Aohan Zeng
12 papers · 2023–2026 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (18) π§ Keyword Pioneer π Conference Polyglot (4) π Cross-Pollinator (12) π Interdisciplinary Bridge
π₯
Mega-Team
(28)
π€
Dynamic Duo
(10)
β‘
Prolific Year
(7)
π
Century Club
(10)
Conferences
ACL (6)
ICLR (4)
EMNLP (1)
NIPS (1)
Top co-authors
Keywords
large language model
(5)
preference optimization
(2)
critique generation
(2)
language model
(2)
question answering
(1)
language modeling
(1)
few-shot learning
(1)
llm evaluation
(1)
direct preference optimization
(1)
instruction tuning
(1)
pairwise comparison
(1)
language model alignment
(1)
foundation model
(1)
data selection
(1)
model scaling
(1)
influence function
(1)
mathematical problem solving
(1)
context window
(1)
long context
(1)
mathematical reasoning
(1)
Papers
Data Efficient RLVR via Off-Policy Influence Guidance
ACL 2026
IF-CRITIC: Towards a Fine-Grained LLM Critic for Instruction-Following Evaluation
ACL 2026
Scaling Speech-Text Pre-training with Synthetic Interleaved Data
ICLR 2025
VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agents
ICLR 2025
Revisiting Parallel Context Windows: A Frustratingly Simple Alternative and Chain-of-Thought Deterioration
ACL 2024
ChatGLM-Math: Improving Math Problem-Solving in Large Language Models with a Self-Critique Pipeline
EMNLP 2024
AgentBench: Evaluating LLMs as Agents
ICLR 2024
Understanding Emergent Abilities of Language Models from the Loss Perspective
NIPS 2024
LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding
ACL 2024
CritiqueLLM: Towards an Informative Critique Generation Model for Evaluation of Large Language Model Generation
ACL 2024
AgentTuning: Enabling Generalized Agent Abilities for LLMs
ACL 2024
GLM-130B: An Open Bilingual Pre-trained Model
ICLR 2023