All entries

arXiv:2604.18955v1 Announce Type: cross Abstract: In this study, we present the first comprehensive evaluation of modern LLMs - including GPT-4, GPT-4o, GPT-3.5-Turbo, Gemini 1.5 Pro, DeepSeek-V3, Lla

arXiv:2604.19509v1 Announce Type: new Abstract: Vision-language models (VLMs) have demonstrated remarkable capabilities in understanding human-object interactions, but their application to robotic sys

arXiv:2506.22174v2 Announce Type: replace-cross Abstract: The transport industry has recently shown significant interest in unmanned surface vehicles (USVs), specifically for port and inland waterway

Atlassian Corp. today announced an expansion of its multiyear partnership with Google Cloud that includes deepening integrations between its Rovo agent platform and Google Workspace and Gemini Enterpr

arXiv:2604.19350v1 Announce Type: new Abstract: Vision Transformers (exttt{ViT}) have become the architecture of choice for many computer vision tasks, yet their performance in computer-aided diagnost

arXiv:2604.19217v1 Announce Type: cross Abstract: Crop yield prediction is one of the most important challenge, which is crucial to world food security and policy-making decisions. The conventional fo

arXiv:2604.19204v1 Announce Type: cross Abstract: LLMs are increasingly being considered for prediction tasks in high-stakes social service settings, but their algorithmic fairness properties in this

Renju Jose / Reuters: Australia's eSafety Commissioner issues transparency notices to Roblox, Microsoft's Minecraft, and other online gaming platforms to detail child safety measures — Australia's int

Auto-Protect is rolling out today on an opt-in basis for paying customers. Over time, our vision is for this kind of maintenance to become almost fully automated by AI. To enable Auto-Protect across y

Deploying large language models (LLMs) in real-world, high-stakes settings is harder than it should be. In high-stakes settings like law, medicine, and cloud incident response, performance and reliabi

arXiv:2604.18993v1 Announce Type: cross Abstract: Perception robustness under adverse weather remains a critical challenge for autonomous driving, with the core bottleneck being the scarcity of real-w

arXiv:2604.15034v2 Announce Type: replace Abstract: Recent advances in LLM based agent systems have shown promise in tackling complex, long horizon tasks. However, existing agent protocols (e.g., A2A

arXiv:2508.13905v2 Announce Type: replace Abstract: Extreme weather events, intensified by climate change, increasingly challenge aging combined sewer systems, raising the risk of untreated wastewater

arXiv:2604.18934v1 Announce Type: new Abstract: Existing AI benchmarks for software automation rarely combine cross-application coordination, autonomous API discovery, and policy adherence. Real busin

arXiv:2604.18740v1 Announce Type: new Abstract: Purpose: Automated C-arm positioning ensures timely treatment in patients requiring emergent interventions. When a conventional Deep Learning (DL) appro

arXiv:2604.19618v1 Announce Type: new Abstract: Reliable pipeline inspection is critical to safe energy transportation, but is constrained by long distances, complex terrain, and risks to human inspec

Amazon Web Services Inc. said today it’s taking steps toward simplifying the creation of the underlying infrastructure for new autonomous artificial intelligence agents. With an update to its Amazon B

B8881 is a release of llama.cpp, an open-source C/C++ project for LLM inference . The project aims to enable LLM inference with minimal setup and state-of-the-art performance on a wide range of hardwa

b8882 is a release of llama.cpp, a C/C++ implementation for LLM inference . The project follows a rapid release cycle with frequent updates to support multiple hardware architectures and platforms. Th

b8883 is a release build of llama.cpp, an open-source software library that performs inference on various large language models, co-developed alongside the GGML tensor library. This intermediate build

llama.cpp is a C/C++ implementation that enables LLM inference with minimal setup and state-of-the-art performance on a wide range of hardware locally and in the cloud. Release b8884 is a build/versio

The search results don't contain specific information about release b8885. Based on the llama.cpp release numbering pattern visible in the results, b8885 is an intermediate build release of llama.cpp,

B8886 is a release version from llama.cpp, the C/C++ project for LLM inference. The main goal of llama.cpp is to enable LLM inference with minimal setup and state-of-the-art performance on a wide rang

Based on the available information, b8888 appears to be a build release version identifier for llama.cpp. While I couldn't locate specific details about this particular release, llama.cpp release vers

b8891 is a release version of llama.cpp, which is a tool for LLM inference in C/C++. llama.cpp is a free and open-source tool that allows users to run AI models locally on Windows, Linux and macOS. Th

arXiv:2604.19133v1 Announce Type: new Abstract: Robust 3D reconstruction across varying environmental conditions remains a critical challenge for robotic perception, particularly when transitioning be

arXiv:2604.19508v1 Announce Type: new Abstract: This paper introduces extit{Bangla Key2Text}, a large-scale dataset of 2.6 million Bangla keyword--text pairs designed for keyword-driven text generatio

arXiv:2601.11037v2 Announce Type: replace Abstract: RL-based agentic search enables LLMs to solve complex questions via dynamic planning and external search. While this approach significantly enhances

arXiv:2512.03467v2 Announce Type: replace Abstract: Chronic diseases often progress differently across patients. Rather than randomly varying, there are typically a small number of subtypes for how a

arXiv:2604.19532v1 Announce Type: cross Abstract: Tokenizing music to fit the general framework of language models is a compelling challenge, especially considering the diverse symbolic structures in

arXiv:2508.21184v3 Announce Type: replace-cross Abstract: We propose a general-purpose approach for improving the ability of large language models (LLMs) to intelligently and adaptively gather informa

been using claude design and loving it it's basically claude code under the hood but with a very opinionated ontology for input and output - the input ontology is logo, colors, fonts, etc. - the outpu

Jeremy Howard shares positive impressions of working with Kimi Moonshot's K2.6 model for two hours, noting it performed well despite being used somewhat unexpectedly. The post suggests K2.6 demonstrat

benchmarking agents by their ability to play video games 🎮 We are excited to launch VideoGameBench on Antim Labs, created by @a1zhang, Thomas L. Griffiths (@cocosci_lab), @karthik_r_n, and @OfirPress

arXiv:2506.06414v2 Announce Type: replace-cross Abstract: Existing language model safety evaluations focus on overt attacks and low-stakes tasks. In reality, an attacker can easily subvert existing sa

arXiv:2509.12483v4 Announce Type: replace Abstract: This study compares the Boundary Element Method (BEM) and Physics-Informed Neural Networks (PINNs) for solving the two-dimensional Helmholtz equatio

arXiv:2604.18837v1 Announce Type: cross Abstract: Quantum kernel methods have been proposed as a promising approach for leveraging near-term quantum computers for supervised learning, yet rigorous ben

arXiv:2604.19196v1 Announce Type: new Abstract: Face Anti-Spoofing (FAS) remains challenging due to the requirement for robust domain generalization across unseen environments. While recent trends lev

arXiv:2604.19724v1 Announce Type: cross Abstract: Despite the remarkable success of Vision Transformers (ViTs) across a wide range of vision tasks, recent studies have revealed that they remain vulner

arXiv:2507.00451v2 Announce Type: replace-cross Abstract: We present an efficient and generalised procedure to accurately identify the best (or near best) performing algorithm for each sub-task in a m

arXiv:2604.18972v1 Announce Type: cross Abstract: We study finite-horizon continuous-time policy evaluation from discrete closed-loop trajectories under time-inhomogeneous dynamics. The target value s

arXiv:2604.18751v1 Announce Type: cross Abstract: Nonlinear machine-learning models are increasingly used to discover causal relationships in time-series data, yet the interpretation of their outputs

arXiv:2604.18663v1 Announce Type: cross Abstract: Existing jamming attacks on Retrieval-Augmented Generation (RAG) systems typically induce explicit refusals or denial-of-service behaviors, which are

arXiv:2604.18697v1 Announce Type: cross Abstract: Indistinguishability properties such as differential privacy bounds or low empirically measured membership inference are widely treated as proxies to

arXiv:2512.22673v3 Announce Type: replace Abstract: Travel planning is a natural real-world task to test large language models' (LLMs) planning and tool-use abilities. Although prior work has studied

arXiv:2509.26238v4 Announce Type: replace Abstract: Monitoring large language models' (LLMs) activations is an effective way to detect harmful requests before they lead to unsafe outputs. However, tra