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

+1284新增论文
+1011其中 AI 相关
+150已有论文修订
+97新增 AI 导读

arXiv 最近完成扫描:2026-11-20 08:48 · 全站最近入库:2026-11-20 10:50各信源进度 →

统计口径与数据新鲜度

统计 2026-11-19 11:54 — 2026-11-20 11:54(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 08:48最近发现新增版本:2026-11-20 10:50库内论文最新更新时间:2026-11-19 12:39

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。

28,155 已收录论文23,386 AI 相关8,624 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 5 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-20 08:46(北京时间)
新论文 · v1arXiv:2611.25448

Atlas: Accelerating Quantum FTQC Compilation with Optimized Algebraic Rotation Synthesis

Anbang Wu, Pu Pang, Wei Geng

原文摘要

As fault-tolerant quantum computing emerges, Clifford+T gate basis becomes a popular choice where we need to decompose single-qubit rotation gates into gates in this gate basis. Quantum rotation synthesis may lead to remarkable overhead in quantum circuit compilation. Considering variational quantum eigensolver (VQE) applications as an example, a conventional UCCSD ansatz in quantum chemistry can generate $O(n^4)$ rotations for $n$ qubits. Each optimization iteration updates the rotation angles, making rotation synthesis a recurring cost that can delay the VQE training loop. We identify two sources of delay in rotation synthesis: redundant computation during synthesis and uneven synthesis times that leave workers waiting for slow requests. Atlas addresses these costs with three optimizations: search pruning skips invalid synthesis candidates through statistical inference; adaptive arithmetic avoid unnecessary high-overhead big integer/float arithmetic when decomposing the target rotation gate; batch scheduling fills the gap between the synthesis time of varied rotations. Across various benchmarks, synthesis method, and compilation machines, Atlas can consistently accelerate the rotation synthesis process by up to 12.65x.

cs.ET

新论文 · v1arXiv:2611.22095

CueSplat: Learning to Schedule Sparse Deformation for Dynamic Gaussian Splatting on Edge Devices

Qingyuan Tang, He Zhu, Shixuan Sun, Anbang Wu, Jingwen Leng, Minyi Guo, Yu Feng

原文摘要

Deformation-based 4D Gaussian splatting (4DGS) enables dynamic scene rendering. However, evaluating deformation networks for all Gaussians at every frame is compute-intensive on edge devices. We find that Gaussian trajectories are often locally predictable, yet prediction reliability varies across Gaussians and time. Thus, we propose CueSplat, a post-training framework that exploits local temporal regularity while keeping the pretrained backbone frozen and retaining its Gaussian set. Specifically, CueSplat predicts Gaussian attributes from recent history and uses a lightweight learned router to select exact deformation updates within a scene-specific budget calibrated offline. Selection accounts for prediction reliability and rendering contribution. Selected indices are reused across nearby frames to reduce routing overhead, while selected Gaussians still receive exact updates each frame. To control accumulated prediction error, we use drift signals to schedule three consecutive full-deformation frames that rebuild the prediction history. Evaluated across four mainstream 4DGS algorithms, CueSplat achieves up to $6.74\times$ and $8.15\times$ speedups on Jetson AGX Orin and Orin NX, respectively, with a negligible quality drop (at most $0.16$ dB in dataset-average PSNR).

cs.CV

新论文 · v1arXiv:2611.19715

Proxima: Optimizing Syndrome Extraction Circuit Scheduling for Practical Quantum LDPC Codes

Ruiyun Zhang, Guangqi Zhao, Zhaohui Yang, Yingjian Liu, Chenghong Zhu, Anbang Wu, Jun Xia, Yuan Xie

原文摘要

The fault-tolerant performance of quantum error correction codes relies critically on the scheduling of parity checks in syndrome extraction circuits (SECs). For general CSS-type quantum low-density parity-check (qLDPC) codes, the vast scheduling space and intricate error-propagation patterns make it computationally prohibitive to directly optimize the logical error rate (LER) or the exact circuit-level distance ($d_{\mathrm{circ}}$). To address this challenge, we introduce Proxima, a highly effective automated SEC scheduling framework guided by a distance-related metric termed proximity. Defined directly on the detector error model (DEM), proximity quantifies the minimum number of additional faults required to complete a seed fault to an undetectable logical failure, naturally capturing arbitrary circuit-level fault mechanisms and bounding $d_{\mathrm{circ}}$ from above. Proxima synthesizes a pool of valid schedules at a target depth and ranks them by evaluating proximity within small, graph-local DEM fault subsets, progressively enlarging the subset only to break ties among top-ranked candidates. Across a broad spectrum of qLDPC code families, Proxima consistently attains low circuit depths and high circuit-level distance bounds, reducing LER by 1.4--2.6$\times$ over the strongest automated baseline and up to $40\times$ over others while generalizing robustly across noise models and decoders. Furthermore, by exploiting translational symmetry via a compact monomial representation, Proxima discovers depth-8 uniform schedules for bivariate bicycle codes that surpass even IBM's depth-7 reference schedule [Nature, 2024] by 2.1--5.1$\times$, establishing the DEM-level proximity as a practical objective for fault-tolerant compilation.

quant-ph · cs.PL

版本更新 · v2arXiv:2611.11098

Efficient VLA Inference via Retrieval-Based Speculation and Hardware Acceleration

Zhengyang Cheng, He Zhu, Zeyu Guo, Zihan Liu, Anbang Wu, Yiming Gan, Jingwen Leng, Yu Feng 等 9 位作者

原文摘要

Vision-language-action (VLA) models enable robots to understand and execute complex instructions, but their autoregressive (AR) action generation introduces significant latency on resource-constrained robotic platforms. Speculative decoding can accelerate AR-based inference by parallelizing action generation and verification; however, existing approaches rely on costly draft models, which are inefficient on edge platforms. In this paper, we propose Zora, a hardware-software co-design framework for accelerating AR-based VLA inference. Specifically, Zora introduces a lightweight retrieval-augmented generation (RAG)-based draft model that exploits robotic dynamics without additional neural draft models. We further reduce batch verification overhead through a kinematics-guided action-acceptance strategy and a KV-cache-sharing attention mechanism. To address the retrieval overhead introduced by RAG-based drafting, we co-design dedicated hardware support, Zora core, to address the memory irregularity in RAG-based drafting. We evaluate Zora on four VLA models with the LIBERO benchmark. Zora retains comparable accuracy while achieving up to 3.4$\times$ speedup with software-only optimization and up to 7.6$\times$ speedup with hardware support over GPUs.

cs.AR · cs.RO

新论文 · v1arXiv:2611.04401

LiquidCP: Decoupling Attention Tasks from Communication and Kernel Boundaries in Context Parallelism

Hongyu Chen, Yikang Ruan, Yuhai Long, Ziyu Huang, Yiyu Luo, Liukun Yu, Yangjie Zhou, Zihan Liu 等 17 位作者

原文摘要

Context parallelism (CP) partitions long sequences across GPUs for LLM training and inference. For variable-length training and full prefill, attention-balanced placement can leave token loads uneven, while ring execution repeats overhead at each computation and communication step. In stage-serialized decode CP (DCP), long-running tasks delay dependent work and leave substantial GPU hardware idle. We propose LiquidCP, which unifies training and inference through a common model of Transfer, Compute, and Reduction tasks with tile-level dependencies, decoupling attention tasks from communication and kernel boundaries. For training and full prefill, MegaRing incorporates BuddyRing placement to balance attention and token loads, and coalesces ready KV regions during forward attention to amortize overhead. For decoding and mixed batches, MegaDCP selects history-KV splits by jointly modeling the completion of attention and its dependent reductions. A shared persistent GPU-resident engine executes both designs. Compared with the fastest baseline per configuration on eight H100 GPUs, MegaRing achieves geometric-mean core-attention speedups of $1.23\times$ forward and $1.18\times$ backward, and accelerates a Transformer layer by $1.08$--$1.16\times$. MegaDCP achieves geometric-mean core-attention speedups of $1.20\times$ for decode-only and $1.35\times$ for mixed batches. In vLLM serving with KV prefix cache, it achieves an average time-to-first-token speedup of $1.22\times$.

cs.DC