Search Results for author:
Found 27 papers, 13 papers with code
A Deep Single Image Rectification Approach for Pan-Tilt-Zoom Cameras
This paper presents a Forward Distortion and Backward Warping Network (FDBW-Net), a novel framework for wide-angle image rectification.
On a Connection Between Imitation Learning and RLHF
We establish a close theoretical connection between reinforcement learning from human feedback RLHF and imitation learning (IL), revealing that RLHF implicitly performs imitation learning on the preference data distribution.
SimPER: A Minimalist Approach to Preference Alignment without Hyperparameters
Existing preference optimization objectives for language model alignment require additional hyperparameters that must be extensively tuned to achieve optimal performance, increasing both the complexity and time required for fine-tuning large language models.
Cal-DPO: Calibrated Direct Preference Optimization for Language Model Alignment
Contrastive preference optimization has shown promising results in aligning LLMs with available preference data by optimizing the implicit reward associated with the policy.
Fact-Level Confidence Calibration and Self-Correction
Confidence calibration in LLMs, i. e., aligning their self-assessed confidence with the actual accuracy of their responses, enabling them to self-evaluate the correctness of their outputs.
GeomCLIP: Contrastive Geometry-Text Pre-training for Molecules
Based on this dataset, we propose the GeomCLIP framework to enhance for multi-modal representation learning from molecular structures and biomedical text.
Tracing Human Stress from Physiological Signals using UWB Radar
Experimental results show that the proposed DST method significantly outperforms all the baselines in terms of tracing human stress states.
How to Leverage Demonstration Data in Alignment for Large Language Model? A Self-Imitation Learning Perspective
This paper introduces a novel generalized self-imitation learning ($\textbf{GSIL}$) framework, which effectively and efficiently aligns large language models with offline demonstration data.
MITA: Bridging the Gap between Model and Data for Test-time Adaptation
Test-Time Adaptation (TTA) has emerged as a promising paradigm for enhancing the generalizability of models.
Leveraging Invariant Principle for Heterophilic Graph Structure Distribution Shifts
However, existing works are only devoted to designing better HGNN backbones or architectures for node classification tasks on heterophilic and homophilic graph benchmarks simultaneously, and their analyses of HGNN performance with respect to nodes are only based on the determined data distribution without exploring the effect caused by this structural difference between training and testing nodes.
Discovering Invariant Neighborhood Patterns for Heterophilic Graphs
We propose a novel Invariant Neighborhood Pattern Learning (INPL) to alleviate the distribution shifts problem on non-homophilous graphs.
MolBind: Multimodal Alignment of Language, Molecules, and Proteins
Recent advancements in biology and chemistry have leveraged multi-modal learning, integrating molecules and their natural language descriptions to enhance drug discovery.
3M-Diffusion: Latent Multi-Modal Diffusion for Language-Guided Molecular Structure Generation
We propose 3M-Diffusion, a novel multi-modal molecular graph generation method, to generate diverse, ideally novel molecular structures with desired properties.
In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation
Large language models (LLMs) frequently hallucinate and produce factual errors, yet our understanding of why they make these errors remains limited.
Towards Off-Policy Reinforcement Learning for Ranking Policies with Human Feedback
Probabilistic learning to rank (LTR) has been the dominating approach for optimizing the ranking metric, but cannot maximize long-term rewards.
Learning to Reweight for Graph Neural Network
In this paper, we study the problem of the generalization ability of GNNs in Out-Of-Distribution (OOD) settings.
Simple and Asymmetric Graph Contrastive Learning without Augmentations
Experimental results show that the simple GraphACL significantly outperforms state-of-the-art graph contrastive learning and self-supervised learning methods on homophilic and heterophilic graphs.
Certifiably Robust Graph Contrastive Learning
Extensive experiments on real-world datasets demonstrate the effectiveness of our proposed method in providing effective certifiable robustness and enhancing the robustness of any GCL model.
Learning How to Propagate Messages in Graph Neural Networks
To compensate for this, in this paper, we present learning to propagate, a general learning framework that not only learns the GNN parameters for prediction but more importantly, can explicitly learn the interpretable and personalized propagate strategies for different nodes and various types of graphs.
A General Offline Reinforcement Learning Framework for Interactive Recommendation
This paper studies the problem of learning interactive recommender systems from logged feedbacks without any exploration in online environments.
Towards Fair Graph Neural Networks via Graph Counterfactual
Despite their great performance in modeling graphs, recent works show that GNNs tend to inherit and amplify the bias from training data, causing concerns of the adoption of GNNs in high-stake scenarios.
Fairness-aware Message Passing for Graph Neural Networks
Graph Neural Networks (GNNs) have shown great power in various domains.
Counterfactual Learning on Graphs: A Survey
To facilitate the development of this promising direction, in this survey, we categorize and comprehensively review papers on graph counterfactual learning.
Decoupled Self-supervised Learning for Non-Homophilous Graphs
This paper studies the problem of conducting self-supervised learning for node representation learning on graphs.
Reconsidering Learning Objectives in Unbiased Recommendation with Unobserved Confounders
In this paper, we propose a theoretical understanding of why existing unbiased learning objectives work for unbiased recommendation.
Semi-supervisedly Co-embedding Attributed Networks
Deep generative models (DGMs) have achieved remarkable advances.
Neural Variational Hybrid Collaborative Filtering
Specifically, we consider both the generative processes of users and items, and the prior of latent factors of users and items to be side informationspecific, which enables our model to alleviate matrix sparsity and learn better latent representations of users and items.
