Knowledge catalogue
arXiv:2609.21713v1 Announce Type: cross Abstract: Edge AI accelerators are increasingly deployed in safety-critical environments, where model outputs may control physical actuators, make access-contro
arXiv:2609.21172v1 Announce Type: new Abstract: Large language models (LLMs) are moving onto mobile devices for increasingly diverse workloads over text, images, video, and audio. These applications o
arXiv:2609.21073v1 Announce Type: new Abstract: Behavioral tasks measuring facial affect perception assume that identical stimuli impose equivalent perceptual difficulty across participants. However,
arXiv:2609.20905v1 Announce Type: cross Abstract: In this work, we present an uncertainty-driven training framework for three-dimensional computed tomography (CT) lung nodule classification, where val
arXiv:2609.21225v1 Announce Type: new Abstract: Parametric CAD reconstruction requires recovering both precise geometry and editable modeling operations from visual observations, making it challenging
arXiv:2609.21729v1 Announce Type: new Abstract: As robots transition from performing repetitive tasks to collaborating with humans, understanding human intent becomes crucial to effective interaction.
arXiv:2609.21498v1 Announce Type: new Abstract: Recent feed-forward 3D Gaussian Splatting (3DGS) methods typically regress pixel-aligned Gaussian primitives, often causing excessive overlap and artifa
arXiv:2505.10202v2 Announce Type: replace Abstract: Large Language Models (LLMs) have achieved remarkable success but face significant computational and memory challenges, particularly due to their ex
arXiv:2609.21858v1 Announce Type: cross Abstract: Large language models (LLMs) have achieved state-of-the-art performance across a wide range of tasks, motivating two important aspects of deployment:
Physical AI is moving rapidly from research to large-scale deployment. By 2035, ABI Research projects an installed base of 49 million level 3-5 autonomous vehicles (AVs), while Omdia estimates that ro
xAI's Grok 4.6 is now available in Amazon Bedrock: a frontier model for long-running agents, coding, and knowledge work, with a 500K token context window and four reasoning effort levels. It runs on b
arXiv:2609.21712v1 Announce Type: new Abstract: Generative world models offer controllable and repeatable closed-loop simulation for end-to-end and vision-language-action driving policies, but product
So this jev thingy is getting kind of big... tbh it seems overhyped by a large margin, but here we are. Not that its bad, just feels like we usually ignored larger things... Anyway to the point of thi
i have been running local models as browser agents on an m5 macbook pro, 128gb, all through mlx, no cloud. first i just wanted to know which one was faster at real browser work, so i gave gemma 4 31b
lNot only is this “no moat” regime literally what I predicted in August 2023 but China maybe seems to be understanding the full implications of that faster. (Perhaps informed by their painful housing
Meet Qwen-Image-2.1, the most balanced and cost-effective image generation model in the Qwen-Image series! Now open weights! 🎨 A unified model for both generation and editing, delivering top-tier qual
Meet Qwen-Image-2.1, the most balanced and cost-effective image generation model in the Qwen-Image series! Now open weights! 🎨 A unified model for both generation and editing, delivering top-tier qual
I am trying to learn more about long-term memory and how people are handling that nowadays. Historically, I have used a mixture of paid cloud AI services (ChatGPT, Gemini, OpenRouter API) and my own l
I needed a relatively simple but acceptable level of AI for working on one project. I didn't have any heavy requests, I just needed to give the AI access to the project files so it could search throug
Play it right in your browser, no download. Some of the GLB’s are messy, but overall I’ve enjoyed playing with it, and the last iteration made was the gun/weapon placement. Contributors are welcome, w
I improved the TPS of Gemma 4 31B. Improving TPS and performing optimisations requires understanding of the model architecture, and I had to fork VLLM and apply my own patch to break into making a con
Given the recent interest in tools like Jev, I wanted to share ProgramAsWeights (PAW), an open-source research project I'm working on at the University of Waterloo. You describe a text function in Eng
Since OpenAI retired SWE-bench Verified in February (every frontier model tested could reproduce reference fixes for some tasks; underspecified tests rewarded knowing the intended fix), I've been tryi
I have always posted about budget builds on here, and often asked how we are going to run the next big models. Often Plenty of downvotes too or folks telling me that it's not running if I'm getting 5t
arXiv:2609.20562v1 Announce Type: new Abstract: Automated quality assessment, enhancement, and segmentation of multiple structures in 0.064,T ultra-low-field pediatric MRI are limited by a low signal-
arXiv:2609.19555v1 Announce Type: cross Abstract: Artificial intelligence for plant disease analysis has advanced from task-specific classifiers to multi-modal models capable of jointly interpreting v
arXiv:2609.20349v1 Announce Type: new Abstract: Spatial reasoning abilities correlate strongly with performance in STEM fields. Games offer a compelling medium for training these critical skills in de
arXiv:2609.20509v1 Announce Type: new Abstract: For art historians, goldsmith marks play a critical role in the identification and dating of artifacts. In practice, experts must manually compare a que
arXiv:2609.20605v1 Announce Type: new Abstract: Recent factor graph approaches to continuum robot state estimation have been successful for quasi-static applications and spatiotemporal estimation usin
arXiv:2609.19934v1 Announce Type: new Abstract: Depth-recurrent language models iteratively apply a small layer stack, decoupling per-token compute from distinct parameter count. To determine whether
Big fan of how @LangChain is doing these insta-webinars The news is a few days old, @typesafeai is integrated and documented with example code in LangChains Docs 👇 And they are doing a webinar on the
arXiv:2609.19875v1 Announce Type: new Abstract: We propose a new probabilistic model for general-purpose medical image registration that builds upon the mutual information registration criterion. It c
arXiv:2609.19199v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly adopted for compliance and legal reasoning tasks, yet their outputs often lack explicit grounding in leg
arXiv:2609.19674v1 Announce Type: new Abstract: A learned simulator can reproduce its training conditions accurately yet fail in two distinct ways once those conditions change. Over long rollouts, sma
arXiv:2607.09557v2 Announce Type: replace Abstract: Fine grain control and positioning of autonomous underwater vehicles (AUVs) is critical for sampling, maintenance, and survey applications. Traditio
Hi there, I'm Yuesong, a researcher at Video Rebirth. We open-sourced HyperFlow, an 8-step LoRA for MiniMax-H3. The core idea: data-free flow self-distillation. Diffusers' default sampler does 49 mode
arXiv:2609.20817v1 Announce Type: cross Abstract: Modeling articulated objects from sparse monocular views is challenging because each observation reveals only partial geometry and motion evidence. Mo
arXiv:2609.19475v1 Announce Type: new Abstract: Diffusion-based Vision-Language-Action (VLA) models achieve strong performance in embodied tasks, but their iterative sampling imposes heavy computation
arXiv:2609.20341v1 Announce Type: new Abstract: Magnetic Resonance Imaging (MRI) acquired at different field strengths exhibits pronounced variation in noise, resolution, homogeneity, and contrast, wh
arXiv:2609.19740v1 Announce Type: new Abstract: Recent innovations in deep learning have significantly enhanced the diagnosis of medical images, although they are based on the use of centralized data
arXiv:2609.19549v1 Announce Type: cross Abstract: Communication is made possible by common ground---the unspoken knowledge that people share and presuppose of one another, whether that be online or of
arXiv:2609.19850v1 Announce Type: new Abstract: Actor-critic architecture has been widely used in continuous robot control. However, they rely on learning a value network, introducing additional compu
arXiv:2609.20012v1 Announce Type: new Abstract: Feed-forward 3D reconstruction provides an efficient paradigm for scene modeling from image sequences. Scaling these models to large monocular scenarios
arXiv:2609.20659v1 Announce Type: cross Abstract: Large-scale vision-language-action (VLA) models provide powerful priors for robot manipulation, yet adapting them to a specific deployment remains cha
arXiv:2609.19356v1 Announce Type: cross Abstract: We introduce a new method to guide flow matching models. Our approach, which we call probe guidance, uses the frozen internal states of an existing di
arXiv:2607.15394v2 Announce Type: replace Abstract: Black-box models limit the adoption of artificial intelligence in medicine because their predictions are difficult to interpret and reproduce. We pr
Jev was adopted faster than any other AI model in the history of AI Gateway, achieving roughly 13 % of total team adoption on its first day. This rate represented twice the uptake of the GPT‑5.6 famil
arXiv:2609.19877v1 Announce Type: new Abstract: Efficient long-term conversational memory requires retrieving sufficient evidence without indiscriminately expanding the context presented to the langua
arXiv:2609.19569v1 Announce Type: cross Abstract: Disease severity classification for genetic conditions is subjective and labor-intensive, creating bottlenecks in genomic screening, where commercial
arXiv:2609.19721v1 Announce Type: new Abstract: Clinical coding agents repeatedly encounter the same failure modes, including unsupported codes, missed documented conditions, specificity errors, and p
arXiv:2609.20669v1 Announce Type: cross Abstract: 3D diffusion policies are strong at generating geometrically grounded actions from current observations, but successful manipulation requires not only
arXiv:2609.20558v1 Announce Type: new Abstract: Roofing requires workers to coordinate locomotion, balance, and work-related body motions on pitched surfaces, creating a challenging application for hu
arXiv:2609.19417v1 Announce Type: new Abstract: Graph-based retrieval-augmented generation (RAG) is widely used for multimodal, cross-document question answering. However, building corpus-level graphs
arXiv:2609.19796v1 Announce Type: new Abstract: Robotic manipulation under partial observability requires spatial information that extends beyond the current view. Geometry-aware RGB features describe
arXiv:2609.19515v1 Announce Type: new Abstract: Verifier-based selection improves LLM performance by generating multiple candidate solutions and using a verifier to select the most promising one. Howe
arXiv:2609.19683v1 Announce Type: cross Abstract: The deployment of Vision-Language Models (VLMs) on edge devices is severely bottlenecked by memory bandwidth, necessitating aggressive sub-8-bit quant
arXiv:2609.19148v1 Announce Type: new Abstract: Ambivalence and hesitancy (A/H) are affective states in which individuals express contradictory signals across facial, vocal, and linguistic channels. A
arXiv:2602.01346v2 Announce Type: replace Abstract: While open sourced Vision-Language Models (VLMs) have proliferated, selecting the optimal pretrained model for a specific downstream task remains ch
arXiv:2609.20124v1 Announce Type: cross Abstract: Evaluating live streaming speech synthesis (TTS) requires assessing fine-grained, highly expressive prosody such as emotion, intonation, and energy wh
Saw this little dude in a Forbes article (https://www.forbes.com/sites/johnkoetsier/2026/08/18/american-humanoid-robot-launches-for-just-1688-delivery-this-fall-made-in-san-francisco/) This is definit