Profiles2020-2026
Haobo Wang
Zhejiang University
36Papers
12Last author
60Unique co-authors
2First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers36
- Stop Unnecessary Reflection: Training LRMs for Efficient Reasoning with Adaptive Reflection and Length Coordinated PenaltyAuthor 7 of 7ICLR 2026 · 2 citations
- An Invariant Latent Space Perspective on Language Model InversionAuthor 3 of 10AAAI 2026 · 1 citation
- FLaG: Fine-Grained Latent Grouping for Hallucination DetectionAuthor 9 of 9KDD 2026 · 1 citation
- Awakening Visual Reasoning: Mitigating Post-Training Failure in Vision-Text CompressionAuthor 9 of 12ICML 2026
- Dual Graph Disambiguation for Multi-Instance Partial-Label LearningAuthor 5 of 8AAAI 2026
- Everyone is unique: Towards Behaviorally Heterogeneous Negotiation Dialogue Systems for Debt CollectionAuthor 4 of 7ACL 2026
- FinMRAGBench: A Realistic and Complex Benchmark for Multi-Modal RAG in Financial Document AnalysisAuthor 8 of 13ACL Findings 2026
- Towards Interpretable Tabular Reasoning: Enhancing LLM Reasoning on Tabular Data with Pre-Constructed Logic GraphAuthor 7 of 10ACL 2026
- Table as a Modality for Large Language ModelsAuthor 6 of 12NeurIPS 2025 · 5 citations
- LongTableBench: Benchmarking Long-Context Table Reasoning across Real-World Formats and DomainsAuthor 6 of 10EMNLP Findings 2025 · 3 citations
- CoLA: Model Collaboration for Log-based Anomaly DetectionAuthor 4 of 7VLDB 2025 · 2 citations
- RealHiTBench: A Comprehensive Realistic Hierarchical Table Benchmark for Evaluating LLM-Based Table AnalysisAuthor 13 of 13ACL Findings 2025 · 2 citations
- Ensembling Prompting Strategies for Zero-Shot Hierarchical Text Classification with Large Language ModelsAuthor 3 of 6EMNLP 2025 · 1 citation
- Harnessing Feature Resonance under Arbitrary Target Alignment for Out-of-Distribution Node DetectionAuthor 7 of 7NeurIPS 2025 · 1 citation
- Large Margin Representation Learning for Robust Cross-lingual Named Entity RecognitionAuthor 3 of 6ACL 2025 · 1 citation
- Multi-Instance Multi-Label Classification from Crowdsourced LabelsAuthor 7 of 7AAAI 2025 · 1 citation
- Enhance Multi-View Classification Through Multi-Scale Alignment and Expanded BoundaryAuthor 7 of 8ICLR 2025
- Towards Reverse Engineering of Language Models: A SurveyAuthor 7 of 8EMNLP Findings 2025
- Towards Transferable Personality Representation Learning based on Triplet Comparisons and Its ApplicationsAuthor 9 of 9EMNLP 2025
- On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A SurveyAuthor 7 of 7ACL Findings 2024 · 131 citations
- Towards Cross-Table Masked Pretraining for Web Data MiningAuthor 3 of 7WWW 2024 · 23 citations
- FlowBench: Revisiting and Benchmarking Workflow-Guided Planning for LLM-based AgentsAuthor 6 of 8EMNLP Findings 2024 · 15 citations
- A Separation and Alignment Framework for Black-Box Domain AdaptationAuthor 7 of 7AAAI 2024 · 12 citations
- Targeted Representation Alignment for Open-World Semi-Supervised LearningAuthor 7 of 7CVPR 2024 · 12 citations
- RECOST: External Knowledge Guided Data-efficient Instruction TuningAuthor 3 of 4ACL Findings 2024 · 3 citations
- Positive-Unlabeled Learning by Latent Group-Aware Meta DisambiguationAuthor 2 of 7CVPR 2024 · 2 citations
- Unbiased Multi-Label Learning from Crowdsourced AnnotationsAuthor 7 of 7ICML 2024 · 1 citation
- Learning Geometry-Aware Representations for New Intent DiscoveryAuthor 7 of 7ACL 2024
- iDAG: Invariant DAG Searching for Domain GeneralizationAuthor 2 of 3ICCV 2023 · 23 citations
- Regression with Cost-based RejectionAuthor 3 of 6NeurIPS 2023 · 14 citations
Showing the 30 most recent indexed papers.
