36 citations · 128 across the 24 of their papers we have counts for
24 papers
DLM-One: Diffusion Language Models for One-Step Sequence Generation
Tianqi Chen, Shujian Zhang, Mingyuan Zhou
This paper introduces DLM-One, a score-distillation-based framework for one-step sequence generation with continuous diffusion language models (DLMs). DLM-One eliminates iterative…
Score Forgetting Distillation: A Swift, Data-Free Method for Machine Unlearning in Diffusion Models
Tianqi Chen, Shujian Zhang, Mingyuan Zhou
The machine learning community is increasingly recognizing the importance of fostering trust and safety in modern generative AI (GenAI) models. We posit machine unlearning (MU) as…
WPO: Enhancing RLHF with Weighted Preference Optimization
Wenxuan Zhou, Ravi Agrawal, Shujian Zhang +5
Reinforcement learning from human feedback (RLHF) is a promising solution to align large language models (LLMs) more closely with human values. Off-policy preference optimization,…
Switchable Decision: Dynamic Neural Generation Networks
Shujian Zhang, Korawat Tanwisuth, Chengyue Gong +2
Auto-regressive generation models achieve competitive performance across many different NLP tasks such as summarization, question answering, and classifications. However, they are…
Language Rectified Flow: Advancing Diffusion Language Generation with Probabilistic Flows
Shujian Zhang, Lemeng Wu, Chengyue Gong +1
Recent works have demonstrated success in controlling sentence attributes (, sentiment) and structure (, syntactic structure) based on the diffusion language model. A k…
Sliced Wasserstein with Random-Path Projecting Directions
Khai Nguyen, Shujian Zhang, Tam Le +1
Slicing distribution selection has been used as an effective technique to improve the performance of parameter estimators based on minimizing sliced Wasserstein distance in applica…
Preference-grounded Token-level Guidance for Language Model Fine-tuning
Shentao Yang, Shujian Zhang, Congying Xia +3
Aligning language models (LMs) with preferences is an important problem in natural language generation. A key challenge is that preferences are typically provided at the sequence l…
AutoML-GPT: Automatic Machine Learning with GPT
Shujian Zhang, Chengyue Gong, Lemeng Wu +2
AI tasks encompass a wide range of domains and fields. While numerous AI models have been designed for specific tasks and applications, they often require considerable human effort…
POUF: Prompt-oriented unsupervised fine-tuning for large pre-trained models
Korawat Tanwisuth, Shujian Zhang, Huangjie Zheng +2
Through prompting, large-scale pre-trained models have become more expressive and powerful, gaining significant attention in recent years. Though these big models have zero-shot ca…
Fantastic Rewards and How to Tame Them: A Case Study on Reward Learning for Task-oriented Dialogue Systems
Yihao Feng, Shentao Yang, Shujian Zhang +4
When learning task-oriented dialogue (ToD) agents, reinforcement learning (RL) techniques can naturally be utilized to train dialogue strategies to achieve user-specific goals. Pri…
A Prototype-Oriented Clustering for Domain Shift with Source Privacy
Korawat Tanwisuth, Shujian Zhang, Pengcheng He +1
Unsupervised clustering under domain shift (UCDS) studies how to transfer the knowledge from abundant unlabeled data from multiple source domains to learn the representation of the…
Passage-Mask: A Learnable Regularization Strategy for Retriever-Reader Models
Shujian Zhang, Chengyue Gong, Xingchao Liu
Retriever-reader models achieve competitive performance across many different NLP tasks such as open question answering and dialogue conversations. In this work, we notice these mo…
A Unified Framework for Alternating Offline Model Training and Policy Learning
Shentao Yang, Shujian Zhang, Yihao Feng +1
In offline model-based reinforcement learning (offline MBRL), we learn a dynamic model from historically collected data, and subsequently utilize the learned model and fixed datase…
Regularizing a Model-based Policy Stationary Distribution to Stabilize Offline Reinforcement Learning
Shentao Yang, Yihao Feng, Shujian Zhang +1
Offline reinforcement learning (RL) extends the paradigm of classical RL algorithms to purely learning from static datasets, without interacting with the underlying environment dur…
ALLSH: Active Learning Guided by Local Sensitivity and Hardness
Shujian Zhang, Chengyue Gong, Xingchao Liu +3
Active learning, which effectively collects informative unlabeled data for annotation, reduces the demand for labeled data. In this work, we propose to retrieve unlabeled samples w…
FuseDream: Training-Free Text-to-Image Generation with Improved CLIP+GAN Space Optimization
Xingchao Liu, Chengyue Gong, Lemeng Wu +3
Generating images from natural language instructions is an intriguing yet highly challenging task. We approach text-to-image generation by combining the power of the retrained CLIP…
Alignment Attention by Matching Key and Query Distributions
Shujian Zhang, Xinjie Fan, Huangjie Zheng +2
The neural attention mechanism has been incorporated into deep neural networks to achieve state-of-the-art performance in various domains. Most such models use multi-head self-atte…
A Prototype-Oriented Framework for Unsupervised Domain Adaptation
Korawat Tanwisuth, Xinjie Fan, Huangjie Zheng +4
Existing methods for unsupervised domain adaptation often rely on minimizing some statistical distance between the source and target samples in the latent space. To avoid the sampl…
Learning with Different Amounts of Annotation: From Zero to Many Labels
Shujian Zhang, Chengyue Gong, Eunsol Choi
Training NLP systems typically assumes access to annotated data that has a single human label per example. Given imperfect labeling from annotators and inherent ambiguity of langua…
Bayesian Attention Belief Networks
Shujian Zhang, Xinjie Fan, Bo Chen +1
Attention-based neural networks have achieved state-of-the-art results on a wide range of tasks. Most such models use deterministic attention while stochastic attention is less exp…
Knowing More About Questions Can Help: Improving Calibration in Question Answering
Shujian Zhang, Chengyue Gong, Eunsol Choi
We study calibration in question answering, estimating whether model correctly predicts answer for each question. Unlike prior work which mainly rely on the model's confidence scor…
Contextual Dropout: An Efficient Sample-Dependent Dropout Module
Xinjie Fan, Shujian Zhang, Korawat Tanwisuth +2
Dropout has been demonstrated as a simple and effective module to not only regularize the training process of deep neural networks, but also provide the uncertainty estimation for…
Capturing Label Distribution: A Case Study in NLI
Shujian Zhang, Chengyue Gong, Eunsol Choi
We study estimating inherent human disagreement (annotation label distribution) in natural language inference task. Post-hoc smoothing of the predicted label distribution to match…
Bayesian Attention Modules
Xinjie Fan, Shujian Zhang, Bo Chen +1
Attention modules, as simple and effective tools, have not only enabled deep neural networks to achieve state-of-the-art results in many domains, but also enhanced their interpreta…