Jinchang Hou
5 papers · 2024–2026 · 2 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
π£ Hot Topic Early Bird π§ Keyword Pioneer π Conference Polyglot (2) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (11)
π
Cross-Pollinator
(8)
π
Renaissance Researcher
(6)
π₯
Mega-Team
(21)
β
The Questioner
Conferences
ACL (4)
COLING (1)
Top co-authors
Research topics
Keywords
large language model
(3)
reinforcement learning
(1)
benchmark evaluation
(1)
few-shot learning
(1)
mathematical reasoning
(1)
chain-of-thought reasoning
(1)
safety alignment
(1)
multi-objective optimization
(1)
entropy regularization
(1)
reward model
(1)
multimodal large language model
(1)
higher-order perception
(1)
cultural knowledge
(1)
few-shot prompting
(1)
chain of thought
(1)
semantic understanding
(1)
multiple-choice question
(1)
sparse fine-tuning
(1)
chinese image understanding
(1)
cultural understanding
(1)
Papers
Safety-Utility Conflicts Are Not Global: Surgical Alignment via Head-Level Diagnosis
ACL 2026
Token-Level Policy Optimization: Linking Group-Level Rewards to Token-Level Aggregation via sequence-level likelihood
ACL 2026
Can MLLMs Understand the Deep Implication Behind Chinese Images?
ACL 2025
E-EVAL: A Comprehensive Chinese K-12 Education Evaluation Benchmark for Large Language Models
ACL 2024
CLHA: A Simple Yet Effective Contrastive Learning Framework for Human Alignment
COLING 2024