Tom Lu

eigentom's activity

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

upvoted a paper 26 days ago

MemTrain: Self-Supervised Context Memory Training

Paper • 2606.03197 • Published Jun 2 • 19

upvoted a paper 27 days ago

Does On-Policy Distillation Really Distill? From Noisy Teacher to Self-Improvement

Paper • 2608.31046 • Published about 1 month ago • 97

upvoted a paper about 2 months ago

SAF-OPD: Stable Advantage Fusion for On-Policy Distillation

Paper • 2607.29209 • Published Jul 31 • 34

upvoted 2 papers 3 months ago

Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models

Paper • 2607.12463 • Published Jul 14 • 48

Program-as-Weights: A Programming Paradigm for Fuzzy Functions

Paper • 2607.02512 • Published Jul 2 • 308

upvoted 3 papers 4 months ago

Learning from the Self-future: On-policy Self-distillation for dLLMs

Paper • 2606.18195 • Published Jun 16 • 42

Dr-DCI: Scaling Direct Corpus Interaction via Dynamic Workspace Expansion

Paper • 2606.14885 • Published Jun 12 • 13

Masking Stale Observations Helps Search Agents -- Until It Doesn't: A Regime Map and Its Mechanism

Paper • 2606.00408 • Published May 29 • 64

upvoted 2 papers 5 months ago

WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors

Paper • 2605.10434 • Published May 11 • 30

Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction

Paper • 2605.05242 • Published May 3 • 126

upvoted 7 papers 6 months ago

Lyra 2.0: Explorable Generative 3D Worlds

Paper • 2604.13036 • Published Apr 14 • 42

MMDeepResearch-Bench: A Benchmark for Multimodal Deep Research Agents

Paper • 2601.12346 • Published Jan 18 • 52

Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding

Paper • 2604.05015 • Published Apr 6 • 232

Watch Before You Answer: Learning from Visually Grounded Post-Training

Paper • 2604.05117 • Published Apr 6 • 34

ClawBench: Can AI Agents Complete Everyday Online Tasks?

Paper • 2604.08523 • Published Apr 9 • 159

SWE-QA-Pro: A Representative Benchmark and Scalable Training Recipe for Repository-Level Code Understanding

Paper • 2603.16124 • Published Mar 17 • 3

OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis

Paper • 2603.20278 • Published Mar 17 • 103

upvoted a paper 7 months ago

AI Can Learn Scientific Taste

Paper • 2603.14473 • Published Mar 15 • 317

upvoted 2 papers 8 months ago

Self-Refining Video Sampling

Paper • 2601.18577 • Published Jan 26 • 25

VisGym: Diverse, Customizable, Scalable Environments for Multimodal Agents

Paper • 2601.16973 • Published Jan 23 • 40