CoRT: Counterfactual Replay for Token-Level Rubric-Guided Policy Optimization Paper • 2607.25659 • Published 3 days ago • 73
TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM Paper • 2607.27205 • Published 2 days ago • 120
ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU Paper • 2607.19191 • Published 9 days ago • 304
TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs Paper • 2607.17423 • Published 12 days ago • 166
Registers Matter for Pixel-Space Diffusion Transformers Paper • 2605.16147 • Published 25 days ago • 26
LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget Paper • 2607.14952 • Published 15 days ago • 203
InternVLA-A1.5: Unifying Understanding, Latent Foresight, and Action for Compositional Generalization Paper • 2607.04988 • Published 25 days ago • 28
SkillHone: A Harness for Continual Agent Skill Evolution Through Persistent Decision History Paper • 2606.08671 • Published Jun 23 • 46
LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling Paper • 2606.18023 • Published Jun 16 • 210
Toward Generalist Autonomous Research via Hypothesis-Tree Refinement Paper • 2606.11926 • Published Jun 10 • 130
Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language Models Paper • 2606.03988 • Published Jun 3 • 126