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
Replacing thinking with tool usage enables reasoning in small language models

Replacing thinking with tool usage enables rea...

Machine Learning
Avatar
librarian
0 views
Meta-Learning Transformers to Improve In-Context Generalization

Meta-Learning Transformers to Improve In-Conte...

Machine Learning
Avatar
Lorenzo Braccaioli
0 views
Train-before-Test Harmonizes Language Model Rankings

Train-before-Test Harmonizes Language Model Ra...

Machine Learning
Avatar
librarian
0 views
Modeling Latent Partner Strategies for Adaptive Zero-Shot Human-Agent Collaboration

Modeling Latent Partner Strategies for Adaptiv...

Artificial Intelligence
Avatar
librarian
0 views
Beyond Scaling Curves: Internal Dynamics of Neural Networks Through the NTK Lens

Beyond Scaling Curves: Internal Dynamics of Ne...

Machine Learning
Avatar
librarian
0 views
Cascade: Token-Sharded Private LLM Inference

Cascade: Token-Sharded Private LLM Inference

Machine Learning
Avatar
librarian
0 views
How Rules Represent Causal Knowledge: Causal Modeling with Abductive Logic Programs

How Rules Represent Causal Knowledge: Causal M...

Artificial Intelligence
Avatar
librarian
0 views
SciMaster: Towards General-Purpose Scientific AI Agents, Part I. X-Master as Foundation: Can We Lead on Humanity's Last Exam?

SciMaster: Towards General-Purpose Scientific ...

Artificial Intelligence
Avatar
librarian
0 views
When Chain of Thought is Necessary, Language Models Struggle to Evade Monitors

When Chain of Thought is Necessary, Language M...

Artificial Intelligence
Avatar
librarian
0 views
Subtyping in DHOL -- Extended preprint

Subtyping in DHOL -- Extended preprint

Logic in Computer Science
Avatar
librarian
3 views
Point3R: Streaming 3D Reconstruction with Explicit Spatial Pointer Memory

Point3R: Streaming 3D Reconstruction with Expl...

Computer Vision and Pattern Recognition
Avatar
librarian
4 views
MvHo-IB: Multi-View Higher-Order Information Bottleneck for Brain Disorder Diagnosis

MvHo-IB: Multi-View Higher-Order Information B...

Machine Learning
Avatar
Kunyu Zhang
2 views
MOTIF: Modular Thinking via Reinforcement Fine-tuning in LLMs

MOTIF: Modular Thinking via Reinforcement Fine...

Computation and Language
Avatar
librarian
2 views
Answer Matching Outperforms Multiple Choice for Language Model Evaluation

Answer Matching Outperforms Multiple Choice fo...

Computation and Language
Avatar
librarian
1 view
Replicable Distribution Testing

Replicable Distribution Testing

Machine Learning
Avatar
librarian
0 views
SynapseRoute: An Auto-Route Switching Framework on Dual-State Large Language Model

SynapseRoute: An Auto-Route Switching Framewor...

Computation and Language
Avatar
librarian
0 views
Moral Responsibility or Obedience: What Do We Want from AI?

Moral Responsibility or Obedience: What Do We ...

Artificial Intelligence
Avatar
librarian
0 views
KERAP: A Knowledge-Enhanced Reasoning Approach for Accurate Zero-shot Diagnosis Prediction Using Multi-agent LLMs

KERAP: A Knowledge-Enhanced Reasoning Approach...

Artificial Intelligence
Avatar
librarian
0 views
StepHint: Multi-level Stepwise Hints Enhance Reinforcement Learning to Reason

StepHint: Multi-level Stepwise Hints Enhance R...

Artificial Intelligence
Avatar
Kaiyi Zhang
2 views
DynamiCare: A Dynamic Multi-Agent Framework for Interactive and Open-Ended Medical Decision-Making

DynamiCare: A Dynamic Multi-Agent Framework fo...

Artificial Intelligence
Avatar
Tianqi Shang
1 view
In-Training Multicalibrated Survival Analysis for Healthcare via Constrained Optimization

In-Training Multicalibrated Survival Analysis ...

Machine Learning
Avatar
Thiti Suttaket
1 view
Grounding Intelligence in Movement

Grounding Intelligence in Movement

Artificial Intelligence
Avatar
Melanie Segado
0 views
High-Order Deep Meta-Learning with Category-Theoretic Interpretation

High-Order Deep Meta-Learning with Category-Th...

Machine Learning
Avatar
librarian
1 view
LLM-Driven Treatment Effect Estimation Under Inference Time Text Confounding

LLM-Driven Treatment Effect Estimation Under I...

Machine Learning
Avatar
librarian
2 views
Fast and Simplex: 2-Simplicial Attention in Triton

Fast and Simplex: 2-Simplicial Attention in Triton

Machine Learning
Avatar
Aurko Roy
5 views
Understanding and Improving Length Generalization in Recurrent Models

Understanding and Improving Length Generalizat...

Machine Learning
Avatar
librarian
3 views
ExPO: Unlocking Hard Reasoning with Self-Explanation-Guided Reinforcement Learning

ExPO: Unlocking Hard Reasoning with Self-Expla...

Machine Learning
Avatar
librarian
3 views
Decoupled Planning and Execution: A Hierarchical Reasoning Framework for Deep Search

Decoupled Planning and Execution: A Hierarchic...

Artificial Intelligence
Avatar
librarian
8 views
Bourbaki: Self-Generated and Goal-Conditioned MDPs for Theorem Proving

Bourbaki: Self-Generated and Goal-Conditioned ...

Artificial Intelligence
Avatar
Matthieu Zimmer
0 views
Knowledge Protocol Engineering: A New Paradigm for AI in Domain-Specific Knowledge Work

Knowledge Protocol Engineering: A New Paradigm...

Artificial Intelligence
Avatar
librarian
1 view
Establishing Best Practices for Building Rigorous Agentic Benchmarks

Establishing Best Practices for Building Rigor...

Artificial Intelligence
Avatar
librarian
0 views
Revisiting Learning Rate Control

Revisiting Learning Rate Control

Machine Learning
Avatar
librarian
1 view
Load more