Knowledge catalogue
arXiv:2510.03988v2 Announce Type: replace Abstract: Distilling long-form reasoning from teacher models into smaller students requires selecting which candidate solutions to train on. Recent work argue
arXiv:2604.13315v1 Announce Type: new Abstract: High-resolution data in spatial and temporal contexts is imperative for developing climate resilient cities. Current datasets for monitoring urban param
arXiv:2604.13186v1 Announce Type: new Abstract: Unsafe surgical care is a critical health concern, often linked to limitations in surgeon experience, skills, and situational awareness. Integrating pat
arXiv:2604.14074v1 Announce Type: new Abstract: Semantic Multi-Object Tracking (SMOT) extends multi-object tracking with semantic outputs such as video summaries, instance-level captions, and interact
arXiv:2604.13425v1 Announce Type: new Abstract: Video chroma-lux editing, which aims to modify illumination and color while preserving structural and temporal fidelity, remains a significant challenge
arXiv:2603.08486v2 Announce Type: replace Abstract: Multimodal large language models (MLLMs) face safety misalignment, where visual inputs enable harmful outputs. To address this, existing methods req
arXiv:2506.01247v2 Announce Type: replace Abstract: Steering vision foundation models at test time, without updating foundation-model weights or using labeled target data, is a desirable yet challengi
AI agents struggle to effectively process and extract information from complex enterprise documents due to limitations in context windows, reasoning capabilities, and handling of unstructured data for
4/5 We upgraded our original 3-line “be correct” prompt → a much more detailed prompt that enforced a hierarchy of constraints for correctness, regression safety, and minimality. Basically, get the LL
arXiv:2604.12904v1 Announce Type: new Abstract: Composed Image Retrieval (CIR) aims to retrieve a target image based on a query composed of a reference image, and a relative caption that specifies the
arXiv:2604.12179v1 Announce Type: new Abstract: Recent advancements in Large Language Models (LLMs) have improved their ability to process extended conversational contexts, yet fine-tuning and evaluat
arXiv:2602.04204v2 Announce Type: replace Abstract: Human trajectory forecasting requires capturing the multimodal nature of pedestrian behavior. However, existing approaches suffer from prior misalig
arXiv:2603.21011v2 Announce Type: replace-cross Abstract: Finite element (FE) analysis guides the design and verification of nearly all manufactured objects. It is at the core of computational enginee
arXiv:2604.11861v1 Announce Type: new Abstract: Accurate and continuous localization of Autonomous Underwater Vehicles (AUVs) in GPS-denied environments is a persistent challenge in marine robotics. I
arXiv:2604.12307v1 Announce Type: new Abstract: The proliferation of highly realistic AI-Generated Image (AIGI) has necessitated the development of practical detection methods. While current AIGI dete
arXiv:2507.21990v4 Announce Type: replace-cross Abstract: Atomized chemical knowledge, such as functional group information of molecules and reactions, plays a pivotal intermediate role in the reasoni
arXiv:2604.05407v2 Announce Type: replace Abstract: LLM-based code agents treat repositories as unstructured text, applying edits through brittle string matching that frequently fails due to formattin
arXiv:2604.12353v1 Announce Type: new Abstract: In recent years, the rapid development of generative artificial intelligence technology has significantly lowered the barrier to creating high-quality f
arXiv:2604.12243v1 Announce Type: cross Abstract: Scientific hypothesis generation requires tracking how knowledge evolves, not just what is currently known. We introduce Continuous Knowledge Metaboli
arXiv:2604.12551v1 Announce Type: new Abstract: Vision-language models have been key to the development of open-vocabulary 2D semantic segmentation. Lifting these models from 2D images to 3D scenes, h
arXiv:2604.12967v1 Announce Type: new Abstract: Reinforcement Learning (RL) has shown strong potential for optimizing search agents in complex information retrieval tasks. However, existing approaches
arXiv:2604.12293v1 Announce Type: new Abstract: As the number of fatalities involving Autonomous Vehicles increase, the need for a universal method of communicating between vehicles and other agents o
arXiv:2604.01315v2 Announce Type: replace Abstract: Money launderers take advantage of limitations in existing detection approaches by hiding their financial footprints in a deceitful manner. They man
arXiv:2604.12443v1 Announce Type: new Abstract: Modern diffusion-based inpainting models pose significant challenges for image forgery localization (IFL), as their full regeneration pipelines reconstr
arXiv:2604.11867v1 Announce Type: cross Abstract: We set out to train behavioral dispositions (self-verification, uncertainty acknowledgment, feedback integration) into small language models (0.6B to
arXiv:2604.12152v1 Announce Type: cross Abstract: Latent diffusion models for medical image super-resolution universally inherit variational autoencoders designed for natural photographs. We show that
arXiv:2603.22607v2 Announce Type: replace Abstract: Recent advances in Virtual Try-On (VTON) and Virtual Try-Off (VTOFF) have greatly improved photo-realistic fashion synthesis and garment reconstruct
arXiv:2604.11954v1 Announce Type: cross Abstract: We study dynamic multi-robot task allocation under uncertain task completion, time-window constraints, and incomplete information. Tasks arrive online
arXiv:2604.12518v1 Announce Type: new Abstract: Multimodal sentiment analysis (MSA) integrates heterogeneous text, audio, and visual signals to infer human emotions. While recent approaches leverage c
arXiv:2505.19261v2 Announce Type: replace-cross Abstract: Current text-to-image diffusion generation typically employs complete-text conditioning. Due to the intricate syntax, diffusion transformers (
arXiv:2604.12855v1 Announce Type: new Abstract: Musculoskeletal robots offer intrinsic compliance and flexibility, providing a promising paradigm for versatile locomotion. However, existing research t
arXiv:2604.11929v1 Announce Type: new Abstract: Our ability to predict, control, and ultimately understand complex systems rests on discovering the equations that govern their dynamics. Identifying th
arXiv:2604.12288v1 Announce Type: cross Abstract: Fine-tuning is a widely used strategy for adapting pre-trained models to new tasks, yet its methodology and theoretical properties in high-dimensional
arXiv:2503.10676v2 Announce Type: replace-cross Abstract: We study the efficacy of fine-tuning Large Language Models (LLMs) for the specific task of report (government archives, news, intelligence rep
arXiv:2503.05167v3 Announce Type: replace Abstract: Traditional Chinese medicine (TCM) exhibits remarkable therapeutic efficacy in healthcare through patient-specific formulas. However, current AI-bas
arXiv:2604.12425v1 Announce Type: new Abstract: Trajectory prediction models often fail in real-world automated driving due to distributional shifts between training and test conditions. Such distribu
arXiv:2506.14092v3 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed in decision-support systems for high-stakes domains such as hiring and university admissions,
arXiv:2504.06983v3 Announce Type: replace Abstract: Hierarchical inductive biases are hypothesized to promote generalizable policies in reinforcement learning, as demonstrated by explicit hyperbolic l
arXiv:2604.12351v1 Announce Type: new Abstract: Automated diagnosis based on color fundus photography is essential for large-scale glaucoma screening. However, existing deep learning models are typica
arXiv:2604.12748v1 Announce Type: new Abstract: Although large language models (LLMs) excel in complex reasoning tasks, they suffer from severe causal hallucination in event causality identification (
arXiv:2511.00179v2 Announce Type: replace-cross Abstract: Capturing the structural changes that molecules undergo during chemical reactions in real space and time is a long-standing dream and an essen
arXiv:2511.13790v2 Announce Type: replace-cross Abstract: This paper describes GeoPl@ntNet, an interactive web application designed to make Essential Biodiversity Variables accessible and understandab
arXiv:2604.12757v1 Announce Type: cross Abstract: Adversarial robustness is essential for deploying neural networks in safety-critical applications, yet standard evaluation methods either require expe
arXiv:2604.12843v1 Announce Type: new Abstract: The rapid release of both language models and benchmarks makes it increasingly costly to evaluate every model on every dataset. In practice, models are
arXiv:2510.07285v3 Announce Type: replace-cross Abstract: The escalating complexity of network threats and the inherent class imbalance in traffic data present formidable challenges for modern Intrusi
Today, Gemini 3.1 Flash TTS, our latest text-to-speech model, is available on Google AI Studio and Vertex AI. It delivers precise controllability and expressivity, empowering developers and enterprise
arXiv:2511.17537v2 Announce Type: replace-cross Abstract: Wireless Sensor Networks (WSN) are the backbone of essential monitoring applications, but their deployment in unfavourable conditions increase
arXiv:2604.12665v1 Announce Type: new Abstract: Motion reasoning serves as the cornerstone of multi-object tracking (MOT), as it enables consistent association of targets across frames. However, exist
arXiv:2604.12440v1 Announce Type: cross Abstract: Real-world industrial inspection requires not only localizing defects, but also explaining them in natural language and generating controlled defect e
arXiv:2507.13647v2 Announce Type: replace-cross Abstract: Real-time trajectory planning for unmanned aerial vehicles (UAVs) in dynamic environments remains a key challenge due to high computational de
arXiv:2508.01620v3 Announce Type: replace-cross Abstract: Machine Unlearning (MU) aims to selectively erase the influence of specific data points from pretrained models. However, most existing MU meth
arXiv:2604.12709v1 Announce Type: cross Abstract: Task-adapted compressed sensing magnetic resonance imaging (CS-MRI) is emerging to address the specific demands of downstream clinical tasks with sign
VAKRA (Versatile Agent and Knowledge Reasoning Assessment) is a benchmark developed by IBM Research to evaluate AI agents on complex reasoning, tool use, and multi-step task execution across diverse d
arXiv:2604.12084v1 Announce Type: new Abstract: Spatial transcriptomics (ST) measures mRNA expression while preserving spatial organization, but multi-slice analysis faces two coupled difficulties: la
arXiv:2604.12185v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) enhances large language models by grounding outputs in retrieved knowledge. However, existing RAG methods including
arXiv:2601.14004v4 Announce Type: replace Abstract: Mechanistic Interpretability (MI) has emerged as a vital approach to demystify the opaque decision-making of Large Language Models (LLMs). However,
arXiv:2604.12416v1 Announce Type: cross Abstract: In this review I summarize how machine learning can be used in lattice gauge theory simulations and what ap-proaches are currently available to improv
arXiv:2603.19042v4 Announce Type: replace Abstract: The integration of artificial intelligence (AI) technologies into judicial decision-making, particularly in pretrial, sentencing, and parole context
arXiv:2604.12380v1 Announce Type: new Abstract: Camouflaged Object Detection (COD) aims to segment objects that blend seamlessly into complex backgrounds, with growing interest in exploiting additiona
arXiv:2604.11811v1 Announce Type: cross Abstract: Large language model agents rely on specialized memory systems to accumulate and reuse knowledge during extended interactions. Recent architectures ty