OmniDirector: General Multi-Shot Camera Cloning without Cross-Paired Data Paper • 2606.13432 • Published 6 days ago • 96
WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces Paper • 2606.09426 • Published 9 days ago • 100
DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Paper • 2606.05758 • Published 13 days ago • 5
Toward Generalist Autonomous Research via Hypothesis-Tree Refinement Paper • 2606.11926 • Published 7 days ago • 111
Retrospective Harness Optimization: Improving LLM Agents via Self-Preference over Trajectory Rollouts Paper • 2606.05922 • Published 13 days ago • 52
On the Scaling of PEFT: Towards Million Personal Models of Trillion Parameters Paper • 2606.02437 • Published 16 days ago • 228
PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training Paper • 2606.03264 • Published 15 days ago • 16
LongAttnComp: Cross-Family Context Compression for Long-Context Reasoning Paper • 2606.01336 • Published 17 days ago • 7
Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players Paper • 2605.28816 • Published 21 days ago • 423
ThriftAttention: Selective Mixed Precision for Long-Context FP4 Attention Paper • 2605.23081 • Published 27 days ago • 41
Injecting Image Guidance into Text-Conditioned Diffusion Models at Inference Paper • 2605.25191 • Published 24 days ago • 5