Changyu CHEN
12 papers · 2021–2025 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
🌍 Conference Polyglot (7) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🌉 Interdisciplinary Bridge 🐝 Cross-Pollinator (7)
🐝
Cross-Pollinator
(7)
🌍
Conference Polyglot
(7)
🏆
Grand Slam
🗃️
Keyword Collector
(58)
💎
Century Club
(12)
🔥
Unstoppable
(5)
⚡
Prolific Year
(5)
Conferences
ACL (5)
NIPS (2)
AAAI (1)
ICLR (1)
ICML (1)
IJCNLP (1)
NAACL (1)
Top co-authors
Keywords
large language model
(4)
knowledge-grounded dialogue
(2)
pre-training strategy
(2)
multi-turn dialogue
(2)
response selection
(2)
knowledge selection
(2)
mathematical reasoning
(1)
policy gradient
(1)
sample efficiency
(1)
text generation
(1)
question understanding
(1)
graph representation
(1)
safety alignment
(1)
reinforcement learning from human feedback
(1)
in-context learning
(1)
transfer learning
(1)
adversarial attack
(1)
feedback mechanism
(1)
generative model
(1)
knowledge distillation
(1)
Papers
Unlocking the Planning Capabilities of Large Language Models with Maximum Diversity Fine-tuning
NAACL 2025
Bootstrapping Language Models with DPO Implicit Rewards
ICLR 2025
Masked Thought: Simply Masking Partial Reasoning Steps Can Improve Mathematical Reasoning Learning of Language Models
ACL 2024
Fortify the Shortest Stave in Attention: Enhancing Context Awareness of Large Language Models for Effective Tool Use
ACL 2024
Prototypical Reward Network for Data-Efficient RLHF
ACL 2024
Uncovering Safety Risks of Large Language Models through Concept Activation Vector
NIPS 2024
CycleAlign: Iterative Distillation from Black-box LLM to White-box Models for Better Human Alignment
ACL 2024
Semi-Offline Reinforcement Learning for Optimized Text Generation
ICML 2023
Generative Modelling of Stochastic Actions with Arbitrary Constraints in Reinforcement Learning
NIPS 2023
Multiscale Generative Models: Improving Performance of a Generative Model Using Feedback from Other Dependent Generative Models
AAAI 2022
A Pre-training Strategy for Zero-Resource Response Selection in Knowledge-Grounded Conversations
ACL 2021
A Pre-training Strategy for Zero-Resource Response Selection in Knowledge-Grounded Conversations
IJCNLP 2021