VepAgent: Bridging Causal-Transition via Tool-Augmented Reinforcement Learning for Video Event Prediction Paper • 2610.06293 • Published 12 days ago • 144
On-Policy Parameter Update Direction Underlies Generalization in LLM Post-Training Paper • 2609.36659 • Published 18 days ago • 87
VisionHOPE: Visual Backbones as Self-Modifying Learning Systems Paper • 2609.33325 • Published 20 days ago • 344
IterSynth: Rethinking Deep Search Agents via Role-Decoupled Iterative Synthesis Paper • 2609.29444 • Published 23 days ago • 21
Emergent Collusion in Long-Horizon LLM Agent Interaction Paper • 2609.24967 • Published 26 days ago • 20
Paint-Anything: Unified Any-Color Control for Image Generation and Editing Paper • 2609.20816 • Published about 1 month ago • 57
VākQA: A Benchmark and Evaluation Study for Telugu Spoken Factoid Question Answering Paper • 2609.19879 • Published about 1 month ago • 33
An Empirical Study of Harness Design for Coding Agents Paper • 2609.20804 • Published about 1 month ago • 95
JEPA-Anything: Learning Predictive Models across Different Worlds Paper • 2609.20800 • Published about 1 month ago • 79
LimiX-2: A Contextual Mechanism Network Towards General Structured-Data Intelligence Paper • 2609.17488 • Published Sep 15 • 865
BVB: Benchmarking Agentic Video Understanding via Programmatic Reconstruction in Blender Paper • 2609.15478 • Published Sep 14 • 34
Why Is Video Still So Expensive? A Survey of Inference-Efficiency Mechanisms in Video and Audiovisual LLMs Paper • 2609.10355 • Published Sep 9 • 17
SpatialBlock: Enhancing Spatial Intelligence in LVLMs via Synthetic Block-Stacking Problem Paper • 2609.07064 • Published Sep 7 • 123