Computer Science

Artificial IntelligenceComputational ComplexityComputational Engineering, Finance, and ScienceComputational GeometryComputation and LanguageComputers and SocietyComputer Science and Game TheoryComputer Vision and Pattern RecognitionCryptography and SecurityDatabasesData Structures and AlgorithmsDigital LibrariesDiscrete Mathematics
Distributed, Parallel, and Cluster ComputingEmerging TechnologiesFormal Languages and Automata TheoryGraphicsHardware ArchitectureHuman-Computer InteractionInformation RetrievalInformation TheoryLogic in Computer ScienceMachine LearningMathematical SoftwareMultiagent Systems
MultimediaNetworking and Internet ArchitectureNeural and Evolutionary ComputingNumerical AnalysisOperating SystemsPerformanceProgramming LanguagesRoboticsSocial and Information NetworksSoftware EngineeringSoundSymbolic Computation
Entropy Is Not Enough: Unlocking Effective Reinforcement Learning for Visual Reasoning via Vision-Anchored Token Selection

Entropy Is Not Enough: Unlocking Effective Rei...

Artificial Intelligence
Avatar
Senjie Jin
1 view
Neuron Populations Exhibit Divergent Selectivity with Scale

Neuron Populations Exhibit Divergent Selectivi...

Machine Learning
Avatar
Amil Dravid
7 views
Skill-RM: Unifying Heterogeneous Evaluation Criteria via Agent Skill

Skill-RM: Unifying Heterogeneous Evaluation Cr...

Machine Learning
Avatar
librarian
5 views
Dynamic Short Convolutions Improve Transformers

Dynamic Short Convolutions Improve Transformers

Machine Learning
Avatar
librarian
5 views
q0: Primitives for Hyper-Epoch Pretraining

q0: Primitives for Hyper-Epoch Pretraining

Machine Learning
Avatar
librarian
7 views
Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories

Language Models Need Sleep: Learning to Self-M...

Machine Learning
Avatar
Ali Behrouz
6 views
Reasoning Structure of Large Language Models

Reasoning Structure of Large Language Models

Artificial Intelligence
Avatar
librarian
4 views
Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language Models

Imaginative Perception Tokens Enhance Spatial ...

Artificial Intelligence
Avatar
librarian
5 views
Rethinking the Role of Tensor Decompositions in Post-Training LLM Compression

Rethinking the Role of Tensor Decompositions i...

Machine Learning
Avatar
librarian
7 views
Training a Predictive Coding Network on ImageNet using Equilibrium Propagation

Training a Predictive Coding Network on ImageN...

Machine Learning
Avatar
librarian
10 views
When Model Merging Breaks Routing: Training-Free Calibration for MoE

When Model Merging Breaks Routing: Training-Fr...

Machine Learning
Avatar
Xiaojun Quan
7 views
KVarN: Variance-Normalized KV-Cache Quantization Mitigates Error Accumulation in Reasoning Tasks

KVarN: Variance-Normalized KV-Cache Quantizati...

Machine Learning
Avatar
librarian
9 views
CauTion: Knowing When to Trust LLMs for Ensemble Causal Discovery

CauTion: Knowing When to Trust LLMs for Ensemb...

Machine Learning
Avatar
librarian
6 views
Gender-Dependent Diagnostic Substitution in LLM Medical Triage: Same Symptoms, Unequal Urgency

Gender-Dependent Diagnostic Substitution in LL...

Artificial Intelligence
Avatar
Qi Han Wong
6 views
Diagnosing Knowledge Gaps in LLM Tool Use: An Agentic Benchmark for Novel API Acquisition

Diagnosing Knowledge Gaps in LLM Tool Use: An ...

Artificial Intelligence
Avatar
Jinnuo Liu
7 views
From Answers to States: Verifiable Process-Level Evaluation of Chemical Reasoning in Large Language Models

From Answers to States: Verifiable Process-Lev...

Artificial Intelligence
Avatar
librarian
6 views
Measurement Geometry and Design for Trustworthy Generative Inverse Problems

Measurement Geometry and Design for Trustworth...

Machine Learning
Avatar
librarian
8 views
SPADE-Bench: Evaluating Spontaneous Strategic Deception in Agents via Plan-Action Divergence

SPADE-Bench: Evaluating Spontaneous Strategic ...

Computation and Language
Avatar
librarian
4 views
MCP-Persona: Benchmarking LLM Agents on Real-World Personal Applications via Environment Simulation

MCP-Persona: Benchmarking LLM Agents on Real-W...

Artificial Intelligence
Avatar
librarian
8 views
Drifting Preference Optimization for One-Step Generative Models

Drifting Preference Optimization for One-Step ...

Machine Learning
Avatar
librarian
11 views
Policy and World Modeling Co-Training for Language Agents

Policy and World Modeling Co-Training for Lang...

Machine Learning
Avatar
librarian
9 views
Iteris: Agentic Research Loops for Computational Mathematics

Iteris: Agentic Research Loops for Computation...

Artificial Intelligence
Avatar
librarian
9 views
A Local Perturbation Theory for Cross-Domain Interference and Recovery in Multi-Domain RL

A Local Perturbation Theory for Cross-Domain I...

Machine Learning
Avatar
librarian
9 views
On the Scaling of PEFT: Towards Million Personal Models of Trillion Parameters

On the Scaling of PEFT: Towards Million Person...

Machine Learning
Avatar
librarian
11 views
A Biconvex Formulation for Stable Transport of Mixture Models with a Unique Solution

A Biconvex Formulation for Stable Transport of...

Machine Learning
Avatar
librarian
9 views
IntraShuffler: A Privacy Preserving Framework for Heterogeneous DP Federated Learning

IntraShuffler: A Privacy Preserving Framework ...

Machine Learning
Avatar
librarian
7 views
AGENTCL: Toward Rigorous Evaluation of Continual Learning in Language Agents

AGENTCL: Toward Rigorous Evaluation of Continu...

Artificial Intelligence
Avatar
Yiheng Shu
9 views
ClinEnv: An Interactive Multi-Stage Long Horizon EHR Environment for Agents

ClinEnv: An Interactive Multi-Stage Long Horiz...

Artificial Intelligence
Avatar
librarian
9 views
ContinuousBench: Can Differentially Private Synthetic Text Improve Capabilities?

ContinuousBench: Can Differentially Private Sy...

Machine Learning
Avatar
librarian
10 views
Beyond $\ell_2$-norm and $\ell_\infty$-norm: A Curvature-Inspired $\ell_p$-Norm Scheme for Deep Neural Networks

Beyond $\ell_2$-norm and $\ell_\infty$-norm: A...

Machine Learning
Avatar
Jianhao Xu
6 views
eMoT: evolving Memory-of-Thought via Symbolic Anchoring and Memory Corrosion

eMoT: evolving Memory-of-Thought via Symbolic ...

Artificial Intelligence
Avatar
librarian
7 views
Property Prediction of Stacked Bilayer Materials: A Multimodal Learning Approach

Property Prediction of Stacked Bilayer Materia...

Artificial Intelligence
Avatar
librarian
7 views
Load more