Search Results for author:
Found 23 papers, 9 papers with code
RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment
Utilizing a reward model and a sufficient number of samples, our approach selects the high-quality samples, discarding those that exhibit undesired behavior, and subsequently enhancing the model by fine-tuning on these filtered samples.
LMFlow: An Extensible Toolkit for Finetuning and Inference of Large Foundation Models
As the number of available models and specialized tasks keeps growing, the job of general finetuning becomes highly nontrivial.
DetGPT: Detect What You Need via Reasoning
Overall, our proposed paradigm and DetGPT demonstrate the potential for more sophisticated and intuitive interactions between humans and machines.
Local Augmentation for Graph Neural Networks
To address this, we propose a simple and efficient data augmentation strategy, local augmentation, to learn the distribution of the node features of the neighbors conditioned on the central node's feature and enhance GNN's expressive power with generated features.
Weakly Supervised Disentangled Generative Causal Representation Learning
This paper proposes a Disentangled gEnerative cAusal Representation (DEAR) learning method under appropriate supervised information.
MLLM-Protector: Ensuring MLLM's Safety without Hurting Performance
The deployment of multimodal large language models (MLLMs) has brought forth a unique vulnerability: susceptibility to malicious attacks through visual inputs.
Mathematical Models of Overparameterized Neural Networks
Deep learning has received considerable empirical successes in recent years.
Normalizing Flow with Variational Latent Representation
The resulting method is significantly more powerful than the standard normalization flow approach for generating data distributions with multiple modes.
Vocabulary-informed Zero-shot and Open-set Learning
Despite significant progress in object categorization, in recent years, a number of important challenges remain; mainly, the ability to learn from limited labeled data and to recognize object classes within large, potentially open, set of labels.
Vocabulary-informed Extreme Value Learning
To solve this problem, we propose the Extreme Value Learning (EVL) formulation to learn the mapping from visual feature to semantic space.
Learning the Compositional Spaces for Generalized Zero-shot Learning
This paper studies the problem of Generalized Zero-shot Learning (G-ZSL), whose goal is to classify instances belonging to both seen and unseen classes at the test time.
Over Parameterized Two-level Neural Networks Can Learn Near Optimal Feature Representations
Recently, over-parameterized neural networks have been extensively analyzed in the literature.
Higher-order Weighted Graph Convolutional Networks
Graph Convolution Network (GCN) has been recognized as one of the most effective graph models for semi-supervised learning, but it extracts merely the first-order or few-order neighborhood information through information propagation, which suffers performance drop-off for deeper structure.
Bayesian Invariant Risk Minimization
Generalization under distributional shift is an open challenge for machine learning.
How Powerful is Implicit Denoising in Graph Neural Networks
However, the analysis of implicit denoising effect in graph neural networks remains open.
Particle-based Variational Inference with Preconditioned Functional Gradient Flow
With the popularity of Stein variational gradient descent (SVGD), the focus of particle-based VI algorithms has been on the properties of functions in Reproducing Kernel Hilbert Space (RKHS) to approximate the gradient flow.
PAPAL: A Provable PArticle-based Primal-Dual ALgorithm for Mixed Nash Equilibrium
To circumvent this difficulty, we examine the problem of identifying a mixed Nash equilibrium, where strategies are randomized and characterized by probability distributions over continuous domains. To this end, we propose PArticle-based Primal-dual ALgorithm (PAPAL) tailored for a weakly entropy-regularized min-max optimization over probability distributions.
Mitigating the Alignment Tax of RLHF
Building on the analysis and the observation that averaging different layers of the transformer leads to significantly different reward-tax trade-offs, we propose Adaptive Model Averaging (AMA) to adaptively find various combination ratios of model layers.
Spurious Feature Diversification Improves Out-of-distribution Generalization
Contrary to the conventional wisdom that focuses on learning invariant features for better OOD performance, our findings suggest that incorporating a large number of diverse spurious features weakens their individual contributions, leading to improved overall OOD generalization performance.
Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-Constraint
This includes an iterative version of the Direct Preference Optimization (DPO) algorithm for online settings, and a multi-step rejection sampling strategy for offline scenarios.
Faster Sampling without Isoperimetry via Diffusion-based Monte Carlo
Specifically, DMC follows the reverse SDE of a diffusion process that transforms the target distribution to the standard Gaussian, utilizing a non-parametric score estimation.
An Improved Analysis of Langevin Algorithms with Prior Diffusion for Non-Log-Concave Sampling
Along this line, Freund et al. (2022) suggest that the modified Langevin algorithm with prior diffusion is able to converge dimension independently for strongly log-concave target distributions.
