Memory-Efficient Looped Transformer: Decoupling Compute from Memory in Looped Language Models Paper β’ 2605.07721 β’ Published May 8 β’ 31
TabSTAR: A Foundation Tabular Model With Semantically Target-Aware Representations Paper β’ 2505.18125 β’ Published May 23, 2025 β’ 113
SkillMimic-V2: Learning Robust and Generalizable Interaction Skills from Sparse and Noisy Demonstrations Paper β’ 2505.02094 β’ Published May 4, 2025 β’ 19
Teaching Models to Understand (but not Generate) High-risk Data Paper β’ 2505.03052 β’ Published May 5, 2025 β’ 6
HoloTime: Taming Video Diffusion Models for Panoramic 4D Scene Generation Paper β’ 2504.21650 β’ Published Apr 30, 2025 β’ 16
Absolute Zero: Reinforced Self-play Reasoning with Zero Data Paper β’ 2505.03335 β’ Published May 6, 2025 β’ 191
ZeroSearch: Incentivize the Search Capability of LLMs without Searching Paper β’ 2505.04588 β’ Published May 7, 2025 β’ 66
Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunities Paper β’ 2505.02567 β’ Published May 5, 2025 β’ 83
Generating Physically Stable and Buildable LEGO Designs from Text Paper β’ 2505.05469 β’ Published May 8, 2025 β’ 30
On Path to Multimodal Generalist: General-Level and General-Bench Paper β’ 2505.04620 β’ Published May 7, 2025 β’ 83
Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models Paper β’ 2505.04921 β’ Published May 8, 2025 β’ 184
Flow-GRPO: Training Flow Matching Models via Online RL Paper β’ 2505.05470 β’ Published May 8, 2025 β’ 89