Tong Zhang

110

Papers

780

Total Citations

Papers (110)

Deep Subspace Clustering Networks

NeurIPS 2017arXiv

PerceptionGPT: Effectively Fusing Visual Perception into LLM

Exact Recovery of Hard Thresholding Pursuit

ASGO: Adaptive Structured Gradient Optimization

AdaGrad under Anisotropic Smoothness

On Quadratic Convergence of DC Proximal Newton Algorithm in Nonconvex Sparse Learning

NeurIPS 2017arXiv

Diffusion Approximations for Online Principal Component Estimation and Global Convergence

NeurIPS 2017arXiv

MergeBench: A Benchmark for Merging Domain-Specialized LLMs

Efficient Optimization for Linear Dynamical Systems with Applications to Clustering and Sparse Coding

Data Augmentation via Latent Diffusion for Saliency Prediction

Accelerated Convergence of Stochastic Heavy Ball Method under Anisotropic Gradient Noise

Generating Multimodal Driving Scenes via Next-Scene Prediction

Refining CLIP's Spatial Awareness: A Visual-Centric Perspective

FDS: Frequency-Aware Denoising Score for Text-Guided Latent Diffusion Image Editing

TagFog: Textual Anchor Guidance and Fake Outlier Generation for Visual Out-of-Distribution Detection

Rotated Runtime Smooth: Training-Free Activation Smoother for accurate INT4 inference

Faster Sampling via Stochastic Gradient Proximal Sampler

Understanding Overadaptation in Supervised Fine-Tuning: The Role of Ensemble Methods

Self-Ensembling Gaussian Splatting for Few-Shot Novel View Synthesis

Controlling the Fidelity and Diversity of Deep Generative Models via Pseudo Density

TransNAS-Bench-101: Improving Transferability and Generalizability of Cross-Task Neural Architecture Search

Reinforced Attention for Few-Shot Learning and Beyond

Involution: Inverting the Inherence of Convolution for Visual Recognition

Few-Shot Human Motion Transfer by Personalized Geometry and Texture Modeling

Uncertainty-Aware Joint Salient Object and Camouflaged Object Detection

Effective Sparsification of Neural Networks With Global Sparsity Constraint

Joint-DetNAS: Upgrade Your Detector With NAS, Pruning and Dynamic Distillation

Bayesian Invariant Risk Minimization

Exploring Geometric Consistency for Monocular 3D Object Detection

MulT: An End-to-End Multitask Learning Transformer

Leverage Your Local and Global Representations: A New Self-Supervised Learning Strategy

TempSAL - Uncovering Temporal Information for Deep Saliency Prediction

Spatiotemporal Self-Supervised Learning for Point Clouds in the Wild

VolRecon: Volume Rendering of Signed Ray Distance Functions for Generalizable Multi-View Reconstruction

DyNCA: Real-Time Dynamic Texture Synthesis Using Neural Cellular Automata

G-DetKD: Towards General Distillation Framework for Object Detectors via Contrastive and Semantic-Guided Feature Imitation

Wasserstein Coupled Graph Learning for Cross-Modal Retrieval

NEMTO: Neural Environment Matting for Novel View and Relighting Synthesis of Transparent Objects

CATCH: Context-based Meta Reinforcement Learning for Transferrable Architecture Search

Graph Wasserstein Correlation Analysis for Movie Retrieval

Semi-Supervised Monocular 3D Object Detection by Multi-View Consistency

RC-MVSNet: Unsupervised Multi-View Stereo with Neural Rendering

Quartz: Randomized Dual Coordinate Ascent with Arbitrary Sampling

Local Smoothness in Variance Reduced Optimization

Semi-supervised Convolutional Neural Networks for Text Categorization via Region Embedding

Learning Additive Exponential Family Graphical Models via $\ell_{2,1}$-norm Regularized M-Estimation

Pessimism Meets Risk: Risk-Sensitive Offline Reinforcement Learning

Distribution Prototype Diffusion Learning for Open-set Supervised Anomaly Detection

TimeBooth: Disentangled Facial Invariant Representation for Diverse and Personalized Face Aging

MatchDiffusion: Training-free Generation of Match-Cuts

Scene Graph-Grounded Image Generation

Desigen: A Pipeline for Controllable Design Template Generation

InNeRF360: Text-Guided 3D-Consistent Object Inpainting on 360-degree Neural Radiance Fields

DVMNet: Computing Relative Pose for Unseen Objects Beyond Hypotheses

Mitigating Object Dependencies: Improving Point Cloud Self-Supervised Learning through Object Exchange

The Non-linear $F$-Design and Applications to Interactive Learning

Towards Robust Model-Based Reinforcement Learning Against Adversarial Corruption

Scaling Mesh Generation via Compressive Tokenization

Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-constraint

Deep Unsupervised Saliency Detection: A Multiple Noisy Labeling Perspective

Efficient Decision-Based Black-Box Adversarial Attacks on Face Recognition

Pattern-Structure Diffusion for Multi-Task Learning

Cross-Modal Pattern-Propagation for RGB-T Tracking

UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoders

Synthetic Learning: Learn From Distributed Asynchronized Discriminator GAN Without Sharing Medical Image Data

MiLeNAS: Efficient Neural Architecture Search via Mixed-Level Reformulation

Adaptive Sampling Towards Fast Graph Representation Learning

Stochastic Primal-Dual Method for Empirical Risk Minimization with O(1) Per-Iteration Complexity

SPIDER: Near-Optimal Non-Convex Optimization via Stochastic Path-Integrated Differential Estimator

Gradient Sparsification for Communication-Efficient Distributed Optimization

Communication Compression for Decentralized Training

Exponentially Weighted Imitation Learning for Batched Historical Data

Stochastic Expectation Maximization with Variance Reduction

Divergence-Augmented Policy Optimization

Bridging the Gap between Sample-based and One-shot Neural Architecture Search with BONAS

How to Characterize The Landscape of Overparameterized Convolutional Neural Networks

Residual Distillation: Towards Portable Deep Neural Networks without Shortcuts

A Generalized Neural Tangent Kernel Analysis for Two-layer Neural Networks

Decentralized Accelerated Proximal Gradient Descent

Model Rubik’s Cube: Twisting Resolution, Depth and Width for TinyNets

Stochastic Recursive Gradient Descent Ascent for Stochastic Nonconvex-Strongly-Concave Minimax Problems

A Provably Efficient Model-Free Posterior Sampling Method for Episodic Reinforcement Learning

Efficient Neural Network Training via Forward and Backward Propagation Sparsification

Error Compensated Distributed SGD Can Be Accelerated

Nearly Optimal Algorithms for Linear Contextual Bandits with Adversarial Corruptions

Model-based RL with Optimistic Posterior Sampling: Structural Conditions and Sample Complexity

Inconsistency, Instability, and Generalization Gap of Deep Neural Network Training

Posterior Sampling for Competitive RL: Function Approximation and Partial Observation

Corruption-Robust Offline Reinforcement Learning with General Function Approximation

Double Pessimism is Provably Efficient for Distributionally Robust Offline Reinforcement Learning: Generic Algorithm and Robust Partial Coverage

Double Randomized Underdamped Langevin with Dimension-Independent Convergence Guarantee

A Theoretical Analysis of Optimistic Proximal Policy Optimization in Linear Markov Decision Processes

Stochastic Optimization with Importance Sampling for Regularized Loss Minimization

Adaptive Stochastic Alternating Direction Method of Multipliers

Supervised and Semi-Supervised Text Categorization using LSTM for Region Embeddings

Sparse Nonlinear Regression: Parameter Estimation under Nonconvexity

Efficient Distributed Learning with Sparsity

Projection-free Distributed Online Learning in Networks

Candidates vs. Noises Estimation for Large Multi-Class Classification Problem

Composite Functional Gradient Learning of Generative Adversarial Models

End-to-end Active Object Tracking via Reinforcement Learning

An Algorithmic Framework of Variable Metric Over-Relaxed Hybrid Proximal Extra-Gradient Method

Graphical Nonconvex Optimization via an Adaptive Convex Relaxation

Error Compensated Quantized SGD and its Applications to Large-scale Distributed Optimization

Safe Element Screening for Submodular Function Minimization

Fully Decentralized Multi-Agent Reinforcement Learning with Networked Agents

Grid-Wise Control for Multi-Agent Reinforcement Learning in Video Game AI

NATTACK: Learning the Distributions of Adversarial Examples for an Improved Black-Box Attack on Deep Neural Networks

DoubleSqueeze: Parallel Stochastic Gradient Descent with Double-pass Error-Compensated Compression

Neural Collaborative Subspace Clustering