ROSS: Relearning from Self-Generated Rollouts through Selective Supervision Paper • 2609.35954 • Published 5 days ago • 38
Beyond the Timeline: Augmenting Long-Video Memory with Grounded Entity Biographies Paper • 2609.38155 • Published 4 days ago • 97
Learning to Learn from Context: Synthetic Training from Perturbed Public Documents Paper • 2609.33642 • Published 6 days ago • 32
Agent-Editing World Model: Rethinking World Modeling for LLM Agents Paper • 2609.28416 • Published 10 days ago • 42
HARMONY: Hierarchical Agentic Reasoning for MONocular Image-to-Scene Synthesis Paper • 2609.26793 • Published 11 days ago • 9
RULER: Instance-aware Rubric Rewards for SVG Generation Paper • 2609.25270 • Published 12 days ago • 102
Why Do Video Diffusion Models Violate Physics? Unveiling the Flaws in Attention Mechanisms Paper • 2609.23658 • Published 13 days ago • 30