1 citations · 2 across the 12 of their papers we have counts for
20 papers
SAVeR: Reasoning-based Safety Alignment for Large Reasoning Models via Verifiable Rewards
Yichen Sun, Qirui Liu, Yan Wang +5
Large Reasoning Models (LRMs) have achieved impressive performance via explicit Chain-of-Thought (CoT) reasoning, yet this process introduces critical safety risks. We formalize LR…
Beyond Fresnel Approximation: Exact Airy Beamforming for Near-Field THz Communications
Fangjie Shen, Weidong Mei, Aoran Liu +2
Line-of-sight (LoS) blockage can severely degrade the performance of conventional focused beams in terahertz (THz) communications. Recently, bending beams (e.g., Airy beams) have a…
From Imitation to Reward Discovery: On-Policy Warmup for Agentic RL
Yitong Qiao, Tiantian He, Lei Liu +4
Reinforcement learning with a verifiable reward (RLVR) offers a scalable approach to training language-model agents, yet sparse outcome rewards can leave early training with little…
EHR-RobustGym: Benchmarking and Training Agents for Robust Clinical Reasoning
Yitong Qiao, Yancheng Jin, Lei Liu +4
In hospital workflows, electronic health records (EHRs) are often noisy, and may not contain the evidence needed to confirm events or measurements referenced in a clinical query. E…
DeShortcut-Align: Decoupling Spurious Shortcuts for Robust Safety Alignment in Large Reasoning Models
Qirui Liu, Yichen Sun, Yan Wang +4
Safety alignment of large reasoning models (LRMs) via supervised fine-tuning (SFT) and reinforcement learning (RL) often yields near-perfect safety scores, yet this apparent succes…
EOPSA: Efficient On-Policy Self-Distilled Safety Alignment
Qirui Liu, Yichen Sun, Yan Wang +5
On-Policy Self-Distillation (OPSD) has emerged as a promising paradigm for safety alignment, delivering dense, token-level supervision by distilling from a teacher conditioned on r…
SALA: Semantic-Aware Logical Alignment for Complex Reasoning in In-Context Learning
Zhao Ji, Wenqing Chen, Zhixuan Chu +4
Effective in-context learning (ICL) for complex reasoning relies on selecting the right demonstrations. Traditional retrieval methods based on surface similarity fail to capture th…
CoMerge: Conflict-Driven Preference Optimization for Multi-Task Model Merging
Mingjie Zheng, Zihao Chen, Wenqing Chen +4
Model merging provides an efficient paradigm for constructing multi-task large language models (LLMs) without full model retraining, yet it remains challenged by parameter interfer…
AgentSnare: Learning to Delay, Divert, and Defuse Autonomous Web Penetration Agents
Ruoyu Wang, Heng Zhao, Renjie Wu +5
Large language model agents automate web penetration testing through observation-action loops, enabling defenders to influence decisions with deceptive decoy observations. Advanced…
REIN: Bridging the Gap between Reasoning and Reliability via Reflection and Abstention Alignment
Zhengze Huang, Luyang Yu, Di Hong +5
Large reasoning models (LRMs) are prone to hallucination, which undermines their reliability and poses challenges for safe deployment. Hallucinations in LRMs arise from two distinc…
EHR-Complex: Benchmarking Medical Agents for Complex Clinical Reasoning
Yitong Qiao, Lei Liu, Yue Shen +4
Clinical agents promise to democratize access to electronic health records (EHRs), yet existing benchmarks fail to reflect the complexity of practical EHR analysis, e.g., often ope…
ConsisGuard: Aligning Safety Deliberation with Policy Enforcement in LLM Guardrails
Yan Wang, Zhixuan Chu, Zihao Xue +9
Reasoning-based LLM guardrails improve safety moderation by generating explicit rationales before issuing final decisions. However, their rationales do not always lead to faithful…
JANUS: A Lightweight Framework for Jailbreaking Text-to-Image Models via Distribution Optimization
Haolun Zheng, Yu He, Tailun Chen +6
Text-to-image (T2I) models such as Stable Diffusion and DALLE remain susceptible to generating harmful or Not-Safe-For-Work (NSFW) content under jailbreak attacks despite deployed…
Explainable Token-level Noise Filtering for LLM Fine-tuning Datasets
Yuchen Yang, Wenze Lin, Enhao Huang +6
Large Language Models (LLMs) have seen remarkable advancements, achieving state-of-the-art results in diverse applications. Fine-tuning, an important step for adapting LLMs to spec…
Perplexity-Aware Data Scaling Law: Perplexity Landscapes Predict Performance for Continual Pre-training
Lei Liu, Hao Zhu, Yue Shen +4
Continual Pre-training (CPT) serves as a fundamental approach for adapting foundation models to domain-specific applications. Scaling laws for pre-training define a power-law relat…
Mitigating Social Bias in Large Language Models: A Multi-Objective Approach within a Multi-Agent Framework
Zhenjie Xu, Wenqing Chen, Yi Tang +6
Natural language processing (NLP) has seen remarkable advancements with the development of large language models (LLMs). Despite these advancements, LLMs often produce socially bia…
JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit
Zeqing He, Zhibo Wang, Zhixuan Chu +4
Despite the outstanding performance of Large language Models (LLMs) in diverse tasks, they are vulnerable to jailbreak attacks, wherein adversarial prompts are crafted to bypass th…
Prompt-Consistency Image Generation (PCIG): A Unified Framework Integrating LLMs, Knowledge Graphs, and Controllable Diffusion Models
Yichen Sun, Zhixuan Chu, Zhan Qin +1
The rapid advancement of Text-to-Image(T2I) generative models has enabled the synthesis of high-quality images guided by textual descriptions. Despite this significant progress, th…
A Survey on Medical Large Language Models: Technology, Application, Trustworthiness, and Future Directions
Lei Liu, Xiaoyan Yang, Junchi Lei +6
With the advent of Large Language Models (LLMs), medical artificial intelligence (AI) has experienced substantial technological progress and paradigm shifts, highlighting the poten…
Towards Real-world Debiasing: Rethinking Evaluation, Challenge, and Solution
Peng Kuang, Zhibo Wang, Zhixuan Chu +2
Spurious correlations in training data significantly hinder the generalization capability of machine learning models when faced with distribution shifts, leading to the proposition…