Knowledge catalogue
arXiv:2608.29058v1 Announce Type: new Abstract: Dynamic sparse attention can reduce the quadratic cost of long-context prefilling without changing model weights. MInference assigns each attention head
arXiv:2608.30889v1 Announce Type: cross Abstract: Deploying a new control policy for voltage control in active distribution grids requires evidence that physical limits will be satisfied before the po
arXiv:2308.08025v2 Announce Type: replace-cross Abstract: This paper develops a simulation-based framework for evaluating the energy implications of quantum and classical computing firms competing in
arXiv:2608.30368v1 Announce Type: new Abstract: Tactile sensing is essential for physical interaction in robotics and human--machine systems. However, combining rich tactile information with compact h
arXiv:2608.28664v1 Announce Type: cross Abstract: Despite the success of foundation models in language and vision, their expansion into embodied AI is bottlenecked by a lack of generalized touch sensi
arXiv:2608.29396v1 Announce Type: new Abstract: Reliable localisation of shallow subsurface vessels is important for safe robot-assisted venous access and vessel-aware manipulation, but collecting div
arXiv:2608.30567v1 Announce Type: new Abstract: We present Turing-20B-A2B, a 20B-parameter Mixture-of-Experts language model that activates approximately 2B parameters per token, designed for long-con
arXiv:2608.29296v1 Announce Type: cross Abstract: Larger batches reduce the variance of stochastic gradients per update and are therefore often expected to accelerate training. Yet whether this statis
arXiv:2608.28409v1 Announce Type: new Abstract: Multi-robot systems are well-positioned for exploration in hazardous environments, but effective deployment requires deciding not only where robots shou
arXiv:2608.28191v1 Announce Type: new Abstract: Vision Foundation Models (VFMs) are widely used in computational pathology but remain sensitive to domain shifts arising from variations in staining, ti
arXiv:2608.28113v1 Announce Type: new Abstract: The NVIDIA Blackwell architecture, with native support for the ultra-fine-grained NVFP4 format, opens new opportunities for accelerating large language
Hi all, I have recently been experimenting with different LLM set ups and after everyone was raving about how good Qwen 3.8 27b was, I was inspired to try and get it deploying. After some battling wit
People don't understand. You can create a rl env to teach it to find quarters. This will make money while you sleep. Media I DON’T THINK PEOPLE REALIZE HOW MASSIVE THIS IS YET @HuggingFace and @Pollen
arXiv:2504.04342v2 Announce Type: replace Abstract: Scaling up model parameters and training data consistently improves the performance of large language models (LLMs), but at the cost of rapidly grow
SlopTV: a YouTube live stream where the chat writes the programming. You type 'capybara dj underwater rave', an LLM inflates it into a 400-word structured video prompt, one of my 5090s renders 15 seco
I’ve been experimenting with MiniMax H3 and finally have video generation working in TensorSharp. TensorSharp started primarily as a local GGUF/LLM inference engine, so getting a video-generation pipe
Since I spent the time to figure it out and it is not like it will make me any money ever. I think I'd share with you all what I managed to cobble together. First and foremost here the relevant bits a
“What Ilya saw” is what Dario saw which is that Sam can’t be trusted. Which is why they left. A lot of other people have discovered the same, since. If OpenAI is going to IPO or OpenAI has AGI Then Wh
I have a 2 DGX Spark setup recently and I have been happily running Deepseek V4 Flash 0731. Since the release of GLM5.3 Flash and Qwen 3.8 Flash Next this week, a lot of folks are still waiting to see
Hey! I forked NInfer (a from-scratch C++20/CUDA inference engine for Qwen models) and added two things: tensor-parallel across two GPUs, and YaRN ×4 rope scaling. Together they let Qwen3.8-27B NVFP4 r
~20–30GB smaller than Unsloth/AesSedai Q4 at similar PPL. After several days of testing I released a set of mainline-compatible imatrix quants for Qwen3.8-Flash-Next. Goal: same quality band as the po
arXiv:2608.26581v1 Announce Type: new Abstract: Low-bit quantization offers a promising avenue for reducing the computational and memory demands of Multimodal Large Language Models (MLLMs). Recent har
arXiv:2608.26198v1 Announce Type: new Abstract: Operating a scientific instrument such as an atomic force microscope (AFM) requires continuous expert decision-making. A trained user defines the experi
Andreessen Horowitz today announced that it has raised a 1.1 billion fund to back artificial intelligence infrastructure startups. The Machine Age Fund will invest in companies that make data center e
arXiv:2608.26505v1 Announce Type: new Abstract: The Poppy Humanoid is an open-source, low-cost robot suitable for research and education in artificial intelligence. However, we are unaware of any publ
arXiv:2608.26314v1 Announce Type: new Abstract: Steering-based planners require solutions to state-to-state boundary value problems, which can be inaccessible for nonlinear platforms. Forward propagat
Fast, fault‑tolerant PyTorch training on AI Runtime is designed for GPU scale environments where failures occur routinely. By employing intelligent data loading and robust checkpointing strategies, th
Hey guys, FastVideo team here. We saw how important speed and quality is for everyone. And we've been working to create our own step distill checkpoints and LORAs for MINIMAX h3. Here's is our v1 rele
arXiv:2509.10969v3 Announce Type: replace Abstract: This paper examines the key factors that influence the performance of state-of-the-art gaze-based authentication. Experiments were conducted on a la
arXiv:2512.13965v1 Announce Type: cross Abstract: We present Generative Monte Carlo (GMC), a novel paradigm for particle transport simulation that integrates generative artificial intelligence directl
arXiv:2608.27137v1 Announce Type: cross Abstract: The recently envisioned goal-oriented communications paradigm requires machine learning inference to be performed directly on wirelessly transferred d
arXiv:2608.27046v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) and other RL-style post-training paradigms have been used for aligning large language models (LL
arXiv:2608.26882v1 Announce Type: cross Abstract: Industrial control systems (ICSs) rely on programmable logic controllers (PLCs) to connect networked computation with physical control. Tool-using lar
TL;DR: llama.cpp with --load-mode mmap used 21-32 GB of RAM, with ik_llama.cpp using 106-108 GB. -sm tensor killed my prefill, changing to -sm layer went from 36 tps to 135 tps. After that, -ubatch 20
arXiv:2608.26644v1 Announce Type: new Abstract: Event cameras capture pixel-level intensity changes with microsecond resolution to produce highly sparse asynchronous data streams. For visual perceptio
Hey all, and hello fellow DGX Spark-ers! Today I managed some pretty crazy numbers: 181 tok/s aggregate on 2× DGX Spark on Qwen3.8-Flash-Next at 512Kcontext (2.8M kvc) I hit 181 tok/s aggregate today
arXiv:2601.22300v4 Announce Type: replace-cross Abstract: We propose a deep photonic neuromorphic network (PNN) architecture based on phase-change material (PCM) synapses and local optical feedback fo
arXiv:2608.26148v1 Announce Type: new Abstract: Depression affects millions worldwide, yet diagnosis relies on subjective self-reports that may miss authentic behavior. This paper presents an approach
arXiv:2608.26165v1 Announce Type: cross Abstract: Automated creativity assessment has been a long standing challenge, with traditional methods often being resource intensive or lacking practical accur
arXiv:2608.24935v1 Announce Type: new Abstract: Accurate identification of early-stage apple fruitlet anatomical structures, including the calyx, fruitlet body, and peduncle, is essential for robotic
@ComfyUI is now the first and only commercial license distributor for @MiniMax_AI's generative media models. Which means you can train on them, on your own data. A foundation model's training data is
arXiv:2506.14006v2 Announce Type: replace-cross Abstract: We present a framework for chemical learning based on Competitive Dimerization Networks (CDNs) - systems in which multiple molecular species,
Bloomberg: Hugging Face unveils Microduck, a 400, 1.7lb, 10-inch-tall bipedal robot developed in part by Pollen Robotics and manufactured by Shenzhen-based Seeed Studio — Artificial intelligence platf
Sharing my harness for running local LLMs that I built using Qwen 3.x 27B (> 90% locally built) under my supervision - not vibe-coded. Its free, no telemetry, and open-source (AGPL). Works on Windows,
arXiv:2608.26058v1 Announce Type: new Abstract: Scaling generalist vision-language-action (VLA) policies is severely bottlenecked by the inherent heterogeneity of embodied data, which spans diverse ro
The coolest part of Microduck might not be the robot. It's how it learns to move. This repo shows the full reinforcement learning pipeline behind Microduck. The robot learns in simulation using MuJoCo
arXiv:2608.25872v1 Announce Type: new Abstract: Contact-rich manipulation requires precise interaction feedback. While vision-centric imitation learning is prevalent, external visual observations prov
Want to learn how robots actually learn? Start here. Hugging Face has a free Robotics Course that takes you from classical robotics to modern learning-based approaches. You will explore how robots lea
Forgive the typos and rambling - human actually wrote this post 😂 I've had a Strix Halo board for about a year and been playing around with it for various projects when it's not just being a beefy lin
arXiv:2402.11215v4 Announce Type: replace Abstract: The choice of batch size in minibatch stochastic gradient optimization is critical for both optimization and generalization performance in large-sca
arXiv:2608.24051v1 Announce Type: new Abstract: Can a sequence model remain competitive with only a few thousand parameters and an explicitly auditable prediction interface? We introduce ALPHABET, a c
arXiv:2608.23863v1 Announce Type: new Abstract: Robots are beginning to act on world-model predictions, yet reliability is still expressed through instantaneous, model-internal signals. DreamLedger in
arXiv:2608.24793v1 Announce Type: new Abstract: Automated malaria diagnosis from stained blood-smear microscopy is dominated by deep convolutional neural networks that are accurate but computationally
As AI takes on more complex work, business leaders face a new challenge: enabling rapid innovation using agents while protecting their margins and budgets. To get a real return on AI, financial operat
arXiv:2608.24877v1 Announce Type: new Abstract: Smart glasses are evolving from capture and display accessories into first-person intelligence platforms that connect human perception, persistent conte
arXiv:2608.24020v1 Announce Type: cross Abstract: Generating executable parametric CAD code from dimension-annotated orthographic drawings is a challenging task requiring geometric understanding, proc
arXiv:2608.23897v1 Announce Type: cross Abstract: When a code generating language model fabricates a Python package name, an adversary who has pre-registered that name on PyPI can convert that halluci
arXiv:2602.13554v2 Announce Type: replace-cross Abstract: This article develops a four stage observability engineering framework for interaction driven sensing. The framework integrates physical model
arXiv:2608.24073v1 Announce Type: cross Abstract: Low-earth-orbit (LEO) satellites enable high-resolution, large-scale Earth observation for applications such as disaster monitoring and environmental
https://preview.redd.it/i8rjx0ar5mlh1.png?width=2160&format=png&auto=webp&s=c2588bc7b2519ea71b176ca73faf566dfc585496 I wanted to see whether a heavily quantized 27B model running entirely on an older