8 papers
Probing the Misaligned Thinking Process of Language Models
Kaiwen Zhou, Constantin Venhoff, Jonathan Michala +2
Large language models exhibit a growing range of misaligned behaviors such as strategic deception, sandbagging, and self-preservation. As they are increasingly deployed in high-sta…
"PhyWorldBench": A Comprehensive Evaluation of Physical Realism in Text-to-Video Models
Jing Gu, Xian Liu, Yu Zeng +8
Video generation models have achieved remarkable progress in creating high-quality, photorealistic content. However, their ability to accurately simulate physical phenomena remains…
SafePro: Evaluating the Safety of Professional-Level AI Agents
Kaiwen Zhou, Shreedhar Jangam, Ashwin Nagarajan +7
Large language model-based agents are rapidly evolving from simple conversational assistants into autonomous systems capable of performing complex, professional-level tasks in vari…
SafeKey: Amplifying Aha-Moment Insights for Safety Reasoning
Kaiwen Zhou, Xuandong Zhao, Gaowen Liu +4
Large Reasoning Models (LRMs) introduce a new generation paradigm of explicitly reasoning before answering, leading to remarkable improvements in complex tasks. However, they pose…
The Hidden Risks of Large Reasoning Models: A Safety Assessment of R1
Kaiwen Zhou, Chengzhi Liu, Xuandong Zhao +5
The rapid development of large reasoning models (LRMs), such as OpenAI-o3 and DeepSeek-R1, has led to significant improvements in complex reasoning over non-reasoning large languag…
Presenting a Paper is an Art: Self-Improvement Aesthetic Agents for Academic Presentations
Chengzhi Liu, Yuzhe Yang, Kaiwen Zhou +5
The promotion of academic papers has become an important means of enhancing research visibility. However, existing automated methods struggle limited storytelling, insufficient aes…