Select, Compress, Reinvest: A Controlled Study of Visual-Token Allocation in Long-Video MLLMs Paper • 2609.03820 • Published 3 days ago • 15
LatentPress: Context Compression Beyond Text and Vision Paper • 2609.01507 • Published 5 days ago • 107
SemComp-Bench: Benchmarking Semantic Task Completion in Video Generation Paper • 2608.17426 • Published 19 days ago • 158
Zetta ζ: An Efficient Closed-Loop Embodied Harness for Self-Evolving Physical Intelligence Paper • 2608.16590 • Published 20 days ago • 150
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 23 days ago • 282
OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolution Paper • 2608.00677 • Published Aug 1 • 263
SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Paper • 2608.02023 • Published Aug 3 • 158