microsoft/Fara1.5-27B · Hugging Face
Fara1.5-27B is a multimodal computer use agent (CUA) for web browsers, from Microsoft Research AI Frontiers. It observes the browser through screenshots and acts on the user's behalf by emitting struc
Knowledge catalogue
Fara1.5-27B is a multimodal computer use agent (CUA) for web browsers, from Microsoft Research AI Frontiers. It observes the browser through screenshots and acts on the user's behalf by emitting struc
This story is wild. The short version: OpenAI were running a cybersecurity test against an unreleased model, with the model's guardrail features turned off. Rather than solve the test, the model broke
I thought this was a very good post by @c_valenzuelab and really highlights how transformative video models already are for the businesses that are using them. I think video models are one of the most
We are living in the golden age of the weekend AI side project. Thanks to agentic engineering and LLMs, the time to go from a blank IDE to a functional local application has dropped from quarters to h
Long-running models can solve hard open-ended problems, but their persistence can create safety risks that shorter-horizon evaluations miss. We’re sharing what we learned from studying a long-running
arXiv:2607.13038v1 Announce Type: cross Abstract: We present the design and implementation of a safety constrained large language model (LLM) system for public health information access, focusing on m
arXiv:2603.19063v2 Announce Type: replace Abstract: Most existing robot simulators prioritize rigid-body dynamics and photorealistic rendering, but largely neglect the thermally and optically complex
arXiv:2607.13373v1 Announce Type: cross Abstract: Column generation (CG) is central to many large-scale optimization algorithms, including branch-price-and-cut methods for vehicle routing problems, bu
arXiv:2607.13460v1 Announce Type: new Abstract: We present the Large Processing Model (LPM), a diffusion-based generative framework for photorealistic video restoration under complex, in-the-wild degr
arXiv:2607.13652v1 Announce Type: new Abstract: Many design tasks can be cast as black-box function optimization, enabling use of Bayesian optimization to find an ideal design with minimal number of t
arXiv:2607.13596v1 Announce Type: cross Abstract: When cast as the protector of a vulnerable user yet given no explicit capability boundary, a large language model (LLM) may respond not by acknowledgi
arXiv:2607.13124v1 Announce Type: cross Abstract: Structured pruning is a hardware-friendly way to compress LLMs, but it is mostly validated on multiple-choice recognition tasks, while the same compre
arXiv:2607.13099v1 Announce Type: cross Abstract: Large language models (LLMs) have achieved remarkable success but raise growing concerns about content provenance and misuse, motivating the need for
arXiv:2607.12200v1 Announce Type: new Abstract: As frontier language models advance, policymakers and model developers need methods for assessing whether model access materially increases a non-expert
arXiv:2607.12829v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) offer a theoretical advantage in parallel generation over standard autoregressive models. However, parallel ge
arXiv:2604.25834v2 Announce Type: replace Abstract: With the rapid development of the Internet, users have increasingly higher expectations for the recommendation accuracy of online content consumptio
arXiv:2607.12110v1 Announce Type: new Abstract: Ground segmentation is a fundamental prerequisite for autonomous navigation, environmental perception, and object detection in ground mobile platforms.
arXiv:2510.13698v4 Announce Type: replace Abstract: Even modern AI models often remain vulnerable to multimodal queries in which harmful intent is embedded in images. A widely used approach for safety
Below Upstream Status sections are from https://github.com/PrismML-Eng/Bonsai-demo Upstream Status for Binary Q1_0 is supported out of the box in upstream llama.cpp across many backends: CPU (generic,
arXiv:2607.12112v1 Announce Type: cross Abstract: Federated fine-tuning of Multimodal Large Language Models (MLLMs) across distributed networks enables privacy-sensitive adaptation to evolving data st
arXiv:2607.11638v2 Announce Type: replace Abstract: City-scale outdoor navigation is currently hindered by the heavy reliance on dense maps or costly navigation supervision. In this work, we introduce
Enterprise AI agents lose effectiveness when they must access data outside of protected, governed systems. The article argues that truly reliable agents need to be *data‑native*—run directly inside th
arXiv:2607.12787v1 Announce Type: new Abstract: Recent advances in multimodal large language models (MLLMs) have significantly improved the performance of multimodal emotion recognition (MER) and enab
arXiv:2607.12544v1 Announce Type: new Abstract: Thermal infrared (TIR) imaging is essential for UAV swarm operations in visually degraded environments. However, tracking tiny UAVs remains challenging
arXiv:2607.11942v1 Announce Type: cross Abstract: KV-cache compression methods are predominantly evaluated with the query appended to the context before compression -- a query-aware protocol. Yet the
arXiv:2607.12924v1 Announce Type: new Abstract: In this paper, we study Reinforcement Learning in Parametrized Action Markov Decision Processes (PAMDP), where each decision consists of a symbolic acti
arXiv:2607.12663v1 Announce Type: new Abstract: Accurate differentiation between gastric adenoma and carcinoma during endoscopy is critical for clinical decision-making. Yet, this task is highly chall
arXiv:2607.09760v2 Announce Type: replace-cross Abstract: Radio frequency fingerprint identification (RFFI) exploits transmitter-specific hardware imperfections as physicallayer identity cues for Inte
arXiv:2607.11899v1 Announce Type: cross Abstract: High-altitude Clear Air Turbulence (CAT) poses significant risks to aviation safety due to its unpredictability and challenges in detection. This stud
arXiv:2607.12903v1 Announce Type: new Abstract: In operational 1:N face identification, a crucial question arises for each probe: is this person enrolled in the gallery or not? The stakes are high and
arXiv:2607.12985v1 Announce Type: new Abstract: Aligned language models routinely misreport under non-evidential incentive pressure: they agree with a confident user or overstate certainty even when t
arXiv:2607.12266v1 Announce Type: new Abstract: Mixed-precision quantization must decide which parts of a model to keep at higher precision. A common premise, shared by sensitivity-based methods such
🆕 5 Trends That Defined AI Engineering at World’s Fair 2026 https://latent.space/p/aiewf26trends @ricmac's big recap of @aidotengineer: 1. The focus shifts from agents to systems 2. Loop engineering i
In this post, we share how Flo Health’s engineering team turned a proof of concept (PoC) from the AWS Generative AI Innovation Center into a production-grade, AI-powered medical content review and gen
arXiv:2607.07985v1 Announce Type: cross Abstract: We report the empirical reliability of Gemini models as audio judges that score full-duplex agent conversations directly from the raw stereo waveform,
arXiv:2607.08742v1 Announce Type: new Abstract: Keypoint tracking alone is insufficient for object interaction tasks such as sitting on a chair, wiping a board, or pushing furniture, where the robot c
arXiv:2607.08077v1 Announce Type: new Abstract: AI developers face a dual-use dilemma. An AI capability that helps one user cure a disease can help another synthesize one. This dilemma could be resolv
arXiv:2603.15136v2 Announce Type: replace-cross Abstract: Offline safe reinforcement learning (RL) seeks reward-maximizing policies from static datasets under strict safety constraints. Existing metho
arXiv:2607.08010v1 Announce Type: new Abstract: Production LLM agents often waste latency and reliability by regenerating code for the same procedural steps on every request. We replace this inference
arXiv:2607.07370v1 Announce Type: cross Abstract: In embodied intelligence systems, the motion controller serves as the critical bridge between semantic reasoning and physical execution. Humanoid cont
arXiv:2607.06982v1 Announce Type: new Abstract: Convolutional neural networks (CNNs) have demonstrated encouraging results in image classification tasks. However, the prohibitive computational cost of
arXiv:2607.07459v1 Announce Type: cross Abstract: We present EmbodiedGen V2, a generative 3D world engine for building executable sim-ready environments for embodied intelligence. Sim-ready 3D asset g
arXiv:2607.06964v1 Announce Type: cross Abstract: Bridging the gap between human pilot intent and autonomous flight operation is critical for real-world electric vertical takeoff and landing (eVTOL) a
arXiv:2604.25605v2 Announce Type: replace-cross Abstract: Introduction: Semantic search, which retrieves documents based on conceptual similarity rather than keywords, offers advantages for retrieval
arXiv:2607.07403v1 Announce Type: cross Abstract: Vision Language Models (VLMs) and Vision Language Action (VLA) models have shown promise in robotic control. Yet, they face significant challenges reg
New renderings of SpaceX's AI satellite, called AI1. • AI chip vendor agnostic. System architecture supports compute modules from any provider. • 150 kW peak compute payload • 120 kW average compute p
arXiv:2603.23800v2 Announce Type: replace-cross Abstract: We present a novel LLM-informed model-based planning framework, and a novel prompt selection method, for object search in partially-known envi
arXiv:2607.06291v1 Announce Type: new Abstract: Game worlds have traditionally been built through labor-intensive production pipelines, making them costly to develop, difficult to customization, and e
The next generation of AI is evolving from a tool into a platform where models, applications, and human workflows converge to create integrated operating environments capable of automating tasks and e
The agentic AI era is here, transforming how higher education institutions innovate, operate, and fundamentally empower learners, faculty, and researchers. AI agents can deliver unprecedented efficien
arXiv:2607.05968v1 Announce Type: cross Abstract: Matching influencers (KOLs) to free-form, multi-part Thai marketing criteria is today served either by keyword search over structured profiles, which
arXiv:2607.05468v1 Announce Type: cross Abstract: World Action Models (WAMs) have shown strong potential for robotic manipulation by jointly modeling visual future dynamics and executable action seque
arXiv:2504.20198v2 Announce Type: replace-cross Abstract: This work presents a comprehensive evaluation of neural network graph compilers across heterogeneous hardware platforms, addressing the critic
arXiv:2607.06173v1 Announce Type: new Abstract: Recent advances in video diffusion have been driven by scaling transformer-based architectures to billions of parameters, substantially improving visual
arXiv:2607.05533v1 Announce Type: new Abstract: Computational pathology foundation models (PFMs) have advanced whole-slide image analysis. However, their size and inference cost hinder local deploymen
arXiv:2607.06535v1 Announce Type: new Abstract: A learning-enabled disturbance-rejection framework based on a Neural Extended State Observer (Neural-ESO) is presented in this letter. Unlike existing l
arXiv:2607.05397v1 Announce Type: cross Abstract: Agent systems increasingly execute rather than advise. When an AI agent queries regulated data, invokes effectful tools, and mutates persistent state,
arXiv:2607.06411v1 Announce Type: cross Abstract: Developers increasingly delegate real maintenance work to product-grade coding agents, and many state tasks in their native language, in the style of
arXiv:2607.05876v1 Announce Type: cross Abstract: LLM serving optimization typically benchmarks many configurations and reaches for heavy profilers when latency targets are missed. We argue for the re
arXiv:2607.05669v1 Announce Type: cross Abstract: Reliable localization in GNSS-denied environments remains a fundamental challenge for intelligent vehicles, as inertial navigation systems accumulate