Online Draft Co-Training for Speculative Decoding in Large-Scale, Long-Context RL Post-Training Paper • 2609.07108 • Published 4 days ago • 27
LatentPress: Context Compression Beyond Text and Vision Paper • 2609.01507 • Published 10 days ago • 117
SemComp-Bench: Benchmarking Semantic Task Completion in Video Generation Paper • 2608.17426 • Published 24 days ago • 159
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 28 days ago • 282
RibAssist 3D: Biplanar Rib-Fracture Detection, Addressing, and Selective 3D Localization from CT-Derived Projections Paper • 2608.06914 • Published Aug 10 • 9
UniSwap: Streaming Audio-Visual Identity Swapping for Talking Videos Paper • 2608.11752 • Published 29 days ago • 22
OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolution Paper • 2608.00677 • Published Aug 1 • 263
360CityArena: A Realistic Virtual Urban Navigation Benchmark for Embodied Agents Paper • 2608.08814 • Published Aug 9 • 11
AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning Paper • 2608.05987 • Published Aug 6 • 102
KVAE: Family of Tokenizers for Multimodal Generative Models Paper • 2608.05798 • Published Aug 6 • 29
OneDayAgent: Towards a Long-Horizon Harness for Autonomous Agents Paper • 2608.05013 • Published Aug 4 • 37