Wentao Zhang

Heterogeneous Adaptive Policy Optimization: Tailoring Optimization to Every Token’s Nature ACL 2026 Look Less, Reason More: Rollout-Guided Adaptive Pixel-Space Reasoning ACL 2026 CodeFlowBench: A Multi-turn, Iterative Benchmark for Complex Code Generation ACL 2026 MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing ACL 2026 The Data Frontier for Large Language Models: Selection, Synthesis, and Tools ACL 2026 EthicMind: A Risk-Aware Framework for Ethical-Emotional Alignment in Multi-Turn Dialogue ACL 2026 LEASH: Adaptive Length Penalty and Reward Shaping for Efficient Large Reasoning Model ACL 2026 VerifyBench: A Systematic Benchmark for Evaluating Reasoning Verifiers Across Domains AAAI 2026 UniDataBench: Evaluating Data Analytics Agents Across Structured and Unstructured Data ACL 2026 Beyond Explicit Refusals: Soft-Failure Attacks on Retrieval-Augmented Generation ACL 2026 Trust Within? Seek Beyond? Knowledge Boundary Aware Policy Optimization for Agentic Search ACL 2026 Nested Browser-Use Learning for Agentic Information Seeking ACL 2026 SciFlow-Bench: Evaluating Structure-Aware Scientific Diagram Generation via Inverse Parsing ACL 2026 ChartVerse: Scaling Chart Reasoning via Reliable Programmatic Synthesis from Scratch ACL 2026 Cross-Domain Few-Shot Learning via Multi-View Collaborative Optimization with Vision-Language Models AAAI 2026 CausalStep: A Benchmark for Explicit Stepwise Causal Reasoning in Videos AAAI 2026 Decoupling Continual Semantic Segmentation AAAI 2026 FB-Bench: A Fine-Grained Multi-Task Benchmark for Evaluating LLMs’ Responsiveness to Human Feedback EMNLP 2025 Can LLMs be Good Graph Judge for Knowledge Graph Construction? EMNLP 2025 From Chat Logs to Collective Insights: Aggregative Question Answering EMNLP 2025 Interactive Training: Feedback-Driven Neural Network Optimization EMNLP 2025 Knowledge Graph-Driven Memory Editing with Directional Interventions EMNLP 2025 Any2AnyTryon: Leveraging Adaptive Position Embeddings for Versatile Virtual Clothing Tasks ICCV 2025 OCR Hinders RAG: Evaluating the Cascading Impact of OCR on Retrieval-Augmented Generation ICCV 2025 SysBench: Can LLMs Follow System Message? ICLR 2025 Time Series Supplier Allocation via Deep Black-Litterman Model AAAI 2025 Towards Scalable and Deep Graph Neural Networks via Noise Masking AAAI 2025 FedVCK: Non-IID Robust and Communication-Efficient Federated Learning via Valuable Condensed Knowledge for Medical Image Analysis AAAI 2025 Taming LLMs with Gradient Grouping ACL 2025 QAEncoder: Towards Aligned Representation Learning in Question Answering Systems ACL 2025 Enhancing Unsupervised Sentence Embeddings via Knowledge-Driven Data Augmentation and Gaussian-Decayed Contrastive Learning ACL 2025 Efficient Pretraining Data Selection for Language Models via Multi-Actor Collaboration ACL 2025 TC–RAG: Turing–Complete RAG’s Case study on Medical LLM Systems ACL 2025 MM-Verify: Enhancing Multimodal Reasoning with Chain-of-Thought Verification ACL 2025 CFBench: A Comprehensive Constraints-Following Benchmark for LLMs ACL 2025 HopRAG: Multi-Hop Reasoning for Logic-Aware Retrieval-Augmented Generation ACL 2025 Towards Precise Scaling Laws for Video Diffusion Transformers CVPR 2025 Beyond Sight: Towards Cognitive Alignment in LVLM via Enriched Visual Knowledge CVPR 2025 SEA: Supervised Embedding Alignment for Token-Level Visual-Textual Integration in MLLMs EMNLP 2025 Improving Low-Resource Sequence Labeling with Knowledge Fusion and Contextual Label Explanations EMNLP 2025 VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs EMNLP 2025 Video In-context Learning: Autoregressive Transformers are Zero-Shot Video Imitators ICLR 2025 Facilitating Multi-turn Function Calling for LLMs via Compositional Instruction Tuning ICLR 2025 GlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning ICLR 2025 IPDreamer: Appearance-Controllable 3D Object Generation with Complex Image Prompts ICLR 2025 Sparse Causal Discovery with Generative Intervention for Unsupervised Graph Domain Adaptation ICML 2025 Cradle: Empowering Foundation Agents towards General Computer Control ICML 2025 Modeling All-Atom Glycan Structures via Hierarchical Message Passing and Multi-Scale Pre-training ICML 2025 AdaMixT: Adaptive Weighted Mixture of Multi-Scale Expert Transformers for Time Series Forecasting IJCAI 2025 Interaction-based Retrieval-augmented Diffusion Models for Protein-specific 3D Molecule Generation ICML 2024 OpenBox: A Python Toolkit for Generalized Black-box Optimization JMLR 2024 Protein-Ligand Interaction Prior for Binding-aware 3D Molecule Diffusion Models ICLR 2024 True Knowledge Comes from Practice: Aligning Large Language Models with Embodied Environments via Reinforcement Learning ICLR 2024 ProtLLM: An Interleaved Protein-Language LLM with Protein-as-Word Pre-Training ACL 2024 EarnHFT: Efficient Hierarchical Reinforcement Learning for High Frequency Trading AAAI 2024 Towards Effective and General Graph Unlearning via Mutual Evolution AAAI 2024 VQGraph: Rethinking Graph Representation Space for Bridging GNNs and MLPs ICLR 2024 Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models NIPS 2024 Distribution-Aware Data Expansion with Diffusion Models NIPS 2024 Efficient Multi-task LLM Quantization and Serving for Multiple LoRA Adapters NIPS 2024 RAGraph: A General Retrieval-Augmented Graph Learning Framework NIPS 2024 TradeMaster: A Holistic Quantitative Trading Platform Empowered by Reinforcement Learning NIPS 2023 Improving Diffusion-Based Image Synthesis with Context Prediction NIPS 2023 ProxyBO: Accelerating Neural Architecture Search via Bayesian Optimization with Zero-Cost Proxies AAAI 2023 RLEKF: An Optimizer for Deep Potential with Ab Initio Accuracy AAAI 2023 Patton: Language Model Pretraining on Text-Rich Networks ACL 2023 Deep and Flexible Graph Neural Architecture Search ICML 2022 Information Gain Propagation: a New Way to Graph Active Learning with Soft Labels ICLR 2022 DivBO: Diversity-aware CASH for Ensemble Learning NIPS 2022 NAFS: A Simple yet Tough-to-beat Baseline for Graph Representation Learning ICML 2022 Node Dependent Local Smoothing for Scalable Graph Learning NIPS 2021 RIM: Reliable Influence-based Active Learning on Graphs NIPS 2021