Profiles2021-2026ORCID 0000-0003-2425-1499
Huawei Shen
Chinese Academy of Sciences
51Papers
4Last author
79Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers51
- The Evolution of Thought: Tracking LLM Overthinking via Reasoning Dynamics AnalysisAuthor 9 of 10ACL 2026 · 14 citations
- DIVA-GRPO: Enhancing Multimodal Reasoning through Difficulty-Adaptive Variant AdvantageAuthor 9 of 10ICLR 2026 · 3 citations
- Learning from Mistakes: Negative Reasoning Samples Enhance Out-of-Domain GeneralizationAuthor 9 of 9ACL 2026 · 3 citations
- Projecting Out the Malice: A Global Subspace Approach to LLM DetoxificationAuthor 10 of 11ACL 2026 · 2 citations
- RLKD: Distilling LLMs' Reasoning via Reinforcement LearningAuthor 8 of 9AAAI 2026 · 2 citations
- AsarRec: Adaptive Sequential Augmentation for Robust Self-supervised Sequential RecommendationAuthor 5 of 6SIGIR 2026
- Do We Always Need Query-Level Workflows? Rethinking Agentic Workflow Generation for Multi-Agent SystemsAuthor 4 of 5ACL Findings 2026
- Personalized Denoising Implicit Feedback for Robust Recommender SystemAuthor 5 of 6WWW 2025 · 12 citations
- InfoNCE is a Free Lunch for Semantically guided Graph Contrastive LearningAuthor 4 of 5SIGIR 2025 · 4 citations
- MIGE: Mutually Enhanced Multimodal Instruction-Based Image Generation and EditingAuthor 4 of 7ACM MM 2025 · 4 citations
- Generative Ghost: Investigating Ranking Bias Hidden in AI-Generated VideosAuthor 5 of 6ACM MM 2025 · 1 citation
- Low-Entropy Watermark Detection via Bayes' Rule Derived DetectorAuthor 5 of 6ACL Findings 2025 · 1 citation
- A Theory for Token-Level Harmonization in Retrieval-Augmented GenerationAuthor 3 of 4ICLR 2025
- Cross-Modal Safety Mechanism Transfer in Large Vision-Language ModelsAuthor 4 of 5ICLR 2025
- Everything is Editable: Extend Knowledge Editing to Unstructured Data in Large Language ModelsAuthor 5 of 6ICLR 2025
- Following the Autoregressive Nature of LLM Embeddings via Compression and AlignmentAuthor 8 of 9EMNLP 2025
- ToolCoder: A Systematic Code-Empowered Tool Learning Framework for Large Language ModelsAuthor 7 of 8ACL 2025
- Search-in-the-Chain: Interactively Enhancing Large Language Models with Search for Knowledge-intensive TasksAuthor 3 of 5WWW 2024 · 104 citations
- Toward Practical Entity Alignment Method Design: Insights from New Highly Heterogeneous Knowledge Graph DatasetsAuthor 10 of 10WWW 2024 · 26 citations
- Invisible Relevance Bias: Text-Image Retrieval Models Prefer AI-Generated ImagesAuthor 6 of 7SIGIR 2024 · 18 citations
- Unlocking the Power of Large Language Models for Entity AlignmentAuthor 8 of 9ACL 2024 · 17 citations
- Tree-of-Reasoning Question Decomposition for Complex Question Answering with Large Language ModelsAuthor 7 of 8AAAI 2024 · 14 citations
- List-aware Reranking-Truncation Joint Model for Search and Retrieval-augmented GenerationAuthor 4 of 5WWW 2024 · 13 citations
- LoRec: Combating Poisons with Large Language Model for Robust Sequential RecommendationAuthor 5 of 6SIGIR 2024 · 13 citations
- Understanding and Improving Adversarial Collaborative Filtering for Robust RecommendationAuthor 5 of 6NeurIPS 2024 · 11 citations
- When to Trust LLMs: Aligning Confidence with Response QualityAuthor 8 of 9ACL Findings 2024 · 10 citations
- SACH: Significant-Attributed Community Search in Heterogeneous Information NetworksAuthor 5 of 6ICDE 2024 · 8 citations
- TEA: Test-Time Energy AdaptationAuthor 5 of 6CVPR 2024 · 8 citations
- PDE+: Enhancing Generalization via PDE with Adaptive Distributional DiffusionAuthor 6 of 7AAAI 2024 · 6 citations
- Enhancing Training Data Attribution for Large Language Models with Fitting Error ConsiderationAuthor 3 of 4EMNLP 2024
Showing the 30 most recent indexed papers.
