23 citations · 38 across the 12 of their papers we have counts for
12 papers
Not Just Reason, Not Just Scan: Reinforcement Learning for Proactive Scientific Error Verification over Academic Paper
Rongjin Li, Yuanxin Liu, Hao Zhou +3
Multimodal large language models (MLLMs) are increasingly capable scientific assistants, yet they remain far from fully autonomous research. This transition requires models to acti…
The Missing Half: Unveiling Training-time Implicit Safety Risks Beyond Deployment
Zhexin Zhang, Yida Lu, Junfeng Fang +8
Safety risks of AI models have been widely studied at deployment time, such as jailbreak attacks that elicit harmful outputs. In contrast, safety risks emerging during training rem…
Readability-Robust Code Summarization via Meta Curriculum Learning
Wenhao Zeng, Yitian Chai, Hao Zhou +3
Code summarization has emerged as a fundamental technique in the field of program comprehension. While code language models have shown significant advancements, the current models…
Conan: Progressive Learning to Reason Like a Detective over Multi-Scale Visual Evidence
Kun Ouyang, Yuanxin Liu, Linli Yao +5
Video reasoning, which requires multi-step deduction across frames, remains a major challenge for multimodal large language models (MLLMs). While reinforcement learning (RL)-based…
SpaceR: Reinforcing MLLMs in Video Spatial Reasoning
Kun Ouyang, Yuanxin Liu, Haoning Wu +5
Video spatial reasoning, which involves inferring the underlying spatial structure from observed video frames, poses a significant challenge for existing Multimodal Large Language…
PunchBench: Benchmarking MLLMs in Multimodal Punchline Comprehension
Kun Ouyang, Yuanxin Liu, Shicheng Li +5
Multimodal punchlines, which involve humor or sarcasm conveyed in image-caption pairs, are a popular way of communication on online multimedia platforms. With the rapid development…
MiniPLM: Knowledge Distillation for Pre-Training Language Models
Yuxian Gu, Hao Zhou, Fandong Meng +2
Knowledge distillation (KD) is widely used to train small, high-performing student language models (LMs) using large teacher LMs. While effective in fine-tuning, KD during pre-trai…
On Prompt-Driven Safeguarding for Large Language Models
Chujie Zheng, Fan Yin, Hao Zhou +5
Prepending model inputs with safety prompts is a common practice for safeguarding large language models (LLMs) against queries with harmful intents. However, the underlying working…
RECALL: A Benchmark for LLMs Robustness against External Counterfactual Knowledge
Yi Liu, Lianzhe Huang, Shicheng Li +5
LLMs and AI chatbots have improved people's efficiency in various fields. However, the necessary knowledge for answering the question may be beyond the models' knowledge boundaries…
Large Language Models Are Not Robust Multiple Choice Selectors
Chujie Zheng, Hao Zhou, Fandong Meng +2
Multiple choice questions (MCQs) serve as a common yet important task format in the evaluation of large language models (LLMs). This work shows that modern LLMs are vulnerable to o…
Towards Codable Watermarking for Injecting Multi-bits Information to LLMs
Lean Wang, Wenkai Yang, Deli Chen +5
As large language models (LLMs) generate texts with increasing fluency and realism, there is a growing need to identify the source of texts to prevent the abuse of LLMs. Text water…
Diffusion Theory as a Scalpel: Detecting and Purifying Poisonous Dimensions in Pre-trained Language Models Caused by Backdoor or Bias
Zhiyuan Zhang, Deli Chen, Hao Zhou +3
Pre-trained Language Models (PLMs) may be poisonous with backdoors or bias injected by the suspicious attacker during the fine-tuning process. A core challenge of purifying potenti…