Search: “hardware”

arXiv:2608.11844v1 Announce Type: new Abstract: Automated plant species identification from citizen-science imagery is an established, demanding fine-grained recognition problem: large taxonomic label

dots3-note preview is the first open-weight model in the dots3 family. It is a Mixture-of-Experts model with 280B total parameters, 16B activated parameters, and support for a context length of up to

Qwen just released their first 3.8 model. The main addition in 3.8 is prompt-steered reasoning effort. You can tell the model how deeply to think by setting reasoning_effort to xhigh, medium, or low.

arXiv:2608.12239v1 Announce Type: cross Abstract: Use this plain-text version for the arXiv abstract field: Learned image compression (LIC) models achieve strong rate-distortion performance but are hi

arXiv:2509.24235v2 Announce Type: replace Abstract: This paper proposes an optimization-based task and motion planning framework, named 'Logic Network Flow,' that integrates temporal logic specificati

arXiv:2608.11288v1 Announce Type: cross Abstract: Assessing catheter and tube placement on chest X-rays is safety-critical yet tedious and error-prone. Current deep learning methods either classify pl

arXiv:2608.11585v1 Announce Type: cross Abstract: Physical computing systems exploit device dynamics for computation, but their gradient-based optimization is challenging: backpropagation through a di

arXiv:2608.11050v1 Announce Type: cross Abstract: Deep learning systems perform mainly within the 2D for a single image domain and take the face as a single-dimension representation, losing sight of t

arXiv:2608.10090v1 Announce Type: new Abstract: Large language models (LLMs) have advanced code generation, where executable feedback provides a more reliable learning signal than textual imitation al

arXiv:2608.09949v1 Announce Type: new Abstract: This study evaluates the application of Large Language Models (LLMs) in complex biological systems, evolving from data analysis to autonomous, AI-guided

arXiv:2608.10605v1 Announce Type: cross Abstract: In large-scale pretraining, the algorithm, architecture, and systems decisions are conventionally made in disconnected stages. A scaling law stage sel

arXiv:2608.10847v1 Announce Type: new Abstract: Kinesthetic teaching through robot hand-guiding provides a natural interface for collecting demonstrations in imitation learning and programming-by-demo

Victoria Song / The Verge: Google unveils the 399 Pixel Watch 5 with a satin pyrite case finish, offline Gemini, proactive AI suggestions, better GPS maps, and insulin resistance trends — The 399 Goog

Ivan Mehta / TechCrunch: Google unveils the 899+ Pixel 11, 1,099+ 11 Pro, and $1,299+ 11 Pro XL, with a Tensor G6, new Gemini features, Magic Capture to pick the best frames, and more — For the last f

Hey guys, Just finished benchmarking DeepSeek V4 Flash 284B + DSpark on a single RTX PRO 6000 96GB. Short version: DSpark: ~15–17% faster generation on my coding workload On this setup, the DSpark dra

arXiv:2510.07749v2 Announce Type: replace Abstract: Perception failures in autonomous vehicles (AV) remain a major safety concern because they are the basis for many accidents. To study how these fail

arXiv:2607.10309v2 Announce Type: replace Abstract: Reinforcement learning (RL) is commonly employed to enhance the performance of autonomous systems, including the Autonomous Internet of Things (AIoT

arXiv:2608.10649v1 Announce Type: new Abstract: Colorectal cancer (CRC) remains one of the leading causes of cancer-related mortality worldwide, predominantly arising from precancerous polyps. Accurat

arXiv:2608.10464v1 Announce Type: new Abstract: Incremental learning models are required to learn new classes sequentially without catastrophic forgetting, while operating under parameter and memory c

Qwen3.8-Max is live on Together AI on day zero. Proud to have supported early testing alongside @Alibaba_Qwen, @vllm_project, and Inferact to get day-zero support live. We’re continuing to optimize pe

arXiv:2608.11175v1 Announce Type: new Abstract: For autonomous space exploration, robotic agents need to perform motion planning in which environmental interactions may be unknown. Learning these inte

arXiv:2608.10718v1 Announce Type: new Abstract: This technical report describes the RMC2 Team's champion solution for the WBCD 2026 Track 4: Deformable Manipulation Challenge. The task requires a robo

Today, we’re adding another member to our model family. Meet North Micro Vision. Our smallest vision-language model yet, ideal for sophisticated document understanding. Available open-source under an

arXiv:2608.08744v1 Announce Type: cross Abstract: The carbon footprint of any deployed Large Language Model (LLM) accumulates during inference, where repeated use of the model substantially exceeds th

arXiv:2608.08085v1 Announce Type: cross Abstract: Code performance optimization is a vital aspect of modern software development, as it enables faster response times and reduced resource usage. These

arXiv:2403.09752v4 Announce Type: replace-cross Abstract: The Internet of Medical Things transcends traditional medical boundaries, enabling a transition from reactive treatment to proactive preventio

arXiv:2608.09225v1 Announce Type: cross Abstract: The key-value (KV) cache is the primary throughput optimization in modern large language model (LLM) inference, enabling prefix reuse across requests.

arXiv:2608.08961v1 Announce Type: new Abstract: AI training's rising resource intensity is straining electricity supplies and carbon budgets, motivating systematic study of memory-efficient training o

Everything started with the sudden death of my old ASRock J1900. While looking for the perfect ITX replacement, I stumbled upon the Chinese CW-NAS-ADLN-K motherboard, which looked perfect on paper: In

I wanted to find out whether a huge text-only MoE could be given basic vision without retraining the language model itself. The short answer is yes. I froze DeepSeek V4 Flash and a 417M-parameter Moon

arXiv:2608.08996v1 Announce Type: cross Abstract: Quantum low-density parity-check (qLDPC) codes can encode multiple logical qubits using sparse parity checks, yet searching for useful finite-length i

arXiv:2608.08860v1 Announce Type: cross Abstract: Robotic neural-thread placement requires regulating the insertion-tool tip relative to tissue that moves with cardiac and respiratory pulsation. This

arXiv:2608.07573v1 Announce Type: new Abstract: Model Predictive Path Integral (MPPI) control is widely used in manipulation for its gradient-free, parallel handling of non-convex costs. Manipulation

arXiv:2608.09272v1 Announce Type: cross Abstract: The 4th 'AI Olympics with RealAIGym' competition, to be held at IJCAI-ECAI 2026 in Bremen, challenges participants to develop a global control policy

arXiv:2608.07945v1 Announce Type: cross Abstract: Cloud-native serverless data warehouses achieve fine-grained elasticity by decoupling storage from compute, yet determining the optimal resource alloc

arXiv:2608.09138v1 Announce Type: cross Abstract: While learned robotic policies hold promise for advancing generalizable manipulation, their practical deployment is often hindered by suboptimal execu

arXiv:2608.08479v1 Announce Type: cross Abstract: Spiking neural networks (SNNs) offer a promising pathway to energy-efficient AI and brain-inspired computing. However, their widespread adoption is hi

arXiv:2608.09125v1 Announce Type: new Abstract: Surgical robotic systems are increasingly being adopted as clinical workload rises, motivating autonomous solutions for repetitive manipulation subtasks

arXiv:2608.08354v1 Announce Type: new Abstract: Tropical cyclones are growing more destructive in a changing climate, and efficient forecasting of their structure and track has become a necessity. Dee

We converted the model from the original safetensors and found two issues. The first one made our quantization fail several times, the second one does not fail at all, it just quietly ruins the base 1

arXiv:2608.09519v1 Announce Type: new Abstract: We present a reproducibility study of XFeat, a lightweight local feature extractor and matcher designed to identify corresponding points across images e

arXiv:2608.06488v1 Announce Type: new Abstract: Difficulty in haptic feedback for surgical robots has been a long-term problem for decades. In recent years, learning-based force estimation from robot

Wowee!! Just when you thought it couldn't get better for open weight models, we probably have had our best period yet!?!?! Models that rival the closed frontier, Opus level models on non-insane hardwa

arXiv:2608.06860v1 Announce Type: cross Abstract: Hyperdimensional computing (HDC) is an approach from the cognitive science literature for solving information processing tasks using data represented

arXiv:2608.06536v1 Announce Type: cross Abstract: Nonadiabatic dynamics needs an excited-state gradient and an interstate nonadiabatic coupling matrix element (NACME) at every nuclear geometry, and a

There's an interactive chart and some extra data in the blog post if you're interested. There are plenty of KL-divergence benchmarks for GGUF models, but most of them compare one GGUF quant against an