activity
20242026
collaborators

10 papers

cs.LG2026

Krause Synchronization Transformers

Jingkun Liu, Yisong Yue, Max Welling +1

Self-attention in Transformers relies on globally normalized softmax weights, causing all tokens to compete for influence at every layer. When composed across depth, this interacti…

cs.LG2026

Spontaneous symmetry breaking and Goldstone modes for deep information propagation

Nabil Iqbal, T. Anderson Keller, Yue Song +2

In physical systems, whenever a continuous symmetry is spontaneously broken, the system possesses excitations called Goldstone modes, which allow coherent information propagation o…

cs.LG2026

Higher-Order Equilibrium Tracking for EM-Compressible Online Estimation

ZhiMing Li, Yue Song

We study online estimation in latent-variable models by recasting the problem as tracking a moving empirical equilibrium. Standard online EM and stochastic approximation analyses p…

cs.MM2026

Anisotropic Modality Align

Xiaomin Yu, Yijiang Li, Yuhui Zhang +8

Training multimodal large language models has long been limited by the scarcity of high-quality paired multimodal data. Recent studies show that the shared representation space of…

cs.CV2026

MOVA: Towards Scalable and Synchronized Video-Audio Generation

OpenMOSS Team, Donghua Yu, Mingshu Chen +38

Audio is indispensable for real-world video, yet generation models have largely overlooked audio components. Current approaches to producing audio-visual content often rely on casc…

cs.CR2026

Constitutional Classifiers++: Efficient Production-Grade Defenses against Universal Jailbreaks

Hoagy Cunningham, Jerry Wei, Zihan Wang +26

We introduce enhanced Constitutional Classifiers that deliver production-grade jailbreak robustness with dramatically reduced computational costs and refusal rates compared to prev…