Dan Zhang

Verification-Aware Planning for Multi-Agent Systems EACL 2026 RECAP: REwriting Conversations for Intent Understanding in Agentic Planning EACL 2026 VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation AAAI 2026 SOAR: Semi-Supervised Open-Vocabulary Aerial Object Detection via Dual-Aware Enhanced Prior Denoising AAAI 2026 CtrlNews: LLM-based Multi-Agent Controllable News Writing via Knowledge Gravitational Field EMNLP 2025 VSTAR: Generative Temporal Nursing for Longer Dynamic Video Synthesis ICLR 2025 LoftUp: Learning a Coordinate-Based Feature Upsampler for Vision Foundation Models ICCV 2025 SPaR: Self-Play with Tree-Search Refinement to Improve Instruction-Following in Large Language Models ICLR 2025 CLIP-DSA: Textual Knowledge-Guided Cerebrovascular Diseases Recognition in Multi-View Digital Subtraction Angiography MICCAI 2025 How LLMs React to Industrial Spatio-Temporal Data? Assessing Hallucination with a Novel Traffic Incident Benchmark Dataset NAACL 2025 Generative Uncertainty in Diffusion Models UAI 2025 AndroidLab: Training and Systematic Benchmarking of Android Autonomous Agents ACL 2025 A Survey of Post-Training Scaling in Large Language Models ACL 2025 SceneGenAgent: Precise Industrial Scene Generation with Coding Agent ACL 2025 IntelliCockpitBench: A Comprehensive Benchmark to Evaluate VLMs for Intelligent Cockpit ACL 2025 FactLens: Benchmarking Fine-Grained Fact Verification ACL 2025 Cross-Modal Graph Learning for Perivascular Spaces Segmentation MICCAI 2025 DivGCL: A Graph Contrastive Learning Model for Diverse Recommendation AAAI 2025 A Stronger Mixture of Low-Rank Experts for Fine-Tuning Foundation Models ICML 2025 ZeroFlow: Overcoming Catastrophic Forgetting is Easier than You Think ICML 2025 AIPOM: Agent-aware Interactive Planning for Multi-Agent Systems EMNLP 2025 MPMNet: Modal Prior Mutual-support Network for Age-related Macular Degeneration Classification MICCAI 2024 SciInstruct: a Self-Reflective Instruction Annotated Dataset for Training Scientific Language Models NIPS 2024 ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search NIPS 2024 Renovating Names in Open-Vocabulary Segmentation Benchmarks NIPS 2024 Fast yet Safe: Early-Exiting with Risk Control NIPS 2024 AutoRE: Document-Level Relation Extraction with Large Language Models ACL 2024 MEGAnno+: A Human-LLM Collaborative Annotation System EACL 2024 ViewFormer: Exploring Spatiotemporal Modeling for Multi-View 3D Occupancy Perception via View-Guided Transformers ECCV 2024 Adversarial Supervision Makes Layout-to-Image Diffusion Models Thrive ICLR 2024 Directly Denoising Diffusion Models ICML 2024 FactCHD: Benchmarking Fact-Conflicting Hallucination Detection IJCAI 2024 DSNet: A Spatio-Temporal Consistency Network for Cerebrovascular Segmentation in Digital Subtraction Angiography Sequences MICCAI 2024 Early-Exit Neural Networks with Nested Prediction Sets UAI 2024 SciOL and MuLMS-Img: Introducing a Large-Scale Multimodal Scientific Dataset and Models for Image-Text Tasks in the Scientific Domain WACV 2024 DeakinNLP at ProbSum 2023: Clinical Progress Note Summarization with Rules and Language ModelsClinical Progress Note Summarization with Rules and Languague Models ACL 2023 GOOD: Exploring geometric cues for detecting objects in an open world ICLR 2023 Controlling Text-to-Image Diffusion by Orthogonal Finetuning NIPS 2023 Intra-Source Style Augmentation for Improved Domain Generalization WACV 2023 Learning Sample Difficulty from Pre-trained Models for Reliable Prediction NIPS 2023 Identification of Systematic Errors of Image Classifiers on Rare Subgroups ICCV 2023 Towards Anytime Classification in Early-Exit Architectures by Enforcing Conditional Monotonicity NIPS 2023 One-Shot Synthesis of Images and Segmentation Masks WACV 2023 Panoptic-PHNet: Towards Real-Time and High-Precision LiDAR Panoptic Segmentation via Clustering Pseudo Heatmap CVPR 2022 MEGAnno: Exploratory Labeling for NLP in Computational Notebooks EMNLP 2022 Low-resource Interactive Active Labeling for Fine-tuning Language Models EMNLP 2022 Multi-level Distillation of Semantic Knowledge for Pre-training Multilingual Language Model EMNLP 2022 Multi-Class Uncertainty Calibration via Mutual Information Maximization-based Binning ICLR 2021 You Only Need Adversarial Supervision for Semantic Image Synthesis ICLR 2021 Understanding Anomaly Detection with Deep Invertible Networks through Hierarchies of Distributions and Features NIPS 2020 Progressive Augmentation of GANs NIPS 2019 MILEAGE: Multiple Instance LEArning with Global Embedding ICML 2013 Multiple Instance Learning on Structured Data NIPS 2011