Search: “meta”

arXiv:2605.27628v1 Announce Type: new Abstract: As autonomous and agentic AI systems scale in robotic and human-machine environments, managing hallucination and persistent but unjustified action remai

arXiv:2605.27477v1 Announce Type: cross Abstract: Causal-discovery algorithms return a directed graph, yet provide no principled means of distinguishing edge directions identified by the data from tho

just imagine what will happen to the economy and people’s retirement funds if these projections from FT are correct. brace for bailouts. The AI numbers are starting to look very ugly. Even under 'best

arXiv:2605.28173v1 Announce Type: new Abstract: End-to-end manga generation is a structured visual storytelling task that requires story decomposition, recurring character and scene grounding, page la

arXiv:2605.28629v1 Announce Type: new Abstract: Recent advancements in multimodal large language models (MLLMs) have shown exceptional potential in enabling mobile-using agents to autonomously execute

arXiv:2601.18006v2 Announce Type: replace Abstract: We present PEAR (Pairwise Evaluation for Automatic Relative Scoring), a supervised quality estimation (QE) metric family that reframes reference-fre

arXiv:2605.27527v1 Announce Type: cross Abstract: Astrophysical observations taken from Earth are subject to weather, environmental, and scientific constraints that lead to sparse, irregular light cur

arXiv:2509.25582v3 Announce Type: replace Abstract: In-context reinforcement learning (ICRL) is an emerging RL paradigm where an agent, after pretraining, can adapt to out-of-distribution test tasks w

arXiv:2602.02259v2 Announce Type: replace-cross Abstract: Latent action models (LAMs) offer a promising path to pre-training embodied agents on large amounts of action-free video. They infer latent ac

arXiv:2605.28210v1 Announce Type: new Abstract: Drawing on Ullmann-Margalit's concept of opting (transformative, irrevocable, and shadowed by foreclosed alternatives), we show that current AI systems

arXiv:2605.28710v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used for the automatic evaluation of generated text, yet most prior work focuses on English. Despite the

arXiv:2605.27659v1 Announce Type: cross Abstract: Due to limited resources and public safety concerns, deep reinforcement learning (RL) agents for many cyber-physical systems (e.g., autonomous vehicle

arXiv:2605.28227v1 Announce Type: new Abstract: Speech translation models are increasingly capable of preserving speech-specific information (e.g., speaker gender, prosody, and emphasis), yet evaluati

arXiv:2605.26146v1 Announce Type: cross Abstract: Organizations increasingly deploy separate purpose-built AI tools across professional domains, often hiring domain specialists for each, recreating th

arXiv:2605.27044v1 Announce Type: new Abstract: Early battery degradation trajectory forecasting (BDTF), which predicts the full-life state-of-health trajectory from early operational data, is critica

arXiv:2605.27073v1 Announce Type: new Abstract: Adaptive orchestration of heterogeneous agents requires making sequential delegation decisions under uncertain and evolving agent behaviour, e.g., coord

arXiv:2605.27246v1 Announce Type: cross Abstract: This position statement looks back on two decades of work on shallow embeddings of non-classical logics in classical higher-order logic (HOL), a line

arXiv:2605.26454v1 Announce Type: new Abstract: Large language models (LLMs) learn undesirable properties during pretraining, including dangerous knowledge and toxic text generation. Just as post-trai

arXiv:2503.08600v3 Announce Type: replace Abstract: We introduce NSF-SciFy, a comprehensive dataset of scientific claims and investigation proposals extracted from National Science Foundation award ab

arXiv:2507.16679v3 Announce Type: replace-cross Abstract: In-Context Learning has shown great potential for aligning Large Language Models (LLMs) with human values, helping reduce harmful outputs and

arXiv:2605.27276v1 Announce Type: new Abstract: Humans are the bottleneck in building and improving AI. Both the models and the agents that wrap them are written, tuned, and corrected by people. The l

arXiv:2605.24410v1 Announce Type: new Abstract: Graph few-shot learning, which aims to classify nodes from novel classes with only a few labeled examples, is a widely studied problem in graph learning

arXiv:2605.25454v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly being used for emotional support. They are also being developed for formal therapy purposes. However, LL

arXiv:2605.25489v1 Announce Type: new Abstract: Visual analytics (VA) workflows are inherently complex, involving data transformation, feature engineering, visual representation, and human interpretat

arXiv:2605.23931v1 Announce Type: new Abstract: The formal verification of operating system kernels requires precise specifications that capture the intended behavior of system calls. Writing these sp

arXiv:2508.09801v3 Announce Type: replace-cross Abstract: Malware detection in modern computing environments demands models that are not only accurate but also interpretable and robust to evasive tech

arXiv:2605.24614v1 Announce Type: cross Abstract: Large language model (LLM) unlearning has emerged as a crucial post-hoc mechanism for privacy protection and AI safety, yet auditing whether target kn

arXiv:2605.25004v1 Announce Type: cross Abstract: Inferring network-wide traffic states from sparse observations with high accuracy and trustworthy uncertainty quantification is essential for intellig

arXiv:2605.25050v1 Announce Type: cross Abstract: Integrating multimodal datasets in clinical oncology is frequently hindered by high dimensionality and blockwise missingness, where entire data source

Nine reasons why I warned OpenAI might fail and turn out to be the WeWork of AI, from two years ago. 9 reasons that OpenAI could someday be seen as the WeWork of AI: 👉 Lots of competitors are catching

arXiv:2605.24775v1 Announce Type: new Abstract: Operating LLMs as coordinated multi-agent research systems over multi-hour runs surfaces failure modes that single-shot evaluation cannot: upstream prov

arXiv:2605.24326v1 Announce Type: cross Abstract: The rapid scaling of large language model training requires distributing GPU resources across multiple data center buildings and regions. We refer to

this logic from 2024 held up pretty well considering all that’s changed. 9 reasons that OpenAI could someday be seen as the WeWork of AI: 👉 Lots of competitors are catching up. 👉 OpenAI has been force

arXiv:2605.23899v1 Announce Type: new Abstract: Language agents increasingly improve by reusing skills -- structured procedural artifacts distilled from past experience. In particular, domain-level an

Listen to my conversation with @jerryjliu0 of @llama_index on Spotify: https://bit.ly/3v1R0Tu Apple: https://bit.ly/4bTCwpD Youtube: https://bit.ly/3uXthnv LinkedIn: http://bit.ly/3Xs8GQP Website: htt

arXiv:2605.23057v1 Announce Type: cross Abstract: ModeSwitch-LLM is a lightweight request-boundary controller for improving single-GPU large language model inference efficiency by routing each request

arXiv:2605.23411v1 Announce Type: cross Abstract: Test-time adaptation (TTA) effectively counters distribution shifts but exposes models to adversarial manipulation via the unlabeled test stream. Exis

arXiv:2601.03260v2 Announce Type: replace-cross Abstract: AI agents have seen widespread adoption in information retrieval for scientific research, giving rise to tools such as Deep Research. However,

arXiv:2603.10453v2 Announce Type: replace Abstract: This study proposes a multi-resolution Convolutional Long Short-Term Memory (ConvLSTM) ensemble framework that leverages diverse temporal input reso

It’s no longer just AI companies & their founders being sued over AI training - individual researchers are now being sued, too. In a new lawsuit, two authors allege that Guillaume Lample, while an AI

La plupart des grandes boîtes sont des organisations zombies. Voici pourquoi. Dans League of Legends, ton rang n'est pas un titre. C'est une mesure continue. Tu es Master parce que tu joues comme un M

arXiv:2605.20456v1 Announce Type: cross Abstract: Agentic AI coding systems can inspect repositories, plan implementation steps, edit files, call tools, run tests, and submit pull requests. These capa

arXiv:2605.22123v1 Announce Type: new Abstract: Designing reward functions that generalize beyond controlled laboratory settings remains a fundamental challenge in reinforcement learning for robotics.

arXiv:2605.22020v1 Announce Type: new Abstract: Feed-forward 3D Gaussian Splatting (3DGS) models offer fast single-pass reconstruction,but scaling them to match per-scene optimization quality is funda

arXiv:2410.12771v2 Announce Type: replace-cross Abstract: The ability to discover new materials with desirable properties is critical for numerous applications from helping mitigate climate change to

Biomedical AI may be headed for a replication crisis. (This work below is not about AI-generated reports; it’s about studies of biomedicine that use ML in their methods, and how they are evaluted.) In