- 论文公开站arXiv
Rapid Fredholm stabilization of the Kuramoto--Sivashinsky equation with unrestricted, spatially-varying anti-diffusion
We develop the first feedback design for rapid stabilization of the Kuramoto--Sivashinsky equation with a spatially varying anti-diffusion coefficient. For constant coefficients, the single-input Fredholm design of Coron…
- 论文公开站arXiv
LBA-CBF: Rapidly Adaptive Safety Filters via Parallel Dynamics Inference
Control barrier functions (CBFs) certify commands through an assumed dynamics model, so an abrupt, unmeasured regime change can undermine the certificate exactly when safety matters most. We present Look-Back Adaptive Co…
- 论文公开站arXiv
IdeaAnchor: Teaching LLMs to Turn Literature into Research Ideas
Scientific research often begins by synthesizing ideas from a set of related papers to identify gaps and formulate new directions. However, training language models to perform this form of literature-grounded ideation re…
- 资讯公开站Ars Technica
Amazon kills Alexa’s ability to control Echo speakers' AUX input
- 论文公开站arXiv
TasteVal: Measuring the Experimental Research Taste of AI Systems Against Human Experts
We introduce TasteVal, a benchmark to evaluate the experimental research taste of frontier models. We define research taste as the ability to pick interesting problems to solve, design experiments, and interpret experime…
- 论文公开站arXiv
UniSlider: Perceptually Uniform Sliders for Continuous Image Editing
Sliders provide an intuitive interface for continuous image editing. In current generative approaches, however, the slider is simply a rescaling of the method's strength parameter, such as an adapter coefficient, a promp…
- 论文公开站arXiv
Towards Looped Models Done Right, Part II: Rethinking at Fixed Points
Every recurrence of a looped language model adds cost in training, decoding, prefill, and reinforcement learning (RL). The closer recurrent states get to fixed points, the less the path to them matters. This enables trun…
- 论文公开站arXiv
Learning to Read the Contextual Tokens in Diffusion Transformers
Multimodal Diffusion Transformers (MM-DiTs) jointly process visual and textual representations throughout generation. These models repeatedly update the text tokens through multimodal attention, forming dynamic contextua…
- 资讯公开站CNX Software
DEBIX M8391-01 industrial SBC features MediaTek Genio 720 SoC with 9 TOPS NPU, dual-display support
The DEBIX M8391-01 is a compact industrial SBC built around the MediaTek MT8391 (Genio 720) processor, designed for edge AI, computer vision, robotics, and intelligent IoT applications. The S0C’s 9-TOPS NPU enables…
- 资讯公开站MIT Technology Review
EmTech Future 2026: When AI Meets Everything
Yossi Matias, Vice President & Head of Google Research, explores how AI is beginning to reshape biology, infrastructure, manufacturing, and science, and why its greatest impact may come when it intersects with other …
- 论文公开站arXiv
Revisiting Input Time-frequency Representations in Multi-pitch Estimation for Vocal Ensembles
Multi-pitch estimation in vocal ensembles is challenging because singers occupy overlapping pitch ranges and often sing at closely spaced fundamental frequencies, causing their harmonics to overlap in time-frequency repr…
- 论文公开站arXiv
Risk-Aware Input-Constrained Safe Intercept Guidance Against Multiple Moving Defenders
This paper develops a risk-aware guidance law for an attacker to intercept a stationary target in the presence of multiple moving defenders while respecting the control input limits. We represent defender threats via eng…
- 资讯公开站CNX Software
Geekworm UPS Scap 5V5A – A supercapacitor UPS HAT for Raspberry Pi 5
Geekworm, in collaboration with Mcuzone, has launched the UPS Scap 5V5A, a new supercapacitor UPS HAT for the Raspberry Pi 5 designed to keep the Raspberry Pi running long enough (a few seconds to a few minutes) to save …
- 资讯公开站CNX Software
UP Xtreme PTL Edge Air Panther Lake Mini PC gets AirJet solid-state active cooling solution
AAEON has introduced a new version of its UP Xtreme PTL Edge Panther Lake mini PC with the “Air” variant featuring Frore Systems AirJet solid-state active cooling solution. The company says the AirJet passive…
- 资讯公开站Digitimes
DIGITIMES Insight: Intel, TSMC, Samsung converge on backside power — packaging becomes the next divide
Data center AI accelerator package power has climbed from about 500W in the A100 generation to roughly 3,500–4,000W for Rubin Ultra-class products expected in 2027, pushing supply current into the thousands of ampe…
- 论文公开站arXiv
VISTA: A Visual Harness for Reasoning in an Interactive World
We show that multimodal models possess strong reasoning abilities and that an appropriate harness can unlock their potential to solve tasks across diverse interactive environments. We introduce VISTA, a visual harness th…
- 资讯公开站CNX Software
ASRock Industrial NUC 300 series – Intel Core 3 304/Core 5 320 mini PCs and motherboards
ASRock Industrial has introduced the NUC Core 300 BOX series of mini PCs and the NUC Core 300 motherboards built around Intel Core Series 3 Wildcat Lake-U processors. The lineup includes the NUC BOX-320, with the Intel C…
- 资讯公开站rss_arxiv_cs_ai
CARAT: Do Materials LLMs Reason or Recite?
arXiv:2609.38340v1 Announce Type: new Abstract: When a materials LLM answers a question about crystal structure, does it reason from the structure or copy an answer already printed in its input? Accuracy cannot tell: a …
- 资讯公开站Digitimes
Google skips Gemini 3.5 Pro, launches Gemini 4 Argon at US$2/$10 per million tokens
Google has unveiled Gemini 4 Argon, its new top-tier AI model, after months of delays and the cancellation of Gemini 3.5 Pro, launching it at introductory prices of US$2 per million input tokens and US$10 per million out…
- 论文公开站arXiv
Compression Footprints as Security Signals for Model-Poisoning Defense in Federated Learning
Lossy compression is widely used in Federated Learning (FL) but is generally treated as an error source, while conventional poisoning defenses inspect update geometry. In this work, we instead treat the compressor's resp…
- 论文公开站arXiv
DP-SGD 下权重绑定对纯解码器 LLM 是否仍有益？
Is Weight Tying Still Beneficial for Decoder-Only LLMs in Private Settings Under DP-SGD?
DP-SGD 是大模型隐私保护微调的主流方法。许多纯解码器 LLM 采用输入输出嵌入权重绑定，本文在差分隐私设定下重新审视这一设计是否仍然有利。
- 资讯公开站rss_arxiv_cs_ai
有效的大语言模型微调是否必须依赖人类可读文本？
Is Human-Readable Text Necessary for Effective LLM Fine-Tuning?
arXiv:2609.35868v1 公告类型：新 摘要：有效微调大语言模型是否必须依赖人类可读性？我们研究模型条件化的训练表示能否在无需人类可读文本形式的情况下保持或提升适配效用。我们提出 Desired-Update-Aligned Synthetic Data（DASA），利用冻结参考模型的激活梯度反馈来指导连续合成输入嵌入的优化。受激活梯度在局部风险降低中作用的启发，DASA 针对有用的适配更新，而非源文本重建或语言流畅性。所得…
- 资讯公开站Digitimes
AMD苏姿丰据悉10月再访韩国，深化HBM4与NPU合作
AMD's Lisa Su reportedly revisiting South Korea in October to deepen HBM4, NPU ties
AMD CEO苏姿丰据悉将于2026年10月再次访问韩国，继3月访韩正式启动与三星电子的下一代AI内存合作后，此行预计将进一步扩大合作，涉及HBM4与NPU等领域。
- 论文公开站arXiv
大模型图重建失真的谱理论：紧界与实证刻画
A Spectral Theory of Distortion in LLM Graph Reconstruction: Sharp Bounds and Empirical Characterization
语言模型图重建评估通常报告原始图与重建图之间的单一聚合距离。本文证明对于拉普拉斯谱间的Wasserstein距离，该汇总受两个边计数约束。
- 论文公开站arXiv
Rho：高效可适应VLA模型的基础
Rho: A Foundation for Efficiently Adaptable VLA Models
通用物理AI模型须结合广泛视觉语言能力与跨机器人本体的精确控制及高效下游适应。本文提出Rho系列开放权重VLA模型，用于双臂操作，专为数据高效适应设计。
