Knowledge catalogue
arXiv:2610.18948v1 Announce Type: cross Abstract: Finite safety assessments cannot exclude an adversary that preserves unattacked behavior until certification and activates afterward. We characterize
Meta’s Muse Spark Open, a high‑capacity US open‑weight model for agentic software engineering, is now live on Together AI as a Day 0 launch partner. The model supports a 1‑million‑token context window
arXiv:2610.20606v1 Announce Type: cross Abstract: Recent advances in robot learning have driven rapid progress in humanoid control, enabling increasingly agile behaviors in the real world. However, hu
Nvidia Corp. today announced the launch of customizable Nemotron 3.5 Super LV large language models for always-on artificial intelligence agents and edge-focused 3.5 Bolt for local systems. The compan
NVIDIA’s open‑source Nemotron 3.5 Super VL is a 120 B parameter mixture‑of‑experts multimodal model that activates only 12 B parameters per token, enabling combined reasoning, instruction following, t
https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB-GGUF https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB-LiLiCorr-GGUF NVIDIA Nemotron 3.5 Bolt 74B-A9B 24GB is a vi
Old friends are the best friends. Jensen rocks. The Star Mind computer being co-engineered by SpaceX and Nvidia is far better than almost anyone expects and will reach volume production next year. Wor
arXiv:2610.19857v1 Announce Type: new Abstract: Recovering 3D human motion from sparse wearable sensors is challenging due to the inherent noise, occlusion, and instability of real-world tracking sign
arXiv:2610.04693v2 Announce Type: replace Abstract: Agents are entering finance, healthcare and law, sectors where a violation leaves no lexical signature and carries real penalties. Whether an omissi
arXiv:2603.23678v2 Announce Type: replace Abstract: Large Language Models (LLMs) offer transformative solutions across many domains, but healthcare integration is hindered by strict data privacy const
arXiv:2610.19615v1 Announce Type: new Abstract: Reinforcement learning has enabled robust locomotion for legged robots, but learned policies are typically tied to a specific robot morphology and requi
arXiv:2610.14937v1 Announce Type: new Abstract: How do language models generalize from their training data? This is a central challenge for alignment: models reliably learn their training distribution
arXiv:2610.19439v1 Announce Type: new Abstract: While LLM-based agent systems have demonstrated remarkable proficiency in reasoning and solving complex real-world tasks, they also come with substantia
arXiv:2606.18060v2 Announce Type: replace Abstract: As Large Language Model based agents enter autonomous scientific research, their ability to resist pseudoscience becomes increasingly important. Oth
arXiv:2610.19385v1 Announce Type: new Abstract: Large Language Model (LLM) unlearning is often evaluated primarily by target suppression and clean retain utility. These metrics can miss a local failur
arXiv:2610.17584v1 Announce Type: new Abstract: Operational mobile networks are rich in observations but poor in interventions: they continuously generate large volumes of passive telemetry, while con
arXiv:2610.16443v1 Announce Type: new Abstract: Recent world action models draw on video generation priors to jointly predict future observations and robot actions. Adapting these priors to control re
arXiv:2610.19044v1 Announce Type: cross Abstract: Tiny robots have limited computation and memory, yet visual navigation systems often maintain more state than a task requires. We ask whether persiste
arXiv:2610.14299v1 Announce Type: cross Abstract: Recent Speech Full-Duplex (FDX) models are capable of engaging in naturalistic conversation by listening and speaking at the same time. Building on th
arXiv:2610.15218v1 Announce Type: new Abstract: A recurrent-depth language model reuses one block of weights several times in a row. The number of repetitions, which we call loops, is chosen when the
Meta’s Muse Spark Open is an 816‑billion‑parameter mixture‑of‑experts coding model that activates only 42 billion parameters per token through top‑8 routing across 256 experts, and has been trained on
arXiv:2603.07373v2 Announce Type: replace-cross Abstract: The rapid growth of AI training has dramatically increased datacenter traffic demand and energy consumption, which has motivated renewed inter
arXiv:2610.18813v1 Announce Type: new Abstract: Harness self-evolution revises an agent's software scaffolding, including prompts, memory, workflows, and executable components, while keeping model wei
arXiv:2601.04948v2 Announce Type: replace Abstract: Although recent years have seen significant progress of humanoid robots in walking and running, the frequent foot strikes with ground during these l
arXiv:2610.15964v1 Announce Type: new Abstract: A self-evolving agent rewrites its own harness and must decide which rewrites to keep, so its improvement signal is the check a rewrite has to pass. Ver
arXiv:2601.07239v2 Announce Type: replace Abstract: Deterministic inference is a comforting ideal in classical software: the same program on the same input should always produce the same output. As la
Going to try these out to see if they have the same looping behaviors that other Bonsai models have had. Still requires their fork of llama.cpp (branch prism) so dont expect it to work with vanilla ll
arXiv:2609.35557v2 Announce Type: replace-cross Abstract: The compiler must read modules a physics-based solver cannot build without; the coding agent must not read that intellectual property. The har
arXiv:2610.18445v1 Announce Type: new Abstract: Automating AI research creates a positive feedback loop between software capability and research effort. We study a stochastic realisation of this loop
arXiv:2610.17296v1 Announce Type: new Abstract: Emerging healthcare services, such as real-time diagnostics, remote health monitoring and computer-assisted surgery, require stringent Quality of Servic
arXiv:2610.19133v1 Announce Type: new Abstract: Indirect prompt injection uses untrusted retrieved content, tool outputs, or agent messages to override an LLM's intended behavior. We show that defense
arXiv:2610.19401v1 Announce Type: cross Abstract: As large, powerful pre-trained models become more prevalent, there is growing interest in developing methods that allow different neural networks to b
arXiv:2610.19316v1 Announce Type: cross Abstract: Assigning routine tasks to cheaper large language model (LLM) providers can reduce generation cost, but switching providers may require processing acc
arXiv:2502.12713v2 Announce Type: replace Abstract: Echocardiography plays a fundamental role in the extraction of clinical parameters (e.g. left ventricular volume and ejection fraction) required to
arXiv:2610.17609v1 Announce Type: new Abstract: Training-free self-improvement lets an agent use feedback to revise the response it is about to return and to update the harness state that shapes how i
arXiv:2610.16979v1 Announce Type: cross Abstract: Generative retrieval (GR) offers a promising paradigm for industrial search by unifying candidate generation within an autoregressive framework. Howev
Small teams, short runway, and constant pressure to ship faster — it’s the reality we see every day among the founders we work with at Google for Startups. When you are building a company from the gro
arXiv:2610.15883v1 Announce Type: cross Abstract: Text wrapped in a trigger can be made behaviorally invisible to a language model: omitted from summaries and quotations, ignored in question answering
arXiv:2610.17365v1 Announce Type: new Abstract: As LLM agents take on more autonomous roles, they may interact with multiple clients and counterparties whose goals and incentives conflict. If an agent
arXiv:2610.17643v1 Announce Type: new Abstract: An enterprise agent that answers under a written policy must choose an action before it says anything: answer, ask for a missing fact, ask for confirmat
arXiv:2610.16881v1 Announce Type: cross Abstract: There is a specific challenge designers face in developing autonomous robots capable of open-ended learning. This challenge is how one can develop suc
arXiv:2610.15623v1 Announce Type: new Abstract: Hybrid federated semantic communication enables user equipment (UEs) to contribute model updates or semantic features under a shared training framework.
arXiv:2610.17881v1 Announce Type: new Abstract: Can an AI agent turn high-level user intent into a functioning robot and teach it how to behave? We study this question from two complementary aspects:
arXiv:2610.15015v1 Announce Type: new Abstract: In the presence of feedback loops, algorithmic decisions at one time step can influence observed data in subsequent steps, potentially introducing selec
arXiv:2508.06313v2 Announce Type: replace Abstract: This paper presents a unified system-level modeling and control framework for an all-electric heavy-duty robotic manipulator (HDRM) driven by electr
arXiv:2603.15046v2 Announce Type: replace Abstract: In this study, we address the problem of language-guided robotic manipulation, where a robot is required to manipulate a wide range of objects based
arXiv:2610.15245v1 Announce Type: cross Abstract: Objective. To develop an automated method for segmentation and uptake quantification of carotid atherosclerotic inflammation on 64Cu-CANF-comb PET whi
arXiv:2610.17966v1 Announce Type: new Abstract: Long-context inference makes the key-value (KV) cache a major memory bottleneck for large language models. We propose BELT, a low-rank KV cache compress
arXiv:2610.16863v1 Announce Type: cross Abstract: Organizations pairing a human and a machine on a task decide, often by default, which executes each instance and what happens when both do. We account
arXiv:2610.14753v1 Announce Type: new Abstract: Versatile quadruped locomotion depends on a tight coupling between what the robot perceives and what its body can execute. Yet existing visual controlle
BREAKING: SpaceXSI just revealed that Starlink uses Grok Voice 3.0 to handle 20,000 daily calls in multiple languages. About 70% need no human & 1 in 4 sales calls ends in a purchase. AI agent verifie
arXiv:2610.15453v1 Announce Type: cross Abstract: Neural audio codecs achieve remarkable performance but operate as closed ecosystems with rigidly co-trained encoderdecoder pairs, severely hindering i
arXiv:2610.14715v1 Announce Type: new Abstract: Early-stage design of heterogeneous UAV computing systems requires evaluating how algorithm, hardware, communication, and system topology affect closed-
arXiv:2610.17962v1 Announce Type: cross Abstract: Predictive service assurance converts forecasts of key performance indicators into alarms, and that conversion decides whether the assurance function
arXiv:2610.14564v1 Announce Type: cross Abstract: Model-based reinforcement learning has shown superior sample efficiency by leveraging the learned latent dynamics either in the form of derivative-fre
arXiv:2610.14413v1 Announce Type: new Abstract: Computational coarse-graining aims to replace a sequence of updates with a cheaper module while preserving task performance. We present a continuation-r
arXiv:2610.15763v1 Announce Type: new Abstract: Modern industrial automation demands autonomous collaborative systems capable of coordinated manipulation in workspaces with heterogeneous object arrang
arXiv:2610.14941v1 Announce Type: new Abstract: Diffusion-based policies have recently emerged as a powerful paradigm for offline reinforcement learning, but their reliance on multi-step denoising int
arXiv:2610.16737v1 Announce Type: cross Abstract: Video-to-robot pipelines for quadrupedal imitation insert a learned lifting stage, either a monocular depth model or a per-clip 3D reconstruction, to
arXiv:2511.12528v5 Announce Type: replace Abstract: Visual Place Recognition (VPR) aims to determine the geographic location of a query image by retrieving its most visually similar counterpart from a