3 papers
cs.CL2026
Attention Residuals
Kimi Team, Guangyu Chen, Yu Zhang +34
Residual connections with PreNorm are standard in modern LLMs, yet they accumulate all layer outputs with fixed unit weights. This uniform aggregation causes uncontrolled hidden-st…
cs.CV2025
LangBridge: Interpreting Image as a Combination of Language Embeddings
Jiaqi Liao, Yuwei Niu, Fanqing Meng +9
Recent years have witnessed remarkable advances in Large Vision-Language Models (LVLMs), which have achieved human-level performance across various complex vision-language tasks. F…
cs.CV2025
VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation Models
Xiangdong Zhang, Jiaqi Liao, Shaofeng Zhang +4
Recent advancements in text-to-video (T2V) diffusion models have enabled high-fidelity and realistic video synthesis. However, current T2V models often struggle to generate physica…