Knowledge catalogue
arXiv:2604.05301v2 Announce Type: replace Abstract: Real-world smoke simultaneously attenuates scene radiance, adds airlight, and destabilizes multi-view appearance consistency, making robust 3D recon
arXiv:2510.17925v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) excel at code-related tasks but often struggle in realistic software repositories, where project-specific APIs an
arXiv:2604.18591v1 Announce Type: cross Abstract: Game UI implementation requires translating stylized mockups into interactive engine entities. However, current 'Screenshot-to-Code' tools often strug
The future is taking shape in Las Vegas this week, where the world’s leading startups are showcasing their groundbreaking AI work at Google Cloud Next. Whether they need the top AI models, infrastruct
arXiv:2510.10074v2 Announce Type: replace Abstract: Effective incident management in large-scale IT systems relies on troubleshooting guides (TSGs), but their manual execution is slow and error-prone.
arXiv:2604.18780v1 Announce Type: new Abstract: Semi-Markov Conditional Random Fields (semi-CRFs) assign labels to segments of a sequence rather than to individual positions, enabling exact inference
arXiv:2604.19251v1 Announce Type: cross Abstract: Streamliner constraints reduce the search space of combinatorial problems by ruling out portions of the solution space. We adapt the StreamLLM approac
arXiv:2604.18951v1 Announce Type: cross Abstract: Adaptive multi-agent systems (MAS) are increasingly adopted to tackle complex problems.However, the narrow task coverage of their optimization raises
arXiv:2508.08080v2 Announce Type: replace Abstract: Symbolic Regression (SR) is a well-established framework for generating interpretable or white-box predictive models. Although SR has been successfu
arXiv:2601.09953v2 Announce Type: replace Abstract: Standardized math assessments require expensive human pilot studies to establish the difficulty of test items. We investigate the predictive value o
arXiv:2604.19420v1 Announce Type: new Abstract: Maintaining long-term accuracy of stereo camera calibration parameters is important for autonomous systems' perception. This work proposes Online Tracki
arXiv:2602.06400v2 Announce Type: replace-cross Abstract: The prediction of 3D semantic occupancy enables autonomous vehicles (AVs) to perceive the fine-grained geometric and semantic scene structure
arXiv:2412.01763v3 Announce Type: replace-cross Abstract: We study a censored variant of the data-driven newsvendor problem, where the decision-maker must select an ordering quantity that minimizes ex
arXiv:2604.19064v1 Announce Type: new Abstract: In vision-and-language navigation (VLN), self-improvement from policy-induced experience, using only standard VLN action supervision, critically depends
arXiv:2604.18850v1 Announce Type: cross Abstract: AI systems are increasingly embedded in multi-user social environments, yet most alignment frameworks conceptualize interaction as a dyadic relationsh
arXiv:2604.18606v1 Announce Type: cross Abstract: Damage caused by bushfires and volcanic eruptions escalates rapidly when detection is delayed, making fast and reliable early warning capabilities ess
arXiv:2604.18900v1 Announce Type: new Abstract: Aerobat is a bat-inspired flapping-wing robot with a wing gait generate by the computational structure, a planar linkage of carbon fiber links driven by
arXiv:2604.19070v1 Announce Type: new Abstract: Zero-shot reasoning on text-rich networks (TRNs) remains a challenging frontier, as models must integrate textual semantics with relational structure wi
arXiv:2512.07761v3 Announce Type: replace Abstract: Large language models have seen widespread adoption, yet they remain vulnerable to multi-turn jailbreak attacks, threatening their safe deployment.
arXiv:2604.19748v1 Announce Type: new Abstract: Recent advances in image generation and editing have opened new opportunities for virtual try-on. However, existing methods still struggle to meet compl
arXiv:2604.18607v1 Announce Type: cross Abstract: LLM-driven program evolution can discover high-quality programs, but its cost and run-to-run variance hinder reliable progress. We propose TurboEvolve
arXiv:2604.18592v1 Announce Type: cross Abstract: We introduce a two-dimensional (2D) early exit strategy that coordinates layer-wise and sentence-wise exiting for classification tasks in large langua
arXiv:2604.19221v1 Announce Type: new Abstract: Full-duplex speech interaction, as the most natural and intuitive mode of human communication, is driving artificial intelligence toward more human-like
arXiv:2604.19712v1 Announce Type: new Abstract: In [97,99,100], an fl-RDT framework is introduced to characterize statistical computational gaps (SCGs). Studying symmetric binary perceptrons (SBPs), [
arXiv:2603.22608v2 Announce Type: replace Abstract: Users often rely on Large Language Models (LLMs) for processing multiple documents or performing analysis over a number of instances. For example, a
arXiv:2604.19444v1 Announce Type: new Abstract: Reasoning language models can solve increasingly complex tasks, but struggle to produce the calibrated confidence estimates necessary for reliable deplo
arXiv:2604.18747v1 Announce Type: new Abstract: Relative position embedding has become a standard mechanism for encoding positional information in Transformers. However, existing formulations are typi
arXiv:2509.11253v2 Announce Type: replace Abstract: The technical complexity of research papers often limits their reach, necessitating more accessible formats like scientific videos to disseminate ke
arXiv:2602.12735v2 Announce Type: replace-cross Abstract: Effectively retrieving, reasoning, and understanding multimodal information remains a critical challenge for agentic systems. Traditional Retr
arXiv:2509.07966v2 Announce Type: replace-cross Abstract: Visual reasoning over structured data such as tables is a critical capability for modern vision-language models (VLMs), yet current benchmarks
arXiv:2604.19270v1 Announce Type: new Abstract: As groups of robots increasingly collaborate with humans, understanding how humans perceive them is critical for designing effective human-robot teams.
Succeeding in the agentic era requires a transformation in your data strategy: moving from human-scale to agent-first workloads, evolving from reactive intelligence to proactive action, and shifting f
At Google Cloud Next, we’re announcing a range of compute capabilities to enable your core general purpose and AI workloads for the agentic world with higher performance and lower costs. Why it matter
arXiv:2604.19335v1 Announce Type: new Abstract: The rapid growth of chemical literature has generated vast amounts of unstructured data, where reaction information is particularly valuable for applica
arXiv:2604.19206v1 Announce Type: new Abstract: The deployment of AI systems in safety-critical domains, such as industrial defect inspection, autonomous driving, and medical diagnosis, is severely ha
arXiv:2512.02304v2 Announce Type: replace Abstract: Large language models (LLMs) can act as both problem solvers and solution verifiers, where the latter select high-quality answers from a pool of sol
arXiv:2402.06922v5 Announce Type: replace-cross Abstract: Large language model (LLM)-based agents combine LLMs with external tools to automate tasks such as scheduling meetings, managing documents, or
arXiv:2509.12516v2 Announce Type: replace Abstract: Autonomous robots must go from zero prior knowledge to safe control within seconds to operate in unstructured environments. Abrupt terrain changes,
arXiv:2411.12142v4 Announce Type: replace Abstract: Qualitative analysis is critical to understanding human datasets in many social science disciplines. A central method in this process is inductive c
arXiv:2604.01798v2 Announce Type: replace Abstract: Breast cancer is a highly heterogeneous disease with diverse molecular profiles. The PAM50 gene signature is widely recognized as a standard for cla
arXiv:2604.16491v1 Announce Type: new Abstract: Pain is a multifaceted and widespread phenomenon with substantial clinical and societal burden, making reliable automated assessment a critical objectiv
This guide from Databricks covers practical techniques and best practices for fine-tuning large language models, including methodologies for adapting pre-trained LLMs to specific tasks and domains. It
arXiv:2604.17494v1 Announce Type: new Abstract: Counterfactual explanations (CFEs) are essential for interpreting black-box models, yet they often become invalid when models are slightly changed. Exis
arXiv:2604.17130v1 Announce Type: cross Abstract: The present study aims to investigate a cluster cleaning algorithm that is both computationally simple and capable of solving the PU classification wh
arXiv:2604.16586v1 Announce Type: new Abstract: Molecular property prediction integrates quantum chemistry, cheminformatics, and deep learning to connect molecular structure with physicochemical and b
arXiv:2506.07969v2 Announce Type: replace Abstract: We consider the problem of modeling high-speed flows using machine learning methods. While most prior studies focus on low-speed fluid flows in whic
arXiv:2512.15923v2 Announce Type: replace Abstract: To model discrete sequences such as DNA, proteins, and language using diffusion, practitioners must choose between three major methods: diffusion in
arXiv:2508.18025v4 Announce Type: replace-cross Abstract: Autonomous planetary exploration demands real-time, high-fidelity environmental perception. Standard deep learning models require massive comp
arXiv:2604.16984v1 Announce Type: new Abstract: This paper presents the report of the URVIS 2026 challenge on adverse-to-extreme panoptic segmentation. As the first challenge of its kind, it attracted
arXiv:2604.17889v1 Announce Type: new Abstract: Despite recent progress in multimodal large language models (MLLMs), reliable visual question answering in aerial scenes remains challenging. In such sc
arXiv:2604.17846v1 Announce Type: new Abstract: MRI is preferred over CT in paediatric imaging because it avoids ionising radiation, but its use in spine deformity assessment is largely limited by the
arXiv:2604.16622v1 Announce Type: new Abstract: Backchannels (e.g., `yeah', `mhm', and `right') are short, non-interruptive feedback signals whose lexical form and prosody jointly convey pragmatic mea
arXiv:2604.18489v1 Announce Type: cross Abstract: Large Language Models (LLMs) show promise in lyric-to-melody generation, but models trained with Supervised Fine-Tuning (SFT) often produce musically
arXiv:2505.23114v3 Announce Type: replace Abstract: Human preference data is essential for aligning large language models (LLMs) with human values, but collecting such data is often costly and ineffic
arXiv:2604.18293v1 Announce Type: new Abstract: Surprisal theory hypothesizes that the difficulty of human sentence processing increases linearly with surprisal, the negative log-probability of a word
arXiv:2604.16550v1 Announce Type: new Abstract: Despite the high accuracy of 'black box' deep learning models, drug discovery still relies on protein-ligand interaction principles and heuristics. To i
arXiv:2603.04545v2 Announce Type: replace Abstract: Efficient inference for graph neural networks (GNNs) on large knowledge graphs (KGs) is essential for many real-world applications. GNN inference qu
arXiv:2604.16490v1 Announce Type: new Abstract: Accurate brain image segmentation, particularly for distinguishing various tissues from magnetic resonance imaging (MRI) images, plays a pivotal role in
arXiv:2604.16851v1 Announce Type: cross Abstract: This dissertation explores how deep generative models can advance the analysis of challenging biological problems by integrating domain knowledge with
arXiv:2604.18137v1 Announce Type: cross Abstract: Processing-in-Memory (PIM) architectures offer a promising solution to the memory bottlenecks in data-intensive machine learning, yet often overlook t