Select, Compress, Reinvest: A Controlled Study of Visual-Token Allocation in Long-Video MLLMs Paper • 2609.03820 • Published 4 days ago • 15
SemComp-Bench: Benchmarking Semantic Task Completion in Video Generation Paper • 2608.17426 • Published 20 days ago • 158
Scaling Creative Writing Beyond Story-Centric Data with Attribute-Guided Genre Expansion Paper • 2608.13947 • Published 24 days ago • 15
Can We Defend Against AI-Generated Video Attacks on Real-World Crisis Events? A Systematic Evaluation of Detectors, Generators and Social Dissemination Paper • 2608.14391 • Published 24 days ago • 282
OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolution Paper • 2608.00677 • Published Aug 1 • 263
OSReward: Instituting Standardized Evaluation for Cross-Platform Computer-Use Reward Models Paper • 2607.28609 • Published Jul 30 • 73
ChronoVision: Temporal Reasoning via Latent State Reconstruction Paper • 2608.05631 • Published Aug 6 • 40
WorldCycle: Self-Verifiable Reinforcement Learning for Long-Horizon Video World Models Paper • 2608.04964 • Published Aug 5 • 13
SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Paper • 2608.02023 • Published Aug 3 • 158