Profiles2020-2026
Yue Zhang
Westlake University
83Papers
58Last author
133Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers83
- DeepScientist: Advancing Frontier-Pushing Scientific Findings ProgressivelyAuthor 7 of 8ICLR 2026 · 57 citations
- AutoFigure: Generating and Refining Publication-Ready Scientific IllustrationsAuthor 9 of 9ICLR 2026 · 28 citations
- Beyond English-Centric Training: How Reinforcement Learning Improves Cross-Lingual Reasoning in LLMsAuthor 4 of 4ICLR 2026 · 11 citations
- Pre-DPO: Improving Data Utilization in Direct Preference Optimization Using a Guiding Reference ModelAuthor 5 of 5AAAI 2026 · 7 citations
- LAMDAS: LLM as an Implicit Classifier for Domain-specific Data SelectionAuthor 7 of 7AAAI 2026 · 1 citation
- Minimizing Mismatch Risk: A Prototype-Based Routing Framework for Zero-shot LLM-generated Text DetectionAuthor 4 of 4ICML 2026 · 1 citation
- ReEfBench: Quantifying the Reasoning Efficiency of LLMsAuthor 5 of 5ACL 2026 · 1 citation
- Zero-Shot Text-to-Motion Evaluation using Video Language ModelsAuthor 3 of 3ICML 2026
- DeepReview: Improving LLM-based Paper Review with Human-like Deep Thinking ProcessAuthor 4 of 4ACL 2025 · 70 citations
- Lost in Literalism: How Supervised Training Shapes Translationese in LLMsAuthor 8 of 8ACL 2025 · 12 citations
- Exploring Model Editing for LLM-based Aspect-Based Sentiment ClassificationAuthor 4 of 5AAAI 2025 · 9 citations
- Unveiling Attractor Cycles in Large Language Models: A Dynamical Systems View of Successive ParaphrasingAuthor 5 of 5ACL 2025 · 3 citations
- ALLabel: Three-stage Active Learning for LLM-based Entity Recognition using Demonstration RetrievalAuthor 5 of 5EMNLP 2025 · 1 citation
- Learning to Rank for In-Context Example RetrievalAuthor 7 of 7NeurIPS 2025 · 1 citation
- Multi-Document Event Extraction Using Large and Small Language ModelsAuthor 6 of 6EMNLP 2025 · 1 citation
- Reasoning is All You Need for Video Generalization: A Counterfactual Benchmark with Sub-question EvaluationAuthor 8 of 8ACL Findings 2025 · 1 citation
- Constrain Alignment with Sparse AutoencodersAuthor 10 of 11ICML 2025
- CycleResearcher: Improving Automated Research via Automated ReviewAuthor 6 of 7ICLR 2025
- ELICIT: LLM Augmentation Via External In-context CapabilityAuthor 3 of 4ICLR 2025
- Glimpse: Enabling White-Box Methods to Use Proprietary Models for Zero-Shot LLM-Generated Text DetectionAuthor 4 of 4ICLR 2025
- NovelQA: Benchmarking Question Answering on Documents Exceeding 200K TokensAuthor 11 of 11ICLR 2025
- Personality Alignment of Large Language ModelsAuthor 4 of 4ICLR 2025
- PerSphere: A Comprehensive Framework for Multi-Faceted Perspective Retrieval and SummarizationAuthor 8 of 8ACL 2025
- Task Calibration: Calibrating Large Language Models on Inference TasksAuthor 4 of 4ACL Findings 2025
- Unaligned Message-Passing and Contextualized-Pretraining for Robust Geo-Entity ResolutionAuthor 7 of 7AAAI 2025
- PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning OptimizationAuthor 14 of 14ICLR 2024 · 368 citations
- Fast-DetectGPT: Efficient Zero-Shot Detection of Machine-Generated Text via Conditional Probability CurvatureAuthor 5 of 5ICLR 2024 · 311 citations
- AutoSurvey: Large Language Models Can Automatically Write SurveysAuthor 13 of 13NeurIPS 2024 · 151 citations
- Can Language Models Learn to Skip Steps?Author 5 of 9NeurIPS 2024 · 92 citations
- MAGE: Machine-generated Text Detection in the WildAuthor 9 of 9ACL 2024 · 44 citations
Showing the 30 most recent indexed papers.
