190 citations · 942 across the 77 of their papers we have counts for
36 papers · 1 filter
BanditSpec: Adaptive Speculative Decoding via Bandit Algorithms
Yunlong Hou, Fengzhuo Zhang, Cunxiao Du +6
Speculative decoding has emerged as a popular method to accelerate the inference of Large Language Models (LLMs) while retaining their superior text generation performance. Previou…
Understanding R1-Zero-Like Training: A Critical Perspective
Zichen Liu, Changyu Chen, Wenjun Li +5
DeepSeek-R1-Zero has shown that reinforcement learning (RL) at scale can directly enhance the reasoning capabilities of LLMs without supervised fine-tuning. In this work, we critic…
Improved Techniques for Optimization-Based Jailbreaking on Large Language Models
Xiaojun Jia, Tianyu Pang, Chao Du +5
Large language models (LLMs) are being rapidly developed, and a key component of their widespread deployment is their safety-related alignment. Many red-teaming efforts aim to jail…
Graph Diffusion Policy Optimization
Yijing Liu, Chao Du, Tianyu Pang +3
Recent research has made significant progress in optimizing diffusion models for downstream objectives, which is an important pursuit in fields such as graph generation for drug de…
Benchmarking Large Multimodal Models against Common Corruptions
Jiawei Zhang, Tianyu Pang, Chao Du +3
This technical report aims to fill a deficiency in the assessment of large multimodal models (LMMs) by specifically examining the self-consistency of their outputs when subjected t…
Gaussian Mixture Solvers for Diffusion Models
Hanzhong Guo, Cheng Lu, Fan Bao +4
Recently, diffusion models have achieved great success in generative tasks. Sampling from diffusion models is equivalent to solving the reverse diffusion stochastic differential eq…
Finetuning Text-to-Image Diffusion Models for Fairness
Xudong Shen, Chao Du, Tianyu Pang +3
The rapid adoption of text-to-image diffusion models in society underscores an urgent need to address their biases. Without interventions, these biases could propagate a skewed wor…
Intriguing Properties of Data Attribution on Diffusion Models
Xiaosen Zheng, Tianyu Pang, Chao Du +2
Data attribution seeks to trace model outputs back to training data. With the recent development of diffusion models, data attribution has become a desired module to properly assig…
On Memorization in Diffusion Models
Xiangming Gu, Chao Du, Tianyu Pang +3
Due to their capacity to generate novel and high-quality samples, diffusion models have attracted significant research interest in recent years. Notably, the typical training objec…
Improving Adversarial Robustness of DEQs with Explicit Regulations Along the Neural Dynamics
Zonghan Yang, Peng Li, Tianyu Pang +1
Deep equilibrium (DEQ) models replace the multiple-layer stacking of conventional deep networks with a fixed-point iteration of a single-layer transformation. Having been demonstra…
A Closer Look at the Adversarial Robustness of Deep Equilibrium Models
Zonghan Yang, Tianyu Pang, Yang Liu
Deep equilibrium models (DEQs) refrain from the traditional layer-stacking paradigm and turn to find the fixed point of a single layer. DEQs have achieved promising performance on…
Efficient Diffusion Policies for Offline Reinforcement Learning
Bingyi Kang, Xiao Ma, Chao Du +2
Offline reinforcement learning (RL) aims to learn optimal policies from offline datasets, where the parameterization of policies is crucial but often overlooked. Recently, Diffsuio…
Nonparametric Generative Modeling with Conditional Sliced-Wasserstein Flows
Chao Du, Tianbo Li, Tianyu Pang +2
Sliced-Wasserstein Flow (SWF) is a promising approach to nonparametric generative modeling but has not been widely adopted due to its suboptimal generative quality and lack of cond…
CoSDA: Continual Source-Free Domain Adaptation
Haozhe Feng, Zhaorui Yang, Hesun Chen +5
Without access to the source data, source-free domain adaptation (SFDA) transfers knowledge from a source-domain trained model to target domains. Recently, SFDA has gained populari…
On Calibrating Diffusion Probabilistic Models
Tianyu Pang, Cheng Lu, Chao Du +3
Recently, diffusion probabilistic models (DPMs) have achieved promising results in diverse generative tasks. A typical DPM framework includes a forward process that gradually diffu…
BAFFLE: A Baseline of Backpropagation-Free Federated Learning
Haozhe Feng, Tianyu Pang, Chao Du +3
Federated learning (FL) is a general principle for decentralized clients to train a server model collectively without sharing local data. FL is a promising framework with practical…
Universal Antisymmetry in Fermionic Neural Networks
Tianyu Pang, Shuicheng Yan, Min Lin
Fermionic neural network (FermiNet) is a recently proposed wavefunction Ansatz, which is used in variational Monte Carlo (VMC) methods to solve the many-electron Schrödinger equati…
A Roadmap for Big Model
Sha Yuan, Hanyu Zhao, Shuai Zhao +97
With the rapid development of deep learning, training Big Models (BMs) for multiple downstream tasks becomes a popular paradigm. Researchers have achieved various outcomes in the c…
Query-Efficient Black-box Adversarial Attacks Guided by a Transfer-based Prior
Yinpeng Dong, Shuyu Cheng, Tianyu Pang +2
Adversarial attacks have been extensively studied in recent years since they can identify the vulnerability of deep learning models before deployed. In this paper, we consider the…
Robustness and Accuracy Could Be Reconcilable by (Proper) Definition
Tianyu Pang, Min Lin, Xiao Yang +2
The trade-off between robustness and accuracy has been widely studied in the adversarial literature. Although still controversial, the prevailing view is that this trade-off is inh…
Model-Agnostic Meta-Attack: Towards Reliable Evaluation of Adversarial Robustness
Xiao Yang, Yinpeng Dong, Wenzhao Xiang +3
The vulnerability of deep neural networks to adversarial examples has motivated an increasing number of defense strategies for promoting model robustness. However, the progress is…
Boosting Transferability of Targeted Adversarial Examples via Hierarchical Generative Networks
Xiao Yang, Yinpeng Dong, Tianyu Pang +2
Transfer-based adversarial attacks can evaluate model robustness in the black-box setting. Several methods have demonstrated impressive untargeted transferability, however, it is s…
Accumulative Poisoning Attacks on Real-time Data
Tianyu Pang, Xiao Yang, Yinpeng Dong +2
Collecting training data from untrusted sources exposes machine learning services to poisoning adversaries, who maliciously manipulate training data to degrade the model accuracy.…
Exploring Memorization in Adversarial Training
Yinpeng Dong, Ke Xu, Xiao Yang +4
Deep learning models have a propensity for fitting the entire training set even with random labels, which requires memorization of every training sample. In this paper, we explore…