Pseudo-Unification: Entropy Probing Reveals Divergent Information Patterns in Unified Multimodal Models Paper • 2604.10949 • Published 1 day ago • 30
Strips as Tokens: Artist Mesh Generation with Native UV Segmentation Paper • 2604.09132 • Published 4 days ago • 26
TorchUMM: A Unified Multimodal Model Codebase for Evaluation, Analysis, and Post-training Paper • 2604.10784 • Published 2 days ago • 2
Zero-shot World Models Are Developmentally Efficient Learners Paper • 2604.10333 • Published 3 days ago • 3
Solving Physics Olympiad via Reinforcement Learning on Physics Simulators Paper • 2604.11805 • Published 1 day ago • 3
General365: Benchmarking General Reasoning in Large Language Models Across Diverse and Challenging Tasks Paper • 2604.11778 • Published 1 day ago • 4
Tracing the Roots: A Multi-Agent Framework for Uncovering Data Lineage in Post-Training LLMs Paper • 2604.10480 • Published 2 days ago • 9
ClawGUI: A Unified Framework for Training, Evaluating, and Deploying GUI Agents Paper • 2604.11784 • Published 1 day ago • 16
OmniShow: Unifying Multimodal Conditions for Human-Object Interaction Video Generation Paper • 2604.11804 • Published 1 day ago • 21
Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation Paper • 2604.10098 • Published 3 days ago • 27
MixFlow: Mixed Source Distributions Improve Rectified Flows Paper • 2604.09181 • Published 4 days ago • 1
AgentSwing: Adaptive Parallel Context Management Routing for Long-Horizon Web Agents Paper • 2603.27490 • Published 16 days ago • 12
ELT: Elastic Looped Transformers for Visual Generation Paper • 2604.09168 • Published 4 days ago • 15
WildDet3D: Scaling Promptable 3D Detection in the Wild Paper • 2604.08626 • Published 5 days ago • 219
Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory Paper • 2604.08995 • Published 4 days ago • 38
ClawBench: Can AI Agents Complete Everyday Online Tasks? Paper • 2604.08523 • Published 5 days ago • 248
MegaStyle: Constructing Diverse and Scalable Style Dataset via Consistent Text-to-Image Style Mapping Paper • 2604.08364 • Published 5 days ago • 92