StreamPI: Streaming Multimodal Temporal Modeling for Vision-Language-Action Models Paper • 2608.26067 • Published about 1 month ago • 20
PlayWorld: Benchmarking World Models with Agent Players over Long-Horizon Objectives Paper • 2608.13552 • Published Aug 13 • 47
Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation Paper • 2607.11886 • Published Jul 13 • 60
UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Paper • 2607.08768 • Published Jul 9 • 35
AlphaGRPO: Unlocking Self-Reflective Multimodal Generation in UMMs via Decompositional Verifiable Reward Paper • 2605.12495 • Published May 12 • 35