Knowledge catalogue
arXiv:2604.09063v1 Announce Type: cross Abstract: Human action recognition is pivotal in computer vision, with applications ranging from surveillance to human-robot interaction. Despite the effectiven
arXiv:2604.09327v1 Announce Type: new Abstract: Pose-based Video Anomaly Detection (VAD) has gained significant attention for its privacy-preserving nature and robustness to environmental variations.
arXiv:2604.08883v1 Announce Type: cross Abstract: Inspired by the general Vision-and-Language Navigation (VLN) task, aerial VLN has attracted widespread attention, owing to its significant practical v
arXiv:2604.08952v1 Announce Type: new Abstract: Document Question Answering (DQA) involves generating answers from a document based on a user's query, representing a key task in document understanding
arXiv:2604.08615v1 Announce Type: cross Abstract: Fine-grained visual understanding and high-level reasoning in real-world open-water environments remain under-explored due to the lack of dedicated be
arXiv:2603.21396v2 Announce Type: replace Abstract: Recent work has shown that LLMs can sometimes detect when steering vectors are injected into their residual stream and identify the injected concept
arXiv:2604.09338v1 Announce Type: new Abstract: Spatial reasoning is central to navigation and robotics, yet measuring model capabilities on these tasks remains difficult. Existing benchmarks evaluate
arXiv:2604.09232v1 Announce Type: cross Abstract: LiDAR-based perception is critical for autonomous driving due to its robustness to poor lighting and visibility conditions. Yet, current models operat
arXiv:2604.08562v1 Announce Type: cross Abstract: Ensuring that Text-to-Speech (TTS) systems deliver human-perceived quality at scale is a central challenge for modern speech technologies. Human subje
arXiv:2604.09072v1 Announce Type: new Abstract: Humans effortlessly navigate the physical world by predicting how objects behave under gravity and contact forces, yet how such judgments support sequen
arXiv:2604.08986v1 Announce Type: cross Abstract: Persona prompting has been widely adopted to steer large language models (LLMs) behavior and improve their instruction performance by assigning specif
arXiv:2604.08557v1 Announce Type: cross Abstract: Diffusion-based language models (dLLMs) generate text by iteratively denoising masked token sequences. We show that their safety alignment rests on a
arXiv:2601.07663v3 Announce Type: replace Abstract: Hint-based faithfulness evaluations have established that Large Reasoning Models (LRMs) may not say what they think: they do not always volunteer in
arXiv:2512.07833v2 Announce Type: replace-cross Abstract: Humans do not just see attribute similarity -- we also see relational similarity. An apple is like a peach because both are reddish fruit, but
arXiv:2604.09104v1 Announce Type: cross Abstract: Scheming, the covert pursuit of misaligned goals by AI systems, represents a potentially catastrophic risk, yet scheming research suffers from signifi
arXiv:2604.08608v1 Announce Type: cross Abstract: We introduce Semantic Intent Fragmentation (SIF), an attack class against LLM orchestration systems where a single, legitimately phrased request cause
arXiv:2604.09025v1 Announce Type: cross Abstract: Vision-language models (VLMs) have shown a promising ability in image geolocation, but they still lack structured geographic reasoning and the capacit
arXiv:2604.08761v1 Announce Type: new Abstract: Sign language recognition suffers from catastrophic scaling failure: models achieving high accuracy on small vocabularies collapse at realistic sizes. E
arXiv:2604.08620v1 Announce Type: cross Abstract: Reinforcement learning is typically treated as a uniform, data-driven optimization process, where updates are guided by rewards and temporal-differenc
arXiv:2604.09411v1 Announce Type: new Abstract: Reliable 3D dynamic perception requires models that can anticipate motion beyond predefined categories, yet progress is hindered by the scarcity of dens
arXiv:2604.07720v2 Announce Type: replace Abstract: Deep Research (DR) requires LLM agents to autonomously perform multi-step information seeking, processing, and reasoning to generate comprehensive r
arXiv:2604.09159v1 Announce Type: new Abstract: Maximum entropy reinforcement learning (MaxEnt RL) has become a standard framework for sequential decision making, yet its standard Gaussian policy para
arXiv:2604.09330v1 Announce Type: cross Abstract: Recent advances in robot foundation models trained on large-scale human teleoperation data have enabled robots to perform increasingly complex real-wo
arXiv:2604.03058v2 Announce Type: replace-cross Abstract: LLMs can be socially sycophantic, affirming users when they ask questions like 'am I in the wrong?' rather than providing genuine assessment.
arXiv:2604.09197v1 Announce Type: cross Abstract: Purpose. High-grade serous ovarian carcinoma (HGSOC) is characterized by pronounced biological and spatial heterogeneity and is frequently diagnosed a
arXiv:2604.09508v1 Announce Type: cross Abstract: Visual Retrieval-Augmented Generation (VRAG) empowers Vision-Language Models to retrieve and reason over visually rich documents. To tackle complex qu
Auto-generated index of all people mentioned across the wiki.
arXiv:2604.08042v1 Announce Type: new Abstract: Sketching in 3D space enables expressive reasoning about shape, structure, and spatial relationships, yet generating 3D sketches through natural languag
A playable, digital piano built with Gemma 4 E2B (2B). https://x.com/0xCVYH/status/2039929097141318129?s=20 Google lancou 'Agent Skills' junto com o Gemma 4 Um app Android onde voce importa skills e o
arXiv:2604.08077v1 Announce Type: new Abstract: Processing long-form videos with Video Large Language Models (Video-LLMs) is computationally prohibitive. Current efficiency methods often compromise fi
arXiv:2601.10587v2 Announce Type: replace Abstract: The paper introduces a white-box attack on computer vision models using SHAP values. It demonstrates how adversarial evasion attacks can compromise
All is not lost. Duckerton is still possible. Here is Seedance 2.0 with the same prompt. Media My most popular Sora video was “an Elaborate regency romance where everyone is wearing a live duck for a
arXiv:2604.07831v1 Announce Type: cross Abstract: Existing red-teaming studies on GUI agents have important limitations. Adversarial perturbations typically require white-box access, which is unavaila
arXiv:2510.07927v2 Announce Type: replace Abstract: Anomaly detection plays a pivotal role in manufacturing quality control, yet its application is constrained by limited abnormal samples and high man
arXiv:2604.07740v1 Announce Type: new Abstract: In recent years, video-based person Re-Identification (ReID) has gained attention for its ability to leverage spatiotemporal cues to match individuals a
arXiv:2604.06685v1 Announce Type: cross Abstract: While Vision-Language Models (VLMs) have demonstrated significant potential in chemical visual understanding, current models are predominantly optimiz
arXiv:2604.06198v1 Announce Type: cross Abstract: The rapid rise of generative artificial intelligence (AI) is driving unprecedented growth in global computational demand, placing increasing pressure
arXiv:2510.18196v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are commonly used as evaluators in various applications, but the reliability of the outcomes remains a challenge.
arXiv:2604.08088v1 Announce Type: new Abstract: Text-to-motion generation has attracted increasing attention in the research community recently, with potential applications in animation, virtual reali
arXiv:2601.22451v2 Announce Type: replace-cross Abstract: Despite progress in Large Vision Language Models (LVLMs), object hallucination remains a critical issue in image captioning task, where models
In support of our mission to accelerate the developer journey on Google Cloud, we built Dev Signal: a multi-agent system designed to transform raw community signals into reliable technical guidance by
arXiv:2510.20549v2 Announce Type: replace Abstract: Despite advancements in SLAM technologies, robust operation under challenging conditions such as low-texture, motion-blur, or challenging lighting r
arXiv:2604.07253v1 Announce Type: cross Abstract: In gender-restrictive and surveilled contexts, where access to formal education may be restricted for women, pursuing education involves safety and pr
arXiv:2604.06491v1 Announce Type: cross Abstract: We introduce Discrete flow Matching policy Optimization (DoMinO), a unified framework for Reinforcement Learning (RL) fine-tuning Discrete Flow Matchi
arXiv:2504.17069v2 Announce Type: replace Abstract: Autoregressive (AR) image generators are becoming increasingly popular due to their ability to produce high-quality images and their scalability. Ty
arXiv:2412.08637v4 Announce Type: replace Abstract: Identifying the training data samples that most influence a generated image is a critical task in understanding diffusion models (DMs), yet existing
arXiv:2604.06342v1 Announce Type: cross Abstract: Although tension between university curricula and industry expectations has existed in some form for decades, the rapid integration of generative AI (
arXiv:2604.08543v1 Announce Type: new Abstract: Event cameras offer multiple advantages in monocular egocentric 3D human pose estimation from head-mounted devices, such as millisecond temporal resolut
arXiv:2604.07180v1 Announce Type: cross Abstract: We propose a geometric framework for longitudinal multi-parametric MRI analysis based on patient-specific energy modelling in sequence space. Rather t
arXiv:2604.07772v1 Announce Type: new Abstract: Open-world video anomaly detection (OWVAD) aims to detect and explain abnormal events under different anomaly definitions, which is important for applic
arXiv:2604.06172v1 Announce Type: cross Abstract: Cold-start cross-domain recommender (CDR) systems predict a user's preferences in a target domain using only their source-domain behavior, yet existin
arXiv:2604.07997v1 Announce Type: new Abstract: Incremental 3D object perception is a critical step toward embodied intelligence in dynamic indoor environments. However, existing incremental 3D detect
arXiv:2411.18084v2 Announce Type: replace-cross Abstract: Mobile apps are essential in daily life but frequently employ deceptive patterns, such as visual emphasis or linguistic nudging, to manipulate
arXiv:2604.08322v1 Announce Type: new Abstract: Fundus imaging such as CFP, OCT and UWF is crucial for the early detection of retinal anomalies and diseases. Fundus image understanding, due to its kno
arXiv:2604.03317v2 Announce Type: replace Abstract: Previous studies have illustrated the potential of analysing gaze behaviours in collaborative learning to provide educationally meaningful informati
Google's Gemma 4 models — the 26B (Mixture of Experts) and 31B (Dense) variants — are now available on Vercel AI Gateway. Built on the same architecture as Gemini 3, both open models support functi...
arXiv:2604.06767v1 Announce Type: new Abstract: Language models operate on discrete tokens but compute in continuous vector spaces, inducing a Voronoi tessellation over the representation manifold. We
arXiv:2510.23868v4 Announce Type: replace Abstract: This paper proposes extit{Group-relative Implicit Fine-Tuning (GIFT)}, a reinforcement learning framework for aligning large language models (LLMs
arXiv:2604.06195v1 Announce Type: cross Abstract: Large language models often produce unsupported claims. We frame this as a misclassification error at the output boundary, where internally generated
arXiv:2603.18203v3 Announce Type: replace Abstract: Current artificial intelligence systems struggle with systematic compositional reasoning: the capacity to recombine known components in novel config