Jiaqi Han

InfoTok: Adaptive Discrete Video Tokenizer via Information-Theoretic Compression

Principled RL for Diffusion LLMs Emerges from a Sequence-Level Perspective

PRISM-Physics: Causal DAG-Based Process Evaluation for Physics Reasoning

Align Your Structures: Generating Trajectories with Structure Pretraining for Molecular Dynamics

Inference-Time Scaling of Diffusion Language Models with Particle Gibbs Sampling

Discrete Diffusion Trajectory Alignment via Stepwise Decomposition

Improving Diffusion Language Model Reasoning through Joint Search in Generation Order and Token Space

Divergence Minimization Preference Optimization for Diffusion Model Alignment

Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models

GeoAda: Efficiently Finetune Geometric Diffusion Models with Equivariant Adapters

Zero-Shot Cyclic Peptide Design via Composable Geometric Constraints

CPSample: Classifier Protected Sampling for Guarding Training Data During Diffusion