Xin Teng — accepted AI-conference papers

2026

InfoFlow KV: Information-Flow-Aware KV Recomputation for Long Context

Xin Teng, Canyu Zhang, Shaoyi Zheng, Danyang Zhuo, Tianyi Zhou, Shenji Wan

ICML 2026poster

Retrieval-augmented generation (RAG) for long-context question answering is bottlenecked by inference-time prefilling over large retrieved contexts. A common strategy is to precompute key–value (KV) caches for individual documents and selectively recompute a small subset of tokens to restore global …

Cited by 0 Source ↗Scholar ↗

2025

Reveal and Release: Iterative LLM Unlearning with Self-generated Data

Linxi Xie, Xin Teng, Shichang Ke, Hongyi Wen, Shenji Wan

EMNLP 2025

Large language model (LLM) unlearning has demonstrated effectiveness in removing the influence of undesirable data (also known as forget data). Existing approaches typically assume full access to the forget dataset, overlooking two key challenges: (1) Forget data is often privacy-sensitive, rare, or

Cited by 0 Source ↗PDF ↗Scholar ↗