Profiles2020-2026ORCID 0000-0002-0750-6923
Tingwen Liu
Chinese Academy of Sciences
46Papers
20Last author
93Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers46
- AttnPO: Attention-Guided Process Supervision for Efficient ReasoningAuthor 10 of 10ACL 2026 · 21 citations
- HyperMem: Hypergraph Memory for Long-Term ConversationsAuthor 6 of 8ACL 2026 · 4 citations
- Information-Theoretic Minimal Sufficient Representation for Multi-Domain Knowledge Graph CompletionAuthor 6 of 6AAAI 2026 · 2 citations
- Beyond Patches: Superpixel Token-based Transformers for Attribute-Specific Fashion RetrievalAuthor 5 of 5WWW 2026
- Conditional Diffusion Guided Knowledge Transfer for Multi-Domain Knowledge Graph CompletionAuthor 5 of 5WWW 2026
- Detecting RAG Extraction Attack via Dual-Path Runtime Integrity GameAuthor 8 of 8ACL 2026
- ExpSeek: Self-Triggered Experience Seeking for Web AgentsAuthor 7 of 8ACL Findings 2026
- Fashion Microscope: Pixel-Level Attribute Perception via Optimal Transport and Neural Semantic AggregationAuthor 7 of 7AAAI 2026
- From Agnostic to Specific: Latent Preference Diffusion for Multi-Behavior Sequential RecommendationAuthor 9 of 9KDD 2026
- S2CDR: Smoothing-Sharpening Process Model for Cross-Domain RecommendationAuthor 8 of 9WWW 2026
- Sparse Growing Transformer: Training-Time Sparse Depth Allocation via Progressive Attention LoopingAuthor 12 of 12ACL Findings 2026
- Uncertainty-Aware Routing for Principled Alignment with MoE DynamicsAuthor 7 of 11ACL 2026
- SOTOPIA-: Dynamic Strategy Injection Learning and Social Instruction Following Evaluation for Social AgentsAuthor 5 of 5ACL 2025 · 17 citations
- Revealing and Mitigating the Challenge of Detecting Character Knowledge Errors in LLM Role-PlayingAuthor 7 of 7EMNLP 2025 · 10 citations
- Exploring Preference-Guided Diffusion Model for Cross-Domain RecommendationAuthor 8 of 8KDD 2025 · 6 citations
- Graph Wave NetworksAuthor 7 of 8WWW 2025 · 5 citations
- Mitigating Modality Bias in Multi-modal Entity Alignment from a Causal PerspectiveAuthor 8 of 8SIGIR 2025 · 4 citations
- Beyond Surface Alignment: Rebuilding LLMs Safety Mechanism via Probabilistically Ablating Refusal DirectionAuthor 5 of 5EMNLP Findings 2025 · 2 citations
- Towards S²-Challenges Underlying LLM-Based Augmentation for Personalized News RecommendationAuthor 8 of 9AAAI 2025 · 2 citations
- Personalized Multi-Interest Modeling for Cross-Domain Recommendation to Cold-Start UsersAuthor 9 of 9ICDE 2025 · 1 citation
- Debiasing Multimodal Large Language Models via Noise-Aware Preference OptimizationAuthor 9 of 9CVPR 2025
- Improving Reasoning Capabilities in Small Models through Mixture-of-layers Distillation with Stepwise Attention on Key InformationAuthor 4 of 4EMNLP 2025
- Inner Thinking Transformer: Leveraging Dynamic Depth Scaling to Foster Adaptive Internal ThinkingAuthor 6 of 10ACL 2025
- Mixture of Hidden-Dimensions: Not All Hidden-States' Dimensions are Needed in TransformerAuthor 5 of 9ICML 2025
- DHA: Learning Decoupled-Head Attention from Transformer Checkpoints via Adaptive Heads FusionAuthor 5 of 7NeurIPS 2024 · 12 citations
- Optimal Transport Guided Correlation Assignment for Multimodal Entity LinkingAuthor 7 of 7ACL Findings 2024 · 10 citations
- NACL: A General and Effective KV Cache Eviction Framework for LLM at Inference TimeAuthor 6 of 10ACL 2024 · 8 citations
- IBMEA: Exploring Variational Information Bottleneck for Multi-modal Entity AlignmentAuthor 6 of 6ACM MM 2024 · 7 citations
- Exogenous and Endogenous Data Augmentation for Low-Resource Complex Named Entity RecognitionAuthor 5 of 6SIGIR 2024 · 3 citations
- Exploring the Trade-Off within Visual Information for MultiModal Sentence SummarizationAuthor 6 of 6SIGIR 2024 · 3 citations
Showing the 30 most recent indexed papers.
