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

+549新增论文
+443其中 AI 相关
+62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 17:57 — 2026-11-21 17:57(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:2611.23806

Breaking the Myth of Four-Tier Stacked Transistors for Logic: an Investigation from Process to Device and Block-Level PPA

Jianxiang Jin, Haoran Lu, Yihan Luo, Yanbang Chu, Yibo Zhang, Jingru Jiang, Yuji Cheng, Wanyue Peng 等 16 位作者

原文摘要

For the first time, this work evaluated whether 4-tier stacked transistors can translate the straightforward density gains into realistic chip-level scaling benefits. A practical dual-sided 4-tier transistor-stacking CFFET (Flipped CFET-to-CFET) process was proposed, on which a DTCO framework spanning standard-cell design, local interconnects, RO analysis, and physical implementation was built under 2A node design rules. The CFFET was also benchmarked with its 2-tier transistor-stacking counterparts FFET. Among CFFET configurations, the best-performing Symmetric Power still lags FFET by 11.2% in RO frequency due to the complex MOL parasitics. At the block level, CFFET reduces the Ibex RISC-V core area by only 12.8% (far below the 40% nominal cell-height reduction), while running 10.9% slower at iso-power. We further introduced a novel Tetris-like cell stitching to minimize the area overhead, which allows non-rectangular cell design and recovers 7.4% area in a 1-bit ALU design. An optimized NanoStack CFFET was finally proposed, inspired by previous work. This work indicates that straightforward vertical 4-tier stacking proves insufficient to guarantee enough PPA benefits, though the resulting design insights may guide future advanced architectures.

cond-mat.mes-hall · cs.ET

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.866ACL Anthology · ACL 2026

SEE: Signal Embedding Energy for Quantifying Noise Interference in Large Audio Language Models

Yuanhe Zhang, Jiayu Tian, Yibo Zhang Beijing University of Posts and Telecommunications, Shilinlu Yan, Liang Lin, Zhenhong Zhou, Li Sun Beijing University of Post and Telecommunications, Sen Su Beijing University of Posts and Telecommunications

原文摘要

Large Audio Language Models (LALMs) have been widely applied in real-time scenarios, such as in-car assistants and online meeting comprehension. In practice, audio inputs are often corrupted by device and environmental noise, leading to performance degradation. However, existing LALM studies on noise lack quantitative analysis and rely mainly on intuition and empirical observation, thus failing to understand practical robustness. To address this issue, we introduce Signal Embedding Energy (SEE), a method for quantifying the impact of noise intensity on LALM inputs, enabling the differentiation of LALM robustness in real-world deployments. SEE introduces a perspective based on structured activation subspaces derived from the model’s internal representations, which more accurately captures its perception of noise than raw audio features. Across experiments, SEE exhibits a strong correlation with LALM performance, achieving a correlation of 0.98. Surprisingly, traditional audio denoising methods are only marginally effective for LALMs, and, in some cases, even increase SEE and impair performance. This suggests a mismatch between speech-centric denoising objectives and the noise sensitivity of modern LALMs. Therefore, we propose a mitigation strategy derived from SEE to denoise LALM inputs, outperforming existing denoising methods. This paper introduces a novel metric for noise quantification in LALMs, providing guidance for robustness improvements in real-world deployments.

cs.CL

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