4 citations · 5 across the 20 of their papers we have counts for
21 papers
One-Step Generative Modeling via Wasserstein Gradient Flows
Jiaqi Han, Puheng Li, Qiushan Guo +3
Diffusion models and flow-based methods have shown impressive generative capability, especially for images, but their sampling is expensive because it requires many iterative updat…
End-to-End Autoregressive Image Generation with 1D Semantic Tokenizer
Wenda Chu, Bingliang Zhang, Jiaqi Han +4
Autoregressive image modeling relies on visual tokenizers to compress images into compact latent representations. We design an end-to-end training pipeline that jointly optimizes r…
Beyond Pairwise Preferences: Listwise Reward-Aware Alignment for Diffusion Models
Austin Wang, Jiaqi Han, Stefano Ermon +1
Preference optimization has emerged as an efficient alternative to online reinforcement learning from human feedback (RLHF) for aligning text-to-image diffusion models. However, ex…
Align Your Structures: Generating Trajectories with Structure Pretraining for Molecular Dynamics
Aniketh Iyengar, Jiaqi Han, Pengwei Sun +3
Generating molecular dynamics (MD) trajectories using deep generative models has attracted increasing attention, yet remains inherently challenging due to the limited availability…
Adaptive Spectral Feature Forecasting for Diffusion Sampling Acceleration
Jiaqi Han, Juntong Shi, Puheng Li +3
Diffusion models have become the dominant tool for high-fidelity image and video generation, yet are critically bottlenecked by their inference speed due to the numerous iterative…
Data-regularized Reinforcement Learning for Diffusion Models at Scale
Haotian Ye, Kaiwen Zheng, Jiashu Xu +15
Aligning generative diffusion models with human preferences via reinforcement learning (RL) is critical yet challenging. Most existing algorithms are often vulnerable to reward hac…
Principled RL for Diffusion LLMs Emerges from a Sequence-Level Perspective
Jingyang Ou, Jiaqi Han, Minkai Xu +5
Reinforcement Learning (RL) has proven highly effective for autoregressive language models, but adapting these methods to diffusion large language models (dLLMs) presents fundament…
InfoTok: Adaptive Discrete Video Tokenizer via Information-Theoretic Compression
Haotian Ye, Qiyuan He, Jiaqi Han +12
Accurate and efficient discrete video tokenization is essential for long video sequences processing. Yet, the inherent complexity and variable information density of videos present…
Energy Scaling Laws for Diffusion Models: Quantifying Compute in Image Generation
Aniketh Iyengar, Jiaqi Han, Boris Ruf +3
The rapidly growing computational demands of diffusion models for image generation have raised significant concerns about energy consumption and environmental impact. While existin…
Generative Modeling Enables Molecular Structure Retrieval from Coulomb Explosion Imaging
Xiang Li, Till Jahnke, Rebecca Boll +12
Capturing the structural changes that molecules undergo during chemical reactions in real space and time is a long-standing dream and an essential prerequisite for understanding an…
PRISM-Physics: Causal DAG-Based Process Evaluation for Physics Reasoning
Wanjia Zhao, Qinwei Ma, Jingzhe Shi +7
Benchmarks for competition-style reasoning have advanced evaluation in mathematics and programming, yet physics remains comparatively explored. Most existing physics benchmarks eva…
CHORDS: Diffusion Sampling Accelerator with Multi-core Hierarchical ODE Solvers
Jiaqi Han, Haotian Ye, Puheng Li +3
Diffusion-based generative models have become dominant generators of high-fidelity images and videos but remain limited by their computationally expensive inference procedures. Exi…
Zero-Shot Cyclic Peptide Design via Composable Geometric Constraints
Dapeng Jiang, Xiangzhe Kong, Jiaqi Han +6
Cyclic peptides, characterized by geometric constraints absent in linear peptides, offer enhanced biochemical properties, presenting new opportunities to address unmet medical need…
GeoAda: Efficiently Finetune Geometric Diffusion Models with Equivariant Adapters
Wanjia Zhao, Jiaqi Han, Siyi Gu +3
Geometric diffusion models have shown remarkable success in molecular dynamics and structure generation. However, efficiently fine-tuning them for downstream tasks with varying geo…
Inference-Time Scaling of Diffusion Language Models via Trajectory Refinement
Meihua Dang, Jiaqi Han, Minkai Xu +3
Discrete diffusion models have recently emerged as strong alternatives to autoregressive language models, matching their performance through large-scale training. However, inferenc…
Divergence Minimization Preference Optimization for Diffusion Model Alignment
Binxu Li, Minkai Xu, Jiaqi Han +2
Diffusion models have achieved remarkable success in generating realistic and versatile images from text prompts. Inspired by the recent advancements of language models, there is a…
Discrete Diffusion Trajectory Alignment via Stepwise Decomposition
Jiaqi Han, Austin Wang, Minkai Xu +6
Discrete diffusion models have demonstrated great promise in modeling various sequence data, ranging from human language to biological sequences. Inspired by the success of RL in l…
Geometric Trajectory Diffusion Models
Jiaqi Han, Minkai Xu, Aaron Lou +2
Generative models have shown great promise in generating 3D geometric systems, which is a fundamental problem in many natural science domains such as molecule and protein design. H…
-PO: Generalizing Preference Optimization with -divergence Minimization
Jiaqi Han, Mingjian Jiang, Yuxuan Song +2
Preference optimization has made significant progress recently, with numerous methods developed to align language models with human preferences. This paper introduces -divergenc…
CPSample: Classifier Protected Sampling for Guarding Training Data During Diffusion
Joshua Kazdan, Hao Sun, Jiaqi Han +2
Diffusion models have a tendency to exactly replicate their training data, especially when trained on small datasets. Most prior work has sought to mitigate this problem by imposin…
TFG: Unified Training-Free Guidance for Diffusion Models
Haotian Ye, Haowei Lin, Jiaqi Han +6
Given an unconditional diffusion model and a predictor for a target property of interest (e.g., a classifier), the goal of training-free guidance is to generate samples with desira…