Huan Wang

Towards Zero-Shot Diabetic Retinopathy Grading: Learning Generalized Knowledge via Prompt-Driven Matching and Emulating AAAI 2026 OmniBench: A Comprehensive Benchmark Integrating Real-World, Time-sensitive, and Multi-Hop Questions with a Multi-Dimensional Hybrid Evaluation Framework AAAI 2026 Toward Multimodal Fake News Detection by Multi-perspective Rationale Generation and Verification AAAI 2026 Zero-shot Recommendation: Towards Class Semantic Relation Learning for Inferring Labels of Unseen Micro-videos AAAI 2026 xLAM: A Family of Large Action Models to Empower AI Agent Systems NAACL 2025 CRMArena: Understanding the Capacity of LLM Agents to Perform Professional CRM Tasks in Realistic Environments NAACL 2025 FedDifRC: Unlocking the Potential of Text-to-Image Diffusion Models in Heterogeneous Federated Learning ICCV 2025 Diffuse&Refine: Intrinsic Knowledge Generation and Aggregation for Incremental Object Detection IJCAI 2025 Collapsing Sequence-Level Data-Policy Coverage via Poisoning Attack in Offline Reinforcement Learning UAI 2025 ABNet: Mitigating Sample Imbalance in Anomaly Detection Within Dynamic Graphs IJCAI 2025 DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models CVPR 2025 On-Device Diffusion Transformer Policy for Efficient Robot Manipulation ICCV 2025 LATTE: Learning to Think with Vision Specialists EMNLP 2025 ActionStudio: A Lightweight Framework for Data and Training of Large Action Models EMNLP 2025 MCPEval: Automatic MCP-based Deep Evaluation for AI Agent Models EMNLP 2025 Text2Data: Low-Resource Data Generation with Textual Control AAAI 2025 PersonaBench: Evaluating AI Models on Understanding Personal Information through Accessing (Synthetic) Private User Data ACL 2025 Accessing Vision Foundation Models via ImageNet-1K ICLR 2025 LAM SIMULATOR: Advancing Data Generation for Large Action Model Training via Online Exploration and Trajectory Feedback ACL 2025 Diversity Empowers Intelligence: Integrating Expertise of Software Engineering Agents ICLR 2025 SlackAgents: Scalable Collaboration of AI Agents in Workspaces EMNLP 2025 Sparse Enhanced Network: An Adversarial Generation Method for Robust Augmentation in Sequential Recommendation AAAI 2024 PRACT: Optimizing Principled Reasoning and Acting of LLM Agent EMNLP 2024 Customized Relationship Graph Neural Network for Brain Disorder Identification MICCAI 2024 Slicing Vision Transformer for Flexible Inference NIPS 2024 APIGen: Automated PIpeline for Generating Verifiable and Diverse Function-Calling Datasets NIPS 2024 A Simple Low-bit Quantization Framework for Video Snapshot Compressive Imaging ECCV 2024 Causal Layering via Conditional Entropy CLEAR 2024 Sample-Efficient Learning of POMDPs with Multiple Observations In Hindsight ICLR 2024 Retroformer: Retrospective Large Language Agents with Policy Gradient Optimization ICLR 2024 PRACT: Optimizing Principled Reasoning and Acting of LLM Agent CONLL 2024 Don't Judge by the Look: Towards Motion Coherent Video Representation ICLR 2024 On the Unlikelihood of D-Separation PGM 2024 HIVE: Harnessing Human Feedback for Instructional Visual Editing CVPR 2024 DialogStudio: Towards Richest and Most Diverse Unified Dataset Collection for Conversational AI EACL 2024 How Do Transformers Learn In-Context Beyond Simple Functions? A Case Study on Learning with Representations ICLR 2024 Merlion: End-to-End Machine Learning for Time Series JMLR 2023 SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Seconds NIPS 2023 Latent Graph Inference with Limited Supervision NIPS 2023 UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild NIPS 2023 Transformers as Statisticians: Provable In-Context Learning with In-Context Algorithm Selection NIPS 2023 Frame Flexible Network CVPR 2023 Real-Time Neural Light Field on Mobile Devices CVPR 2023 Iterative Soft Shrinkage Learning for Efficient Image Super-Resolution ICCV 2023 Recovering a Molecule's 3D Dynamics from Liquid-phase Electron Microscopy Movies ICCV 2023 Fantastic Rewards and How to Tame Them: A Case Study on Reward Learning for Task-oriented Dialogue Systems ICLR 2023 Trainability Preserving Neural Pruning ICLR 2023 Image as Set of Points ICLR 2023 CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis ICLR 2023 Improved Online Conformal Prediction via Strongly Adaptive Online Learning ICML 2023 Lower Bounds for Learning in Revealing POMDPs ICML 2023 What Makes a "Good" Data Augmentation in Knowledge Distillation - A Statistical Perspective NIPS 2022 Learning Efficient Image Super-Resolution Networks via Structure-Regularized Pruning ICLR 2022 Local calibration: metrics and recalibration UAI 2022 Privacy-Preserving Face Recognition with Learnable Privacy Budgets in Frequency Domain ECCV 2022 Efficient and Differentiable Conformal Prediction with General Function Classes ICLR 2022 R2L: Distilling Neural Radiance Field to Neural Light Field for Efficient Novel View Synthesis ECCV 2022 WarpDrive: Fast End-to-End Deep Multi-Agent Reinforcement Learning on a GPU JMLR 2022 Recent Advances on Neural Network Pruning at Initialization IJCAI 2022 Look More but Care Less in Video Recognition NIPS 2022 Policy Optimization for Markov Games: Unified Framework and Faster Convergence NIPS 2022 Ensemble of Averages: Improving Model Selection and Boosting Performance in Domain Generalization NIPS 2022 Parameter-Efficient Masking Networks NIPS 2022 Dual Lottery Ticket Hypothesis ICLR 2022 Neural Pruning via Growing Regularization ICLR 2021 Sample-Efficient Learning of Stackelberg Equilibria in General-Sum Games NIPS 2021 Understanding the Under-Coverage Bias in Uncertainty Estimation NIPS 2021 Slow Learning and Fast Inference: Efficient Graph Similarity Computation via Knowledge Distillation NIPS 2021 BatchMixup: Improving Training by Interpolating Hidden States of the Entire Mini-batch ACL 2021 How Important is the Train-Validation Split in Meta-Learning? ICML 2021 Don’t Just Blame Over-parametrization for Over-confidence: Theoretical Analysis of Calibration in Binary Classification ICML 2021 Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization ICML 2021 Evaluating State-of-the-Art Classification Models Against Bayes Optimality NIPS 2021 Aligned Structured Sparsity Learning for Efficient Image Super-Resolution NIPS 2021 BatchMixup: Improving Training by Interpolating Hidden States of the Entire Mini-batch IJCNLP 2021 Context Reasoning Attention Network for Image Super-Resolution ICCV 2021 Polyjuice: High-Performance Transactions via Learned Concurrency Control OSDI 2021 Policy Finetuning: Bridging Sample-Efficient Offline and Online Reinforcement Learning NIPS 2021 Unsupervised Paraphrasing with Pretrained Language Models EMNLP 2021 Towards Understanding Hierarchical Learning: Benefits of Neural Representations NIPS 2020 Collaborative Distillation for Ultra-Resolution Universal Style Transfer CVPR 2020 Assessing Local Generalization Capability in Deep Models AISTATS 2020 Miss Detection vs. False Alarm: Adversarial Learning for Small Object Segmentation in Infrared Images ICCV 2019 On the Generalization Gap in Reparameterizable Reinforcement Learning ICML 2019 Adaptive Dropout with Rademacher Complexity Regularization ICLR 2018 A Constituent Syntactic Parse Tree Based Discourse Parser CONLL 2016 Exact Recovery of Sparsely-Used Dictionaries IJCAI 2013 Exact Recovery of Sparsely-Used Dictionaries COLT 2012