AgenticGen: Reward-Guided Agentic Video Generation for Advertising Paper • 2609.09187 • Published 18 days ago • 9
OpenWAM: An Open, Modular Exploration Towards Systematic World-Action Model Pretraining Paper • 2609.07398 • Published 11 days ago • 77
The Missing Temporal Link: Temporal Context Routing for Script-Driven Audio-Video Generation Paper • 2609.02367 • Published 16 days ago • 37
MemTrapBench: Benchmarking Cognitive Traps in LLM Memory Use Paper • 2608.20202 • Published 29 days ago • 34
Mechanist: AI as a Scientific Instrument for Discovering the Mechanisms of Intelligence Paper • 2608.12036 • Published Aug 12 • 88
Beyond Survival: Evaluating LLMs in Social Deduction Games with Human-Aligned Strategies Paper • 2510.11389 • Published Oct 13, 2025
Beyond Borrowed Histories: Person-Aligned User Simulation for Interactive Role-Playing Evaluation Paper • 2607.27816 • Published Jul 30 • 35
MPIE-Bench: Benchmarking Anatomically Plausible Multi-Person Interaction Editing Paper • 2607.27616 • Published Jul 30 • 40
Beyond Borrowed Histories: Person-Aligned User Simulation for Interactive Role-Playing Evaluation Paper • 2607.27816 • Published Jul 30 • 35
MPIE-Bench: Benchmarking Anatomically Plausible Multi-Person Interaction Editing Paper • 2607.27616 • Published Jul 30 • 40
Keep It InMind: Benchmarking the Implicit-Association Blind Spot in Agent Memory Paper • 2607.24368 • Published Jul 27 • 34
A-RAG: Scaling Agentic Retrieval-Augmented Generation via Hierarchical Retrieval Interfaces Paper • 2602.03442 • Published Feb 3 • 22
HOMIE: Human-object Centric Video Personalization via Multimodal Intelligent Enchancement Paper • 2607.18217 • Published Jul 20 • 64
HOMIE: Human-object Centric Video Personalization via Multimodal Intelligent Enchancement Paper • 2607.18217 • Published Jul 20 • 64
DomainShuttle: Freeform Open Domain Subject-driven Text-to-video Generation Paper • 2606.26058 • Published Jun 24 • 68
DomainShuttle: Freeform Open Domain Subject-driven Text-to-video Generation Paper • 2606.26058 • Published Jun 24 • 68
SkillEvolBench: Benchmarking the Evolution from Episodic Experience to Procedural Skills Paper • 2605.24117 • Published May 22 • 23
SkillEvolBench: Benchmarking the Evolution from Episodic Experience to Procedural Skills Paper • 2605.24117 • Published May 22 • 23
CARPE: Context-Aware Image Representation Prioritization via Ensemble for Large Vision-Language Models Paper • 2601.13622 • Published Jan 20 • 1