Submitted by Shibo-UCSD 38 Offline Reinforcement Learning for LLM Multi-Step Reasoning · 7 authors 116 6
Submitted by Huage001 23 CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up · 3 authors 215 5
Submitted by callanwu 21 SCOPE: Optimizing Key-Value Cache Compression in Long-context Generation · 6 authors 35 3
Submitted by hkchengrex 20 Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis Sony 2.19k 2
Submitted by saehyungl 15 Toward Robust Hyper-Detailed Image Captioning: A Multiagent Approach and Dual Evaluation Metrics for Factuality and Coverage · 5 authors 2
Submitted by JamesTheZ 15 MixLLM: LLM Quantization with Global Mixed-precision between Output-features and Highly-efficient System Design · 3 authors 4 5
Submitted by lanikoworld 11 Sequence Matters: Harnessing Video Models in 3D Super-Resolution · 6 authors 44 2
Submitted by yiyuzhuang 6 IDOL: Instant Photorealistic 3D Human Creation from a Single Image · 10 authors 312 2
Submitted by sted97 4 LLMs Lost in Translation: M-ALERT uncovers Cross-Linguistic Safety Gaps · 8 authors 3
Epiphqny 
