Thomas Taylor

SunHaoyu1's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 8 days ago

Multi-Turn Agentic Scientific Literature Search via Workflow Induction

Paper • 2607.00597 • Published 14 days ago • 28

upvoted a paper 12 days ago

LUMOS: A Semantic Operating-System Layer for Accessibility-Grounded AI Agents

Paper • 2606.30697 • Published 16 days ago • 7

upvoted 6 papers about 2 months ago

How LoRA Remembers? A Parametric Memory Law for LLM Finetuning

Paper • 2605.30260 • Published May 28 • 44

SNLP: Layer-Parallel Inference via Structured Newton Corrections

Paper • 2605.17842 • Published May 18 • 5

AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration

Paper • 2605.20025 • Published May 19 • 191

SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution

Paper • 2605.18401 • Published May 18 • 130

CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence

Paper • 2605.12882 • Published May 13 • 274

Learning POMDP World Models from Observations with Language-Model Priors

Paper • 2605.13740 • Published May 13 • 7

upvoted 7 papers 3 months ago

Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability

Paper • 2604.06628 • Published Apr 8 • 329

SkillClaw: Let Skills Evolve Collectively with Agentic Evolver

Paper • 2604.08377 • Published Apr 9 • 295

ClawBench: Can AI Agents Complete Everyday Online Tasks?

Paper • 2604.08523 • Published Apr 9 • 265

Adam's Law: Textual Frequency Law on Large Language Models

Paper • 2604.02176 • Published Apr 2 • 509

When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models

Paper • 2604.08546 • Published Apr 9 • 116

Emergent Compositional Communication for Latent World Properties

Paper • 2604.03266 • Published Mar 18 • 7

GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning

Paper • 2604.02721 • Published Apr 3 • 639

upvoted 5 papers 4 months ago

EpochX: Building the Infrastructure for an Emergent Agent Civilization

Paper • 2603.27304 • Published Mar 28 • 47

Astrolabe: Steering Forward-Process Reinforcement Learning for Distilled Autoregressive Video Models

Paper • 2603.17051 • Published Mar 17 • 109

Efficient Reasoning with Balanced Thinking

Paper • 2603.12372 • Published Mar 12 • 151

SocialOmni: Benchmarking Audio-Visual Social Interactivity in Omni Models

Paper • 2603.16859 • Published Mar 17 • 248

Demystifing Video Reasoning

Paper • 2603.16870 • Published Mar 17 • 373