Dawei Li

27 papers · 2018–2026 · 13 conferences · across top CS/AI conferences

Achievements

+10 more ↓

🌍 Conference Polyglot (12) 🏃 Academic Marathon (7) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird

🌉 Interdisciplinary Bridge 🌍 Conference Polyglot (12) 🏃 Academic Marathon (7) 🧬 Topic Evolution 🗃️ Keyword Collector (113) ⚡ Prolific Year (6) 🚀 Conference Pioneer 💎 Century Club (25) 🔥 Unstoppable (8) ❓ The Questioner

Conferences

ACL (5) EMNLP (5) ICLR (3) NAACL (3) IJCAI (2) WACV (2) AAAI (1) AACL (1) CVPR (1) EACL (1) ECCV (1) IJCNLP (1) SEMEVAL (1)

Top co-authors

Hengyuan Zhang (6) Huan Liu (5) Zhen Tan (5) Yanran Li (5) Tianlong Chen (4) Jie Zhang (3) Shiping Yang (3) Heming Zhang (2) Jingbo Shang (2) Shuchen Weng (2)

Research topics

Education (1)

Keywords

large language model (7) contrastive learning (4) definition generation (3) catastrophic forgetting (3) model compression (3) knowledge distillation (3) pre-trained language model (3) chain-of-thought reasoning (2) prompt engineering (2) recurrent neural network (2) semantic representation (2) in-context learning (2) knowledge graph (2) sparse coding (1) causal reasoning (1) ensemble learning (1) transfer learning (1) image classification (1) causal inference (1) adversarial learning (1)

Papers

Model Editing as a Double-Edged Sword: Steering Agent Behavior Toward Beneficence or Harm AAAI 2026 Stop When Enough: Adaptive Early-Stopping for Chain-of-Thought Reasoning ACL 2026 BPO: Towards Balanced Preference Optimization between Knowledge Breadth and Depth in Alignment NAACL 2025 LLMs as World Models: Data-Driven and Human-Centered Pre-Event Simulation for Disaster Impact Assessment EMNLP 2025 CausalEval: Towards Better Causal Reasoning in Language Models NAACL 2025 From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge EMNLP 2025 Contextualization Distillation from Large Language Model for Knowledge Graph Completion EACL 2024 Can LLMs Learn from Previous Mistakes? Investigating LLMs’ Errors to Boost for Reasoning ACL 2024 READ: Improving Relation Extraction from an ADversarial Perspective NAACL 2024 Large Language Models for Data Annotation and Synthesis: A Survey EMNLP 2024 DALK: Dynamic Co-Augmentation of LLMs and KG to answer Alzheimer’s Disease Questions with Scientific Literature EMNLP 2024 Balancing Speciality and Versatility: a Coarse to Fine Framework for Supervised Fine-tuning Large Language Model ACL 2024 NTK-SAP: Improving neural network pruning by aligning training dynamics ICLR 2023 Assisting Language Learners: Automated Trans-Lingual Definition Generation via Contrastive Prompt Learning ACL 2023 Multi-level Contrastive Learning for Script-based Character Understanding EMNLP 2023 Instance-wise Batch Label Restoration via Gradients in Federated Learning ICLR 2023 Fine-grained Contrastive Learning for Definition Generation AACL 2022 C3KG: A Chinese Commonsense Conversation Knowledge Graph ACL 2022 Fine-grained Contrastive Learning for Definition Generation IJCNLP 2022 RMSprop converges with proper hyper-parameter ICLR 2021 MISC: Multi-Condition Injection and Spatially-Adaptive Compositing for Conditional Person Image Synthesis CVPR 2020 Regularize, Expand and Compress: NonExpansive Continual Learning WACV 2020 Class-incremental Learning via Deep Model Consolidation WACV 2020 Conditional Image Repainting via Semantic Bridge and Piecewise Value Function ECCV 2020 YUN-HPCC at SemEval-2019 Task 3: Multi-Step Ensemble Neural Network for Sentiment Analysis in Textual Conversation SEMEVAL 2019 Talking Face Generation by Conditional Recurrent Adversarial Network IJCAI 2019 Dynamically Hierarchy Revolution: DirNet for Compressing Recurrent Neural Network on Mobile Devices IJCAI 2018