DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models Paper • 2512.02556 • Published about 19 hours ago • 22 • 2
GUI Exploration Lab: Enhancing Screen Navigation in Agents via Multi-Turn Reinforcement Learning Paper • 2512.02423 • Published about 24 hours ago • 1 • 1
UnicEdit-10M: A Dataset and Benchmark Breaking the Scale-Quality Barrier via Unified Verification for Reasoning-Enriched Edits Paper • 2512.02790 • Published 1 day ago • 1
Benchmarking Scientific Understanding and Reasoning for Video Generation using VideoScience-Bench Paper • 2512.02942 • Published about 12 hours ago • 1
PAI-Bench: A Comprehensive Benchmark For Physical AI Paper • 2512.01989 • Published 1 day ago • 3 • 1
TUNA: Taming Unified Visual Representations for Native Unified Multimodal Models Paper • 2512.02014 • Published 1 day ago • 33 • 4
WiseEdit: Benchmarking Cognition- and Creativity-Informed Image Editing Paper • 2512.00387 • Published 4 days ago • 2 • 2
ChronosObserver: Taming 4D World with Hyperspace Diffusion Sampling Paper • 2512.01481 • Published 2 days ago • 2 • 3
ChronosObserver: Taming 4D World with Hyperspace Diffusion Sampling Paper • 2512.01481 • Published 2 days ago • 2 • 3
HiconAgent: History Context-aware Policy Optimization for GUI Agents Paper • 2512.01763 • Published 1 day ago • 5 • 2
REASONEDIT: Towards Reasoning-Enhanced Image Editing Models Paper • 2511.22625 • Published 5 days ago • 44 • 2
AnyTalker: Scaling Multi-Person Talking Video Generation with Interactivity Refinement Paper • 2511.23475 • Published 4 days ago • 37 • 4
SO-Bench: A Structural Output Evaluation of Multimodal LLMs Paper • 2511.21750 • Published 9 days ago • 5 • 2
Inferix: A Block-Diffusion based Next-Generation Inference Engine for World Simulation Paper • 2511.20714 • Published 8 days ago • 44 • 2