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

+1112新增论文
+875其中 AI 相关
+133已有论文修订
+97新增 AI 导读

arXiv 最近完成扫描:2026-11-20 04:39 · 全站最近入库:2026-11-19 19:09各信源进度 →

统计口径与数据新鲜度

统计 2026-11-19 05:31 — 2026-11-20 05:31(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:2026-11-20 04:39最近发现新增版本:2026-11-19 19:09库内论文最新更新时间:2026-11-19 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。

27,982 已收录论文23,249 AI 相关8,559 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 4 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-20 04:38(北京时间)
新论文 · v1arXiv:2611.23794

Benchmarking Traditional and Learning-Based Reference-Free Compressors for Long-Read Sequencing Data

Huidong Ma, Hui Sun, Xinyan Shi, Cheng Zhong, Xiaoguang Liu, Gang Wang

原文摘要

Long-read sequencing technologies generate large volumes of data, creating substantial storage and transmission demands. Although reference-based compressors can achieve high compression, their reliance on an appropriate reference genome limits their use. We present LRCBench, a benchmark and survey of reference-free lossless compressors for long-read sequencing data. We review traditional and learning-based general-purpose and sequencing-specific methods, then evaluate 35 compressors on 16 real-world datasets from Oxford Nanopore and PacBio platforms. We compare compression ratio, storage savings, runtime, peak memory use, and robustness across datasets. Learning-based compressors are evaluated on six MinION datasets because of their high computational costs. CoLoRd achieves the best overall compression ratios in our experiments, while other methods offer trade-offs in speed, memory use, and robustness. We also examine multithreaded speedup and discuss future directions in parallel acceleration, privacy protection, adaptive parameter tuning, and hardware-algorithm co-design.

cs.IT · q-bio.GN

新论文 · v1arXiv:2611.22894

Wear and Go: Calibration Free Sparse Inertial Motion Capture via Online Sensor Setup Estimation

Yuanshuo Tan, Licheng Zhong

原文摘要

Sparse inertial motion capture typically assumes that each sensor's anatomical identity and mounting orientation are known. We present MOSAIC (Motion-based Sensor Assignment and Inertial Calibration), a framework that recovers this setup from ordinary motion without a calibration pose. Our central insight is that body pose changes continuously while the sensor setup persists, allowing movements that are individually ambiguous to provide complementary evidence over time. A setup network processes unordered sensor streams with temporal and cross-sensor attention, then accumulates assignment and rotation evidence into a session-level estimate. The recovered setup canonicalizes measurements for frozen pretrained pose estimators, separating sensor configuration from motion reconstruction. For sensors worn at prescribed body sites, evaluation on real inertial recordings with randomized setups shows near-calibrated pose accuracy for bounded offsets and substantial benefits from accumulation under arbitrary orientations. Transfer across pose networks supports setup recovery as a reusable interface between interchangeable sensors and pretrained pose models.

cs.CV

新论文 · v1arXiv:2611.22491

Progress Predicts Policy

Licheng Zhong, Gim Hee Lee

原文摘要

A task specifies how the world should change, while a policy specifies what the robot should do. We introduce Progress Predicts Policy (PPP), which learns a language-conditioned scalar field through the commands induced by its differential. We obtain action conditioning by composing a latent progress field with a shared world model and read its action gradient at a fixed reference command. Continuous commands scale this gradient by a learned positive gain, while discrete commands use finite differences of the same scalar. This yields a hybrid policy without a separate action head or iterative search. Fitting demonstration progress values alone does not ensure that action gradients align with expert commands. PPP trains the induced commands by imitation and uses double backpropagation for the continuous gradient readout to shape the field's local control geometry. Demonstration timing calibrates field values on observed states without additional annotation. The continuous readout remains learnable without progress labels but these timing-derived targets support progress monitoring during execution. Experiments in simulated and real robot manipulation show that PPP outperforms behavioral cloning under a shared architecture.

cs.RO

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.861ACL Anthology · ACL 2026

TellWhisper: Tell Whisper Who Speaks When

Yifan Hu, Peiji Yang, Zhisheng Wang Tencent, Yicheng Zhong, Rui Liu Inner Mongolia University

原文摘要

Multi-speaker automatic speech recognition (MASR) aims to predict ”who spoke when and what” from multi-speaker speech, a key technology for multi-party dialogue understanding. However, most existing approaches decouple temporal modeling and speaker modeling when addressing ”when” and ”who”: some inject speaker cues before encoding (e.g., speaker masking), which can cause irreversible information loss; others fuse identity by mixing speaker posteriors after encoding, which may entangle acoustic content with speaker identity. This separation is brittle under rapid turn-taking and overlapping speech, often leading to degraded performance. To address these limitations, we propose TellWhisper, a unified framework that jointly models speaker identity and temporal within the speech encoder. Specifically, we design TS\text{-}RoPE, a time-speaker rotary positional encoding: time coordinates are derived from frame indices, while speaker coordinates are derived from speaker activity and pause cues. By applying region-specific rotation angles, the model explicitly captures per-speaker continuity, speaker-turn transitions, and state dynamics, enabling the attention mechanism to simultaneously attend to ”when” and ”who”. Moreover, to estimate frame-level speaker activity, we develop Hyper\text{-}SD, which casts speaker classification in hyperbolic space to enhance inter-class separation and refine speaker-activity estimates. Extensive experiments demonstrate the effectiveness of the proposed approach. The project webpage is available at https://walker-hyf.github.io/TellWhisper.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表