2026
RLCracker: Evaluating the Worst-Case Vulnerability of LLM Watermarks with Adaptive RL Attacks
Hanbo Huang, Yiran Zhang, Hao Zheng, Xuan Gong, Yihan Li, Lin Liu, Zhuotao Liu, Shiyu Liang# (# corresponding author)
ICML 2026
RLCracker studies adaptive reinforcement-learning attacks against LLM watermarks, exposing watermark vulnerabilities under learned black-box attack policies.
RLCracker: Evaluating the Worst-Case Vulnerability of LLM Watermarks with Adaptive RL Attacks
Hanbo Huang, Yiran Zhang, Hao Zheng, Xuan Gong, Yihan Li, Lin Liu, Zhuotao Liu, Shiyu Liang# (# corresponding author)
ICML 2026
RLCracker studies adaptive reinforcement-learning attacks against LLM watermarks, exposing watermark vulnerabilities under learned black-box attack policies.
VCORE: Variance-Controlled Optimization-based Reweighting for Chain-of-Thought Supervision
Xuan Gong, Senmiao Wang, Hanbo Huang, Ruoyu Sun, Shiyu Liang# (# corresponding author)
ACL 2026 Main
VCORE introduces variance-controlled optimization-based reweighting for chain-of-thought supervision, improving how reasoning traces contribute to model training.
VCORE: Variance-Controlled Optimization-based Reweighting for Chain-of-Thought Supervision
Xuan Gong, Senmiao Wang, Hanbo Huang, Ruoyu Sun, Shiyu Liang# (# corresponding author)
ACL 2026 Main
VCORE introduces variance-controlled optimization-based reweighting for chain-of-thought supervision, improving how reasoning traces contribute to model training.
GGBound: A Genome-Grounded Agent for Microbial Life-Boundary Prediction
Hanbo Huang*, Xuan Gong*, Jing Wang, Lei Bai, Xiang Xiao, Weishu Zhao, Shiyu Liang# (* equal contribution, # corresponding author)
Preprint 2026
GGBound presents a genome-grounded agent for predicting microbial life boundaries by combining genomic evidence with agentic reasoning.
GGBound: A Genome-Grounded Agent for Microbial Life-Boundary Prediction
Hanbo Huang*, Xuan Gong*, Jing Wang, Lei Bai, Xiang Xiao, Weishu Zhao, Shiyu Liang# (* equal contribution, # corresponding author)
Preprint 2026
GGBound presents a genome-grounded agent for predicting microbial life boundaries by combining genomic evidence with agentic reasoning.
Reflection Anchors for Propagation-Aware Visual Retention in Long-Chain Multimodal Reasoning
Xuan Gong, Hanbo Huang, Hao Zheng, Yiran Zhang, Wenbin Dai, Weishu Zhao, Shiyu Liang# (# corresponding author)
CompLearn Workshop @ ICML 2026
This work introduces reflection anchors for propagation-aware visual retention, targeting long-chain multimodal reasoning where visual evidence must remain reliable across extended inference.
Reflection Anchors for Propagation-Aware Visual Retention in Long-Chain Multimodal Reasoning
Xuan Gong, Hanbo Huang, Hao Zheng, Yiran Zhang, Wenbin Dai, Weishu Zhao, Shiyu Liang# (# corresponding author)
CompLearn Workshop @ ICML 2026
This work introduces reflection anchors for propagation-aware visual retention, targeting long-chain multimodal reasoning where visual evidence must remain reliable across extended inference.
RLSpoofer: A Lightweight Evaluator for LLM Watermark Spoofing Resilience
Hanbo Huang, Xuan Gong, Yiran Zhang, Hao Zheng, Shiyu Liang# (# corresponding author)
Preprint 2026
RLSpoofer proposes a lightweight evaluation framework for testing LLM watermark spoofing resilience with reinforcement-learning-based attack behavior.
RLSpoofer: A Lightweight Evaluator for LLM Watermark Spoofing Resilience
Hanbo Huang, Xuan Gong, Yiran Zhang, Hao Zheng, Shiyu Liang# (# corresponding author)
Preprint 2026
RLSpoofer proposes a lightweight evaluation framework for testing LLM watermark spoofing resilience with reinforcement-learning-based attack behavior.
2025
From Parameters to Prompts: Understanding and Mitigating the Factuality Gap between Fine-Tuned LLMs
Xuan Gong*, Hanbo Huang*, Yiran Zhang*, Shiyu Liang# (* equal contribution, # corresponding author)
ICASSP 2026
We revisit how supervised fine-tuning affects factual knowledge in LLMs, revealing a factuality gap between known and unknown knowledge. This gap can be mitigated at inference via in-context learning (ICL) or out-of-distribution prompts. Our theoretical and empirical results show that test-time prompts can overshadow fine-tuning data, suggesting ICL can compensate for poor fine-tuning and should be considered in evaluating fine-tuning strategies.
From Parameters to Prompts: Understanding and Mitigating the Factuality Gap between Fine-Tuned LLMs
Xuan Gong*, Hanbo Huang*, Yiran Zhang*, Shiyu Liang# (* equal contribution, # corresponding author)
ICASSP 2026
We revisit how supervised fine-tuning affects factual knowledge in LLMs, revealing a factuality gap between known and unknown knowledge. This gap can be mitigated at inference via in-context learning (ICL) or out-of-distribution prompts. Our theoretical and empirical results show that test-time prompts can overshadow fine-tuning data, suggesting ICL can compensate for poor fine-tuning and should be considered in evaluating fine-tuning strategies.
Reflection Anchors for Interpretable Compositional Visual Reasoning in Multimodal Reinforcement Learning
Xuan Gong, Hanbo Huang, Hao Zheng, Yiran Zhang, Wenbin Dai, Weishu Zhao, Shiyu Liang# (# corresponding author)
Preprint 2026
This work studies reflection anchors for interpretable compositional visual reasoning in multimodal reinforcement learning.
Reflection Anchors for Interpretable Compositional Visual Reasoning in Multimodal Reinforcement Learning
Xuan Gong, Hanbo Huang, Hao Zheng, Yiran Zhang, Wenbin Dai, Weishu Zhao, Shiyu Liang# (# corresponding author)
Preprint 2026
This work studies reflection anchors for interpretable compositional visual reasoning in multimodal reinforcement learning.
RLSpoofer: A Sample-Efficient Black-Box Spoofing Attack for Stress-Testing LLM Watermarks
Hanbo Huang, Xuan Gong, Yiran Zhang, Hao Zheng, Wenbin Dai, Jie Kuang, Shiyu Liang# (# corresponding author)
Trustworthy AI for Good (AI4GOOD) Workshop @ ICML 2026
This workshop paper studies sample-efficient black-box spoofing attacks for stress-testing the robustness of LLM watermarks.
RLSpoofer: A Sample-Efficient Black-Box Spoofing Attack for Stress-Testing LLM Watermarks
Hanbo Huang, Xuan Gong, Yiran Zhang, Hao Zheng, Wenbin Dai, Jie Kuang, Shiyu Liang# (# corresponding author)
Trustworthy AI for Good (AI4GOOD) Workshop @ ICML 2026
This workshop paper studies sample-efficient black-box spoofing attacks for stress-testing the robustness of LLM watermarks.
2024
DAMRO: Dive into the Attention Mechanism of LVLM to Reduce Object Hallucination
Xuan Gong, Tianshi Ming, Xinpeng Wang, Zhihua Wei# (# corresponding author)
EMNLP 2024 Main
We propose DAMRO, a training-free method to reduce object hallucination in LVLMs by filtering misleading high-attention background tokens using the ViT CLS token. DAMRO significantly improves hallucination control on models like LLaVA and InstructBLIP across multiple benchmarks.
DAMRO: Dive into the Attention Mechanism of LVLM to Reduce Object Hallucination
Xuan Gong, Tianshi Ming, Xinpeng Wang, Zhihua Wei# (# corresponding author)
EMNLP 2024 Main
We propose DAMRO, a training-free method to reduce object hallucination in LVLMs by filtering misleading high-attention background tokens using the ViT CLS token. DAMRO significantly improves hallucination control on models like LLaVA and InstructBLIP across multiple benchmarks.