568 citations · 1.6k across the 26 of their papers we have counts for
26 papers
MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Data
Zongxia Li, Hongyang Du, Chengsong Huang +8
Self-evolving has emerged as a key paradigm for improving foundational models such as Large Language Models (LLMs) and Vision Language Models (VLMs) with minimal human intervention…
A Data Perspective on Enhanced Identity Preservation for Diffusion Personalization
Xingzhe He, Zhiwen Cao, Nicholas Kolkin +4
Large text-to-image models have revolutionized the ability to generate imagery using natural language. However, particularly unique or personal visual concepts, such as pets and fu…
Offline Imitation Learning with Suboptimal Demonstrations via Relaxed Distribution Matching
Lantao Yu, Tianhe Yu, Jiaming Song +2
Offline imitation learning (IL) promises the ability to learn performant policies from pre-collected demonstrations without interactions with the environment. However, imitating be…
Generalizing Bayesian Optimization with Decision-theoretic Entropies
Willie Neiswanger, Lantao Yu, Shengjia Zhao +2
Bayesian optimization (BO) is a popular method for efficiently inferring optima of an expensive black-box function via a sequence of queries. Existing information-theoretic BO proc…
A General Recipe for Likelihood-free Bayesian Optimization
Jiaming Song, Lantao Yu, Willie Neiswanger +1
The acquisition function, a critical component in Bayesian optimization (BO), can often be written as the expectation of a utility function under a surrogate model. However, to ens…
GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation
Minkai Xu, Lantao Yu, Yang Song +3
Predicting molecular conformations from molecular graphs is a fundamental problem in cheminformatics and drug discovery. Recently, significant progress has been achieved with machi…
A Unified Framework for Multi-distribution Density Ratio Estimation
Lantao Yu, Yujia Jin, Stefano Ermon
Binary density ratio estimation (DRE), the problem of estimating the ratio given their empirical samples, provides the foundation for many state-of-the-art machine learni…
Pseudo-Spherical Contrastive Divergence
Lantao Yu, Jiaming Song, Yang Song +1
Energy-based models (EBMs) offer flexible distribution parametrization. However, due to the intractable partition function, they are typically trained via contrastive divergence fo…
Multi-Agent Imitation Learning with Copulas
Hongwei Wang, Lantao Yu, Zhangjie Cao +1
Multi-agent imitation learning aims to train multiple agents to perform tasks from demonstrations by learning a mapping between observations and actions, which is essential for und…
Autoregressive Score Matching
Chenlin Meng, Lantao Yu, Yang Song +2
Autoregressive models use chain rule to define a joint probability distribution as a product of conditionals. These conditionals need to be normalized, imposing constraints on the…
Understanding Self-supervised Learning with Dual Deep Networks
Yuandong Tian, Lantao Yu, Xinlei Chen +1
We propose a novel theoretical framework to understand contrastive self-supervised learning (SSL) methods that employ dual pairs of deep ReLU networks (e.g., SimCLR). First, we pro…
Improving Maximum Likelihood Training for Text Generation with Density Ratio Estimation
Yuxuan Song, Ning Miao, Hao Zhou +3
Auto-regressive sequence generative models trained by Maximum Likelihood Estimation suffer the exposure bias problem in practical finite sample scenarios. The crux is that the numb…
MOPO: Model-based Offline Policy Optimization
Tianhe Yu, Garrett Thomas, Lantao Yu +5
Offline reinforcement learning (RL) refers to the problem of learning policies entirely from a large batch of previously collected data. This problem setting offers the promise of…
Infomax Neural Joint Source-Channel Coding via Adversarial Bit Flip
Yuxuan Song, Minkai Xu, Lantao Yu +3
Although Shannon theory states that it is asymptotically optimal to separate the source and channel coding as two independent processes, in many practical communication scenarios t…
Training Deep Energy-Based Models with f-Divergence Minimization
Lantao Yu, Yang Song, Jiaming Song +1
Deep energy-based models (EBMs) are very flexible in distribution parametrization but computationally challenging because of the intractable partition function. They are typically…
Improving Unsupervised Domain Adaptation with Variational Information Bottleneck
Yuxuan Song, Lantao Yu, Zhangjie Cao +5
Domain adaptation aims to leverage the supervision signal of source domain to obtain an accurate model for target domain, where the labels are not available. To leverage and adapt…
Meta-Inverse Reinforcement Learning with Probabilistic Context Variables
Lantao Yu, Tianhe Yu, Chelsea Finn +1
Providing a suitable reward function to reinforcement learning can be difficult in many real world applications. While inverse reinforcement learning (IRL) holds promise for automa…
Multi-Agent Adversarial Inverse Reinforcement Learning
Lantao Yu, Jiaming Song, Stefano Ermon
Reinforcement learning agents are prone to undesired behaviors due to reward mis-specification. Finding a set of reward functions to properly guide agent behaviors is particularly…
Lipschitz Generative Adversarial Nets
Zhiming Zhou, Jiadong Liang, Yuxuan Song +5
In this paper, we study the convergence of generative adversarial networks (GANs) from the perspective of the informativeness of the gradient of the optimal discriminative function…
Deep Reinforcement Learning for Green Security Games with Real-Time Information
Yufei Wang, Zheyuan Ryan Shi, Lantao Yu +4
Green Security Games (GSGs) have been proposed and applied to optimize patrols conducted by law enforcement agencies in green security domains such as combating poaching, illegal l…
Understanding the Effectiveness of Lipschitz-Continuity in Generative Adversarial Nets
Zhiming Zhou, Yuxuan Song, Lantao Yu +5
In this paper, we investigate the underlying factor that leads to failure and success in the training of GANs. We study the property of the optimal discriminative function and show…
Exploiting Data and Human Knowledge for Predicting Wildlife Poaching
Swaminathan Gurumurthy, Lantao Yu, Chenyan Zhang +4
Poaching continues to be a significant threat to the conservation of wildlife and the associated ecosystem. Estimating and predicting where the poachers have committed or would com…
CoT: Cooperative Training for Generative Modeling of Discrete Data
Sidi Lu, Lantao Yu, Siyuan Feng +3
In this paper, we study the generative models of sequential discrete data. To tackle the exposure bias problem inherent in maximum likelihood estimation (MLE), generative adversari…
A Study of AI Population Dynamics with Million-agent Reinforcement Learning
Yaodong Yang, Lantao Yu, Yiwei Bai +4
We conduct an empirical study on discovering the ordered collective dynamics obtained by a population of intelligence agents, driven by million-agent reinforcement learning. Our in…