EngiWorld: What Can Frontier Agents Deliver in Professional Engineering Environments? Paper • 2609.37686 • Published 2 days ago • 53
RayOrch: Programming and Executing Lineage-Controlled Multi-Grain Dataflows for Foundation-Model Data Preparation Paper • 2609.18703 • Published 15 days ago • 54
MultiRef-Compass: Towards Comprehensive Evaluation of Multi-Reference-to-Audio-Video Generation Paper • 2607.14189 • Published Jul 15 • 31
KeyFrame-Compass: Towards Comprehensive Evaluation of Keyframe-Conditioned Video Generation Paper • 2607.14202 • Published Jul 15 • 44
SpatialWorld: Benchmarking Interactive Spatial Reasoning of Multimodal Agents in Real-World Tasks Paper • 2606.09669 • Published Jun 8 • 50
VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Paper • 2606.02564 • Published Jun 1 • 26
LongAV-Compass: Towards Unified Evaluation of Minute-Scale Audio-Visual Generation Across T2AV, I2AV, and V2AV Paper • 2605.26244 • Published May 25 • 37
LatentOmni: Rethinking Omni-Modal Understanding via Unified Audio-Visual Latent Reasoning Paper • 2605.22012 • Published May 21 • 45
Artifact-Bench: Evaluating MLLMs on Detecting and Assessing the Artifacts of AI-Generated Videos Paper • 2605.18984 • Published May 18 • 22
Beyond the Last Layer: Multi-Layer Representation Fusion for Visual Tokenization Paper • 2605.10780 • Published May 12 • 32
Edit-Compass & EditReward-Compass: A Unified Benchmark for Image Editing and Reward Modeling Paper • 2605.13062 • Published May 13 • 33
OpenWorldLib: A Unified Codebase and Definition of Advanced World Models Paper • 2604.04707 • Published Apr 6 • 199
DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models Paper • 2603.26164 • Published Mar 27 • 280