Hallo4D: Multi-Modal Hallucination Mitigation for Consistent Spatio-Temporal Generation Paper • 2607.12752 • Published 13 days ago • 20
Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading Paper • 2607.08964 • Published 19 days ago • 75
LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget Paper • 2607.14952 • Published 12 days ago • 203
VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Paper • 2607.14935 • Published 12 days ago • 170
Metacognition in LLMs: Foundations, Progress, and Opportunities Paper • 2607.11881 • Published 15 days ago • 29
Nemotron-Labs-Diffusion: A Tri-Mode Language Model Unifying Autoregressive, Diffusion, and Self-Speculation Decoding Paper • 2607.05722 • Published 21 days ago • 13
Raster2Seq: Polygon Sequence Generation for Floorplan Reconstruction Paper • 2602.09016 • Published May 11 • 5
OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization Paper • 2605.17757 • Published May 18 • 66
DocAtlas: Multilingual Document Understanding Across 80+ Languages Paper • 2605.12623 • Published May 12 • 4
Learning Visual Feature-Based World Models via Residual Latent Action Paper • 2605.07079 • Published May 8 • 5