Skip to main content

Showing 1–2 of 2 results for author: Yinghui, X

.
  1. arXiv:2603.08145  [pdf, ps, other

    cs.LG cs.AI

    DARC: Disagreement-Aware Alignment via Risk-Constrained Decoding

    Authors: Mingxi Zou, Jiaxiang Chen, Junfan Li, Langzhang Liang, Qifan Wang, Xu Yinghui, Zenglin Xu

    Abstract: Preference-based alignment methods (e.g., RLHF, DPO) typically optimize a single scalar objective, implicitly averaging over heterogeneous human preferences. In practice, systematic annotator and user-group disagreement makes mean-reward maximization brittle and susceptible to proxy over-optimization. We propose **Disagreement-Aware Alignment via Risk-Constrained Decoding (DARC)**, a retraining-fr… ▽ More

    Submitted 9 March, 2026; originally announced March 2026.

  2. arXiv:2512.15550  [pdf, ps, other

    cs.CL

    CTkvr: KV Cache Retrieval for Long-Context LLMs via Centroid then Token Indexing

    Authors: Kuan Lu, Shuhang Lin, Sai Wu, Yichen Yao, Junhan Yang, Huan Li, Wei Chu, Xu Yinghui, Yuan Qi, Gang Chen

    Abstract: Large language models (LLMs) are increasingly applied in long-context scenarios such as multi-turn conversations. However, long contexts pose significant challenges for inference efficiency, including high memory overhead from Key-Value (KV) cache and increased latency due to excessive memory accesses. Recent methods for dynamic KV selection struggle with trade-offs: block-level indexing degrades… ▽ More

    Submitted 17 December, 2025; originally announced December 2025.