4 papers
Predictive Memory Localization: Forecasting Selective Intervention Paths from Internal Signals
Jinhao Jing, Tian Zeyu, Lucas Qingyang Fang +4
Activation steering turns localized representations into control directions, but localization alone does not reveal whether a direction has a selective operating regime. We introdu…
Efficient Data Selection for Multimodal Models via Incremental Optimization Utility
Jinhao Jing, Qiannian Zhao, Chao Huang +1
The scaling of Large Multimodal Models (LMMs) is constrained by the quality-quantity trade-off inherent in synthetic data. Previous approaches, such as LLM-as-a-Judge, have proven…
Know What You Know: Metacognitive Entropy Calibration for Verifiable RL Reasoning
Qiannian Zhao, Chen Yang, Jinhao Jing +5
Large reasoning models (LRMs) have emerged as a powerful paradigm for solving complex real-world tasks. In practice, these models are predominantly trained via Reinforcement Learni…
Statistical Theory of Multi-stage Newton Iteration Algorithm for Online Continual Learning
Xinjia Lu, Chuhan Wang, Qian Zhao +2
We focus on the critical challenge of handling non-stationary data streams in online continual learning environments, where constrained storage capacity prevents complete retention…