gauge invariance by analyzing massless scalar theories. We construct an infinite tower of charges that arise from the subleading equations of motion at null infinity and are built from specific combinations of asymptotic field coefficients. Interestingly, these expressions are finite from the outset, requiring no holographic renormalization. By carefully analyzing the dynamics at spatial infinity, we show that thi…

Families of p-adic fields
Jordi Gu\`ardia R\'ubies, John W. Jones, Kevin Keating, Sebastian Pauli, David P. Roberts, David Roe
https://arxiv.org/abs/2507.02360

Families of p-adic fields
We improve the database of $p$-adic fields in the LMFDB by systematically using Krasner-Monge polynomials and working relatively as well as absolutely. These improvements organize $p$-adic fields into families. They thereby make long lists of fields more manageable and various theoretical structures more evident. In particular, the database now includes all degree $n$ extensions of $\mathbb{Q}_p$, for $p<200$ and $n \leq 23$.

[2025-06-04 Wed (UTC), 4 new articles found for math.ST Statistics Theory]
#toXiv_bot_toot

This https://arxiv.org/abs/2505.24434 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Graph Flow Matching: Enhancing Image Generation with Neighbor-Aware Flow Fields
Flow matching casts sample generation as learning a continuous-time velocity field that transports noise to data. Existing flow matching networks typically predict each point's velocity independently, considering only its location and time along its flow trajectory, and ignoring neighboring points. However, this pointwise approach may overlook correlations between points along the generation trajectory that could enhance velocity predictions, thereby improving downstream generation quality. To …

This https://arxiv.org/abs/2505.17433 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

MemeReaCon: Probing Contextual Meme Understanding in Large Vision-Language Models
Memes have emerged as a popular form of multimodal online communication, where their interpretation heavily depends on the specific context in which they appear. Current approaches predominantly focus on isolated meme analysis, either for harmful content detection or standalone interpretation, overlooking a fundamental challenge: the same meme can express different intents depending on its conversational context. This oversight creates an evaluation gap: although humans intuitively recognize ho…

This https://arxiv.org/abs/2501.07198 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_hept…

Large charge operators at large spin from relativistically rotating vortices
We study the ground states of CFTs with a global $U(1)$ symmetry on $\mathbb{R}\times S^2$ in the regime of large charge $Q$ and large angular momentum $J$, using large charge EFT. We find that in the range $Q \ll J \ll Q^2$, the ground state solution is a superfluid densely populated with vortices rotating at a constant angular velocity $Ω$. This is a relativistic generalization of the known (non-relativistic) rigid rotation phase, which corresponds to the small $Ω$ limit of our solution. In…

This https://arxiv.org/abs/2505.10981 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

Rethinking the Role of Prompting Strategies in LLM Test-Time Scaling: A Perspective of Probability Theory
Recently, scaling test-time compute on Large Language Models (LLM) has garnered wide attention. However, there has been limited investigation of how various reasoning prompting strategies perform as scaling. In this paper, we focus on a standard and realistic scaling setting: majority voting. We systematically conduct experiments on 6 LLMs $\times$ 8 prompting strategies $\times$ 6 benchmarks. Experiment results consistently show that as the sampling time and computational overhead increase, co…

This https://arxiv.org/abs/2505.24298 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning
Reinforcement learning (RL) has become a trending paradigm for training large language models (LLMs), particularly for reasoning tasks. Effective RL for LLMs requires massive parallelization and poses an urgent need for efficient training systems. Most existing large-scale RL systems for LLMs are synchronous by alternating generation and training in a batch setting, where the rollouts in each training batch are generated by the same (or latest) model. This stabilizes RL training but suffers fro…

[2025-07-04 Fri (UTC), 6 new articles found for math.NT Number Theory]
toXiv_bot_toot

This https://arxiv.org/abs/2504.21131 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

A Formalism for Optimal Search with Dynamic Heuristics (Extended Version)
While most heuristics studied in heuristic search depend only on the state, some accumulate information during search and thus also depend on the search history. Various existing approaches use such dynamic heuristics in $\mathrm{A}^*$-like algorithms and appeal to classic results for $\mathrm{A}^*$ to show optimality. However, doing so ignores the complexities of searching with a mutable heuristic. In this paper we formalize the idea of dynamic heuristics and use them in a generic algorithm fr…

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/2503.11207 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

Can Large Reasoning Models do Analogical Reasoning under Perceptual Uncertainty?
This work presents a first evaluation of two state-of-the-art Large Reasoning Models (LRMs), OpenAI's o3-mini and DeepSeek R1, on analogical reasoning, focusing on well-established nonverbal human IQ tests based on Raven's progressive matrices. We benchmark with the I-RAVEN dataset and its extension, I-RAVEN-X, which tests the ability to generalize to longer reasoning rules and ranges of the attribute values. To assess the influence of visual uncertainties on these symbolic analogical reasoning…

This https://arxiv.org/abs/2505.23585 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

On-Policy RL with Optimal Reward Baseline
Reinforcement learning algorithms are fundamental to align large language models with human preferences and to enhance their reasoning capabilities. However, current reinforcement learning algorithms often suffer from training instability due to loose on-policy constraints and computational inefficiency due to auxiliary models. In this work, we propose On-Policy RL with Optimal reward baseline (OPO), a novel and simplified reinforcement learning algorithm designed to address these challenges. O…

This https://arxiv.org/abs/2502.11753 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

HintsOfTruth: A Multimodal Checkworthiness Detection Dataset with Real and Synthetic Claims
Misinformation can be countered with fact-checking, but the process is costly and slow. Identifying checkworthy claims is the first step, where automation can help scale fact-checkers' efforts. However, detection methods struggle with content that is (1) multimodal, (2) from diverse domains, and (3) synthetic. We introduce HintsOfTruth, a public dataset for multimodal checkworthiness detection with 27K real-world and synthetic image/claim pairs. The mix of real and synthetic data makes this dat…

This https://arxiv.org/abs/2505.23527 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Normalizing Flows are Capable Models for RL
Modern reinforcement learning (RL) algorithms have found success by using powerful probabilistic models, such as transformers, energy-based models, and diffusion/flow-based models. To this end, RL researchers often choose to pay the price of accommodating these models into their algorithms -- diffusion models are expressive, but are computationally intensive due to their reliance on solving differential equations, while autoregressive transformer models are scalable but typically require learni…

This https://arxiv.org/abs/2502.00698 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

MM-IQ: Benchmarking Human-Like Abstraction and Reasoning in Multimodal Models
IQ testing has served as a foundational methodology for evaluating human cognitive capabilities, deliberately decoupling assessment from linguistic background, language proficiency, or domain-specific knowledge to isolate core competencies in abstraction and reasoning. Yet, artificial intelligence research currently lacks systematic benchmarks to quantify these critical cognitive capabilities in multimodal systems. To address this crucial gap, we propose MM-IQ, a comprehensive evaluation framew…

This https://arxiv.org/abs/2505.23470 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Refining Labeling Functions with Limited Labeled Data
Programmatic weak supervision (PWS) significantly reduces human effort for labeling data by combining the outputs of user-provided labeling functions (LFs) on unlabeled datapoints. However, the quality of the generated labels depends directly on the accuracy of the LFs. In this work, we study the problem of fixing LFs based on a small set of labeled examples. Towards this goal, we develop novel techniques for repairing a set of LFs by minimally changing their results on the labeled examples suc…

This https://arxiv.org/abs/2505.22813 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

X-Factor: Quality Is a Dataset-Intrinsic Property
In the universal quest to optimize machine-learning classifiers, three factors -- model architecture, dataset size, and class balance -- have been shown to influence test-time performance but do not fully account for it. Previously, evidence was presented for an additional factor that can be referred to as dataset quality, but it was unclear whether this was actually a joint property of the dataset and the model architecture, or an intrinsic property of the dataset itself. If quality is truly d…

This https://arxiv.org/abs/2505.21677 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

What happens when generative AI models train recursively on each others' generated outputs?
The internet is full of AI-generated content while also serving as a common source of training data for generative AI (genAI) models. This duality raises the possibility that future genAI models may be trained on other models' generated outputs. Prior work has studied consequences of models training on their own generated outputs, but limited work has considered what happens if models ingest content produced by other models. Given society's increasing dependence on genAI tools, understanding do…

This https://arxiv.org/abs/2505.20734 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Adversarial bandit optimization for approximately linear functions
We consider a bandit optimization problem for nonconvex and non-smooth functions, where in each trial the loss function is the sum of a linear function and a small but arbitrary perturbation chosen after observing the player's choice. We give both expected and high probability regret bounds for the problem. Our result also implies an improved high-probability regret bound for the bandit linear optimization, a special case with no perturbation. We also give a lower bound on the expected regret.

This https://arxiv.org/abs/2506.02867 has been replaced.
link: https://scholar.google.com/scholar?q=a

Demystifying Reasoning Dynamics with Mutual Information: Thinking Tokens are Information Peaks in LLM Reasoning
Large reasoning models (LRMs) have demonstrated impressive capabilities in complex problem-solving, yet their internal reasoning mechanisms remain poorly understood. In this paper, we investigate the reasoning trajectories of LRMs from an information-theoretic perspective. By tracking how mutual information (MI) between intermediate representations and the correct answer evolves during LRM reasoning, we observe an interesting MI peaks phenomenon: the MI at specific generative steps exhibits a s…

This https://arxiv.org/abs/2505.18570 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

VISTA: Vision-Language Inference for Training-Free Stock Time-Series Analysis
Stock price prediction remains a complex and high-stakes task in financial analysis, traditionally addressed using statistical models or, more recently, language models. In this work, we introduce VISTA (Vision-Language Inference for Stock Time-series Analysis), a novel, training-free framework that leverages Vision-Language Models (VLMs) for multi-modal stock forecasting. VISTA prompts a VLM with both textual representations of historical stock prices and their corresponding line charts to pre…

This https://arxiv.org/abs/2506.02576 has been replaced.
link: https://scholar.google.com/scholar?q=a

ADFormer: Aggregation Differential Transformer for Passenger Demand Forecasting
Passenger demand forecasting helps optimize vehicle scheduling, thereby improving urban efficiency. Recently, attention-based methods have been used to adequately capture the dynamic nature of spatio-temporal data. However, existing methods that rely on heuristic masking strategies cannot fully adapt to the complex spatio-temporal correlations, hindering the model from focusing on the right context. These works also overlook the high-level correlations that exist in the real world. Effectively …

This https://arxiv.org/abs/2505.17226 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Secure and Private Federated Learning: Achieving Adversarial Resilience through Robust Aggregation
Federated Learning (FL) enables collaborative machine learning across decentralized data sources without sharing raw data. It offers a promising approach to privacy-preserving AI. However, FL remains vulnerable to adversarial threats from malicious participants, referred to as Byzantine clients, who can send misleading updates to corrupt the global model. Traditional aggregation methods, such as simple averaging, are not robust to such attacks. More resilient approaches, like the Krum algorithm…

This https://arxiv.org/abs/2506.02139 has been replaced.
link: https://scholar.google.com/scholar?q=a

The Unified Cognitive Consciousness Theory for Language Models: Anchoring Semantics, Thresholds of Activation, and Emergent Reasoning
Few-shot learning in large language models (LLMs) reveals a core paradox: certain tasks generalize from just a few examples, while others demand extensive supervision. To explain this, we introduce the Unified Cognitive Consciousness Theory (UCCT), which reconceptualizes LLMs not as deficient agents, but as unconscious substrates: dense, distributed repositories of linguistic and conceptual patterns that operate without explicit semantics, intention, or goal-directed reasoning. Under this view,…

This https://arxiv.org/abs/2505.16933 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuning
In this work, we introduce LLaDA-V, a purely diffusion-based Multimodal Large Language Model (MLLM) that integrates visual instruction tuning with masked diffusion models, representing a departure from the autoregressive paradigms dominant in current multimodal approaches. Built upon LLaDA, a representative large language diffusion model, LLaDA-V incorporates a vision encoder and MLP connector that projects visual features into the language embedding space, enabling effective multimodal alignme…

This https://arxiv.org/abs/2505.14884 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Polar Sparsity: High Throughput Batched LLM Inferencing with Scalable Contextual Sparsity
Accelerating large language model (LLM) inference is critical for real-world deployments requiring high throughput and low latency. Contextual sparsity, where each token dynamically activates only a small subset of the model parameters, shows promise but does not scale to large batch sizes due to union of active neurons quickly approaching dense computation. We introduce Polar Sparsity, highlighting a key shift in sparsity importance from MLP to Attention layers as we scale batch size and seque…

This https://arxiv.org/abs/2505.14613 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Virtual Cells: Predict, Explain, Discover
Drug discovery is fundamentally a process of inferring the effects of treatments on patients, and would therefore benefit immensely from computational models that can reliably simulate patient responses, enabling researchers to generate and test large numbers of therapeutic hypotheses safely and economically before initiating costly clinical trials. Even a more specific model that predicts the functional response of cells to a wide range of perturbations would be tremendously valuable for disco…

This https://arxiv.org/abs/2505.10360 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

FactsR: A Safer Method for Producing High Quality Healthcare Documentation
There are now a multitude of AI-scribing solutions for healthcare promising the utilization of large language models for ambient documentation. However, these AI scribes still rely on one-shot, or few-shot prompts for generating notes after the consultation has ended, employing little to no reasoning. This risks long notes with an increase in hallucinations, misrepresentation of the intent of the clinician, and reliance on the proofreading of the clinician to catch errors. A dangerous combinati…

This https://arxiv.org/abs/2505.06459 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Improved Uncertainty Quantification in Physics-Informed Neural Networks Using Error Bounds and Solution Bundles
Physics-Informed Neural Networks (PINNs) have been widely used to obtain solutions to various physical phenomena modeled as Differential Equations. As PINNs are not naturally equipped with mechanisms for Uncertainty Quantification, some work has been done to quantify the different uncertainties that arise when dealing with PINNs. In this paper, we use a two-step procedure to train Bayesian Neural Networks that provide uncertainties over the solutions to differential equation systems provided by…

This https://arxiv.org/abs/2505.01874 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Towards Trustworthy Federated Learning with Untrusted Participants
Resilience against malicious participants and data privacy are essential for trustworthy federated learning, yet achieving both with good utility typically requires the strong assumption of a trusted central server. This paper shows that a significantly weaker assumption suffices: each pair of participants shares a randomness seed unknown to others. In a setting where malicious participants may collude with an untrusted server, we propose CafCor, an algorithm that integrates robust gradient agg…

This https://arxiv.org/abs/2504.09132 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Self-Supervised Autoencoder Network for Robust Heart Rate Extraction from Noisy Photoplethysmogram: Applying Blind Source Separation to Biosignal Analysis
Biosignals can be viewed as mixtures measuring particular physiological events, and blind source separation (BSS) aims to extract underlying source signals from mixtures. This paper proposes a self-supervised multi-encoder autoencoder (MEAE) to separate heartbeat-related source signals from photoplethysmogram (PPG), enhancing heart rate (HR) detection in noisy PPG data. The MEAE is trained on PPG signals from a large open polysomnography database without any pre-processing or data selection. Th…

This https://arxiv.org/abs/2504.06212 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

NNN: Next-Generation Neural Networks for Marketing Measurement
We present NNN, an experimental Transformer-based neural network approach to marketing measurement. Unlike Marketing Mix Models (MMMs) which rely on scalar inputs and parametric decay functions, NNN uses rich embeddings to capture both quantitative and qualitative aspects of marketing and organic channels (e.g., search queries, ad creatives). This, combined with its attention mechanism, potentially enables NNN to model complex interactions, capture long-term effects, and improve sales attributi…

This https://arxiv.org/abs/2503.22733 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

RBFleX-NAS: Training-Free Neural Architecture Search Using Radial Basis Function Kernel and Hyperparameter Detection
Neural Architecture Search (NAS) is an automated technique to design optimal neural network architectures for a specific workload. Conventionally, evaluating candidate networks in NAS involves extensive training, which requires significant time and computational resources. To address this, training-free NAS has been proposed to expedite network evaluation with minimal search time. However, state-of-the-art training-free NAS algorithms struggle to precisely distinguish well-performing networks f…

This https://arxiv.org/abs/2503.21224 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Efficient Learning for Entropy-Regularized Markov Decision Processes via Multilevel Monte Carlo
Designing efficient learning algorithms with complexity guarantees for Markov decision processes (MDPs) with large or continuous state and action spaces remains a fundamental challenge. We address this challenge for entropy-regularized MDPs with Polish state and action spaces, assuming access to a generative model of the environment. We propose a novel family of multilevel Monte Carlo (MLMC) algorithms that integrate fixed-point iteration with MLMC techniques and a generic stochastic approximat…

This https://arxiv.org/abs/2503.20117 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Exact and Linear Convergence for Federated Learning under Arbitrary Client Participation is Attainable
This work tackles the fundamental challenges in Federated Learning (FL) posed by arbitrary client participation and data heterogeneity, prevalent characteristics in practical FL settings. It is well-established that popular FedAvg-style algorithms struggle with exact convergence and can suffer from slow convergence rates since a decaying learning rate is required to mitigate these scenarios. To address these issues, we introduce the concept of stochastic matrix and the corresponding time-varyin…

This https://arxiv.org/abs/2503.17797 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Enhancing Fourier Neural Operators with Local Spatial Features
Partial Differential Equation (PDE) problems often exhibit strong local spatial structures, and effectively capturing these structures is critical for approximating their solutions. Recently, the Fourier Neural Operator (FNO) has emerged as an efficient approach for solving these PDE problems. By using parametrization in the frequency domain, FNOs can efficiently capture global patterns. However, this approach inherently overlooks the critical role of local spatial features, as frequency-domain…

This https://arxiv.org/abs/2503.10503 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Sample Compression for Continual Learning
Continual learning algorithms aim to learn from a sequence of tasks, making the training distribution non-stationary. The majority of existing continual learning approaches in the literature rely on heuristics and do not provide learning guarantees. In this paper, we present a new method called Continual Pick-to-Learn (CoP2L), which is able to retain the most representative samples for each task in an efficient way. CoP2L combines the Pick-to-Learn algorithm (rooted in the sample compression th…

This https://arxiv.org/abs/2503.09969 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Detecting Dataset Bias in Medical AI: A Generalized and Modality-Agnostic Auditing Framework
Artificial Intelligence (AI) is now firmly at the center of evidence-based medicine. Despite many success stories that edge the path of AI's rise in healthcare, there are comparably many reports of significant shortcomings and unexpected behavior of AI in deployment. A major reason for these limitations is AI's reliance on association-based learning, where non-representative machine learning datasets can amplify latent bias during training and/or hide it during testing. To unlock new tools capa…

This https://arxiv.org/abs/2503.09532 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability
Sparse autoencoders (SAEs) are a popular technique for interpreting language model activations, and there is extensive recent work on improving SAE effectiveness. However, most prior work evaluates progress using unsupervised proxy metrics with unclear practical relevance. We introduce SAEBench, a comprehensive evaluation suite that measures SAE performance across eight diverse metrics, spanning interpretability, feature disentanglement and practical applications like unlearning. To enable syst…

This https://arxiv.org/abs/2503.09427 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Language-Enhanced Representation Learning for Single-Cell Transcriptomics
Single-cell RNA sequencing (scRNA-seq) offers detailed insights into cellular heterogeneity. Recent advancements leverage single-cell large language models (scLLMs) for effective representation learning. These models focus exclusively on transcriptomic data, neglecting complementary biological knowledge from textual descriptions. To overcome this limitation, we propose scMMGPT, a novel multimodal framework designed for language-enhanced representation learning in single-cell transcriptomics. Un…

This https://arxiv.org/abs/2503.09128 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

FlexiReg: Flexible Urban Region Representation Learning
The increasing availability of urban data offers new opportunities for learning region representations, which can be used as input to machine learning models for downstream tasks such as check-in or crime prediction. While existing solutions have produced promising results, an issue is their fixed formation of regions and fixed input region features, which may not suit the needs of different downstream tasks. To address this limitation, we propose a model named FlexiReg for urban region represe…

This https://arxiv.org/abs/2503.09117 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

GRU: Mitigating the Trade-off between Unlearning and Retention for Large Language Models
Large language model (LLM) unlearning has demonstrated its essential role in removing privacy and copyright-related responses, crucial for their legal and safe applications. However, the pursuit of complete unlearning often comes with substantial costs due to its compromises in their general functionality, leading to a notorious trade-off between unlearning and retention. In examining the update process for unlearning dynamically, we find gradients hold essential information for revealing this …