Zhengyu Chen

27 papers · 2021–2026 · 9 conferences · across top CS/AI conferences

Achievements

+9 more ↓

🌈 Renaissance Researcher (5) 🌉 Interdisciplinary Bridge 🗺️ Taxonomy Completionist (10) 🧭 Keyword Pioneer 🌍 Conference Polyglot (9)

🌈 Renaissance Researcher (5) 🌍 Conference Polyglot (9) 🌉 Interdisciplinary Bridge 🏆 Grand Slam 👥 Mega-Team (34) 🗃️ Keyword Collector (108) 💎 Century Club (23) 🔥 Unstoppable (5) ⚡ Prolific Year (7)

Conferences

AAAI (7) EMNLP (5) NIPS (5) ICLR (4) ACL (2) CVPR (1) ICCV (1) ICML (1) IJCAI (1)

Top co-authors

Teng Xiao (8) Jingang Wang (6) Donglin Wang (4) Fei Wu (4) Jinluan Yang (3) Siqi Wang (3) Kun Kuang (3) Xunliang Cai (3) Min Zhang (3) Hongxia Yang (3)

Research topics

Applications (1)

Keywords

large language model (9) graph neural network (5) representation learning (2) few-shot learning (2) self-supervised learning (2) domain generalization (2) transfer learning (2) variational inference (2) scaling law (2) data quality (2) out-of-distribution generalization (2) in-context learning (1) knowledge distillation (1) information extraction (1) risk management (1) hyperparameter optimization (1) neural network optimization (1) image restoration (1) model architecture (1) text generation (1)

Papers

Mitigating Structural Knowledge Collapse in Domain-Specific LLMs via Morpheme-Aware KV-Aggregation ACL 2026 Scaling and Transferability of Annealing Strategies in Large Language Model Training AAAI 2026 From Mathematical Reasoning to Code: Generalization of Process Reward Models in Test-Time Scaling AAAI 2026 Dual-Teacher Interactive Knowledge Distillation Network for Text-to-Visible & Infrared Person Retrieval AAAI 2026 SimPER: A Minimalist Approach to Preference Alignment without Hyperparameters ICLR 2025 Attributive Reasoning for Hallucination Diagnosis of Large Language Models AAAI 2025 Revisiting Scaling Laws for Language Models: The Role of Data Quality and Training Strategies ACL 2025 On a Connection Between Imitation Learning and RLHF ICLR 2025 Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware Subspace ICLR 2025 Explaining Length Bias in LLM-Based Preference Evaluations EMNLP 2025 SampleMix: A Sample-wise Pre-training Data Mixing Strategy by Coordinating Data Quality and Diversity EMNLP 2025 Let’s Ask GNN: Empowering Large Language Model for Graph In-Context Learning EMNLP 2024 DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset Curation NIPS 2024 FinBen: A Holistic Financial Benchmark for Large Language Models NIPS 2024 HARMONIC: Harnessing LLMs for Tabular Data Synthesis and Privacy Protection NIPS 2024 Learning to Reweight for Generalizable Graph Neural Network AAAI 2024 Scaling Laws Across Model Architectures: A Comparative Analysis of Dense and MoE Models in Large Language Models EMNLP 2024 Let Models Speak Ciphers: Multiagent Debate through Embeddings ICLR 2024 MAP: Towards Balanced Generalization of IID and OOD through Model-Agnostic Adapters ICCV 2023 MAPO: Boosting Large Language Model Performance with Model-Adaptive Prompt Optimization EMNLP 2023 Simple and Asymmetric Graph Contrastive Learning without Augmentations NIPS 2023 The Role of Deconfounding in Meta-learning ICML 2022 End-to-End Open-Set Semi-Supervised Node Classification with Out-of-Distribution Detection IJCAI 2022 Learn Goal-Conditioned Policy with Intrinsic Motivation for Deep Reinforcement Learning AAAI 2022 Decoupled Self-supervised Learning for Graphs NIPS 2022 Pareto Self-Supervised Training for Few-Shot Learning CVPR 2021 Deep Transfer Tensor Decomposition with Orthogonal Constraint for Recommender Systems AAAI 2021