SpatialWorld: Benchmarking Interactive Spatial Reasoning of Multimodal Agents in Real-World Tasks Paper • 2606.09669 • Published 1 day ago • 29
VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Paper • 2606.02564 • Published 8 days ago • 29
DecMem: Towards Minute-Long Consistent World Generation with Decoupled Memory Paper • 2605.31336 • Published 11 days ago • 12
LongAV-Compass: Towards Unified Evaluation of Minute-Scale Audio-Visual Generation Across T2AV, I2AV, and V2AV Paper • 2605.26244 • Published 15 days ago • 38
LatentOmni: Rethinking Omni-Modal Understanding via Unified Audio-Visual Latent Reasoning Paper • 2605.22012 • Published 19 days ago • 46
Artifact-Bench: Evaluating MLLMs on Detecting and Assessing the Artifacts of AI-Generated Videos Paper • 2605.18984 • Published 22 days ago • 22
VGGT-Edit: Feed-forward Native 3D Scene Editing with Residual Field Prediction Paper • 2605.15186 • Published 26 days ago • 26
Beyond the Last Layer: Multi-Layer Representation Fusion for Visual Tokenization Paper • 2605.10780 • Published 28 days ago • 33
Edit-Compass & EditReward-Compass: A Unified Benchmark for Image Editing and Reward Modeling Paper • 2605.13062 • Published 27 days ago • 33
SketchVLM: Vision language models can annotate images to explain thoughts and guide users Paper • 2604.22875 • Published Apr 23 • 37
OmniShow: Unifying Multimodal Conditions for Human-Object Interaction Video Generation Paper • 2604.11804 • Published Apr 13 • 72
OpenWorldLib: A Unified Codebase and Definition of Advanced World Models Paper • 2604.04707 • Published Apr 6 • 203
view article Article Welcome Gemma 4: Frontier multimodal intelligence on device +5 merve, pcuenq, sergiopaniego, burtenshaw, Steveeeeeeen, alvarobartt, SaylorTwift • Apr 2 • 907
DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models Paper • 2603.26164 • Published Mar 27 • 366
MinerU-Diffusion: Rethinking Document OCR as Inverse Rendering via Diffusion Decoding Paper • 2603.22458 • Published Mar 23 • 137
MosaicMem: Hybrid Spatial Memory for Controllable Video World Models Paper • 2603.17117 • Published Mar 17 • 88
AvatarForcing: One-Step Streaming Talking Avatars via Local-Future Sliding-Window Denoising Paper • 2603.14331 • Published Mar 15 • 14
BandPO: Bridging Trust Regions and Ratio Clipping via Probability-Aware Bounds for LLM Reinforcement Learning Paper • 2603.04918 • Published Mar 5 • 56
TimeChat-Captioner: Scripting Multi-Scene Videos with Time-Aware and Structural Audio-Visual Captions Paper • 2602.08711 • Published Feb 9 • 29