13 papers
KVEraser: Learning to Steer KV Cache for Efficient Localized Context Erasing
Mufei Li, Shikun Liu, Dongqi Fu +5
Post-hoc context erasing over the KV cache is challenging because a local edit has a global consequence: once a span has been processed, its influence propagates into the cached st…
Towards Direct Latent-Space Synthesis for Parallel Branches in LLM-Agent Workflows
Shikun Liu, Mufei Li, Dongqi Fu +5
Large language models increasingly serve as execution engines for agentic systems, yet they still consume context through a sequential text interface. This creates a mismatch with…
PrivUn: Unveiling Latent Ripple Effects and Shallow Forgetting in Privacy Unlearning
Xiaoyi Chen, Haoyuan Wang, Siyuan Tang +4
Large language models (LLMs) often memorize private information during training, raising serious privacy concerns. While machine unlearning has emerged as a promising solution, its…
Sampling Transferable Graph Neural Networks with Limited Graph Information
Haoyu Wang, Renyuan Ma, Gonzalo Mateos +1
Graph neural networks (GNNs) achieve strong performance on graph learning tasks, but training on large-scale networks remains computationally challenging. Transferability results s…
Implicit Turn-Wise Policy Optimization for Proactive User-LLM Interaction
Haoyu Wang, Yuxin Chen, Liang Luo +3
Multi-turn human-AI collaboration is fundamental to deploying interactive services such as adaptive tutoring, conversational recommendation, and professional consultation. However,…
What Are Good Positional Encodings for Directed Graphs?
Yinan Huang, Haoyu Wang, Pan Li
Positional encodings (PEs) are essential for building powerful and expressive graph neural networks and graph transformers, as they effectively capture the relative spatial relatio…