Chak Tou Leong
17 papers · 2023–2026 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
π Cross-Pollinator (6) π Conference Polyglot (5) π Interdisciplinary Bridge π§ Keyword Pioneer π Renaissance Researcher (6)
πΊοΈ
Taxonomy Completionist
(42)
π
Interdisciplinary Bridge
π€
Dynamic Duo
(10)
β
The Questioner
β‘
Prolific Year
(9)
ποΈ
Keyword Collector
(76)
π
Century Club
(15)
Conferences
ACL (6)
EMNLP (5)
AAAI (2)
CVPR (2)
EACL (1)
ICML (1)
Top co-authors
Keywords
large language model
(5)
preference learning
(2)
reinforcement learning
(2)
few-shot learning
(2)
preference optimization
(1)
model safety
(1)
mathematical reasoning
(1)
machine-generated text detection
(1)
video generation
(1)
dialogue generation
(1)
in-context learning
(1)
multimodal learning
(1)
error detection
(1)
token skipping
(1)
safety alignment
(1)
direct preference optimization
(1)
iterative refinement
(1)
behavior cloning
(1)
probability distribution
(1)
text classification
(1)
Papers
Merlinβs Whisper: Enabling Efficient Reasoning in Large Language Models via Black-box Persuasive Prompting
ACL 2026
KNN-SSD: Enabling Dynamic Self-Speculative Decoding via Nearest Neighbor Layer Set Optimization
EACL 2026
Why Safeguarded Ships Run Aground? Aligned Large Language Modelsβ Safety Mechanisms Tend to Be Anchored in The Template Region
ACL 2025
Subtle Errors in Reasoning: Preference Learning via Error-injected Self-editing
ACL 2025
STeCa: Step-level Trajectory Calibration for LLM Agent Learning
ACL 2025
Video-Bench: Human-Aligned Video Generation Benchmark
CVPR 2025
Symbolic Representation for Any-to-Any Generative Tasks
CVPR 2025
Imitate Before Detect: Aligning Machine Stylistic Preference for Machine-Revised Text Detection
AAAI 2025
TokenSkip: Controllable Chain-of-Thought Compression in LLMs
EMNLP 2025
Expanding before Inferring: Enhancing Factuality in Large Language Models through Premature Layers Interpolation
EMNLP 2025
Constrain Alignment with Sparse Autoencoders
ICML 2025
E2CL: Exploration-based Error Correction Learning for Embodied Agents
EMNLP 2024
Instruct Once, Chat Consistently in Multiple Rounds: An Efficient Tuning Framework for Dialogue
ACL 2024
Muffin: Mitigating Unhelpfulness in Emotional Support Conversations with Multifaceted AI Feedback
ACL 2024
Cooper: Coordinating Specialized Agents towards a Complex Dialogue Goal
AAAI 2024
Deeper Insights Without Updates: The Power of In-Context Learning Over Fine-Tuning
EMNLP 2024
Self-Detoxifying Language Models via Toxification Reversal
EMNLP 2023