5 papers
VIGOR: VIdeo Geometry-Oriented Reward for Temporal Generative Alignment
Tengjiao Yin, Jinglei Shi, Heng Guo +1
Video diffusion models lack explicit geometric supervision during training, leading to inconsistency artifacts such as object deformation, spatial drift, and depth violations in ge…
Beyond Text Following: Repairable Arbitration Reversals in Audio-Language Models
Yichen Gao, Yiqun Zhang, Zijing Wang +7
Audio-language models (ALMs) often follow text that conflicts with audio, even when the audio evidence is clear. This raises a basic question: is the audio-supported answer unavail…
SignRoundV2: Toward Closing the Performance Gap in Extremely Low-Bit Post-Training Quantization for LLMs
Wenhua Cheng, Weiwei Zhang, Heng Guo +2
Extremely low-bit quantization is critical for efficiently deploying Large Language Models (LLMs), yet it often leads to severe performance degradation at 2 bits and even at 4 bits…
ShaRP: SHAllow-LayeR Pruning for Efficient Video Large Language Models
Yingjie Xia, Tao Liu, Jinglei Shi +4
Video Large Language Models (VLLMs) incur substantial prefilling cost due to the large number of visual tokens. While attention-based token pruning offers a promising acceleration…
BLOCK: An Open-Source Bi-Stage MLLM Character-to-Skin Pipeline for Minecraft
Hengquan Guo
We present \textbf{BLOCK}, an open-source bi-stage character-to-skin pipeline that generates pixel-perfect Minecraft skins from arbitrary character concepts. BLOCK decomposes the p…