Hallo4D: Multi-Modal Hallucination Mitigation for Consistent Spatio-Temporal Generation Paper • 2607.12752 • Published Jul 15 • 15
Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading Paper • 2607.08964 • Published Jul 9 • 77
LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget Paper • 2607.14952 • Published Jul 16 • 91
VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Paper • 2607.14935 • Published Jul 16 • 120
Metacognition in LLMs: Foundations, Progress, and Opportunities Paper • 2607.11881 • Published Jul 13 • 27
Nemotron-Labs-Diffusion: A Tri-Mode Language Model Unifying Autoregressive, Diffusion, and Self-Speculation Decoding Paper • 2607.05722 • Published Jul 7 • 12