Hao Zhang

98

Papers

288

Total Citations

1

Affiliations

Affiliations

UIUC

Papers (98)

Structured Generative Adversarial Networks

NeurIPS 2017arXiv

Visual In-Context Prompting

Revisiting Single Image Reflection Removal In the Wild

Explaining Generalization Power of a DNN Using Interactive Concepts

OpenING: A Comprehensive Benchmark for Judging Open-ended Interleaved Image-Text Generation

CSL: Class-Agnostic Structure-Constrained Learning for Segmentation including the Unseen

Slice3D: Multi-Slice Occlusion-Revealing Single View 3D Reconstruction

Non-parametric Representation Learning with Kernels

Learning Implicit Representation for Reconstructing Articulated Objects

Learning Adaptive Lighting via Channel-Aware Guidance

PALMBENCH: A COMPREHENSIVE BENCHMARK OF COMPRESSED LARGE LANGUAGE MODELS ON MOBILE PLATFORMS

Active Coarse-to-Fine Segmentation of Moveable Parts from Real Images

PhysRig: Differentiable Physics-Based Skinning and Rigging Framework for Realistic Articulated Object Modeling

High-Precision Dichotomous Image Segmentation via Probing Diffusion Capacity

Data Adaptive Traceback for Vision-Language Foundation Models in Image Classification

Cross-Modal Stealth: A Coarse-to-Fine Attack Framework for RGB-T Tracker

Stable Part Diffusion 4D: Multi-View RGB and Kinematic Parts Video Generation

NeurIPS 2025arXiv

MoPFormer: Motion-Primitive Transformer for Wearable-Sensor Activity Recognition

GALA: Geometry-Aware Local Adaptive Grids for Detailed 3D Generation

CLLMs: Consistency Large Language Models

Online Speculative Decoding

S3O: A Dual-Phase Approach for Reconstructing Dynamic Shape and Skeleton of Articulated Objects from Single Monocular Video

MMT-Bench: A Comprehensive Multimodal Benchmark for Evaluating Large Vision-Language Models Towards Multitask AGI

Break the Sequential Dependency of LLM Inference Using Lookahead Decoding

InferCept: Efficient Intercept Support for Augmented Large Language Model Inference

When Will Gradient Regularization Be Harmful?

Learning Multi-Instance Enriched Image Representations via Non-Greedy Ratio Maximization of the l1-Norm Distances

Learning Implicit Fields for Generative Shape Modeling

PQ-NET: A Generative Part Seq2Seq Network for 3D Shapes

BSP-Net: Generating Compact Meshes via Binary Space Partitioning

AdaCoSeg: Adaptive Shape Co-Segmentation With Group Consistency Loss

LayoutGMN: Neural Graph Matching for Structural Layout Similarity

Roof-GAN: Learning To Generate Roof Geometry and Relations for Residential Houses

D2IM-Net: Learning Detail Disentangled Implicit Fields From Single Images

DECOR-GAN: 3D Shape Detailization by Conditional Refinement

Interventional Video Grounding With Dual Contrastive Learning

Memory-Efficient Network for Large-Scale Video Compressive Sensing

MetaSCI: Scalable and Adaptive Reconstruction for Video Compressive Sensing

RIM-Net: Recursive Implicit Fields for Unsupervised Learning of Hierarchical Shape Structures

CAPRI-Net: Learning Compact CAD Shapes With Adaptive Primitive Assembly

DN-DETR: Accelerate DETR Training by Introducing Query DeNoising

UNIST: Unpaired Neural Implicit Shape Translation Network

Group Contextualization for Video Recognition

ArcPro: Architectural Programs for Structured 3D Abstraction of Sparse Points

ConZIC: Controllable Zero-Shot Image Captioning by Sampling-Based Polishing

Mask DINO: Towards a Unified Transformer-Based Framework for Object Detection and Segmentation

MP-Former: Mask-Piloted Transformer for Image Segmentation

Lite DETR: An Interleaved Multi-Scale Encoder for Efficient DETR

HD-CNN: Hierarchical Deep Convolutional Neural Networks for Large Scale Visual Recognition

DualGAN: Unsupervised Dual Learning for Image-To-Image Translation

Recurrent Topic-Transition GAN for Visual Paragraph Generation

BAE-NET: Branched Autoencoder for Shape Co-Segmentation

CompoNet: Learning to Generate the Unseen by Part Synthesis and Composition

3D-FRONT: 3D Furnished Rooms With layOuts and semaNTics

Interpreting Attributions and Interactions of Adversarial Attacks

Diff-Retinex: Rethinking Low-light Image Enhancement with A Generative Diffusion Model

HAL3D: Hierarchical Active Learning for Fine-Grained 3D Part Labeling

A Simple Framework for Open-Vocabulary Segmentation and Detection

DS-Fusion: Artistic Typography via Discriminated and Stylized Diffusion

DFA3D: 3D Deformable Attention For 2D-to-3D Feature Lifting

Detection Transformer with Stable Matching

DR-KFS: A Differentiable Visual Similarity Metric for 3D Shape Reconstruction

BIRNAT: Bidirectional Recurrent Neural Networks with Adversarial Training for Video Snapshot Compressive Imaging

GANHopper: Multi-Hop GAN for Unsupervised Image-to-Image Translation

ARO-Net: Learning Implicit Fields From Anchored Radial Observations

Explaining Domain Shifts in Language: Concept Erasing for Interpretable Image Classification

Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models

IMoRe: Implicit Program-Guided Reasoning for Human Motion Q&A

SDMatte: Grafting Diffusion Models for Interactive Matting

TemCoCo: Temporally Consistent Multi-modal Video Fusion with Visual-Semantic Collaboration

RGB-Only Supervised Camera Parameter Optimization in Dynamic Scenes

NeurIPS 2025arXiv

Advancing Comprehensive Aesthetic Insight with Multi-Scale Text-Guided Self-Supervised Learning

Boosting Vision State Space Model with Fractal Scanning

Scalable Trajectory-User Linking with Dual-Stream Representation Networks

A Robust Mutual-Reinforcing Framework for 3D Multi-Modal Medical Image Fusion Based on Visual-Semantic Consistency

Clarifying the Behavior and the Difficulty of Adversarial Training

Uncovering What Why and How: A Comprehensive Benchmark for Causation Understanding of Video Anomaly

Multi-Task Dense Prediction via Mixture of Low-Rank Experts

MeaCap: Memory-Augmented Zero-shot Image Captioning

LBI-FL: Low-Bit Integerized Federated Learning with Temporally Dynamic Bit-Width Allocation

Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference

Improving Adversarial Energy-Based Model via Diffusion Process

MuxServe: Flexible Spatial-Temporal Multiplexing for Multiple LLM Serving

Deep Poisson gamma dynamical systems

Symbolic Graph Reasoning Meets Convolutions

Deep Relational Topic Modeling via Graph Poisson Gamma Belief Network

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

Bidirectional Convolutional Poisson Gamma Dynamical Systems

PIE-NET: Parametric Inference of Point Cloud Edges

A Prototype-Oriented Framework for Unsupervised Domain Adaptation

AMP: Automatically Finding Model Parallel Strategies with Heterogeneity Awareness

A Variational Edge Partition Model for Supervised Graph Representation Learning

GALOIS: Boosting Deep Reinforcement Learning via Generalizable Logic Synthesis

De novo Drug Design using Reinforcement Learning with Multiple GPT Agents

Segment Everything Everywhere All at Once

D$^2$CSG: Unsupervised Learning of Compact CSG Trees with Dual Complements and Dropouts

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

DiViNeT: 3D Reconstruction from Disparate Views using Neural Template Regularization