Knowledge catalogue
arXiv:2606.01830v1 Announce Type: new Abstract: Recent LLM search agents use reinforcement learning with verifiable rewards (RLVR) to learn search-augmented reasoning from outcome rewards. On hard pro
arXiv:2606.00123v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have shown strong performance on public medical benchmarks, yet existing evaluations often remain weak proxie
arXiv:2510.10982v2 Announce Type: replace-cross Abstract: Recent AI regulations increasingly emphasize the need for mechanisms that preserve the utility of data for AI innovation while preventing misu
arXiv:2606.00169v1 Announce Type: cross Abstract: Increased competition and the growing similarity of products and services offered by retailers have lowered the barriers for customers to switch to co
arXiv:2603.24511v2 Announce Type: replace-cross Abstract: We show that AI agents are capable of discovering novel algorithms for adversarial attacks against LLMs, advancing the state of the art on whi
arXiv:2606.00074v1 Announce Type: cross Abstract: Reliable seizure prediction is a prerequisite for closed-loop neurostimulation therapy, yet existing methods rarely account for the variability in EEG
arXiv:2606.01895v1 Announce Type: cross Abstract: With the growing number of satellites in low Earth orbit (LEO) constellations, the near-Earth space environment has become increasingly congested, mak
arXiv:2606.00047v1 Announce Type: cross Abstract: Frontier AI governance often centres on the model-level governance paradigm, which assumes that a model's capability profile is primarily a function o
arXiv:2606.00374v1 Announce Type: new Abstract: Recent advances in reinforcement learning (RL) have demonstrated impressive whole-body agility for humanoid robots, yet ensuring safety and satisfying c
arXiv:2606.01962v1 Announce Type: new Abstract: Metal surface defect detection is critical for maintaining product quality in industrial manufacturing. However, it faces significant challenges, includ
arXiv:2606.02502v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) unify heterogeneous vision-language tasks under a shared generative framework via instruction tuning, yet real-
arXiv:2606.01478v1 Announce Type: cross Abstract: High-quality, large-scale synthetic data from simulations is becoming a cornerstone for pushing the capabilities of robot algorithms. While aerial rob
arXiv:2606.00846v1 Announce Type: new Abstract: Users increasingly face the challenge of selecting an appropriate LLM for a given task from a rapidly growing pool of LLMs, each with distinct but often
arXiv:2606.01023v1 Announce Type: cross Abstract: Visual inspection remains the dominant quality-control practice in woven and tufted carpet production, yet it is slow, subjective, and inconsistent at
arXiv:2606.00401v1 Announce Type: cross Abstract: Simulating large molecular systems comprising thousands of atoms requires highly scalable methodologies. While modern Density Functional Theory (DFT)
arXiv:2602.19848v2 Announce Type: replace Abstract: Skin lesion classification datasets often suffer from severe class imbalance, with malignant cases significantly underrepresented, leading to biased
arXiv:2603.13312v2 Announce Type: replace-cross Abstract: Interior design is a requirements-to-visual-plan generation process that must simultaneously satisfy verifiable spatial feasibility and compar
arXiv:2512.10236v2 Announce Type: replace-cross Abstract: Modern ML workloads demand distributing training and inference across multiple GPUs. However, these parallelization techniques often suffer fr
arXiv:2606.01324v1 Announce Type: cross Abstract: The evolution toward 6G wireless networks envisions a seamlessly intelligent, Open-RAN-enabled architecture where unmanned aerial vehicles (UAVs) play
arXiv:2510.05566v2 Announce Type: replace-cross Abstract: Large language models have achieved impressive performance across diverse tasks. However, their tendency to produce overconfident and factuall
arXiv:2606.00519v1 Announce Type: new Abstract: We present DriveAnchor, a three-stage framework for autonomous driving planning that achieves behavioral diversity, controllability, and safety in a com
arXiv:2606.00400v1 Announce Type: new Abstract: Continual instruction tuning updates a language model through a sequence of new domains, yet each update can progressively erode previously learned capa
arXiv:2606.01909v1 Announce Type: cross Abstract: We present Echo, a proof-of-concept audio system built around a single 25 M-parameter ViT encoder. The encoder is pretrained with a JEPA objective and
arXiv:2606.00552v1 Announce Type: cross Abstract: Multi-robot systems (MRS) increasingly offload compute-intensive perception tasks to edge nodes to meet strict time-sensitive Quality-of-Service (QoS)
arXiv:2606.02129v1 Announce Type: new Abstract: Image customization learns target subjects from reference concept images and generates conditioned images per text prompts, mainly modifying styles or b
arXiv:2606.00442v1 Announce Type: new Abstract: Many machine learning techniques rely on approximating a loss function's curvature, but this is notoriously hard to do at the scale of modern deep netwo
arXiv:2603.23485v2 Announce Type: replace-cross Abstract: Standard evaluation practices assume that large language model (LLM) outputs are stable when prompts are embedded in contextually equivalent d
arXiv:2606.00355v1 Announce Type: new Abstract: Animal ecology data collection using drones represents a substantial investment of time, expertise, and financial resources. Yet most existing datasets
arXiv:2606.02068v1 Announce Type: cross Abstract: Recently, novel view synthesis has witnessed remarkable progress, with mainstream methods such as Neural Radiance Fields (NeRF) and 3D Gaussian Splatt
arXiv:2606.02307v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models are increasingly used as generalist robot policies, yet their evaluation still relies largely on static benchmarks t
arXiv:2606.01774v1 Announce Type: cross Abstract: Autoregressive (AR) large language models (LLMs) have achieved broad practical success, but sequential decoding remains a key bottleneck for low-laten
arXiv:2606.01713v1 Announce Type: new Abstract: We propose FlipItRight, a framework for stable planar pose-targeted throw-flip with a high-DoF manipulator. The task is decomposed into an object-level
arXiv:2606.00620v1 Announce Type: new Abstract: Recent Large Multimodal Models (LMMs), primarily designed for offline settings, are ill-suited for the dynamic requirements of streaming video. While re
For organizations already using Azure and Fabric, this means a much faster path from governed data to internal software. • Build apps securely on top of governed Fabric data • Use existing authenticat
arXiv:2606.00054v1 Announce Type: cross Abstract: Recent progress in generalizable embodied control has been driven by large-scale pretraining of Vision-Language-Action (VLA) models. However, most exi
GitHub is developing AI agents to automate software development workflows and enhance developer productivity. The discussion likely covers GitHub's strategy for integrating autonomous AI capabilities
arXiv:2606.00637v1 Announce Type: new Abstract: Although reinforcement learning has significantly advanced humanoid locomotion, perceptive policies still struggle on sparse-foothold terrain and constr
arXiv:2606.01386v1 Announce Type: new Abstract: We present GuidaPA, a privacy-preserving chatbot for the Italian Public Administration (PA) trained via Federated Learning (FL) on documentation from tw
arXiv:2606.00642v1 Announce Type: new Abstract: Reasoning traces have become a valuable form of learning signals for improving and transferring the capabilities of large language models. In particular
arXiv:2606.02119v1 Announce Type: cross Abstract: Machine unlearning aims to remove the influence of specific forget training data due to privacy, copyright or bias concerns while maintaining the mode
arXiv:2606.00497v1 Announce Type: cross Abstract: Deceptive web content, widely instantiated across the internet and commonly known as extit{social-engineering attacks}, manipulates autonomous web age
Impulse Space raised 500 million in Series D funding to expand production of orbital transfer vehicles and spacecraft for commercial and government demand. The funds will scale production of Mira, a m
arXiv:2606.00703v1 Announce Type: cross Abstract: Low-precision pretraining (FP8, MXFP4, NVFP4) is now standard for frontier language models, yet the literature is almost entirely achievability -- alg
Devin Desktop is a unified management interface from Cognition AI that enables users to coordinate multiple AI agents operating across local and cloud environments. The platform streamlines workflows
arXiv:2606.01691v1 Announce Type: cross Abstract: Industrial Internet systems face increasing threats from sophisticated industrial control system (ICS) attacks, resulting in critical safety incidents
arXiv:2606.00328v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for knowledge base question answering (KBQA), where answering requires selecting entities from a ques
arXiv:2606.01151v1 Announce Type: new Abstract: Behavior cloning with high-capacity generative policies achieves strong imitation performance, but is often limited by demonstration coverage and distri
arXiv:2606.00991v1 Announce Type: new Abstract: Transportation systems management and operations (TSMO) increasingly depends on timely interpretation of heterogeneous data, from various sensor streams
arXiv:2606.01111v1 Announce Type: new Abstract: Modern industrial recommender systems rely on thousands of heterogeneous features -- ranging from low-dimensional scalars (e.g., statistical value) to h
arXiv:2606.01458v1 Announce Type: new Abstract: Training vision-language-action (VLA) policies for humanoid loco-manipulation is constrained by the high cost and complexity of collecting human teleope
arXiv:2606.00372v1 Announce Type: new Abstract: Reliable object detection is critical for automated driving, yet even state-of-the-art detectors inevitably make errors that can compromise safety. Intr
arXiv:2606.00771v1 Announce Type: cross Abstract: A simple way to improve the performance of almost any machine learning model is not to train a single but several models with diverse algorithms which
arXiv:2606.00975v1 Announce Type: new Abstract: LLM chatbots increasingly serve as a first source of support for people in psychological distress, including those whose distress is entangled with delu
arXiv:2408.01653v4 Announce Type: replace Abstract: Omnidirectional depth estimation presents a significant challenge due to the inherent distortions in panoramic images. Despite notable advancements,
arXiv:2606.01301v1 Announce Type: new Abstract: Hallucinations in medical large language models (LLMs) pose serious risks for clinical decision support, particularly when models must reason over compl
arXiv:2606.01028v1 Announce Type: new Abstract: Medical treatment recommendation poses several challenges to reinforcement learning (RL): patient physiology evolves in continuous time, measurements an
arXiv:2606.00619v1 Announce Type: cross Abstract: Long-horizon autonomous agents require memory systems to retain historical information, track evolving states, and reuse relevant knowledge beyond fin
Microsoft Corp. announced an expansion to its artificial intelligence models and agentic AI infrastructure today that brings more data and context into the hands of developers and business users as th
Microsoft Corp. today introduced Rayfin, an open-source software development kit and command-line interface that lets developers and coding agents define an entire application backend in code and depl
arXiv:2606.01099v1 Announce Type: cross Abstract: Command understanding systems in smart home ecosystems can automate device control and substantially improve user experience. However, while they perf