Knowledge catalogue
For instance whenever a model comes out, what’s the best engine to run it, the best harness and absolute minimum you need to get same or near same re results that the benchmark of that model claims. A
I've been playing around with Ling 3.0 Tiny, which is an 8 billion parameter model (MoE, 1B active). And I've had a lot of poignant thoughts as a result. Just for fun, I got it running with llama.cpp
Open-source RL envs for the win. On Hugging Face of course! was looking for a quiet weekend but xiaomi dropped their rl envs repo last night to put in perspective, if you have to buy some tasks like t
For the last few days, I've been using two computers to run multiple agents. My 4x3090 machine is running Qwen 3.8 27B with parallel=2, so I can run two agents at the same time. My pi instances are ru
arXiv:2609.29017v1 Announce Type: new Abstract: Most robots manipulate objects solely with their end effectors, whereas humans flexibly leverage different body parts, such as the forearm and elbow, es
arXiv:2609.29163v1 Announce Type: new Abstract: This paper presents an Edge AI-based system for detecting sleep and wake states in non-stationary mobile environments using resource-constrained embedde
The jump from Qwen3 Coder 30B A3B to current-day Qwen 3.6 35B A3B is crazy, especially with all the fine-tunes, and that was around 6 months (I didn't care for local AI back then, or AI at all, apart
Compute (EC2) opened the front door to the first generation cloud. Agents need something different: compute, inference, and data working as one. We built the cloud that delivers all three as one simpl
arXiv:2609.27828v1 Announce Type: cross Abstract: Legacy smart HVAC controllers rely on vendor-cloud TLS secured by ECDH and RSA, both broken by Shor's algorithm, and typical 10-15 year lifespans mean
arXiv:2609.28182v1 Announce Type: new Abstract: Coordinating large population of flexible grid-edge devices can alleviate the need for time-consuming and capital-intensive network upgrades, and AI-bas
The availability of resources for AI workloads can be challenging across the industry, especially accelerators. This can slow your AI workload deployment if it’s built around a specific type of accele
I am looking to hire PhD students, post-docs, and ML researchers in our Paris office interested in collaborating on fundamental research in AI model safety, not safety rules, not AI policy, not post h
arXiv:2609.25047v1 Announce Type: new Abstract: Autonomous agents that automatically build artificial intelligence (AI) models could broaden access to AI across science and engineering. A popular line
In light of recent events and media coverage, ai is in the spotlight and people are afraid. How I respond to those fears: If you are afraid of ai then you should also be afraid of all medical research
arXiv:2609.25688v1 Announce Type: new Abstract: Field robots operating across time of day and sensing modalities require accurate image correspondences within onboard time and resource budgets. Howeve
arXiv:2609.26420v1 Announce Type: new Abstract: Text-to-motion models generate plausible human motion but do not model a robot's dynamics; whole-body tracking controllers execute robot references reli
I've been comparing and working on Gemma 4, Phi-4-Mini, and Qwen3-4B for local LLM use on an 8 GB Raspberry Pi 5. The results were indeed close, but each model has a different strength: Gemma 4 E2B: a
arXiv:2609.22376v1 Announce Type: cross Abstract: Quantitative analysis of experimental powder X-ray diffraction data remains challenging when evaluating complex multiphase materials and noisy measure
Mike Wheatley / SiliconANGLE: Alphabet-owned robotics software company Intrinsic open-sources Intrinsic Core under Apache 2.0, giving developers building blocks for physical AI systems — Intrinsic Inn
arXiv:2609.22277v1 Announce Type: cross Abstract: Visual impairment affects over 2.2 billion people worldwide, yet conventional white canes cannot detect elevated hazards or provide semantic environme
arXiv:2603.26687v2 Announce Type: replace Abstract: Hybrid aerial--ground robots can use thrust to cross obstacles that impede wheel-driven motion, but deciding how much thrust to apply during contact
arXiv:2609.22795v1 Announce Type: new Abstract: Different tasks performed by legged robots impose distinct torque and speed requirements on actuators. Existing robotic actuators are generally optimize
arXiv:2609.21817v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have become a prominent paradigm for mapping multimodal inputs, including semantic instructions, visual observations
arXiv:2511.02845v3 Announce Type: replace-cross Abstract: The advancement of next-generation Wi-Fi technology heavily relies on sensing capabilities, which play a pivotal role in enabling sophisticate
arXiv:2609.21158v1 Announce Type: new Abstract: We explore the use of hybrid quantum-classical generative adversarial networks for synthesising CAD-ready vector geometries. Unlike prior work that oper
hey! we're a small swiss and south african lab and we just put out hemmingway-1. it's a 27b model we trained specifically for roleplay, creative writing, dialogue, stories, and for everyday texting. f
The future of artificial intelligence inference isn’t premium; it’s ubiquitous and commoditized. That may sound odd coming from someone in the AI semiconductor business. Conventional wisdom suggests c
TL;DR: I run a mismatched Tesla V100-PCIE pair—one 16 GB card and one 32 GB card, 48 GB total—in a Proxmox/LXC-based local-inference lab. The practical winner so far is a recent CUDA build of llama.cp
arXiv:2609.19793v1 Announce Type: new Abstract: Recent advances in artificial intelligence (AI) are reshaping smart glasses from egocentric capture and display devices into platforms for wearable inte
arXiv:2609.20107v1 Announce Type: new Abstract: Visuomotor policies for multi-fingered dexterous manipulation are highly sensitive to camera viewpoint shifts. To achieve view invariance, recent method
I had Astra run a multi-hour investigation into speeding up local MoE inference while keeping the model weights and quantization unchanged. The experiments covered Qwen3.6-35B-A3B and Qwen3.8 Flash-Ne
arXiv:2609.19533v1 Announce Type: new Abstract: Simultaneous localization and mapping (SLAM) is one of the services running on an autonomous robot. It is typically run to assist other tasks such as pl
arXiv:2609.17564v1 Announce Type: new Abstract: Deploying retrieval-augmented generation (RAG) on commodity GPUs such as the NVIDIA T4 (16 GB VRAM) exposes a practical failure mode we call the Compres
arXiv:2609.18650v1 Announce Type: new Abstract: Learning generalizable robot manipulation policies requires large-scale and diverse interaction data, yet collecting real-world demonstrations remains c
Bloomberg: King Charles III hosts tech leaders, including Jensen Huang, Demis Hassabis, and OpenAI CFO Sarah Friar, to discuss AI risks; Huang calls for AI safety tests — Titans of the artificial inte
arXiv:2609.17896v1 Announce Type: cross Abstract: How much does the noisy measurement add to learned quantum error mitigation? An accuracy table cannot say, because a model handed circuit structure ca
arXiv:2609.17555v1 Announce Type: cross Abstract: Efficient deployment of Deep Neural Networks (DNNs) on edge accelerators requires aggressive model compression while maintaining reliability in fault-
arXiv:2609.17997v1 Announce Type: cross Abstract: Selective state space models (SSMs) have recently emerged as a compelling alternative to transformers, combining competitive performance with substant
arXiv:2609.17172v1 Announce Type: new Abstract: A walking robotic hand must use the same fingers to move its body, support its weight, and interact with the environment. We show how an anthropomorphic
arXiv:2609.16823v1 Announce Type: new Abstract: Photonic neural networks (PNNs) offer efficient analog inference, but parameters optimized under ideal device models can degrade after fabrication, crea
arXiv:2609.16586v1 Announce Type: cross Abstract: Multi-finger dexterous manipulation relies on stable hand-object interactions, yet these interactions are partially observable in practice. Visual obs
arXiv:2609.16089v1 Announce Type: new Abstract: Structured spatial data require quantum encodings that preserve geometric relations, expose measurable observables, and remain implementable on finite-d
Today, we are announcing the availability of Agent Substrate on Google Kubernetes Engine (GKE). Agent Substrate is an open-source, secure-by-default agent execution runtime engineered to run millions
arXiv:2609.13612v1 Announce Type: new Abstract: Modern AI systems are built on the Transformer architecture, whose core operation, attention, accounts for the majority of computation and memory cost.
arXiv:2609.14424v1 Announce Type: cross Abstract: Reporting the Fisher geometry of a trained variational quantum model is routine; quoting the shot budget that would establish it is not. Certifying an
arXiv:2512.24688v2 Announce Type: replace Abstract: Relative localization is essential for cooperation in autonomous multi-robot systems. Existing approaches either rely on shared environmental featur
arXiv:2609.14183v1 Announce Type: new Abstract: This paper presents the development and initial testing of DreamSat-Bench, a modular rendezvous and proximity operation testbed designed to benchmark AI
arXiv:2609.15772v1 Announce Type: cross Abstract: Spiking neural networks (SNNs) have shown promise for sparse, event-driven computation through stateful processing that is naturally compatible with l
arXiv:2609.14783v1 Announce Type: cross Abstract: Robots need touch to manipulate objects safely and reliably, as many properties, such as softness, texture, and contact stability, are hard to infer f
arXiv:2609.14036v1 Announce Type: cross Abstract: Fresh fruits and vegetables (FFVs) are highly perishable, and cold-chain breaks contribute significantly to global food waste. While Machine Learning
arXiv:2608.25536v2 Announce Type: replace-cross Abstract: In this work, we propose a view on electronic Neuromorphic Design Automation (eNDA), which we see as a design automation flow that bridges com
arXiv:2609.12322v1 Announce Type: cross Abstract: Affective computing has advanced wearable state inference, but on-device reasoning about whether, when, and how to intervene remains challenging. We p
Note - This is translated from the actual blog link right at the bottom. A few days ago, DeepSeek v4.1 was released. It raised the ability of small models to a new level. AI is improving much faster t
arXiv:2609.12054v1 Announce Type: cross Abstract: Beam-induced background (BIB) from muon decay products will be an overwhelming and unavoidable background at a future Muon Collider. In order to devel
arXiv:2609.11946v1 Announce Type: cross Abstract: Hyperion is an innovative high-performance computing (HPC) cluster developed for researchers in both science and humanities disciplines at the Univers
I'm documenting a reproducible setup for running current llama.cpp on a mixed AMD Vega system with both: Radeon RX Vega 64 / Vega10 / gfx900 (8GB HBM2) Radeon Instinct MI50 (Vega20) / gfx906 (16GB HBM
Hey everyone, If you run local models via Ollama in production or personal projects, you've probably run into the hallucination problem: how do you know when a model is hallucinating without burning e
arXiv:2609.11248v1 Announce Type: cross Abstract: Reinforcement learning (RL) can automate quantum architecture search, but its scalability is limited when useful circuit trajectories become rare in t
arXiv:2609.10746v1 Announce Type: cross Abstract: The growing reliance on Low-Earth Orbit (LEO) satellite communication systems has increased the need for intelligent methods capable of detecting cybe
arXiv:2609.09380v1 Announce Type: new Abstract: Unlocking the potential of tiny aerial robots requires order of magnitude improvements in the performance of embedded edge control. In particular, altho