Search: “reasoning”

arXiv:2607.19359v1 Announce Type: new Abstract: Long-term memory is essential for LLM agents that interact across sessions, yet current memory benchmarks primarily evaluate single-hop recall, leaving

arXiv:2607.20061v1 Announce Type: new Abstract: Embodied visual tracking (EVT) requires a mobile agent to continuously follow a specific target described in natural language using only onboard vision.

arXiv:2607.19701v1 Announce Type: new Abstract: VLMs are increasingly deployed in AD systems, creating an urgent need for rigorous safety evaluation under rare yet safety-critical scenarios. Among the

arXiv:2607.20145v1 Announce Type: cross Abstract: Full-parameter post-training of trillion-parameter-scale MoE models introduces substantial system-level challenges for large-scale distributed trainin

Welcome to The Blueprint, a new feature where we highlight how Google Cloud customers are tackling unique and common challenges across industries using the latest AI and cloud technologies. We hope to

arXiv:2509.24739v4 Announce Type: replace Abstract: Vision-Language Foundation Models (VLMs), trained on large-scale multimodal datasets, have driven significant advances in Artificial Intelligence (A

arXiv:2607.19595v1 Announce Type: cross Abstract: Large language model (LLM) agents are vulnerable to security risks, such as prompt injection attacks from untrusted context that manipulate downstream

arXiv:2607.19781v1 Announce Type: new Abstract: Autonomous driving requires understanding the road as a graph of drivable lanes and their connectivity, beyond the ego lane alone, to follow routes thro

arXiv:2512.02473v2 Announce Type: replace-cross Abstract: Video world models have attracted significant attention for their ability to produce high-fidelity future visual observations conditioned on p

Scientists today face challenges of extraordinary scale and complexity. From shaping and simulating the intricate dynamics of fusion plasma, to exploring the vast search space of new materials, to mak

Today the Department of Energy (DOE) and Arcee AI announced the development of Genesis-Science-1 (GS1), an open model for scientific research. This is a joint effort to bring advanced AI into scientif

If I had a nickel for every snide but underinformed person who failed to distinguish between pure LLMs and neurosymbolic AI I would be a billionaire. @GaryMarcus Hold on Gary, I thought these LLMs wer

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

Let me try to explain this clearly, simply, and neatly. Originally, I just wanted to build a small WebUI adapter with an admin panel, but things escalated over the last few months. At first, I faced t

Hi everyone, I'm working on extracting the hierarchical structure of long PDF documents (legal/regulatory text, lots of numbered sections) and would like to gather some feedback on my approach before

Nice to see someone around here actually understand the technical details. (The vast majority of the attacks on me come from people who don’t.) And the probabilistic next-token critics were correct ab

We had guessed reward seeking might increase over the course of capabilities-focused RL training, but had no way of measuring it until now. We’re continuing to collaborate with Apollo Research to impr

NVIDIA AI has released Cosmos 3 Edge, a 4‑billion‑parameter open‑source world model designed for on‑device inference. It enables robots to learn and act, autonomous vehicles to interpret road scenes a

Backpropagation by hand ✍️ ~ 11 steps walkthrough below Backpropagation is the algorithm that actually trains a neural network, and it is where most people stop following along. It is not calculus you

Who’s Afraid of Chinese Models? Interesting proposal from Ben Thompson that both addresses the hypocrisy of labs outlawing distillation against their models despite training on unlicensed data, and co

arXiv:2607.13354v1 Announce Type: new Abstract: Autonomous racing demands planning algorithms that balance vehicle dynamics at the limits of handling with strategic decision-making in competitive mult

arXiv:2607.14044v1 Announce Type: new Abstract: By 2030, 59 of every 100 workers will need reskilling or upskilling, yet the average time to close an enterprise skills gap grew from roughly 3 days in

arXiv:2607.13562v1 Announce Type: new Abstract: Knowing when to say 'I don't know' is fundamental to human judgment, yet AI assistants offer a fluent answer to almost any question. In five experiments

arXiv:2607.13574v1 Announce Type: cross Abstract: We develop a convergent scheme to train neural networks involving analytic activation functions based on gradient flows. Convergence properties are gu

arXiv:2607.13608v1 Announce Type: new Abstract: Automatic scientific discovery has long been a goal of computational scholars - a machine that can discover nature's secrets on its own, moving computat

arXiv:2607.13188v1 Announce Type: new Abstract: Human cognition does not separate understanding and generation. A teacher at a whiteboard speaks and draws extit{together}, each modality reshapes the o

arXiv:2607.13239v1 Announce Type: new Abstract: Foundation models, including large language models (LLMs) and vision-language models (VLMs), are increasingly used for transportation management center

arXiv:2607.13653v1 Announce Type: new Abstract: Real-world deployment of embodied agents requires active exploration, visual grounding, and interactive intent disambiguation. However, existing framewo

arXiv:2607.13481v1 Announce Type: new Abstract: Accurate 3D scene understanding is fundamental to embodied intelligence and autonomous driving, where 3D occupancy provides a unified representation of

arXiv:2607.13560v1 Announce Type: cross Abstract: Recent advances in generative and embodied AI have been driven by large-scale predictive learning over multimodal data. However, the resulting systems

arXiv:2607.13646v1 Announce Type: cross Abstract: Recent advances in 3D human reconstruction have improved overall performance, yet current models still fail in the most challenging real-world scenari

arXiv:2607.13115v1 Announce Type: new Abstract: Small language models (SLMs) have shown promise for zero-shot molecular property prediction from SMILES strings, yet they often suffer from structural b

arXiv:2510.10002v3 Announce Type: replace Abstract: As large language models (LLMs) are increasingly deployed in sensitive everyday contexts -- offering personal advice, mental health support, and mor

arXiv:2607.13461v1 Announce Type: new Abstract: Vision-and-Language Navigation (VLN) necessitates an embodied agent to navigate in the physical world by adhering to natural language instructions. Rece

arXiv:2606.18223v2 Announce Type: replace-cross Abstract: With sophisticated cyber-attacks becoming increasingly prevalent, modern networks require intelligent autonomous cyber-defense agents trained

arXiv:2607.13818v1 Announce Type: new Abstract: Robotic manipulation poses fundamental challenges due to uncertainty, long-horizon execution, and compounding errors, which can easily destabilize execu

arXiv:2607.13172v1 Announce Type: new Abstract: We address the problem of safely training an agent policy and deploying a good and safe policy, in settings where the environment dynamics are unknown a

arXiv:2602.12811v2 Announce Type: replace-cross Abstract: When humans and large language models (LLMs) process the same text, activations in the LLMs correlate with brain activity measured, e.g., with

arXiv:2607.09142v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed in online medical consultation, yet existing benchmarks remain poorly aligned with real clini

I managed to get this model working on 2x 3090s with full 262k ctx and N=4, if anyone is interested to try it, thanks to this quant: https://huggingface.co/danielrmay/NVIDIA-Nemotron-Labs-3-Puzzle-75B

arXiv:2607.10057v1 Announce Type: cross Abstract: Can AI agents visually comprehend quantum circuit diagrams and generate verified executable code--and at what cost? We present Quantum Circuit Vision,

arXiv:2607.13318v1 Announce Type: new Abstract: Procedural material creation underpins applications in digital content creation, visual effects, and 3D asset design. Achieving high-quality results req

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:2607.13618v1 Announce Type: new Abstract: LLM agents are increasingly evaluated on multi-week decision tasks in which the state that drives cost is never directly observed. On such tasks the fin

arXiv:2607.13077v1 Announce Type: cross Abstract: Large language models (LLMs) often produce homogeneous outputs, raising concerns that AI coding assistants may lead to convergence in the software art

arXiv:2607.13346v1 Announce Type: cross Abstract: Alignment faking is dangerous because a model can appear compliant under monitoring while preserving behavior it would reveal when unmonitored. When n