activity
20242026
collaborators

6 papers

cs.CV2026

Mixture of States: Routing Token-Level Dynamics for Multimodal Generation

Haozhe Liu, Ding Liu, Mingchen Zhuge +16

We introduce MoS (Mixture of States), a novel fusion paradigm for multimodal diffusion models that merges modalities using flexible, state-based interactions. The core of MoS is a…

cs.AI2025

Causal Head Gating: A Framework for Interpreting Roles of Attention Heads in Transformers

Andrew Nam, Henry Conklin, Yukang Yang +3

We present causal head gating (CHG), a scalable method for interpreting the functional roles of attention heads in transformer models. CHG learns soft gates over heads and assigns…

cs.LG2025

Training-Free Guidance Beyond Differentiability: Scalable Path Steering with Tree Search in Diffusion and Flow Models

Yingqing Guo, Yukang Yang, Hui Yuan +1

Training-free guidance enables controlled generation in diffusion and flow models, but most methods rely on gradients and assume differentiable objectives. This work focuses on tra…

cs.CL2025

Emergent Symbolic Mechanisms Support Abstract Reasoning in Large Language Models

Yukang Yang, Declan Campbell, Kaixuan Huang +3

Many recent studies have found evidence for emergent reasoning capabilities in large language models (LLMs), but debate persists concerning the robustness of these capabilities, an…

stat.ML2024

Gradient Guidance for Diffusion Models: An Optimization Perspective

Yingqing Guo, Hui Yuan, Yukang Yang +2

Diffusion models have demonstrated empirical successes in various applications and can be adapted to task-specific needs via guidance. This paper studies a form of gradient guidanc…

cs.LG2024

Latent Diffusion Models for Controllable RNA Sequence Generation

Kaixuan Huang, Yukang Yang, Kaidi Fu +3

This work presents RNAdiffusion, a latent diffusion model for generating and optimizing discrete RNA sequences of variable lengths. RNA is a key intermediary between DNA and protei…