Chak Tou Leong

Venues

Frequent coauthors

Papers

1. Finding RELIEF: Shaping Reasoning Behavior without Reasoning Supervision via Belief Engineering
   ACL 2026 · Chak Tou Leong
2. KNN-SSD: Enabling Dynamic Self-Speculative Decoding via Nearest Neighbor Layer Set Optimization
   EACL 2026 ·

   Mingbo Song

   DBLP profile ↗ORCID search ↗
3. Merlin's Whisper: Enabling Efficient Reasoning in Large Language Models via Black-box Persuasive Prompting
   ACL 2026 ·

   Heming Xia

   DBLP profile ↗ORCID search ↗
4. Seeing Isn't Believing: Mitigating Belief Inertia via Active Intervention in Embodied Agents
   ACL 2026 ·

   Hanlin Wang

   DBLP profile ↗ORCID search ↗
5. Constrain Alignment with Sparse Autoencoders
   ICML 2025 ·

   Qingyu Yin

   DBLP profile ↗ORCID search ↗
6. Expanding before Inferring: Enhancing Factuality in Large Language Models through Premature Layers Interpolation
   EMNLP 2025 ·

   Dingwei Chen

   DBLP profile ↗ORCID search ↗
7. Imitate Before Detect: Aligning Machine Stylistic Preference for Machine-Revised Text Detection
   AAAI 2025 ·

   Jiaqi Chen

   DBLP profile ↗ORCID search ↗
8. STeCa: Step-level Trajectory Calibration for LLM Agent Learning
   ACL 2025 ·

   Hanlin Wang

   DBLP profile ↗ORCID search ↗
9. Subtle Errors in Reasoning: Preference Learning via Error-injected Self-editing
   ACL 2025 ·

   Kaishuai Xu

   DBLP profile ↗ORCID search ↗
10. Symbolic Representation for Any-to-Any Generative Tasks
    CVPR 2025 ·

    Jiaqi Chen

    DBLP profile ↗ORCID search ↗
11. TokenSkip: Controllable Chain-of-Thought Compression in LLMs
    EMNLP 2025 ·

    Heming Xia

    DBLP profile ↗ORCID search ↗
12. Video-Bench: Human-Aligned Video Generation Benchmark
    CVPR 2025 ·

    Hui Han

    DBLP profile ↗ORCID search ↗
13. Why Safeguarded Ships Run Aground? Aligned Large Language Models' Safety Mechanisms Tend to Be Anchored in The Template Region
    ACL 2025 · Chak Tou Leong
14. Cooper: Coordinating Specialized Agents towards a Complex Dialogue Goal
    AAAI 2024 ·

    Yi Cheng

    DBLP profile ↗ORCID search ↗
15. Deeper Insights Without Updates: The Power of In-Context Learning Over Fine-Tuning
    EMNLP 2024 ·

    Qingyu Yin

    DBLP profile ↗ORCID search ↗
16. E²CL: Exploration-based Error Correction Learning for Embodied Agents
    EMNLP 2024 ·

    Hanlin Wang

    DBLP profile ↗ORCID search ↗
17. Instruct Once, Chat Consistently in Multiple Rounds: An Efficient Tuning Framework for Dialogue
    ACL 2024 ·

    Jian Wang

    DBLP profile ↗ORCID search ↗
18. Muffin: Mitigating Unhelpfulness in Emotional Support Conversations with Multifaceted AI Feedback
    ACL 2024 ·

    Jiashuo Wang

    DBLP profile ↗ORCID search ↗
19. SCREEN: A Benchmark for Situated Conversational Recommendation
    ACM MM 2024 ·

    Dongding Lin

    DBLP profile ↗ORCID search ↗