14 papers
From Hindsight to Foresight: Self-Encouraged Hindsight Distillation for Knowledge-based Visual Question Answering
Yu Zhao, Ying Zhang, Xuhui Sui +4
The paper introduces a teacher‑student framework called Hindsight Distillation (HinD) that uses privileged answer information to generate reasoning trajectories for a multimodal LL…
LLM Evolution as an Industry-Scale Ecosystem: A Lifecycle Perspective on Continual Learning
Hao Jiang, Enneng Yang, Guojie Zhu +7
Continual learning capability is critical for Industrial LLMs, as deployed models must be continuously updated to meet evolving requirements and environments, rather than repeatedl…
Convergent Differential Privacy Analysis for General Federated Learning
Yan Sun, Qixin Zhang, Li Shen +1
The powerful cooperation of federated learning (FL) and differential privacy~(DP) provides a promising paradigm for the large-scale private clients. However, existing analyses in F…
Reason-KE++: Aligning the Process, Not Just the Outcome, for Faithful LLM Knowledge Editing
Yuchen Wu, Liang Ding, Li Shen +1
Aligning Large Language Models (LLMs) to be faithful to new knowledge in complex, multi-hop reasoning tasks is a critical, yet unsolved, challenge. We find that SFT-based methods,…
Sparse Model Inversion: Efficient Inversion of Vision Transformers for Data-Free Applications
Zixuan Hu, Yongxian Wei, Li Shen +4
Model inversion, which aims to reconstruct the original training data from pre-trained discriminative models, is especially useful when the original training data is unavailable du…
Network Sparsity Unlocks the Scaling Potential of Deep Reinforcement Learning
Guozheng Ma, Lu Li, Zilin Wang +3
Effectively scaling up deep reinforcement learning models has proven notoriously difficult due to network pathologies during training, motivating various targeted interventions suc…