Knowledge catalogue
arXiv:2604.18781v1 Announce Type: new Abstract: Large-scale automated morphometric analysis of brain MRI is limited by the thick-slice, anisotropic acquisitions prevalent in routine clinical practice.
arXiv:2604.19124v1 Announce Type: new Abstract: Existing detoxification methods for large language models mainly focus on post-training stage or inference time, while few tackle the source of toxicity
arXiv:2604.18639v1 Announce Type: cross Abstract: Previous LLMs-based RL studies typically follow either supervised learning with high annotation costs, or unsupervised paradigms using voting or entro
arXiv:2604.18790v1 Announce Type: new Abstract: Depth completion from sparse LiDAR measurements and corresponding RGB images is a prerequisite for accurate 3D perception in robotic systems. Existing m
arXiv:2603.15956v2 Announce Type: replace-cross Abstract: Learning generalizable and robust behavior cloning policies requires large volumes of high-quality robotics data. While human demonstrations (
arXiv:2604.19730v1 Announce Type: cross Abstract: Some of the most performant reinforcement learning algorithms today can be prohibitively expensive as they use test-time scaling methods such as sampl
arXiv:2604.04516v2 Announce Type: replace-cross Abstract: Adapting LLMs to new domains causes forgetting because standard methods (e.g., full fine-tuning, LoRA) inject new directions into the weight s
arXiv:2604.19039v1 Announce Type: new Abstract: We present a generative method for texture filtering, which exhibits surprisingly good performance and generalizability. Our core idea is to empower tex
arXiv:2604.19398v1 Announce Type: new Abstract: Large language models (LLMs) are expensive to serve because model parameters, attention computation, and KV caches impose substantial memory and latency
arXiv:2604.19406v1 Announce Type: cross Abstract: Common image editing tasks typically adopt powerful generative diffusion models as the leading paradigm for real-world content editing. Meanwhile, alt
arXiv:2604.19191v1 Announce Type: cross Abstract: Anomaly detection in medical imaging is essential for identifying rare pathological conditions, particularly when annotated abnormal samples are limit
arXiv:2602.04749v2 Announce Type: replace Abstract: Long-tailed class imbalance remains a fundamental obstacle in semantic segmentation of high-resolution remote-sensing imagery, where dominant classe
arXiv:2602.12708v2 Announce Type: replace Abstract: Vertical Federated Learning (VFL) has emerged as a critical paradigm for collaborative model training in privacy-sensitive domains such as finance a
arXiv:2604.19147v1 Announce Type: cross Abstract: Scaling Transformers typically necessitates training larger models from scratch, as standard architectures struggle to expand without discarding learn
arXiv:2604.19087v1 Announce Type: new Abstract: We introduce Options LLM (OLLM), a simple, general method that replaces the single next-token prediction of standard LLMs with a extit{set of learned op
arXiv:2509.15435v2 Announce Type: replace-cross Abstract: Large Vision-Language Models (LVLMs) exhibit strong multimodal capabilities but remain vulnerable to hallucinations from intrinsic errors and
arXiv:2604.18757v1 Announce Type: cross Abstract: The retina provides a unique, noninvasive window into Alzheimer's disease (AD) and dementia, capturing early structural changes through morphometric f
arXiv:2601.04237v2 Announce Type: replace Abstract: We demonstrate SAGE-32B, a 32 billion parameter language model that focuses on agentic reasoning and long range planning tasks. Unlike chat models t
At Google Cloud Next, we are announcing innovations across every layer of our storage stacks — performance, intelligence, and management — to ensure your data is as fast and as useful as the AI models
arXiv:2604.18939v1 Announce Type: new Abstract: Table annotation is crucial for making web and enterprise tables usable in downstream NLP applications. Unlike textual data where learning semantically
arXiv:2604.18756v1 Announce Type: cross Abstract: Large Language Models (LLMs) remain vulnerable to optimization-based jailbreak attacks that exploit internal gradient structure. While Sparse Autoenco
arXiv:2604.19412v1 Announce Type: cross Abstract: Large vision-language models (LVLMs) frequently suffer from Object Hallucination (OH), wherein they generate descriptions containing objects that are
arXiv:2604.19609v1 Announce Type: new Abstract: Transformers have become a common foundation across deep learning, yet 3D scene understanding still relies on specialized backbones with strong domain p
arXiv:2604.16663v1 Announce Type: new Abstract: Landslide detection from high resolution satellite imagery is a critical task for disaster response and risk assessment, yet the relative effectiveness
arXiv:2604.16625v1 Announce Type: new Abstract: Recent large language model (LLM) agents have shown promise in using execution feedback for test-time adaptation. However, robust self-improvement remai
arXiv:2508.13401v3 Announce Type: replace Abstract: This report presents an overview of the AIM 2025 RipSeg Challenge, a competition designed to advance techniques for automatic rip current segmentati
arXiv:2604.16486v1 Announce Type: new Abstract: State-of-the-art deepfake detectors achieve near-perfect in-domain accuracy yet degrade under cross-generator shifts, heavy compression, and adversarial
arXiv:2510.23807v5 Announce Type: replace-cross Abstract: Despite their successes in vision and language, foundation models have stumbled in pathology, revealing low accuracy, instability, and heavy c
arXiv:2604.18423v1 Announce Type: new Abstract: India's linguistic landscape, spanning 22 scheduled languages and hundreds of marginalized dialects, has driven rapid growth in NLP datasets, benchmarks
arXiv:2512.11988v3 Announce Type: replace Abstract: Accurate capture of human-object interaction from ubiquitous sensors like RGB cameras is important for applications in human understanding, gaming,
arXiv:2604.18027v1 Announce Type: cross Abstract: Transpilation, or code translation, aims to convert source code from one programming language (PL) to another. It is beneficial for many downstream ap
arXiv:2506.01732v2 Announce Type: replace Abstract: Large Language Models (LLMs) are pre-trained on large data from different sources and domains. These datasets often contain trillions of tokens, inc
arXiv:2604.17215v1 Announce Type: new Abstract: Large language models require continuous adaptation to new tasks while preserving safety alignment. However, fine-tuning on even benign data often compr
arXiv:2510.08878v3 Announce Type: replace-cross Abstract: Text-to-audio (TTA) generation with fine-grained control signals, e.g., precise timing control or intelligible speech content, has been explor
arXiv:2601.14590v2 Announce Type: replace Abstract: Counterfactual explanations (CFEs) provide human-centric interpretability by identifying the minimal, actionable changes required to alter a machine
arXiv:2604.16979v1 Announce Type: cross Abstract: High-quality and diverse multimodal data are essential for improving vision-language models (VLMs), yet existing datasets often contain noisy, redunda
arXiv:2604.17411v1 Announce Type: new Abstract: Text-attributed graphs integrate semantic information of node texts with topological structure, offering significant value in various applications such
arXiv:2602.03986v2 Announce Type: replace Abstract: Conformal prediction, a post-hoc, distribution-free, finite-sample method of uncertainty quantification that offers formal coverage guarantees under
arXiv:2604.17211v1 Announce Type: new Abstract: We present EmbodiedHead, a speech-driven talking-head framework that equips LLMs with real-time visual avatars for conversation. A practical embodied av
arXiv:2501.12119v3 Announce Type: replace-cross Abstract: We introduce ENTIRE, a novel deep learning-based approach for fast and accurate volume rendering time prediction. Predicting rendering time is
arXiv:2604.16572v1 Announce Type: new Abstract: Wi-Fi Channel State Information (CSI) enables device-free human activity recognition, but existing multi-user approaches assume a fixed set of known use
arXiv:2604.16758v1 Announce Type: new Abstract: We present a system for automated detection, localization, and scoring of arrow punctures on 40,cm indoor archery target faces, trained on only 48 annot
arXiv:2604.17307v1 Announce Type: new Abstract: Detecting face forgeries using CLIP has recently emerged as a promising and increasingly popular research direction. Owing to its rich visual knowledge
arXiv:2601.09173v4 Announce Type: replace-cross Abstract: Representational similarity analysis and related methods have become standard tools for comparing the internal geometries of neural networks a
arXiv:2604.17210v1 Announce Type: new Abstract: Fine-tuning well-aligned large language models (LLMs) on new domains often degrades their safety alignment, even when using benign datasets. Existing sa
arXiv:2604.17259v1 Announce Type: cross Abstract: User behavior in the real world is diverse, cross-domain, and spans long time horizons. Existing user modeling benchmarks however remain narrow, focus
arXiv:2604.16959v1 Announce Type: cross Abstract: Incomplete Multi-View Clustering (IMVC) faces the challenge of learning discriminative representations from fragmentary observations while maintaining
arXiv:2604.16988v1 Announce Type: new Abstract: Non-stationary sequences arise naturally in control, forecasting, and decision-making. The data-generating process shifts at unknown times, and models m
arXiv:2603.00883v2 Announce Type: replace Abstract: LLMs increasingly excel on AI benchmarks, but doing so does not guarantee validity for downstream tasks. This study contrasts LLM alignment on bench
arXiv:2604.17197v1 Announce Type: new Abstract: Recent advances in summarization research focus on improving summary quality across multiple criteria, such as completeness, conciseness, and faithfulne
arXiv:2512.04677v5 Announce Type: replace Abstract: Audio-driven avatar interaction demands real-time, streaming, and infinite-length generation -- capabilities fundamentally at odds with the sequenti
arXiv:2604.17021v1 Announce Type: new Abstract: Video editing aims to modify input videos according to user intent. Recently, end-to-end training methods have garnered widespread attention, constructi
arXiv:2507.02850v3 Announce Type: replace Abstract: We describe a vulnerability in language models (LMs) trained with user feedback, whereby a single user can persistently alter LM knowledge and behav
arXiv:2509.11983v2 Announce Type: replace Abstract: Neural network (NN) training is inherently a large-scale matrix optimization problem, yet the matrix structure of NN parameters has long been overlo
arXiv:2512.00198v2 Announce Type: replace Abstract: Breast cancer is one of the leading causes of death among women worldwide. We introduce Mammo-FM, the first foundation model specifically for mammog
arXiv:2604.17007v1 Announce Type: new Abstract: Mobile deployment of facial age estimation requires models that balance predictive accuracy with low latency and compact size. In this work, we present
arXiv:2604.16503v1 Announce Type: new Abstract: Training strong video generation models usually requires massive datasets, large parameter counts, and substantial compute. In this work, we ask whether
arXiv:2604.17435v1 Announce Type: new Abstract: Recent Speech-to-Speech Translation (S2ST) systems achieve strong semantic accuracy yet consistently strip away non-verbal vocalizations (NVs), such as
arXiv:2510.09474v2 Announce Type: replace Abstract: Modern conversational agents like ChatGPT and Alexa+ rely on predefined policies specifying metadata, response styles, and tool-usage rules. As thes
arXiv:2604.17070v1 Announce Type: new Abstract: This report presents the NTIRE 2026 Rip Current Detection and Segmentation (RipDetSeg) Challenge, which targets automatic rip current understanding in i