Meta Expert: Cross-Layer Expert Sharing for Storage- and Retrieval-Efficient MoE Paper • 2610.27598 • Published 11 days ago • 46
Code2Video-Compass: A Comprehensive Benchmark for General-Purpose Code-Based Video Generation across T2V, I2V, and V2V Paper • 2610.28416 • Published 11 days ago • 49
SpatialScout: Can VLM Agents Actively Explore and Map 3D Scenes? Paper • 2610.26659 • Published 12 days ago • 156 • 3
SpatialScout: Can VLM Agents Actively Explore and Map 3D Scenes? Paper • 2610.26659 • Published 12 days ago • 156
Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation Paper • 2609.11638 • Published Sep 10 • 279
DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression Paper • 2609.19969 • Published Sep 17 • 230
FuseReg: Regularizing Layer Fusion Mitigates the Reconstruction-Generation Gap in Representation Autoencoders Paper • 2609.31620 • Published Sep 25 • 103
OmniEdu: Open Foundation Models for Learning and Teaching Paper • 2609.23088 • Published Sep 19 • 156
DataPrep-Bench: Benchmarking LLMs as Training Data Preparators Paper • 2607.20465 • Published May 19 • 57
CodeMidas: Scaling Agentic Coding RL Environments from Code Itself Paper • 2609.22068 • Published Sep 18 • 138
DataFlex-RL: An Evaluation Platform for RLVR Data Policies Paper • 2609.06107 • Published Sep 5 • 148