Knowledge catalogue
arXiv:2605.20278v1 Announce Type: cross Abstract: Long-form image captioning exposes a reward granularity problem in RL: captions are judged as whole sequences, while the important errors occur at the
We just announced the first release of Datasette Agent, a new extensible AI assistant for Datasette. I've been working on my LLM Python library for just over three years now, and Datasette Agent repre
Google just revealed Omni, personalized cross-device intelligence, and Spark agents at I/O 2025. I sat down with CEO Sundar Pichai to figure out what comes next: 1:46 Omni: 'Nano Banana for video' 4:5
arXiv:2506.16950v2 Announce Type: replace Abstract: Out-of-distribution (OOD) robustness is a desired property of computer vision models. Improving model robustness requires high-quality signals from
arXiv:2605.21465v1 Announce Type: new Abstract: In model-driven engineering, metamodel evolution leads to the need to adapt corresponding grammars to maintain consistency, which typically requires ted
arXiv:2605.20211v1 Announce Type: new Abstract: Educational videos are a cornerstone of remote and blended learning. However, learners' fluctuating attention remains a significant barrier to effective
🦔Microsoft canceled its internal Claude Code licenses this week after token-based billing made the cost untenable, even for a company with effectively infinite cloud resources. Uber's CTO sent an inte
arXiv:2605.20668v1 Announce Type: new Abstract: With the advancement of AI capabilities, AI reviewers are beginning to be deployed in scientific peer review, yet their capability and credibility remai
arXiv:2605.20584v1 Announce Type: new Abstract: Mobile app marketplaces require developers to disclose standardized content rating descriptors (CRDs) to inform users about potentially sensitive or res
arXiv:2605.20809v1 Announce Type: new Abstract: While Large Language Models (LLMs) demonstrate remarkable performance on zero-shot annotation tasks, they often struggle with the specialized convention
arXiv:2605.20626v1 Announce Type: new Abstract: We present the University of Florida Gators submission to the AmericasNLP 2026 shared task on cultural image captioning for Indigenous languages. Our tw
Try Composer 2.5 New CursorBench results just dropped. Two big takeaways. Composer 2.5 is way better than most people think. 63.2% score at $0.55 per task. Nearly matching Opus 4.7 Max and GPT 5.5 Ext
arXiv:2605.19149v1 Announce Type: new Abstract: Agents operating with computer and Web use inevitably encounter errors: inaccessible webpages, missing files, local and remote misconfigurations, etc. T
arXiv:2605.19069v1 Announce Type: cross Abstract: Code-switching -- the natural alternation between two languages within a single utterance -- represents one of the most challenging and under-studied
arXiv:2601.16823v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) exhibit remarkable capabilities, yet it remains unclear to what extent these reflect sophisticated recall or genu
arXiv:2605.18915v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) are vulnerable to jailbreak attacks, which can elicit harmful responses from MLLMs. Many MLLMs support multi-
For centuries, the scientific method has been our best tool for progress. But today, there’s so much data out there that it’s impossible for any one researcher to connect all the dots. We want to fix
Anu Adegbola / Search Engine Land: Google says it is testing new ad formats in search results and AI Mode, including Conversational Discovery ads, Highlighted Answers, and AI-powered Shopping ads — Go
Got to play with a little of this before launch as well. My experience as a social scientist was that it was more bioscience focused right now, but I think Google has been the leading lab in releasing
arXiv:2605.19027v1 Announce Type: new Abstract: Medical foundation models (MedFMs) have emerged as transformative tools in healthcare, demonstrating capabilities across diverse clinical applications.
arXiv:2605.20128v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly integrated into high-stakes decision-making. Inspired by the theory of inattentional blindness in human co
arXiv:2605.19633v1 Announce Type: cross Abstract: Can a single LLM-based optimization system match specialized tools across fundamentally different domains? We show that when optimization problems are
arXiv:2605.19776v1 Announce Type: new Abstract: Pairwise preferences and pointwise ratings are the two dominant annotation protocols in image aesthetic assessment (IAA), yet existing benchmarks adopt
arXiv:2605.19193v1 Announce Type: new Abstract: Multi-agent LLM debate improves factuality and reasoning, but most recipes pick a fixed round count, over-spending on easy items and under-spending on h
We're excited to be an official shoutout at the Google I/O Developer Keynote 🔥 @llama_index is building the document infrastructure for AI agents, and we plan to integrate even more heavily with both
arXiv:2601.22569v2 Announce Type: replace-cross Abstract: Large language model (LLM) based agents are increasingly used to automate financial transactions, yet their reliance on contextual reasoning e
arXiv:2605.17903v1 Announce Type: new Abstract: We automatically generate feedback causal fuzzy cognitive maps (FCMs) from text by teaching large-language-model agents to break the text into overlappi
arXiv:2605.18504v1 Announce Type: new Abstract: Machine Translation (MT) for Ancient Greek (AG) to Modern Greek (MG) is a low-resource task, constrained by the lack of large-scale, high-quality parall
arXiv:2605.17324v1 Announce Type: cross Abstract: Clarification-seeking behavior is widely regarded as a desirable property of LLM agents, enabling them to resolve ambiguity before acting on underspec
arXiv:2605.17079v1 Announce Type: cross Abstract: LLMs are increasingly used as ``digital consumers'' to simulate public opinion, pre-test marketing decisions, and anticipate audience response. Howeve
arXiv:2605.18327v1 Announce Type: new Abstract: AI agents deployed into SRE workflows currently derive their understanding of environment state from raw observability telemetry at query time, paying a
arXiv:2602.18895v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have shown promise in translating model-based explanations into human-readable narratives. This study evaluates w
arXiv:2511.21654v2 Announce Type: replace Abstract: We introduce EvilGenie, a benchmark for reward hacking in programming settings. We source problems from LiveCodeBench and create an environment in w
arXiv:2605.16630v1 Announce Type: cross Abstract: Hybrid local--cloud agents enrich user requests with context from persistent working state before delegating capability-intensive subtasks to a cloud
Fascinatingly Antigravity is actually the best tool so far at providing this sort of transparency, doing something by default that Codex and Code do not: offering a summary of exactly what it did at t
For those saying 'the tomato sauce blood from the sword wound that flying Shakespeare inflicted on the pizza robot while the otters discussed Spirit Airlines wasn't thick enough' or whatever... this w
arXiv:2605.16475v1 Announce Type: cross Abstract: Generative artificial intelligence (GenAI), based on large-language models (LLMs), such as ChatGPT, has taken organizations, academia, and the public
Google Search is entering the next phase of its AI evolution. During Google I/O 2026, the company showed off a reimagined search box that makes it easier to flow between AI Overviews, the AI-generated
arXiv:2605.16385v1 Announce Type: cross Abstract: Geometric problem solving, as a typical multimodal reasoning problem, has attracted much attention and made great progress recently, however most of w
arXiv:2605.18111v1 Announce Type: new Abstract: Recent advancements in Large Language Models (LLMs) and Large Vision Language Models (LVLMs) have enabled general-purpose systems to demonstrate promisi
arXiv:2605.17792v1 Announce Type: new Abstract: Calibrating distributed hydrologic models is a critical bottleneck across operational water resources management - streamflow prediction, reservoir oper
arXiv:2605.17986v1 Announce Type: cross Abstract: AI agents such as OpenClaw are increasingly deployed in local workflows with access to external tools. This creates indirect prompt-injection (IPI) ri
arXiv:2510.10528v3 Announce Type: replace Abstract: Large reasoning models (LRMs) have demonstrated remarkable proficiency in tackling complex tasks through step-by-step thinking. However, this length
arXiv:2605.18239v1 Announce Type: cross Abstract: Large Language Models (LLMs) remain vulnerable to jailbreak attempts that circumvent safety guardrails. We investigate whether multi-turn conversation
arXiv:2605.16409v1 Announce Type: cross Abstract: Optical character recognition (OCR) and multilingual text understanding remain major failure modes of multimodal large language models (MLLMs), partic
open sourcing Marlin-2B 🐟 a tiny VLM to extract structured information from videos Marlin is finetuned for two questions devs want to ask in their videos: what is happening, and when? Best open model
arXiv:2605.17610v1 Announce Type: cross Abstract: The rapid growth of online video platforms and AI-generated content has made reliable video guardrails a key challenge for safety and real-world deplo
arXiv:2512.17843v4 Announce Type: replace-cross Abstract: By evaluating Large Language Models (LLMs) through uniform, text-only interfaces, current academic benchmarks obscure how the unique designs a
arXiv:2605.17789v1 Announce Type: cross Abstract: Memory systems for AI assistants were built for single-user dialogue and fail characteristically when applied to multi-party social group settings. Th
arXiv:2605.17062v1 Announce Type: cross Abstract: Spracklen et al. (USENIX Security '25) showed that code-generating large language models hallucinate package names that do not exist on PyPI or npm at
arXiv:2605.17691v1 Announce Type: cross Abstract: Automating the classification of negative treatment in legal precedent is a critical yet nuanced NLP task where misclassification carries significant
arXiv:2605.16481v1 Announce Type: cross Abstract: Long video understanding requires more than large context windows. It also needs a memory mechanism that decides what visual evidence to retain, keeps
arXiv:2605.16288v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used in clinical and care settings. This exploratory study investigates whether LLMs exhibit sycophantic
Google Cloud is enhancing its “agent-first” coding platform for developers with the launch of Antigravity 2.0, a new standalone desktop application that enables a full “agent-optimized” user experienc
Google is going all in on AI-driven shopping even as some competitors back off. At Google I/O, the company unveiled the latest iteration of its AI commerce tools: a 'Universal Cart' that works across
Accessing enterprise data is shifting from static reports to dynamic use by autonomous systems. To keep up, organizations must route fragmented data from SaaS, IoT, and legacy sources into secure, sca
arXiv:2605.16233v1 Announce Type: new Abstract: Can LLM agents improve decision-making through self-generated memory without gradient updates? We propose FORGE (Failure-Optimized Reflective Graduation
arXiv:2510.02453v3 Announce Type: replace-cross Abstract: Frontier language models are deployed as black-box services, where model weights cannot be modified and customization is limited to prompting.
arXiv:2505.18134v3 Announce Type: replace Abstract: Vision-language models (VLMs) have achieved strong results on coding and math benchmarks that are challenging for humans, yet their ability to perfo
arXiv:2605.16079v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) have shown significant progress in video understanding, yet they face substantial challenges in tasks requiring p