Knowledge catalogue
arXiv:2604.25132v1 Announce Type: new Abstract: Instruction-tuning datasets often contain substantial redundancy and low-quality samples, necessitating effective data selection methods. We propose an
arXiv:2604.25213v1 Announce Type: new Abstract: OpenAI's GPT-Image-2 has effectively erased the visual boundary between authentic and AI-edited document images: a single number on a receipt can be rep
arXiv:2510.07499v2 Announce Type: replace Abstract: Recent Long-Context Language Models (LCLMs) can process hundreds of thousands of tokens in a single prompt, enabling new opportunities for knowledge
arXiv:2603.14248v2 Announce Type: replace-cross Abstract: Large language model (LLM) web agents are increasingly used for web navigation but remain far from human reliability on realistic, long-horizo
arXiv:2604.22830v1 Announce Type: new Abstract: Pre-training is a general method that is used in a range of deep learning tasks. By first training a model on one task, and then further training on the
arXiv:2604.24149v1 Announce Type: new Abstract: Remote sensing images are frequently degraded by adverse weather conditions, particularly clouds and haze, which severely impair downstream applications
arXiv:2601.13288v2 Announce Type: replace Abstract: Production LLM systems often rely on separate models for safety and other classification-heavy steps, increasing latency, VRAM footprint, and operat
arXiv:2603.07475v2 Announce Type: replace Abstract: Autoregressive (AR) language models build representations incrementally via left-to-right prediction, while diffusion language models (dLLMs) are tr
arXiv:2509.21199v3 Announce Type: replace Abstract: Multi-Hop Question Answering (MHQA) requires integrating dispersed, interdependent evidence through sequential reasoning under noise. This task is c
arXiv:2604.23415v1 Announce Type: new Abstract: Most two-stream action recognition networks apply the same convolutional backbone to both RGB and optical flow streams, ignoring the fact that the two m
arXiv:2510.04916v2 Announce Type: replace Abstract: Deep learning has become increasingly important in remote sensing image classification due to its ability to extract semantic information from compl
arXiv:2604.23027v1 Announce Type: new Abstract: Large language models (LLMs) have become central to modern AI workflows, powering applications from open-ended text generation to complex agent-based re
arXiv:2604.24589v1 Announce Type: new Abstract: Vision-language models (VLMs) are increasingly proposed as general-purpose tools for scientific data interpretation, yet their reliability on real astro
arXiv:2604.23821v1 Announce Type: cross Abstract: Autonomous neutron spectroscopy must solve three distinct tasks: detection (where is the signal?), inference (which Hamiltonian governs it?), and refi
arXiv:2604.23239v1 Announce Type: new Abstract: Accurate long-term time series forecasting (LTSF) requires the capture of complex long-range dependencies and dynamic periodic patterns. Recent advances
arXiv:2604.23999v1 Announce Type: cross Abstract: Randomized neural networks (RaNNs) are attractive for partial differential equations (PDEs) because they replace expensive end-to-end training with a
arXiv:2604.24219v1 Announce Type: new Abstract: Multi-intent natural language understanding requires retrieval systems that simultaneously achieve high accuracy and computational efficiency, yet exist
arXiv:2603.21362v2 Announce Type: replace Abstract: LLM-as-Judge evaluation fails agent tasks because a fixed rubric cannot capture what matters for this task: code debugging demands Correctness and E
arXiv:2604.24661v1 Announce Type: new Abstract: Visual reinforcement learning aims to empower an agent to learn policies from visual observations, yet it remains vulnerable to dynamic visual perturbat
arXiv:2512.20164v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) excel at text comprehension and generation, making them ideal for automated tasks like code review and content mo
arXiv:2604.23290v1 Announce Type: cross Abstract: Active learning algorithms automatically identify the most informative samples from large amounts of unlabeled data and tremendously reduce human anno
arXiv:2604.23327v1 Announce Type: new Abstract: Active perception is a fundamental problem in autonomous robotics in which the robot must decide where to move and what to sense in order to obtain the
arXiv:2604.23361v1 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated strong performance on a wide range of software engineering tasks, including code generation and analysi
arXiv:2509.16702v2 Announce Type: replace Abstract: Personalized animal image generation is challenging due to rich appearance cues and large morphological variability. Existing approaches often exhib
arXiv:2602.10139v3 Announce Type: replace-cross Abstract: Mobile Graphical User Interface (GUI) agents have demonstrated strong capabilities in automating complex smartphone tasks by leveraging multim
arXiv:2604.22841v1 Announce Type: new Abstract: Face Image Quality Assessment (FIQA) aims to assess the recognition utility of face samples and is essential for reliable face recognition (FR) systems.
arXiv:2604.23284v1 Announce Type: cross Abstract: In this work, we present Au-M-ol, a novel multimodal architecture that extends Large Language Models (LLMs) with audio processing. It is designed to i
arXiv:2604.22871v1 Announce Type: cross Abstract: Automated red-teaming methods for large language models typically optimize attack prompts within a fixed, human-designed strategy, leaving the attack
arXiv:2510.18346v2 Announce Type: replace Abstract: Audio-Visual Question Answering (AVQA) requires models to effectively utilize both visual and auditory modalities to answer complex and diverse ques
arXiv:2604.24685v1 Announce Type: new Abstract: Chromosome analysis is a fundamental step in the diagnosis of genetic diseases, but the manual karyotyping workflow is time-consuming and heavily depend
arXiv:2604.24428v1 Announce Type: cross Abstract: Electroencephalography (EEG) is highly susceptible to artifact contamination, such as electrooculographic (EOG) and electromyographic (EMG) interferen
arXiv:2512.07868v2 Announce Type: replace-cross Abstract: Bayesian optimization is widely used for optimizing expensive black box functions, but most existing approaches focus on scalar responses. In
arXiv:2604.24018v1 Announce Type: new Abstract: This paper studies the problem of robot performance evaluation, focusing on how to obtain accurate and efficient estimates of real-world behavior under
arXiv:2510.17381v2 Announce Type: replace Abstract: Detecting out-of-distribution (OOD) data is critical for machine learning, be it for safety reasons or to enable open-ended learning. However, beyon
arXiv:2602.02556v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are largely static and often redo reasoning or repeat mistakes. Prior experience reuse typically relies on extern
arXiv:2604.23413v1 Announce Type: new Abstract: Cloud-hosted Large Language Models (LLMs) offer unmatched reasoning capabilities and dynamic knowledge, yet submitting raw queries to these external ser
arXiv:2604.24273v1 Announce Type: new Abstract: The deployment of intelligent reinforcement learning (RL) agents on resource-constrained edge devices remains a fundamental challenge due to the substan
arXiv:2603.08592v2 Announce Type: replace Abstract: While Multimodal Large Language Models (MLLMs) have achieved remarkable success in 2D visual understanding, their ability to reason about 3D space r
arXiv:2604.23345v1 Announce Type: new Abstract: Cross-domain task-oriented dialogue requires reasoning over implicit and explicit feasibility constraints while planning long-horizon, multi-turn action
arXiv:2604.23282v1 Announce Type: new Abstract: Text-based person anomaly search retrieves specific behavioral events from surveillance archives using natural-language queries. Although recent pose-aw
arXiv:2604.23165v1 Announce Type: new Abstract: Spiking Vision Transformers (S-ViTs) offer a promising framework for energy-efficient visual learning. However, existing designs remain limited by two f
arXiv:2604.23061v1 Announce Type: cross Abstract: Large language models (LLMs) show promise for molecular optimization, but aligning them with selective and competing drug-design constraints remains c
arXiv:2604.24697v1 Announce Type: new Abstract: Discovering causal regularities and applying them to build functional systems--the discovery-to-application loop--is a hallmark of general intelligence,
arXiv:2505.14549v3 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly being used in privacy pipelines to detect and remedy sensitive data leakage. These solutions oft
arXiv:2604.22884v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have shown promising potential in diverse understanding tasks, e.g., image and video analysis, math and physi
arXiv:2604.23270v1 Announce Type: new Abstract: Chain-of-Thought (CoT) prompting has emerged as a simple and effective way to elicit step-by-step solutions from large language models (LLMs). However,
arXiv:2604.23576v1 Announce Type: cross Abstract: Ensuring safe exploration in high-dimensional systems with unknown dynamics remains a significant challenge. Existing safe reinforcement learning meth
arXiv:2601.06352v2 Announce Type: replace Abstract: Adapting large language models to individual users remains challenging due to the tension between fine-grained personalization and scalable deployme
arXiv:2604.23633v1 Announce Type: new Abstract: Constraint-based causal discovery is brittle in finite-sample regimes because erroneous conditional-independence (CI) decisions can cascade into substan
arXiv:2603.27507v2 Announce Type: replace Abstract: Recent advancements in multi-modal large language models (MLLMs) have shown strong potential for 3D scene understanding. However, existing methods s
arXiv:2604.23009v1 Announce Type: new Abstract: Job Skill Named Entity Recognition (JobSkillNER) aims to automatically extract key skill information from large-scale job posting data, which is importa
arXiv:2604.16922v2 Announce Type: replace Abstract: Climate research is pivotal for mitigating global environmental crises, yet the accelerating volume of multi-scale datasets and the complexity of an
arXiv:2509.17314v3 Announce Type: replace-cross Abstract: Software increasingly relies on the emergent capabilities of Large Language Models (LLMs), from natural language understanding to program anal
arXiv:2604.23308v1 Announce Type: new Abstract: Offline multi-agent reinforcement learning (MARL) enables policy learning from fixed datasets, but is prone to coordination failure: agents trained on s
arXiv:2509.11717v5 Announce Type: replace-cross Abstract: Text-guided sound separation enables flexible audio editing, assistive listening, and open-domain source extraction, but systems such as Audio
arXiv:2604.23546v1 Announce Type: cross Abstract: Optical chemical structure recognition (OCSR) translates molecular images into machine-readable representations like SMILES strings or molecular graph
arXiv:2604.24393v1 Announce Type: cross Abstract: There has been growing interest in studying the complexity of Rectified Linear Unit (ReLU) based activation networks. Recent work investigates the evo
arXiv:2604.23585v1 Announce Type: new Abstract: Financial institutions must track over 60,000 regulatory events annually, overwhelming manual compliance teams; the industry has paid over USD 300 billi
arXiv:2604.22787v1 Announce Type: cross Abstract: Africa's green industrialization imperative demands reliable infrastructure for monitoring air quality. We present a satellite-reanalysis PM2.5 fusion
arXiv:2604.23377v1 Announce Type: new Abstract: Neurosymbolic systems can satisfy logical constraints during learning without achieving the intended concept-label correspondence; this is a problem kno