Knowledge catalogue
arXiv:2604.22591v1 Announce Type: new Abstract: The real-world deployment of Vision-Language-Action (VLA) models remains limited by the risk of unpredictable and irreversible physical harm. However, w
arXiv:2604.22390v1 Announce Type: new Abstract: Visual Place Recognition (VPR) determines a query image's geographic location by matching it against geotagged databases. However, existing methods stru
arXiv:2602.12469v2 Announce Type: replace Abstract: Deep ensemble methods often improve predictive performance, yet they suffer from three practical limitations: redundancy among base models that infl
arXiv:2604.22746v1 Announce Type: cross Abstract: ReLU neural networks trained as surrogate models can be embedded exactly in mixed-integer linear programs (MILPs), enabling global optimization over t
arXiv:2509.14127v2 Announce Type: replace Abstract: We consider the problem of delivering multiple packages from a single depot to distinct goal locations using a homogeneous fleet of robots with limi
arXiv:2604.22292v1 Announce Type: cross Abstract: The classification of legal documents from an unstructured data corpus has several crucial applications in downstream tasks. Documents relevant to cou
arXiv:2604.22063v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly utilized in clinical reasoning and risk assessment. However, their interpretive reliability in critical
arXiv:2604.22154v1 Announce Type: cross Abstract: Emerging AI systems in behavioral health and psychiatry use multi-step or multi-agent LLM pipelines for tasks like assessing self-harm risk and screen
arXiv:2604.22546v1 Announce Type: new Abstract: Open-vocabulary scene graph generation (SGG) aims to describe visual scenes with flexible relation phrases beyond a fixed predicate set. Existing method
arXiv:2604.22082v1 Announce Type: cross Abstract: As AI systems begin to automate complex tasks, supervision increasingly relies on weaker models or limited human oversight that cannot fully verify ou
arXiv:2601.14541v4 Announce Type: replace-cross Abstract: This report distills the discussions and recommendations from the NSF Workshop on AI for Electronic Design Automation (EDA), held on December
arXiv:2604.22749v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for text generation tasks from everyday use to high-stakes enterprise and government applications, in
arXiv:2604.22180v1 Announce Type: cross Abstract: Large language model (LLM) based listwise reranking has emerged as the dominant paradigm for achieving state-of-the-art ranking effectiveness in infor
arXiv:2604.22597v1 Announce Type: new Abstract: Recent advancements in large language models have led to significant improvements across various tasks, including mathematical reasoning, which is used
arXiv:2604.22026v1 Announce Type: new Abstract: AI research pipelines now produce a growing share of publishable academic output, including work that meets existing peer-review standards for quality a
arXiv:2602.18734v2 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) has demonstrated strong effectiveness in knowledge-intensive tasks by grounding language generation in ex
arXiv:2603.26041v3 Announce Type: replace Abstract: In recent years, GUI visual agents built upon Multimodal Large Language Models (MLLMs) have demonstrated strong potential in navigation tasks. Howev
arXiv:2604.22662v1 Announce Type: cross Abstract: Shapley values are a cornerstone of explainable AI, yet their proliferation into competing formulations has created a fragmented landscape with little
arXiv:2604.22310v1 Announce Type: new Abstract: Privacy-Preserving Image Queries (PPIQ) are an emerging mechanism for cloud-based visual localization, enabling pose estimation from obfuscated features
arXiv:2604.22360v1 Announce Type: new Abstract: Neural activation coverage (NAC) is a recently-proposed technique for out-of-distribution detection and generalization. We build upon this promising fou
@robertskmiles @GaryMarcus “fails less often than a human does” is a terrible metric. We build deterministic software and test it to destruction to ensure it’s 99.99999 reliable . That’s been the basi
arXiv:2604.22118v1 Announce Type: new Abstract: Optical motion capture (mocap) systems are widely used for ground-truth capture in AR/VR, SLAM and robotics datasets. These datasets require extrinsic c
arXiv:2604.22405v1 Announce Type: new Abstract: K-plane clustering (KPC), hyperplane clustering, and mixture regression all essentially fall within the same class of problems. This problem can be conc
arXiv:2604.22040v1 Announce Type: new Abstract: Localization for autonomous vehicles on highways remains under-explored compared to urban roads, and state-of-the-art methods for urban scenes degrade w
arXiv:2604.22520v1 Announce Type: new Abstract: Large Language Models (LLMs) have achieved remarkable performance in Machine Translation (MT), but deploying them at scale remains prohibitively expensi
This post compares TensorRT-LLM and llama.cpp (GGUF) as inference frameworks for running coding agents like Cline and RooCode on RTX 5090 GPUs, examining the tradeoff between inference speed and VRAM
This post documents a technical demonstration of running the large Qwen3.5-397B-A17B model across distributed hardware using llama.cpp with advanced networking protocols. The approach leverages 4-bit
Safety and innovation are not mutually exclusive: for many companies, especially in high-trust industries, AI’s risks are also a hindrance to adoption. In this op-ed in the @FT, I underscore that Euro
Sam Altman cannot be trusted. • The OpenAI board fired him because he was not always honest with them. They said he should not control powerful AI. • A major report talked to over 100 people and saw s
arXiv:2604.22162v1 Announce Type: new Abstract: Automated sports analysis demands robust multi-object tracking (MOT), yet segmentation-based methods often struggle with mask errors and ID switches in
Paresh Dave / Wired: San Francisco public records: in 2024, Salesforce and Airbnb were among the top tech spenders in the city's 10B program, which lets them hire police officers — A recent attack on
Scam Altman Interesting how it works Elon puts up his own money, rounds up the absolute best AI talent on the planet, leverages every connection he has to secure serious resources, and launches OpenAI
Scam Altman and Greg Stockman stole a charity. Full stop. Greg got tens of billions of stock for himself and Scam got dozens of OpenAI side deals with a piece of the action for himself, Y Combinator s
Scam Altman didn’t tell the OpenAI board that he OWNED the OpenAI Startup Fund. Altman lied in congressional testimony that he didn’t have financial gain from OpenAI. Ex-board member of OpenAI calls S
Scam Altman owned the OpenAI Startup fund while simultaneously lying to the world that he didn’t financially benefit from OpenAI The main difference between Elon Musk and Scam Altman: Elon Musk actual
arXiv:2509.25003v2 Announce Type: replace-cross Abstract: Membership inference attacks (MIAs) against Diffusion Models (DMs) raise pressing privacy concerns by revealing whether a sample was part of t
arXiv:2503.12507v3 Announce Type: replace Abstract: Despite their success, Segment Anything Models (SAMs) experience significant performance drops on severely degraded, low-quality images, limiting th
arXiv:2603.29171v3 Announce Type: replace Abstract: Accurate segmentation of brain tissues such as gray matter and white matter from magnetic resonance imaging is essential for studying brain anatomy,
arXiv:2604.22374v1 Announce Type: new Abstract: Sign language translation (SLT) converts continuous sign videos into spoken-language text, yet it remains challenging due to the intrinsic modality mism
arXiv:2604.22338v1 Announce Type: cross Abstract: Depthwise separable convolutional (DSConv) layers have been successfully applied to deep learning (DL)-based joint source-channel coding (JSCC) scheme
arXiv:2511.17388v2 Announce Type: replace Abstract: Position information is essential for language modeling. In softmax transformers, Rotary Position Embeddings (extit{RoPE}) encode positions through
arXiv:2511.14427v3 Announce Type: replace-cross Abstract: Effective contact-rich manipulation requires robots to synergistically leverage vision, force, and proprioception. However, Reinforcement Lear
arXiv:2604.22269v1 Announce Type: cross Abstract: This paper presents a semantic-enhanced receiver framework for transmitting natural language sentences over noisy wireless channels using multiple sho
arXiv:2603.02709v2 Announce Type: replace-cross Abstract: We propose a novel framework for sensory-aware sequential recommendation that enriches item representations with linguistically extracted sens
German robotics startup Sereact GmbH announced today that it has raised 110 million in new funding to scale up its artificial intelligence “robotic brain” platform and expand into the U.S. Founded in
arXiv:2510.05971v3 Announce Type: replace Abstract: The generalization of the Transformer architecture via MetaFormer has reshaped our understanding of its success in computer vision. By replacing sel
arXiv:2604.22134v1 Announce Type: new Abstract: Large Language Models (LLMs) have been widely explored in educational scenarios. We identify a critical vulnerability in current educational LLMs, pedag
arXiv:2604.22072v1 Announce Type: cross Abstract: Federated learning (FL) aggregation on serverless platforms faces a hard scalability ceiling: existing architectures (lambda-FL, LIFL) partition clien
arXiv:2604.22027v1 Announce Type: cross Abstract: One of the most common complaints about large language models (LLMs) is their prompt sensitivity -- that is, the fact that their ability to perform a
arXiv:2604.22170v1 Announce Type: new Abstract: Recommender Systems~(RS) have been shown to be vulnerable to injective attacks, where attackers inject limited fake user profiles to promote the exposur
.@shaunmmaguire says Elon Musk’s X acquisition was in service of civilizational-scale missions. 'I truly believe, like in my soul, that he is trying to help humanity.' 'He has these goals. Like back u
arXiv:2509.24004v2 Announce Type: replace Abstract: Generating high-fidelity 3D head avatars from a single image is challenging, as current methods lack fine-grained, intuitive control over expression
arXiv:2604.22065v1 Announce Type: new Abstract: We present Selective Non-Gaussian Refinement (SNGR), a SLAM framework that augments iSAM2 with targeted nested sampling on windows where Gaussian approx
Sam Altman expresses satisfaction with the positive reception of OpenAI's 5.5 release, highlighting that developer feedback and builders finding value in OpenAI's tools is particularly rewarding to hi
arXiv:2604.22355v1 Announce Type: new Abstract: Classical ReLU-based Input Convex Neural Networks (ICNNs) are equivalent to the optimal value functions of Linear Programming (LP). This intrinsic struc
arXiv:2604.21984v1 Announce Type: new Abstract: We introduce Soft Anisotropic Diagrams (SAD), an explicit and differentiable image representation parameterized by a set of adaptive sites in the image
arXiv:2604.22558v1 Announce Type: cross Abstract: As Multimodal Large Language Models (MLLMs) mature, GUI agents are evolving from static interactions to complex navigation. While Reinforcement Learni
arXiv:2604.22080v1 Announce Type: new Abstract: LLM-based agents are rapidly being adopted for scientific data analysis, automating tasks once limited by human time and expertise. This capability is o
arXiv:2604.22038v1 Announce Type: new Abstract: We define and investigate source-modality monitoring -- the ability of multimodal models to track and communicate the input source from which pieces of
Zac Bowden / Windows Central: Sources detail Microsoft's “Windows K2”, an ongoing initiative to address major Windows 11 user complaints about AI features, OS bloat, performance, and more — Microsoft