Zhengyu Hu

7 papers · 2023–2026 · 6 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (14)

Venues

EMNLP (2) AAAI (1) ACL (1) ICCV (1) ICML (1) NeurIPS (1)

Top co-authors

Kaize Ding (4) Jieyu Zhang (3) Chenyang Ren (2) Di Wang (2) Hui Xiong (2) Lijie Hu (2) Zhengyu Chen (2) Xilin Gong (1) Huanyi Xie (1) Alexander Ratner (1)

Research topics

Artificial Intelligence (6) Core AI (6) Machine Learning (5) Core Methods (3) Optimization & Theory (3) Natural Language Processing (2) Learning Paradigms (2) Resources & Methods (2) Learning Types (1)

Keywords

large language model (4) preference evaluation (2) concept bottleneck model (2) in-context learning (1) pseudo labeling (1) model interpretability (1) human-ai collaboration (1) influence function (1) concept bottleneck (1) model ranking (1) evaluation metric (1) downstream performance (1) concept alignment (1) pretraining dataset (1) graph-structured data (1) length bia (1) graph ensemble (1) intra-class diversity (1) response quality (1) data removal (1)

Papers

CoAct: Co-Active LLM Preference Learning with Human-AI Synergy ACL 2026 Towards Acyclic Preference Evaluation of Language Models via Multiple Evaluators AAAI 2026 Editable Concept Bottleneck Models ICML 2025 Explaining Length Bias in LLM-Based Preference Evaluations EMNLP 2025 Semi-supervised Concept Bottleneck Models ICCV 2025 Let’s Ask GNN: Empowering Large Language Model for Graph In-Context Learning EMNLP 2024 On the Trade-off of Intra-/Inter-class Diversity for Supervised Pre-training NeurIPS 2023