SemComp-Bench: Benchmarking Semantic Task Completion in Video Generation Paper • 2608.17426 • Published 7 days ago • 156
OmniScientist: An Omni-Modal Omni-Discipline AI Scientist Paper • 2608.13558 • Published 12 days ago • 89
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 11 days ago • 277
LycheeMemory V2: Efficient Long-Term Memory for LLM Agents via Semantic Segment-Level Consolidation Paper • 2608.12990 • Published 12 days ago • 14
PlayWorld: Benchmarking World Models with Agent Players over Long-Horizon Objectives Paper • 2608.13552 • Published 12 days ago • 45
SkillZip: Contract-Preserving Graph Compression for Scalable Agent Skill Libraries Paper • 2608.05604 • Published 19 days ago • 79
OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolution Paper • 2608.00677 • Published 24 days ago • 261
Co-Evolution in Agentic Systems: Toward Self-Directed Evolution Beyond Human Design Paper • 2608.10299 • Published 15 days ago • 135
SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Paper • 2608.02023 • Published 22 days ago • 156