Knowledge catalogue
arXiv:2603.07900v2 Announce Type: replace Abstract: Foundation models pretrained on electronic health records (EHR) have demonstrated zero-shot clinical prediction capabilities by generating synthetic
At Google Cloud Next ‘26, we unveiled the blueprint for the Agentic Enterprise, sharing our eighth-generation TPUs, Gemini Enterprise Agent Platform, a fully reimagined Agentic Data Cloud, Workspace I
arXiv:2503.16492v3 Announce Type: replace-cross Abstract: ffective Human-Robot Interaction (HRI) is crucial for enhancing accessibility and usability in real-world robotics applications. However, exis
arXiv:2505.18991v3 Announce Type: replace Abstract: Pansharpening seeks to fuse high-resolution panchromatic (PAN) and low-resolution multispectral (LRMS) images into a single image with both fine spa
arXiv:2605.17201v1 Announce Type: cross Abstract: Social engineering attacks exploit human trust rather than software vulnerabilities, making them difficult to detect using conventional filters. We pr
arXiv:2505.20650v5 Announce Type: replace-cross Abstract: Accurate interpretation of numerical data in financial reports is critical for markets and regulators. Although XBRL (eXtensible Business Repo
arXiv:2605.18346v1 Announce Type: cross Abstract: Recent advances in autoregressive video diffusion have enabled sequential and streaming video generation. However, long-horizon generation requires in
arXiv:2603.00975v2 Announce Type: replace-cross Abstract: Deployed text-to-image diffusion models increasingly require post-hoc concept unlearning for copyright claims, artist opt-outs, safety updates
arXiv:2605.17759v1 Announce Type: new Abstract: To circumvent the inherent fidelity bottlenecks and optimization misalignment of VAE-based latent diffusion, pixel-space diffusion models have emerged a
arXiv:2604.01404v2 Announce Type: replace-cross Abstract: How do language models retrieve entity-specific facts from their parameters? We investigate this question by searching for sparse, entity-sele
arXiv:2603.17588v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are currently applied to scientific paper evaluation by assigning an absolute score to each paper independently.
arXiv:2605.18721v1 Announce Type: cross Abstract: Post-training has split large language model (LLM) alignment into two largely disconnected tracks. Online reinforcement learning (RL) with verifiable
arXiv:2512.23752v5 Announce Type: replace-cross Abstract: Recent work has shown that small transformers trained in controlled 'wind-tunnel'' settings can implement exact Bayesian inference, and that t
arXiv:2605.18663v1 Announce Type: new Abstract: As LLM benchmarks saturate, the evaluation community has pursued two strategies to increase difficulty: escalating knowledge demands (GPQA, HLE) or remo
For a quarter century, the Google search box has been one of the most recognizable interfaces in computing: a thin white rectangle, a blinking cursor, a few typed words, and a list of blue links. On T
arXiv:2512.22473v5 Announce Type: replace-cross Abstract: Transformers empirically perform precise probabilistic reasoning in carefully constructed ``Bayesian wind tunnels'' and in large-scale languag
arXiv:2605.16598v1 Announce Type: cross Abstract: Agentic retrieval improves multi-hop question answering by giving language models autonomy to iteratively gather evidence. Recent work augments these
arXiv:2605.16873v1 Announce Type: new Abstract: Diffusion priors have recently demonstrated strong capability in enhancing the quality of sparse-view 3D reconstruction by augmenting training views at
arXiv:2605.17734v1 Announce Type: new Abstract: Equipping LLM agents with reusable skills derived from past experience has become a popular and successful approach for tackling complex and long-horizo
arXiv:2605.17093v1 Announce Type: cross Abstract: Distilling vision-language models into faster hybrid architectures, such as 3:1 Mamba-2/attention mixes, is now standard practice for making inference
arXiv:2605.17875v1 Announce Type: new Abstract: The accurate automated diagnosis of cardiac abnormalities from 12-lead electrocardiograms (ECGs) is critical for managing cardiovascular disease. Howeve
arXiv:2605.16404v1 Announce Type: new Abstract: Extracting actionable knowledge from industrial visual data is fundamentally bottlenecked by extreme class imbalance and the prohibitive computational c
arXiv:2605.17355v1 Announce Type: new Abstract: As a modern commodity, language has become a vast repository of socially and psychologically significant traits and concepts, reflecting the ways people
arXiv:2603.00607v2 Announce Type: replace-cross Abstract: Multi-subject image generation requires seamlessly harmonizing multiple reference identities within a coherent scene. However, existing method
arXiv:2602.18217v2 Announce Type: replace Abstract: Real-time sentence comprehension imposes a significant load on working memory, as comprehenders must maintain contextual information to anticipate f
arXiv:2605.18467v1 Announce Type: new Abstract: Recent diffusion-based methods have achieved impressive progress in video content manipulation. However, they typically ignore the accompanying audio, l
arXiv:2605.17774v1 Announce Type: new Abstract: Large language models are increasingly used as planning components in agentic systems, but current tool-use pipelines often require full tool schemas to
arXiv:2305.07152v4 Announce Type: replace Abstract: Robotic assisted (RA) surgery promises to transform surgical intervention. Intuitive Surgical is committed to fostering these changes and the machin
arXiv:2605.18657v1 Announce Type: cross Abstract: Time Series Foundation Models (TSFMs) have demonstrated notable success in general-purpose forecasting tasks; however, their adaptation to specialized
arXiv:2605.18556v1 Announce Type: cross Abstract: Embodied control increasingly requires models to follow compositional language instructions while reasoning over dynamic visual states. However, curre
arXiv:2508.04047v2 Announce Type: replace Abstract: Prefix-based methods have emerged as a promising paradigm for Controllable Text Generation (CTG) due to their parameter efficiency. However, while e
arXiv:2605.16352v1 Announce Type: cross Abstract: Repository-level coding agents must first localize the files and symbols relevant to a task; failures at this stage can cascade across downstream obje
arXiv:2605.16899v1 Announce Type: new Abstract: A fundamental challenge in embodied AI is verifying if agents build internal models of spatial structure or merely learn to mimic task-specific expert t
arXiv:2605.17902v1 Announce Type: new Abstract: Stochastic-process-based degradation modeling is a core approach for estimating the distribution of remaining useful life (RUL); however, the selection
arXiv:2605.18627v1 Announce Type: new Abstract: It has been recently shown that lifted STRIPS models can be learned correctly and efficiently from action traces alone; i.e., applicable action sequence
arXiv:2605.17058v1 Announce Type: new Abstract: The combination of exponentially large action spaces, stochastic dynamics, and long-horizon decision-making under limited resources makes Sequential Sto
arXiv:2605.16289v1 Announce Type: cross Abstract: Linguistic uncertainty is common in social media, but its relationship with engagement remains unclear across languages and topics. Using 2,258 Englis
arXiv:2510.25799v2 Announce Type: replace Abstract: Human experts often struggle to select the best option from a large set of items with multiple competing objectives, a process bottlenecked by the d
arXiv:2605.16538v1 Announce Type: cross Abstract: This paper examines the opportunities, limitations, and practical considerations associated with the use of large language models (LLMs) in qualitativ
arXiv:2605.17603v1 Announce Type: cross Abstract: High-resolution precipitation information is essential for climate impact assessment, yet global climate models remain too coarse to resolve key small
arXiv:2605.16365v1 Announce Type: new Abstract: Early identification of individuals at elevated risk of Chlamydia trachomatis infection may enable optimal use of molecular testing in resource-aware sc
arXiv:2605.18617v1 Announce Type: cross Abstract: Most existing vision-language manipulation research targets rigid robotic arms, whose fixed morphology limits adaptability in cluttered or confined sp
arXiv:2605.17640v1 Announce Type: cross Abstract: Retrieval-augmented generation from videos requires systems to retrieve relevant audiovisual evidence from large corpora and synthesize it into cohere
arXiv:2605.18176v1 Announce Type: cross Abstract: This report presents MARS, short for Multimodal Agentic Reasoning with Source selection, our system for the CASTLE Challenge at EgoVis 2026. Participa
arXiv:2605.16290v1 Announce Type: cross Abstract: Predicting the difficulty of multiple-choice questions (MCQs) is important for effective assessment, yet current methods typically assume a unimodal s
arXiv:2605.18652v1 Announce Type: new Abstract: Recent GUI agents have made substantial progress in visual grounding and action prediction, yet they remain brittle in long-horizon tasks that require m
arXiv:2605.17539v1 Announce Type: new Abstract: Combinatorial optimization (CO) underlies decision-making from logistics to chip design, where infeasible solutions are operationally unusable and small
arXiv:2605.17444v1 Announce Type: cross Abstract: Modern software ecosystems face a rapidly growing number of disclosed vulnerabilities, increasing the need for automated repair techniques that can op
arXiv:2605.17398v1 Announce Type: new Abstract: This paper presents MiniGPT, a compact from-scratch implementation of GPT-style autoregressive language modeling in PyTorch. The aim is to rebuild the c
arXiv:2605.16480v1 Announce Type: cross Abstract: Molecules are graphs, but large language models~(LLMs) are usually asked to reason about them through linear strings. The most popular molecular repre
arXiv:2605.17624v1 Announce Type: cross Abstract: We investigate the potential of invariant and equivariant semi-supervised learning for addressing the challenges of training multi-task models on part
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:2605.17596v1 Announce Type: new Abstract: We present NeuSymMS, an adaptive memory system that enables large language model (LLM) agents to learn, remember, and reason about users across sessions
arXiv:2605.17862v1 Announce Type: cross Abstract: Scaling on-policy distillation (OPD) for large language models (LLMs) confronts a fundamental tension: asynchronous execution is necessary for system
arXiv:2605.17488v1 Announce Type: new Abstract: The landscape of joint audio and video generation has been fundamentally transformed by the advent of powerful foundation models. Despite these strides,
'One thing that we've been seeing recently is that inference benchmarks don't really match production workloads that well.' - @realDanFu, VP of Kernels When you're running dozens of concurrent coding
arXiv:2605.17283v1 Announce Type: cross Abstract: Recent progress in formal theorem proving has benefited from large-scale proof generation and verifier-aware training, but agentic proving is rarely i
arXiv:2605.16363v1 Announce Type: new Abstract: Smartphone scams are increasingly prevalent and typically manifest as multi-stage, cross-application processes with gradually emerging intent. Effective
arXiv:2605.17108v1 Announce Type: new Abstract: Transformers have become the dominant architecture for sequence modeling by using self-attention to enable expressive and highly parallel processing. Ho
arXiv:2605.17719v1 Announce Type: new Abstract: CNN- and Transformer-based architectures have achieved strong performance in medical image segmentation, but CNNs are limited in modeling long-range dep