Eric P. Xing

45

Papers

258

Total Citations

Papers (45)

Efficient Test-Time Adaptation of Vision-Language Models

FreGS: 3D Gaussian Splatting with Progressive Frequency Regularization

VideoGLaMM : A Large Multimodal Model for Pixel-Level Visual Grounding in Videos

Synthesizing Privacy-Preserving Text Data via Finetuning without Finetuning Billion-Scale LLMs

SmartCLIP: Modular Vision-language Alignment with Identification Guarantees

Deep Variation-Structured Reinforcement Learning for Visual Relationship and Attribute Detection

Interpretable Structure-Evolving LSTM

Rethinking Knowledge Graph Propagation for Zero-Shot Learning

High-Frequency Component Helps Explain the Generalization of Convolutional Neural Networks

Towards Principled Disentanglement for Domain Generalization

The Two Dimensions of Worst-Case Training and Their Integrated Effect for Out-of-Domain Generalization

Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimation

Vision Transformer Slimming: Multi-Dimension Searching in Continuous Optimization Space

StyleRF: Zero-Shot 3D Style Transfer of Neural Radiance Fields

3D Semantic Segmentation in the Wild: Learning Generalized Models for Adverse-Condition Point Clouds

KD-DLGAN: Data Limited Image Generation via Knowledge Distillation

Deep Determinantal Point Process for Large-Scale Multi-Label Classification

Dual Motion GAN for Future-Flow Embedded Video Prediction

Recurrent Topic-Transition GAN for Visual Paragraph Generation

Nonparametric Variational Auto-Encoders for Hierarchical Representation Learning

Self-Challenging Improves Cross-Domain Generalization

Understanding Masked Autoencoders via Hierarchical Latent Variable Models

GLaMM: Pixel Grounding Large Multimodal Model

They Are Not Equally Reliable: Semantic Event Search Using Differentiated Concept Classifiers

Closed-Form Training of Mahalanobis Distance for Supervised Clustering

Efficient Multiple Instance Metric Learning Using Weakly Supervised Data

AutoSync: Learning to Synchronize for Data-Parallel Distributed Deep Learning

Improving GAN Training with Probability Ratio Clipping and Sample Reweighting

Regularizing Black-box Models for Improved Interpretability

Multi-task Learning of Order-Consistent Causal Graphs

Masked Generative Adversarial Networks are Data-Efficient Generation Learners

AMP: Automatically Finding Model Parallel Strategies with Heterogeneity Awareness

Rare Gems: Finding Lottery Tickets at Initialization

Identification of Nonlinear Latent Hierarchical Models

Temporally Disentangled Representation Learning under Unknown Nonstationarity

Making Scalable Meta Learning Practical

Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena

Weakly Supervised 3D Open-vocabulary Segmentation

Counterfactual Generation with Identifiability Guarantees

Cappy: Outperforming and Boosting Large Multi-Task LMs with a Small Scorer

Squeeze, Recover and Relabel: Dataset Condensation at ImageNet Scale From A New Perspective

FedNAR: Federated Optimization with Normalized Annealing Regularization

Toward Controlled Generation of Text

Learning Latent Space Models with Angular Constraints

Uncorrelation and Evenness: a New Diversity-Promoting Regularizer