跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+729新增论文
+575其中 AI 相关
+82已有论文修订
+95新增 AI 导读

arXiv 最近完成扫描:2026-11-21 12:19 · 全站最近入库:2026-11-21 12:19各信源进度 →

统计口径与数据新鲜度

统计 2026-11-20 15:14 — 2026-11-21 15:14(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-21 12:19最近发现新增版本:2026-11-21 12:19库内论文最新更新时间:2026-11-20 02:59

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

29,158 已收录论文24,181 AI 相关8,992 有修订112 HF 社区发现

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 2 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-21 12:17(北京时间)
新论文 · v1arXiv:2611.25416

Standardized Tolerance for Adaptive Reuse and Repair: A Method for HNSW Migration Under Embedding Model Change Scenarios

Hengzhao Ma, Chenyang Zhu, Bin Wang, Xiaochun Yang

原文摘要

When an embedding model changes, the same collection is re-encoded, and its vector index must be adapted to the new embedding space. Because the source and target vectors represent the same objects, suitable connections in the source index can be reused. We propose STARR (Standardized Tolerance for Adaptive Reuse and Repair) to migrate HNSW indexes after an embedding model change. STARR compares standardized edge lengths over the same source neighbor lists in both embedding spaces and uses the correlation between their distance profiles to set the allowable increase in standardized edge length. It reconnects affected vertices by searching the partially migrated graph and shares the resulting candidates with their neighbors. We bound edge rejection under local distance distortion, characterize migration work, and prove that a final repair pass makes every vertex reachable from the entry point at the base layer while respecting degree limits. Single-threaded experiments on MS MARCO, Wikipedia, and CC3M, each with one million objects, show that STARR achieves 5.25--44.54$\times$ construction speedups over Fresh and migrates faster than both DGM variants on all 15 selected transitions. Recall@10 remains within one percentage point of Fresh in 10 cases, and query throughput exceeds DGM-Local in 14 cases. Parameter sweeps on three transitions further demonstrate favorable migration-time--recall tradeoffs beyond the default settings. Across all 240 directed transitions among 16 MS MARCO models, STARR achieves a median construction speedup of 16.71$\times$ with a median recall loss of 1.0 percentage point.

cs.DB

版本更新 · v2arXiv:2602.18721

ReHear: Iterative Pseudo-Label Refinement for Semi-Supervised Speech Recognition via Audio Large Language Models

Zefang Liu, Chenyang Zhu, Sangwoo Cho, Shi-Xiong Zhang

原文摘要

Semi-supervised learning in automatic speech recognition (ASR) typically relies on pseudo-labeling, which often suffers from confirmation bias and error accumulation due to noisy supervision. To address this limitation, we propose ReHear, a framework for iterative pseudo-label refinement that integrates an instruction-tuned, audio-aware large language model (LLM) into the self-training loop. Unlike conventional text-based correctors, our approach conditions the LLM on both the ASR hypothesis and the source audio, allowing it to recover phonetically accurate transcripts even from severe recognition errors. These refined pseudo-labels serve as high-fidelity targets for fine-tuning the ASR model in an iterative cycle. Experimental results across diverse benchmarks demonstrate that ReHear effectively mitigates error propagation and improves over both supervised and pseudo-labeling baselines.

cs.CL · eess.AS