Yiming Zhang

Can LLMs Act as Historians? Evaluating Historical Research Capabilities of LLMs via the Chinese Imperial Examination ACL 2026 S2O: Static to Openable Enhancement for Articulated 3D Objects WACV 2026 ST-LLM: Spatial Transcriptomics Embedding with Large Language Models AAAI 2026 SPARD: Single-step Inference with Adaptive Sampling in Residual Diffusion for Human Motion Prediction AAAI 2026 Cyto-SSL: A Self-Supervised Pretraining Framework for Cytology Foundation Model AAAI 2026 The Paradox of Outcome Optimization: A Causal Information-Theoretic Bound on Reasoning Shortcuts in LLMs ACL 2026 RSVG-ZeroOV: Exploring a Training-Free Framework for Zero-Shot Open-Vocabulary Visual Grounding in Remote Sensing Images AAAI 2026 AxlePro: Momentum-Accelerated Batched Training of Kernel Machines AISTATS 2025 Vegeta: Enabling Parallel Smart Contract Execution in Leaderless Blockchains NSDI 2025 Persistent Pre-training Poisoning of LLMs ICLR 2025 Human-Aligned Chess With a Bit of Search ICLR 2025 Duoduo CLIP: Efficient 3D Understanding with Multi-View Images ICLR 2025 Backtracking Improves Generation Safety ICLR 2025 AccCtr: Accelerating Training-Free Conditional Control For Diffusion Models IJCAI 2025 FRAME: Feedback-Refined Agent Methodology for Enhancing Medical Research Insights ACL 2025 CIE: Controlling Language Model Text Generations Using Continuous Signals EMNLP 2025 AnchorAttention: Difference-Aware Sparse Attention with Stripe Granularity EMNLP 2025 RPDR: A Round-trip Prediction-Based Data Augmentation Framework for Long-Tail Question Answering EMNLP 2025 MRAG: A Modular Retrieval Framework for Time-Sensitive Question Answering EMNLP 2025 Cognitive Bias and Reassignment: Who Can Contribute High Quality LLM Data AAAI 2025 STI-Bench: Are MLLMs Ready for Precise Spatial-Temporal World Understanding? ICCV 2025 VLIPP: Towards Physically Plausible Video Generation with Vision and Language Informed Physical Prior ICCV 2025 Beyond Training: Dynamic Token Merging for Zero-Shot Video Understanding ICCV 2025 RANKCLIP: Ranking-Consistent Language-Image Pretraining ICCV 2025 Fast Adaptation via Prompted Data: An Efficient Cross-Domain Fine-tuning Method for Large Language Models COLING 2024 PIA: Your Personalized Image Animator via Plug-and-Play Modules in Text-to-Image Models CVPR 2024 RECOST: External Knowledge Guided Data-efficient Instruction Tuning ACL 2024 DORY: Deliberative Prompt Recovery for LLM ACL 2024 Self-Sampling Meta SAM: Enhancing Few-Shot Medical Image Segmentation With Meta-Learning WACV 2024 EFSA: Towards Event-Level Financial Sentiment Analysis ACL 2024 TriCoLo: Trimodal Contrastive Loss for Text To Shape Retrieval WACV 2024 Embedding and Gradient Say Wrong: A White-Box Method for Hallucination Detection EMNLP 2024 FinDVer: Explainable Claim Verification over Long and Hybrid-content Financial Documents EMNLP 2024 Revisiting the Knowledge Injection Frameworks EMNLP 2023 Emergent Communication in Interactive Sketch Question Answering NIPS 2023 FLamE: Few-shot Learning from Natural Language Explanations ACL 2023 Learning to Ignore Adversarial Attacks EACL 2023 BiasX: “Thinking Slow” in Toxic Content Moderation with Explanations of Implied Social Biases EMNLP 2023 Multi3DRefer: Grounding Text Description to Multiple 3D Objects ICCV 2023 Towards Unifying the Label Space for Aspect- and Sentence-based Sentiment Analysis ACL 2022 Temporal aware Multi-Interest Graph Neural Network for Session-based Recommendation ACML 2022 Active Example Selection for In-Context Learning EMNLP 2022 MultiScan: Scalable RGBD scanning for 3D environments with articulated objects NIPS 2022 Co-Modality Graph Contrastive Learning for Imbalanced Node Classification NIPS 2022 Distilling Meta Knowledge on Heterogeneous Graph for Illicit Drug Trafficker Detection on Social Media NIPS 2021 Adapting Meta Knowledge with Heterogeneous Information Network for COVID-19 Themed Malicious Repository Detection IJCAI 2021 On-Policy Deep Reinforcement Learning for the Average-Reward Criterion ICML 2021 MLCVNet: Multi-Level Context VoteNet for 3D Object Detection CVPR 2020 First Order Constrained Optimization in Policy Space NIPS 2020 Argot: Generating Adversarial Readable Chinese Texts IJCAI 2020 iDev: Enhancing Social Coding Security by Cross-platform User Identification Between GitHub and Stack Overflow IJCAI 2019 D-NET: A Pre-Training and Fine-Tuning Framework for Improving the Generalization of Machine Reading Comprehension EMNLP 2019 Supervised Policy Update for Deep Reinforcement Learning ICLR 2019 Automatic Opioid User Detection from Twitter: Transductive Ensemble Built on Different Meta-graph Based Similarities over Heterogeneous Information Network IJCAI 2018 CubicRing: Enabling One-Hop Failure Detection and Recovery for Distributed In-Memory Storage Systems NSDI 2015