3 citations · 7 across the 17 of their papers we have counts for
21 papers
System1-Arena: Which Decisions Can Be Left to System 1?
Tianyu Chen, Xinyang Liu, Ruyi An +2
Large language models (LLMs) often make discrete decisions, such as flagging phishing or escalating to a human. System-1 models, such as Jev and the OpenAI Decisions API, return pr…
Adaptive-GEPA: Make Your Harness Fit Heterogeneous Requests
Tianyu Chen, Yasi Zhang, Ruiyi Wang +3
Reflective optimizers such as GEPA improve language model prompts from execution traces and evaluator feedback; full-program extensions can also rewrite tools and control flow. In…
Learning to Route in Visual Space via Multi-Step Embedding Retrieval
Tianyu Chen, Mingyuan Zhou, Jiaxing Wu
LLM agents rely on retrieval tools to access external knowledge, yet visual agentic search remains severely bottlenecked by standard single-step retrievers. In current pipelines, t…
EdiVal-Agent: An Object-Centric Framework for Automated, Fine-Grained Evaluation of Multi-Turn Editing
Tianyu Chen, Yasi Zhang, Zhi Zhang +13
Instruction-based image editing has advanced rapidly, yet reliable and interpretable evaluation remains a bottleneck. Current protocols either (i) depend on paired reference images…
Improving Data Efficiency for LLM Reinforcement Fine-tuning Through Difficulty-targeted Online Data Selection and Rollout Replay
Yifan Sun, Jingyan Shen, Yibin Wang +4
Reinforcement learning (RL) has become an effective approach for fine-tuning large language models (LLMs), particularly to enhance their reasoning capabilities. However, RL fine-tu…
Few-Step Diffusion via Score identity Distillation
Mingyuan Zhou, Yi Gu, Zhendong Wang
Diffusion distillation has emerged as a promising strategy for accelerating text-to-image (T2I) diffusion models by distilling a pretrained score network into a one- or few-step ge…
A Generative Framework for Causal Estimation via Importance-Weighted Diffusion Distillation
Xinran Song, Tianyu Chen, Mingyuan Zhou
Estimating individualized treatment effects from observational data is a central challenge in causal inference, largely due to covariate imbalance and confounding bias from non-ran…
Score Distillation Beyond Acceleration: Generative Modeling from Corrupted Data
Yasi Zhang, Tianyu Chen, Zhendong Wang +3
Learning generative models directly from corrupted observations is a long standing challenge across natural and scientific domains. We introduce Restoration Score Distillation (RSD…
Denoising Score Distillation: From Noisy Diffusion Pretraining to One-Step High-Quality Generation
Tianyu Chen, Yasi Zhang, Zhendong Wang +3
Diffusion models have achieved remarkable success in generating high-resolution, realistic images across diverse natural distributions. However, their performance heavily relies on…
Enhancing and Accelerating Diffusion-Based Inverse Problem Solving through Measurements Optimization
Tianyu Chen, Zhendong Wang, Mingyuan Zhou
Diffusion models have recently demonstrated notable success in solving inverse problems. However, current diffusion model-based solutions typically require a large number of functi…
Adversarial Score identity Distillation: Rapidly Surpassing the Teacher in One Step
Mingyuan Zhou, Huangjie Zheng, Yi Gu +2
Score identity Distillation (SiD) is a data-free method that has achieved SOTA performance in image generation by leveraging only a pretrained diffusion model, without requiring an…
Diffusion-RPO: Aligning Diffusion Models through Relative Preference Optimization
Yi Gu, Zhendong Wang, Yueqin Yin +2
Aligning large language models with human preferences has emerged as a critical focus in language modeling research. Yet, integrating preference learning into Text-to-Image (T2I) g…
Guided Score identity Distillation for Data-Free One-Step Text-to-Image Generation
Mingyuan Zhou, Zhendong Wang, Huangjie Zheng +1
Diffusion-based text-to-image generation models trained on extensive text-image pairs have demonstrated the ability to produce photorealistic images aligned with textual descriptio…
Self-Augmented Preference Optimization: Off-Policy Paradigms for Language Model Alignment
Yueqin Yin, Zhendong Wang, Yujia Xie +2
Traditional language model alignment methods, such as Direct Preference Optimization (DPO), are limited by their dependence on static, pre-collected paired preference data, which h…
Score identity Distillation: Exponentially Fast Distillation of Pretrained Diffusion Models for One-Step Generation
Mingyuan Zhou, Huangjie Zheng, Zhendong Wang +2
We introduce Score identity Distillation (SiD), an innovative data-free method that distills the generative capabilities of pretrained diffusion models into a single-step generator…
Diffusion Policies creating a Trust Region for Offline Reinforcement Learning
Tianyu Chen, Zhendong Wang, Mingyuan Zhou
Offline reinforcement learning (RL) leverages pre-collected datasets to train optimal policies. Diffusion Q-Learning (DQL), introducing diffusion models as a powerful and expressiv…
Take the Bull by the Horns: Hard Sample-Reweighted Continual Training Improves LLM Generalization
Xuxi Chen, Zhendong Wang, Daouda Sow +5
In the rapidly advancing arena of large language models (LLMs), a key challenge is to enhance their capabilities amid a looming shortage of high-quality training data. Our study st…
Relative Preference Optimization: Enhancing LLM Alignment through Contrasting Responses across Identical and Diverse Prompts
Yueqin Yin, Zhendong Wang, Yi Gu +3
In the field of large language models (LLMs), aligning models with the diverse preferences of users is a critical challenge. Direct Preference Optimization (DPO) has played a key r…
A Dense Reward View on Aligning Text-to-Image Diffusion with Preference
Shentao Yang, Tianqi Chen, Mingyuan Zhou
Aligning text-to-image diffusion model (T2I) with preference has been gaining increasing research attention. While prior works exist on directly optimizing T2I by preference data,…
Improving In-Context Learning in Diffusion Models with Visual Context-Modulated Prompts
Tianqi Chen, Yongfei Liu, Zhendong Wang +4
In light of the remarkable success of in-context learning in large language models, its potential extension to the vision domain, particularly with visual foundation models like St…
Learning Stackable and Skippable LEGO Bricks for Efficient, Reconfigurable, and Variable-Resolution Diffusion Modeling
Huangjie Zheng, Zhendong Wang, Jianbo Yuan +5
Diffusion models excel at generating photo-realistic images but come with significant computational costs in both training and sampling. While various techniques address these comp…