VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning Paper • 2608.26105 • Published 6 days ago • 266
OmniVAE: An Audio-Video VAE with Cross-Modal Alignment for Joint Generation Paper • 2607.23855 • Published Jul 26 • 27
ToolArtist: Tool-Using Unified Multimodal Models for Agentic Image Generation Paper • 2608.04436 • Published 27 days ago • 61
Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents Paper • 2605.30621 • Published May 28 • 25
Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Paper • 2607.07675 • Published Jul 8 • 64
TurnOPD: Making On-Policy Distillation Turn-Aware for Efficient Long-Horizon Agent Training Paper • 2607.05804 • Published Jul 7 • 20
SkillOpt-Lite: Better and Faster Agent Self-evolution via One Line of Vibe Paper • 2607.03451 • Published Jul 3 • 35