9 papers · 1 filter
Continual Learning in Transition
Zhiyan Hou, Dan Zhang, Tao Feng +11
Classical continual learning (CL) has primarily focused on enabling models to update and retain knowledge through parameter-centric mechanisms, e.g., training strategies, architect…
Tiny Brains, Giant Impact: Uncovering the Keystone Neurons of LLM with Just a Few Prompts
Xiangtian Ji, Yuxin Chen, Zhengzhou Cai +3
Large language models (LLMs) display strong comprehensive abilities, yet the internal mechanisms that support these behaviors remain insufficiently understood. In this work, we sho…
Rubric-based On-policy Distillation
Junfeng Fang, Zhepei Hong, Mao Zheng +7
On-policy distillation (OPD) is a powerful paradigm for model alignment, yet its reliance on teacher logits restricts its application to white-box scenarios. We contend that struct…
On the Implicit Reward Overfitting and the Low-rank Dynamics in RLVR
Hao Ye, Jisheng Dang, Junfeng Fang +7
Recent extensive research has demonstrated that the enhanced reasoning capabilities acquired by models through Reinforcement Learning with Verifiable Rewards (RLVR) are primarily c…
Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing
Gengsheng Li, Tianyu Yang, Junfeng Fang +6
Reinforcement learning with verifiable rewards (RLVR) has become a standard paradigm for post-training large language models. While Group Relative Policy Optimization (GRPO) is wid…
DRAFT: Task Decoupled Latent Reasoning for Agent Safety
Lin Wang, Junfeng Fang, Dan Zhang +3
The advent of tool-using LLM agents shifts safety monitoring from output moderation to auditing long, noisy interaction trajectories, where risk-critical evidence is sparse-making…
SafeNeuron: Neuron-Level Safety Alignment for Large Language Models
Zhaoxin Wang, Jiaming Liang, Fengbin Zhu +5
Large language models (LLMs) and multimodal LLMs are typically safety-aligned before release to prevent harmful content generation. However, recent studies show that safety behavio…
NExT-Guard: Training-Free Streaming Safeguard without Token-Level Labels
Junfeng Fang, Nachuan Chen, Houcheng Jiang +5
Large language models are increasingly deployed in streaming scenarios, rendering conventional post-hoc safeguards ineffective as they fail to interdict unsafe content in real-time…
Controllable Value Alignment in Large Language Models through Neuron-Level Editing
Yonghui Yang, Yihui Wang, Junwei Li +6
Aligning large language models (LLMs) with human values has become increasingly important as their influence on human behavior and decision-making expands. However, existing steeri…