Thanh Le

thanhle93's activity

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

upvoted 3 papers 1 day ago

VideoJev: System One Model for Video Understanding and Interaction

Paper • 2610.18615 • Published 5 days ago • 360

JevGPT: Thinking Fast and Slow in Autonomous Research

Paper • 2610.18272 • Published 5 days ago • 37

UltraBERT: Beyond the Limit of BERT Pre-Training

Paper • 2610.15028 • Published 8 days ago • 70

upvoted a paper 2 days ago

Same Output, Different Gold: Measuring How Reference Choice Moves a Multilingual Benchmark Score

Paper • 2610.03825 • Published 16 days ago • 5

upvoted 2 papers 3 days ago

Less from More: Reinforcing Sparse Video Reasoning from Dense References

Paper • 2610.10893 • Published 11 days ago • 10

PolyOCR-Venus: Unified OCR Foundation Models for Text-Centric Visual Intelligence

Paper • 2609.37712 • Published 19 days ago • 36

upvoted a paper 4 days ago

DreamTrue: Action-Faithful Robot World Model with Counterfactual Post-Training

Paper • 2610.12468 • Published 10 days ago • 49

upvoted a paper 5 days ago

Recursive Game Creator: An Agentic Product-Level Experience-Oriented Game Harness

Paper • 2610.08621 • Published 12 days ago • 98

upvoted 2 papers 6 days ago

VepAgent: Bridging Causal-Transition via Tool-Augmented Reinforcement Learning for Video Event Prediction

Paper • 2610.06293 • Published 13 days ago • 145

UniWAM: Unified World-Action Model

Paper • 2610.02054 • Published 17 days ago • 80

upvoted a paper 7 days ago

Equal Ranking Quality, Different Decisions: Measuring and Reducing Order Dependence in LLM Scorers

Paper • 2608.26762 • Published 22 days ago • 24

upvoted 2 papers 8 days ago

Making LLMs Say What They Think: Measuring and Improving CoT-Interpretability Alignment

Paper • 2609.38972 • Published 18 days ago • 29

We Query, Therefore We Compute: On Oracle Computation beyond the Machine, with an Application to Agents

Paper • 2610.09243 • Published 11 days ago • 14

upvoted a paper 9 days ago

LoGRA: Scaling LLM Reinforcement Learning with Low-Rank Gradient Sketches

Paper • 2610.06647 • Published 13 days ago • 153

upvoted a paper 10 days ago

World Editing: Intervening on Executable Worlds at Increasing Depth

Paper • 2610.02331 • Published 17 days ago • 31

upvoted a paper 11 days ago

Align Then Reason: A Multimodal Lip-Sync Judge for Dubbing

Paper • 2610.00825 • Published 18 days ago • 22

upvoted a paper 12 days ago

The Low-Rank Structure of VLA Reinforcement Learning

Paper • 2609.34599 • Published 20 days ago • 23

upvoted a paper 13 days ago

CoEvoWhen: Policy-Tool Coevolution for Ultra-Long Video Temporal Grounding

Paper • 2609.40048 • Published 18 days ago • 16

upvoted 2 papers 14 days ago

Knowledge Pull Requests for Continual Document Authoring

Paper • 2609.26634 • Published 26 days ago • 13

MemoryAthena: Adaptive Routing over Latent and Generated Memories

Paper • 2609.25853 • Published 26 days ago • 16