Knowledge catalogue
arXiv:2609.13057v1 Announce Type: new Abstract: Deep neural networks are expressive enough to contain worst-case targets that can be evaluated in polynomial time but cannot be learned in polynomial ti
If you are tracking agent swarms research, this one is worth reading. Between 24 May and 2 July 2026, autonomous agents running inside a timed research evaluation wrote to a third party's public wiki.
arXiv:2609.13045v1 Announce Type: new Abstract: Speech-to-speech translation (S2ST) has advanced significantly with speech LLMs, offering the potential for joint optimization and preserving non-lingui
arXiv:2606.14957v4 Announce Type: replace Abstract: Brain MRIs are routinely acquired as multiple complementary sequences with unique contrast weighting, including T1-weighed imaging (T1w) anatomic an
arXiv:2609.12469v1 Announce Type: new Abstract: False wake-up activations remain a persistent challenge in conversational AI. Speech phonetically similar to a device's wake word can produce a syntacti
arXiv:2609.12224v1 Announce Type: new Abstract: Electronic health records (EHRs) may incompletely capture patient-reported factors associated with opioid use disorder (OUD). We evaluated whether surve
arXiv:2501.04234v2 Announce Type: replace-cross Abstract: Modern artificial intelligence is supported by machine learning models (e.g., foundation models) that are pretrained on a massive data corpus
arXiv:2609.12623v1 Announce Type: cross Abstract: Full-duplex spoken dialogue models support low-latency turn taking, interruption handling, and backchanneling, yet a key capability remains underexplo
Anthropic CEO Dario Amodei says the time has come to slow down AI development and will give third-party evaluators like METR access to its models to help ensure its 'adherence to safety practices and
I agree with Dario that we need to pace the frontier. This has been a primary topic of discussions we've had at OpenAI in recent weeks. Committing to having independent evaluators with employee-like a
arXiv:2609.11318v1 Announce Type: new Abstract: Deep research agents are increasingly capable of web search, tool use, multimodal evidence analysis, and information synthesis. However, existing benchm
arXiv:2609.11532v1 Announce Type: new Abstract: Commercial text-to-image systems silently revise user prompts before generating images, a step users typically cannot disable or even see. Yet, existing
arXiv:2609.11243v1 Announce Type: new Abstract: Autonomous research agents are increasingly expected to search the literature, analyze experimental evidence, and generate scientific hypotheses. These
arXiv:2609.09212v1 Announce Type: cross Abstract: This paper presents an end-to-end evaluation framework for image-triggered command injection against computer-use agents (CUAs). The goal is to test w
arXiv:2609.10851v1 Announce Type: new Abstract: Few-shot learning is commonly evaluated under protocols that pre-train a model on a large auxiliary set whose classes are disjoint from the target episo
arXiv:2609.09647v1 Announce Type: new Abstract: Agentic systems are rapidly moving to production, where they read untrusted inputs, call tools with real permissions, and act autonomously, expanding th
arXiv:2609.09849v1 Announce Type: cross Abstract: In recent years, AI agents have evolved into capable assistants that carry out multi-step tasks in digital environments. The network systems community
arXiv:2609.10866v1 Announce Type: new Abstract: Reinforcement learning (RL) agents deployed in real-world environments are often vulnerable to adversarial perturbations in state observations, creating
arXiv:2609.11495v1 Announce Type: new Abstract: Manchu, now critically endangered, was one of the principal languages of the Qing empire (1636-1912), and its extensive archival record is increasingly
arXiv:2609.10790v1 Announce Type: cross Abstract: We present a Kubernetes Dynamic Resource Allocation (DRA) driver that makes composable CXL memory a schedulable cluster resource, and evaluate the res
arXiv:2609.11210v1 Announce Type: cross Abstract: The discovery of the EML operator, sufficient to evaluate the standard explicit purely transcendental elementary functions, has led to considerable in
arXiv:2609.11128v1 Announce Type: new Abstract: In disinformation datasets, narratives are often understood as recurring interpretive patterns that group texts under narrative labels. Recent work form
arXiv:2609.10451v1 Announce Type: new Abstract: Real-world GUI usage frequently involves workflows that span multiple devices and platforms, requiring the transfer of intermediate results, maintenance
arXiv:2609.11101v1 Announce Type: new Abstract: Dispute mediation is essential for maintaining social harmony and resilience, yet developing skilled mediators is costly and time-consuming. Existing LL
arXiv:2609.11769v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to analyze and rewrite news, yet current framing studies mainly evaluate generation, detection, or wh
arXiv:2603.23346v2 Announce Type: replace Abstract: Real-time spoken dialogue systems face a fundamental tension between latency and response quality. End-to-end speech-to-speech (S2S) models respond
arXiv:2609.11414v1 Announce Type: new Abstract: Large language models exhibit complementary strengths, motivating routing methods that dispatch each query to the most suitable model. Although existing
arXiv:2601.15645v2 Announce Type: replace Abstract: Large-scale language models (LLMs) often offer clinical judgments based on incomplete information, increasing the risk of misdiagnosis. Existing stu
arXiv:2609.09964v1 Announce Type: new Abstract: Large Language Models (LLMs) have achieved remarkable progress across natural language processing (NLP) tasks, yet their capabilities degrade sharply fo
arXiv:2609.09578v1 Announce Type: cross Abstract: Urban planning is a real-world spatial optimization problem that requires selecting feasible actions from large candidate spaces under practical objec
arXiv:2609.09912v1 Announce Type: new Abstract: Machine learning models used in engineering are typically trained within limited operating ranges, yet reliable predictions are often required beyond th
arXiv:2609.07194v1 Announce Type: new Abstract: We present EmoMed - a multimodal medical consultation agent that adapts its responses based on users' emotional states while maintaining clinical accura
arXiv:2602.20773v2 Announce Type: replace Abstract: Purpose: Developing generalizable medical image segmentation models is challenging because imaging data are distributed across institutions and diff
arXiv:2609.09243v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) grounds a language model in retrieved documents, which reduces hallucination but creates a new attack surface: if
arXiv:2609.09022v1 Announce Type: cross Abstract: AI-assisted programming raises distinct questions about who produces code, who feels ownership of it, and who is responsible when it fails. This resea
arXiv:2609.09090v1 Announce Type: cross Abstract: Large language models (LLMs) may abandon correct positions when users push back, exhibiting a failure mode known as sycophancy. Existing evaluations t
arXiv:2609.10058v1 Announce Type: cross Abstract: Robust speech-to-text translation systems should perform reliably across diverse acoustic conditions, yet practical pipelines lack controllable tools
arXiv:2609.07629v1 Announce Type: cross Abstract: Democratizing access to the knowledge held in large corpora of tables such as data lakes is emerging as a central research challenge. Research in this
arXiv:2609.09863v1 Announce Type: new Abstract: Choosing a deep learning architecture for label-free single-cell classification remains an open question, with microscopy benchmarks reporting conflicti
arXiv:2609.06527v1 Announce Type: cross Abstract: Large language models (LLMs) have shown strong potential for translating natural-language (NL) requirements into PL/SQL programs, attracting increasin
arXiv:2609.06540v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in safety-critical applications, yet jailbreak attacks can conceal harmful intent through role-
arXiv:2609.08589v1 Announce Type: cross Abstract: Recent large language models can emit task-progress signals that agent frameworks use to decide whether a task should continue or stop, yet whether a
arXiv:2609.08226v1 Announce Type: new Abstract: Temporal graph learning models the evolution of dynamic systems, where both structural interactions and semantic states change over time. However, exist
arXiv:2609.10002v1 Announce Type: new Abstract: Deepfake detectors remain vulnerable to transfer-based black-box attacks, in which adversarial examples are generated on a source surrogate model and tr
arXiv:2609.09388v1 Announce Type: new Abstract: Brain-age prediction models are commonly evaluated by predictive accuracy, yet accurate predictions alone do not establish that a model relies on reprod
arXiv:2609.06276v1 Announce Type: new Abstract: This study evaluates pneumonia classification in chest X-rays using VGG19, MobileNetV2, ResNet50, and a custom CNN, and explores Generative Adversarial
arXiv:2609.09030v1 Announce Type: cross Abstract: Chain-of-thought reasoning provides a structured computation between a model's input and final answer. Yet it is often evaluated through endpoint accu
arXiv:2404.06349v3 Announce Type: replace Abstract: The ability to understand causality significantly impacts the competence of large language models (LLMs) in output explanation and counterfactual re
arXiv:2609.07685v1 Announce Type: new Abstract: In real-world applications, pedestrian trajectory prediction models rely on inputs from detection and tracking systems. Prior trajectory prediction benc
arXiv:2602.18613v2 Announce Type: replace Abstract: Standard reranking evaluations study how a reranker orders candidates returned by an upstream retriever. This setup couples ranking behavior with re
arXiv:2609.08117v1 Announce Type: new Abstract: Driver motion can provide cues to ongoing behavior, attention, and near-term driving intent. However, most existing driver-centric datasets focus on rec
We are excited to share that Gartner has named Google a Leader in its inaugural 2026 Magic Quadrant for Enterprise AI Assistants. In this comprehensive evaluation of top enterprise AI assistant vendor
arXiv:2609.06058v1 Announce Type: new Abstract: As vision-language models (VLMs) become increasingly capable and are deployed in consequential real-world settings, they must evaluate evidence independ
arXiv:2609.06976v1 Announce Type: new Abstract: As medical wearables become integrated into daily chronic disease care, effectively interpreting longitudinal monitoring data is essential for patients
arXiv:2505.17966v3 Announce Type: replace-cross Abstract: This paper evaluates single-view mesh reconstruction models for their potential in enabling instant digital twin creation for real-time planni
arXiv:2609.08399v1 Announce Type: new Abstract: Universal machine-learning interatomic potentials (u-MLIPs) aim to generalize across diverse configurations. Benchmarks enable reproducible evaluation b
arXiv:2609.07135v1 Announce Type: new Abstract: An embodied kitchen assistant must do more than recognize food in isolated frames. It must track ingredient states over time and integrate visual observ
arXiv:2609.07655v1 Announce Type: new Abstract: Closed-loop AI scientists can generate candidate designs at low marginal computational cost, whereas reliable feedback may require wet-lab synthesis, ch
arXiv:2405.18253v4 Announce Type: replace Abstract: Data plays a central role in advancements in modern artificial intelligence, with high-quality data emerging as a key driver of model performance. T
arXiv:2609.06078v1 Announce Type: new Abstract: This report summarizes the 8th Large-scale Video Object Segmentation (LSVOS) Challenge, held in conjunction with ECCV 2026. The challenge evaluates vide