13 papers
REAL: Reading Out Transformer Activations for Precise Localization in Language Model Steering
Li-Ming Zhan, Bo Liu, Chengqiang Xie +2
The paper introduces REAL, a method that trains vector-quantized autoencoders on transformer activations to pinpoint attention heads or layers that most influence a target behavior…
Kairos: A Regret-Aware Native World-Action Model Stack for Physical AI
Kairos Team, Fei Wang, Shan You +21
We introduce \textbf{Kairos}, a regret-aware native world-action model stack for Physical AI. Kairos is motivated by the view that a physical world model should not aim to fully si…
COMFYCLAW: Self-Evolving Skill Harnesses for Image Generation Workflows
Zongxia Li, Dawei Liu, Fuxiao Liu +6
Agents are increasingly used to construct workflows and assist humans in completing recurring tasks more efficiently. As these workflows become repeated and domain-specific, agent…
ROSD: Reflective On-Policy Self-Distillation for Language Model Reasoning across Domains
Ziqi Zhao, Xinyu Ma, Liu Yang +6
On-policy self-distillation (OPSD) improves the reasoning performance of large language models (LLMs) by providing dense token-level supervision for on-policy rollouts. However, ex…
FOREVER: Forgetting Curve-Inspired Memory Replay for Language Model Continual Learning
Yujie Feng, Hao Wang, Jian Li +6
Continual learning (CL) for large language models (LLMs) aims to enable sequential knowledge acquisition without catastrophic forgetting. Memory replay methods are widely used for…
CodeSpecBench: Benchmarking LLMs for Executable Behavioral Specification Generation
Zaoyu Chen, Jianbo Dai, Boyu Zhu +6
Large language models (LLMs) can generate code from natural language, but the extent to which they capture intended program behavior remains unclear. Executable behavioral specific…