Search: “gemini”

arXiv:2605.00969v1 Announce Type: cross Abstract: We present MedMosaic, a medical audio question-answering dataset designed to benchmark language and audio reasoning models under realistic clinical co

arXiv:2605.02881v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models aim to provide a single generalist controller for robots, but today's systems fall short on the criteria that matter

arXiv:2605.01630v1 Announce Type: new Abstract: Rankings produced by holistic LLM-as-a-judge scoring are sensitive to the bias of the chosen judge model. We show that switching to binary rubric scorin

The agentic era is here, and the public sector is at the forefront of leading this transformation.At Google Cloud Next ’26, it was clear that academia and public sector organizations are no longer jus

arXiv:2605.01077v1 Announce Type: new Abstract: Brazil's Unified Health System (SUS) relies on official clinical guidelines that define diagnostic criteria, treatments, dosages, and monitoring procedu

arXiv:2605.02398v1 Announce Type: cross Abstract: As frontier AI models are deployed in high-stakes decision pipelines, their ability to maintain metacognitive stability -- knowing what they do not kn

arXiv:2605.01512v1 Announce Type: new Abstract: Grounding traffic accidents in real CCTV footage is a rare-event problem where training on labeled accident video is often prohibited, yet accurate join

arXiv:2605.01662v1 Announce Type: new Abstract: Large vision-language models (VLMs) have advanced multimodal tasks such as video question answering (QA). However, VLMs face the challenge of selecting

arXiv:2605.00647v1 Announce Type: new Abstract: Automated pediatric electrocardiogram (ECG) diagnosis remains challenging because models trained predominantly on adult data suffer from substantial cro

arXiv:2601.06600v2 Announce Type: replace Abstract: Short-video platforms have become major channels for misinformation, where deceptive claims frequently leverage visual experiments and social cues.

Orchestration is no longer just about moving data; it is about governing enterprise intelligence. To reflect our deep commitment to and embrace of open-source software, we shared earlier that Cloud Co

Neural networks were declared scientifically dead in 1987. A French PhD student bet his entire career on them anyway ~ and won. 🤯 >Meet Yann LeCun 🇫🇷 >Paris-born. PhD from Sorbonne in 1987. >Joined Be

arXiv:2604.26969v1 Announce Type: cross Abstract: Modern large-scale recommendation systems are typically constructed as multi-stage pipelines, encompassing pre-ranking, ranking, and re-ranking phases

arXiv:2604.27006v1 Announce Type: cross Abstract: Context: Study screening in systematic literature reviews is costly, inconsistency-prone, and risk-asymmetric, since false negatives can compromise va

arXiv:2604.27974v1 Announce Type: new Abstract: Despite the rapid progress of large vision-language models (LVLMs), fine-grained, state-conditioned GUI interaction remains challenging. Current evaluat

arXiv:2604.27393v1 Announce Type: new Abstract: Recent progress in multimodal large language models (MLLMs) has brought AI capabilities from static offline data processing to real-time streaming inter

arXiv:2604.28123v1 Announce Type: cross Abstract: The standard post-training recipe for large multimodal models (LMMs) applies supervised fine-tuning (SFT) on curated demonstrations followed by reinfo

RL is a bit of a double edged sword: in known territory performance increases, but in unknown territory the model tends to hallucinate that it is performing a completely different task it was trained

arXiv:2604.26954v1 Announce Type: cross Abstract: Strategic model selection and reasoning settings are more effective than ensembling for optimizing automated scoring with large language models (LLMs)

arXiv:2604.27274v1 Announce Type: new Abstract: As AI transitions toward multi-agent systems (MAS) to solve complex workflows, research paradigms operate on the axiomatic assumption that agent collabo

The new Grok comes in below the latest Chinese open weights models, Grok 4 was at the frontier when released. (& Artificial Analysis: please stop using GDPval-AA which is not a useful test of anything

arXiv:2604.27629v1 Announce Type: new Abstract: We present WaferSAGE, a framework for wafer defect visual question answering using small vision-language models. To address data scarcity in semiconduct

音声AIの素早さと賢さを両立できるか？ 私たち人間は会話の中で、言いたいことを全部まとめてから話し始めるのではなく、話しながら考えを整理していきます。応答の速い Speech-to-Speech モデルは、この「話しながら考える」を実現しましたが、そのぶん思考が浅くなりがちです。かといって知識豊富な LLM を挟むカスケード型では、遅延が生じるため「話しながら」が成立しません。 そこで Sakan

arXiv:2604.26328v1 Announce Type: cross Abstract: The rapid advancement of large language models (LLMs) presents new security challenges, particularly in detecting machine-generated text used for misi

arXiv:2604.26173v1 Announce Type: cross Abstract: An effective way to scale up test-time compute of large language models is to sample multiple responses and then select the best one, as in Grok Heavy

Forget goblins, things that GPT-5.5 really likes in its fiction: lighthouses, the ocean, maps, bells, clock towers with bells that ring impossible times, Mira Vale, resonances and echoes (Claude and G

arXiv:2604.26880v1 Announce Type: new Abstract: Patient portals now give individuals direct access to their electronic health records (EHRs), yet access alone does not ensure patients understand or ac

arXiv:2507.01544v2 Announce Type: replace Abstract: Predictive applications of machine learning often rely on small (sub 1 Bn parameter) specialized models tuned to particular domains or modalities. S

Whoever controls the agentic control plane controls enterprise AI. Google LLC just showed up to that fight with everything it has. The company claiming it can own the full stack arrived at Google Clou

arXiv:2512.16918v3 Announce Type: replace Abstract: Recent advances have shown that multimodal large language models (MLLMs) benefit from multimodal interleaved chain-of-thought (CoT) with vision tool

arXiv:2601.03266v2 Announce Type: replace Abstract: Large language models (LLMs) have rapidly advanced in clinical decision-making, yet the deployment of proprietary systems is hindered by privacy con

Proactive agent that thinks and acts like you. Multiplayer AI Brain for teams. Proper GUI for commanding 50 agents. http://Sauna.ai is all three. Sauna goes live today. First 2000 people, use access c

We’re excited to introduce KAME: Tandem Architecture for Enhancing Knowledge in Real-Time Speech-to-Speech Conversational AI, accepted at #ICASSP2026! 🐢 Blog https://pub.sakana.ai/kame/ Paper https://

arXiv:2604.24589v1 Announce Type: new Abstract: Vision-language models (VLMs) are increasingly proposed as general-purpose tools for scientific data interpretation, yet their reliability on real astro

arXiv:2604.22766v1 Announce Type: cross Abstract: In this report, we review the current state of methodologies to forecast the arrival of artificial general intelligence, assess their reliability, and

arXiv:2604.24441v1 Announce Type: new Abstract: Autonomous agents capable of navigating Graphical User Interfaces (GUIs) hold the potential to revolutionize digital productivity. However, achieving tr

arXiv:2512.21110v3 Announce Type: replace Abstract: Current Large Language Models (LLMs) safety approaches focus on explicitly harmful content while overlooking a critical vulnerability: the inability

arXiv:2604.24512v1 Announce Type: new Abstract: As LLM agents transition to autonomous digital coworkers, maintaining deterministic goal-directedness in non-linear multi-turn conversations emerged as

arXiv:2604.24697v1 Announce Type: new Abstract: Discovering causal regularities and applying them to build functional systems--the discovery-to-application loop--is a hallmark of general intelligence,

arXiv:2604.23057v1 Announce Type: new Abstract: We investigate whether explicit belief graphs improve LLM performance in cooperative multi-agent reasoning. Through 3,000+ controlled trials across four

arXiv:2502.04424v4 Announce Type: replace-cross Abstract: With the integration of multimodal large language models (MLLMs) into robotic systems and AI applications, embedding emotional intelligence (E

Enterprise AI transformation has a new home: the boardroom. Across financial services, CEOs are now demanding results, not more roadmaps. As Google Cloud Next 2026 packed Las Vegas with announcements

arXiv:2604.23366v1 Announce Type: new Abstract: Autonomous multi-agent LLM systems are increasingly deployed to investigate operational incidents and produce structured diagnostic reports. Their trust

I used to think the best way to come up with ways to use AI was to think about a painpoint or a problem and see if AI can make it better. I no longer think that. Why? Because that put every person int

arXiv:2604.24110v1 Announce Type: cross Abstract: Multi-agent LLM tutoring systems improve response quality through agent specialization, but each student query triggers several concurrent API calls w

arXiv:2604.22829v1 Announce Type: new Abstract: The digital transformation of industrial manufacturing increasingly relies on the ability of autonomous robots to interact with legacy infrastructure, p