Chak Tou Leong

48 papers A* 10Journal 28Unranked 10

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Finding RELIEF: Shaping Reasoning Behavior without Reasoning Supervision via Belief Engineering. CoRR Chak Tou Leong, Dingwei Chen, Heming Xia, Qingyu Yin, Sunbowen Lee, Jian Wang, Wenjie Li
2026	—	`conf`	KNN-SSD: Enabling Dynamic Self-Speculative Decoding via Nearest Neighbor Layer Set Optimization. EACL (Findings) Mingbo Song, Heming Xia, Jun Zhang, Chak Tou Leong, Qiancheng Xu, Wenjie Li, Sujian Li
2025	A*	`conf`	Constrain Alignment with Sparse Autoencoders. ICML Qingyu Yin, Chak Tou Leong, Hongbo Zhang, Minjun Zhu, Hanqi Yan, Qiang Zhang, Yulan He, Wenjie Li, Jun Wang, Yue Zhang, Linyi Yang
2025	J	`jnl`	Evaluating Parameter Efficient Methods for RLVR. CoRR Qingyu Yin, Yulun Wu, Zhennan Shen, Sunbowen Li, Zhilin Wang, Yanshu Li, Chak Tou Leong, Jiale Kang, Jinjin Gu
2025	A*	`conf`	Expanding before Inferring: Enhancing Factuality in Large Language Models through Premature Layers Interpolation. EMNLP Dingwei Chen, Ziqiang Liu, Feiteng Fang, Chak Tou Leong, Shiwen Ni, Ahmadreza Argha, Hamid Alinejad-Rokny, Min Yang, Chengming Li
2025	J	`jnl`	Expanding before Inferring: Enhancing Factuality in Large Language Models through Premature Layers Interpolation. CoRR Dingwei Chen, Ziqiang Liu, Feiteng Fang, Chak Tou Leong, Shiwen Ni, Ahmadreza Argha, Hamid Alinejad-Rokny, Min Yang, Chengming Li
2025	A*	`conf`	Imitate Before Detect: Aligning Machine Stylistic Preference for Machine-Revised Text Detection. AAAI Jiaqi Chen, Xiaoye Zhu, Tianyang Liu, Ying Chen, Xinhui Chen, Yiwen Yuan, Chak Tou Leong, Zuchao Li, Tang Long, Lei Zhang, Chenyu Yan, Guanghao Mei, Jie Zhang, Lefei Zhang
2025	J	`jnl`	KNN-SSD: Enabling Dynamic Self-Speculative Decoding via Nearest Neighbor Layer Set Optimization. CoRR Mingbo Song, Heming Xia, Jun Zhang, Chak Tou Leong, Qiancheng Xu, Wenjie Li, Sujian Li
2025	J	`jnl`	Merlin's Whisper: Enabling Efficient Reasoning in LLMs via Black-box Adversarial Prompting. CoRR Heming Xia, Cunxiao Du, Rui Li, Chak Tou Leong, Yongqi Li, Wenjie Li
2025	J	`jnl`	Probing the Difficulty Perception Mechanism of Large Language Models. CoRR Sunbowen Lee, Qingyu Yin, Chak Tou Leong, Jialiang Zhang, Yicheng Gong, Shiwen Ni, Min Yang, Xiaoyu Shen
2025	J	`jnl`	Protein as a Second Language for LLMs. CoRR Xinhui Chen, Zuchao Li, Mengqi Gao, Yufeng Zhang, Chak Tou Leong, Haoyang Li, Jiaqi Chen
2025	J	`jnl`	Refusal Falls off a Cliff: How Safety Alignment Fails in Reasoning? CoRR Qingyu Yin, Chak Tou Leong, Linyi Yang, Wenxuan Huang, Wenjie Li, Xiting Wang, Jaehong Yoon, YunXing, XingYu, Jinjin Gu
2025	J	`jnl`	SPA-RL: Reinforcing LLM Agents via Stepwise Progress Attribution. CoRR Hanlin Wang, Chak Tou Leong, Jiashuo Wang, Jian Wang, Wenjie Li
2025	—	`conf`	STeCa: Step-level Trajectory Calibration for LLM Agent Learning. ACL (Findings) Hanlin Wang, Jian Wang, Chak Tou Leong, Wenjie Li
2025	J	`jnl`	STeCa: Step-level Trajectory Calibration for LLM Agent Learning. CoRR Hanlin Wang, Jian Wang, Chak Tou Leong, Wenjie Li
2025	J	`jnl`	Scaling over Scaling: Exploring Test-Time Scaling Pareto in Large Reasoning Models. CoRR Jian Wang, Boyan Zhu, Chak Tou Leong, Yongqi Li, Wenjie Li
2025	—	`conf`	Subtle Errors in Reasoning: Preference Learning via Error-injected Self-editing. ACL (1) Kaishuai Xu, Tiezheng Yu, Wenjun Hou, Yi Cheng, Chak Tou Leong, Liangyou Li, Xin Jiang, Lifeng Shang, Qun Liu, Wenjie Li
2025	A*	`conf`	Symbolic Representation for Any-to-Any Generative Tasks. CVPR Jiaqi Chen, Xiaoye Zhu, Yue Wang, Tianyang Liu, Xinhui Chen, Ying Chen, Chak Tou Leong, Yifei Ke, Joseph Liu, Yiwen Yuan, Julian J. McAuley, Li-jia Li
2025	J	`jnl`	Symbolic Representation for Any-to-Any Generative Tasks. CoRR Jiaqi Chen, Xiaoye Zhu, Yue Wang, Tianyang Liu, Xinhui Chen, Ying Chen, Chak Tou Leong, Yifei Ke, Joseph Liu, Yiwen Yuan, Julian J. McAuley, Li-jia Li
2025	A*	`conf`	TokenSkip: Controllable Chain-of-Thought Compression in LLMs. EMNLP Heming Xia, Chak Tou Leong, Wenjie Wang, Yongqi Li, Wenjie Li
2025	J	`jnl`	TokenSkip: Controllable Chain-of-Thought Compression in LLMs. CoRR Heming Xia, Yongqi Li, Chak Tou Leong, Wenjie Wang, Wenjie Li
2025	A*	`conf`	Video-Bench: Human-Aligned Video Generation Benchmark. CVPR Hui Han, Siyuan Li, Jiaqi Chen, Yiwen Yuan, Yuling Wu, Yufan Deng, Chak Tou Leong, Hanwen Du, Junchen Fu, Youhua Li, Jie Zhang, Chi Zhang, Li-jia Li, Yongxin Ni
2025	J	`jnl`	Video-Bench: Human-Aligned Video Generation Benchmark. CoRR Hui Han, Siyuan Li, Jiaqi Chen, Yiwen Yuan, Yuling Wu, Chak Tou Leong, Hanwen Du, Junchen Fu, Youhua Li, Jie Zhang, Chi Zhang, Li-jia Li, Yongxin Ni
2025	—	`conf`	Why Safeguarded Ships Run Aground? Aligned Large Language Models' Safety Mechanisms Tend to Be Anchored in The Template Region. ACL (1) Chak Tou Leong, Qingyu Yin, Jian Wang, Wenjie Li
2025	J	`jnl`	Why Safeguarded Ships Run Aground? Aligned Large Language Models' Safety Mechanisms Tend to Be Anchored in The Template Region. CoRR Chak Tou Leong, Qingyu Yin, Jian Wang, Wenjie Li
2024	A*	`conf`	Cooper: Coordinating Specialized Agents towards a Complex Dialogue Goal. AAAI Yi Cheng, Wenge Liu, Jian Wang, Chak Tou Leong, Yi Ouyang, Wenjie Li, Xian Wu, Yefeng Zheng
2024	—	`conf`	Deeper Insights Without Updates: The Power of In-Context Learning Over Fine-Tuning. EMNLP (Findings) Qingyu Yin, Xuzheng He, Chak Tou Leong, Fan Wang, Yanzhao Yan, Xiaoyu Shen, Qiang Zhang
2024	J	`jnl`	Deeper Insights Without Updates: The Power of In-Context Learning Over Fine-Tuning. CoRR Qingyu Yin, Xuzheng He, Luoao Deng, Chak Tou Leong, Fan Wang, Yanzhao Yan, Xiaoyu Shen, Qiang Zhang
2024	J	`jnl`	Direct Preference Optimization Using Sparse Feature-Level Constraints. CoRR Qingyu Yin, Chak Tou Leong, Hongbo Zhang, Minjun Zhu, Hanqi Yan, Qiang Zhang, Yulan He, Wenjie Li, Jun Wang, Yue Zhang, Linyi Yang
2024	J	`jnl`	E2CL: Exploration-based Error Correction Learning for Embodied Agents. CoRR Hanlin Wang, Chak Tou Leong, Jian Wang, Wenjie Li
2024	J	`jnl`	Evolving to be Your Soulmate: Personalized Dialogue Agents with Dynamically Adapted Personas. CoRR Yi Cheng, Wenge Liu, Kaishuai Xu, Wenjun Hou, Yi Ouyang, Chak Tou Leong, Xian Wu, Yefeng Zheng
2024	—	`conf`	E²CL: Exploration-based Error Correction Learning for Embodied Agents. EMNLP (Findings) Hanlin Wang, Chak Tou Leong, Jian Wang, Wenjie Li
2024	J	`jnl`	Imitate Before Detect: Aligning Machine Stylistic Preference for Machine-Revised Text Detection. CoRR Jiaqi Chen, Xiaoye Zhu, Tianyang Liu, Ying Chen, Xinhui Chen, Yiwen Yuan, Chak Tou Leong, Zuchao Li, Tang Long, Lei Zhang, Chenyu Yan, Guanghao Mei, Jie Zhang, Lefei Zhang
2024	—	`conf`	Instruct Once, Chat Consistently in Multiple Rounds: An Efficient Tuning Framework for Dialogue. ACL (1) Jian Wang, Chak Tou Leong, Jiashuo Wang, Dongding Lin, Wenjie Li, Xiaoyong Wei
2024	J	`jnl`	Instruct Once, Chat Consistently in Multiple Rounds: An Efficient Tuning Framework for Dialogue. CoRR Jian Wang, Chak Tou Leong, Jiashuo Wang, Dongding Lin, Wenjie Li, Xiao-Yong Wei
2024	J	`jnl`	Mitigating Unhelpfulness in Emotional Support Conversations with Multifaceted AI Feedback. CoRR Jiashuo Wang, Chunpu Xu, Chak Tou Leong, Wenjie Li, Jing Li
2024	—	`conf`	Muffin: Mitigating Unhelpfulness in Emotional Support Conversations with Multifaceted AI Feedback. ACL (Findings) Jiashuo Wang, Chunpu Xu, Chak Tou Leong, Wenjie Li, Jing Li
2024	J	`jnl`	No Two Devils Alike: Unveiling Distinct Mechanisms of Fine-tuning Attacks. CoRR Chak Tou Leong, Yi Cheng, Kaishuai Xu, Jian Wang, Hanlin Wang, Wenjie Li
2024	A*	`conf`	SCREEN: A Benchmark for Situated Conversational Recommendation. ACM Multimedia Dongding Lin, Jian Wang, Chak Tou Leong, Wenjie Li
2024	J	`jnl`	Subtle Errors Matter: Preference Learning via Error-injected Self-editing. CoRR Kaishuai Xu, Tiezheng Yu, Wenjun Hou, Yi Cheng, Chak Tou Leong, Liangyou Li, Xin Jiang, Lifeng Shang, Qun Liu, Wenjie Li
2023	J	`jnl`	COOPER: Coordinating Specialized Agents towards a Complex Dialogue Goal. CoRR Yi Cheng, Wenge Liu, Jian Wang, Chak Tou Leong, Yi Ouyang, Wenjie Li, Xian Wu, Yefeng Zheng
2023	J	`jnl`	Geo-Tile2Vec: A Multi-Modal and Multi-Stage Embedding Framework for Urban Analytics. ACM Trans. Spatial Algorithms Syst. Yan Luo, Chak Tou Leong, Shuhai Jiao, Fu-Lai Chung, Wenjie Li, Guoping Liu
2023	A*	`conf`	Self-Detoxifying Language Models via Toxification Reversal. EMNLP Chak Tou Leong, Yi Cheng, Jiashuo Wang, Jian Wang, Wenjie Li
2023	J	`jnl`	Self-Detoxifying Language Models via Toxification Reversal. CoRR Chak Tou Leong, Yi Cheng, Jiashuo Wang, Jian Wang, Wenjie Li
2023	A*	`conf`	Target-oriented Proactive Dialogue Systems with Personalization: Problem Formulation and Dataset Curation. EMNLP Jian Wang, Yi Cheng, Dongding Lin, Chak Tou Leong, Wenjie Li
2023	J	`jnl`	Target-oriented Proactive Dialogue Systems with Personalization: Problem Formulation and Dataset Curation. CoRR Jian Wang, Yi Cheng, Dongding Lin, Chak Tou Leong, Wenjie Li
2022	—	`conf`	Task Adaptive Network for Image Restoration with Combined Degradation Factors. WACV (Workshops) Jingyuan Zhou, Chak Tou Leong, MinYi Lin, Wantong Liao, Congduan Li
2021	—	`conf`	Unified Feature Fusion Network with Path Router for Multi-task Image Restoration. ICCT Jingyuan Zhou, Chak Tou Leong, Yiyang Luo, MinYi Lin, Wantong Liao, Congduan Li