Knowledge catalogue
arXiv:2604.09276v1 Announce Type: new Abstract: Distributed online convex optimization (D-OCO) is a powerful paradigm for modeling distributed scenarios with streaming data. However, the communication
arXiv:2602.05862v2 Announce Type: replace-cross Abstract: Two-sample testing, where we aim to determine whether two distributions are equal or not equal based on samples from each one, is challenging
arXiv:2604.08577v1 Announce Type: cross Abstract: Large Language Models (LLMs) tend to respond correctly to prompts that align to the data they were trained and fine-tuned on. Yet, small shifts in wor
arXiv:2602.10603v3 Announce Type: replace Abstract: Genomic foundation models have the potential to decode DNA syntax, yet face a fundamental tradeoff in their input representation. Standard fixed-voc
arXiv:2604.09189v1 Announce Type: cross Abstract: LLMs internalize safety policies through RLHF, yet these policies are never formally specified and remain difficult to inspect. Existing benchmarks ev
arXiv:2604.09425v1 Announce Type: new Abstract: Vision Language Models (VLMs) have achieved remarkable success by integrating visual encoders with large language models (LLMs). While VLMs process dens
arXiv:2604.09417v1 Announce Type: new Abstract: Many-objective optimisation, a subset of multi-objective optimisation, involves optimisation problems with more than three objectives. As the number of
arXiv:2604.09018v1 Announce Type: new Abstract: Face Anti-Spoofing (FAS) algorithms, designed to secure face recognition systems against spoofing, struggle with limited dataset diversity, impairing th
arXiv:2604.09251v1 Announce Type: new Abstract: Deep research agents increasingly interleave web browsing with multi-step computation, yet existing benchmarks evaluate these capabilities in isolation,
arXiv:2501.14377v2 Announce Type: replace Abstract: Autonomous drone racing has risen as a challenging robotic benchmark for testing the limits of learning, perception, planning, and control. Expert h
arXiv:2604.08554v1 Announce Type: cross Abstract: The public text record -- the material from which both people and AI systems now learn -- is increasingly shaped by its own outputs. Generated text en
arXiv:2604.09358v1 Announce Type: new Abstract: Accurate prediction of nonstationary multivariate time series remains a critical challenge in complex industrial systems such as iron ore sintering. In
arXiv:2604.09468v1 Announce Type: cross Abstract: In this study, we proposed a deep Swin-Vision Transformer-based transfer learning architecture for robust multi-cancer histopathological image classif
arXiv:2511.06756v3 Announce Type: replace Abstract: Over-smoothing remains a fundamental challenge in deep Graph Neural Networks (GNNs), where repeated message passing causes node representations to b
arXiv:2604.08965v1 Announce Type: new Abstract: Semantic segmentation of satellite imagery plays a vital role in land cover mapping and environmental monitoring. However, annotating large-scale, high-
arXiv:2604.08565v1 Announce Type: cross Abstract: At typical context lengths, the feed-forward MLP block accounts for a large share of a transformer's compute budget, motivating sparse alternatives to
arXiv:2604.09455v1 Announce Type: new Abstract: While Large Language Models (LLMs) have demonstrated significant potential in Tool-Integrated Reasoning (TIR), existing training paradigms face signific
arXiv:2604.08791v1 Announce Type: cross Abstract: User-space Adaptive Bitrate (ABR) algorithms cannot see the transport layer signals that matter most, such as minimum RTT and instantaneous delivery r
arXiv:2604.09450v1 Announce Type: cross Abstract: Chest X-ray report generation (CXR-RG) has the potential to substantially alleviate radiologists' workload. However, conventional autoregressive visio
arXiv:2512.19396v3 Announce Type: replace Abstract: Contemporary GUI agents, while increasingly capable due to advances in Large Vision-Language Models (VLMs), often operate with a critical limitation
arXiv:2604.08960v1 Announce Type: new Abstract: Offline goal-conditioned reinforcement learning (GCRL) is a practical reinforcement learning paradigm that aims to learn goal-conditioned policies from
arXiv:2604.08706v1 Announce Type: new Abstract: While Experience Replay - the practice of storing rollouts and reusing them multiple times during training - is a foundational technique in general RL,
arXiv:2604.09164v1 Announce Type: new Abstract: Temporal human action detection aims to identify and localize action segments within untrimmed videos, serving as a pivotal task in video understanding.
arXiv:2604.09391v1 Announce Type: cross Abstract: Machine unlearning poses challenges in removing mislabeled, contaminated, or problematic data from a pretrained model. Current unlearning approaches a
arXiv:2604.08694v1 Announce Type: new Abstract: How do you build a sign language recognizer that works on a phone? That question drove this work. We built EfficientSign, a lightweight model which take
arXiv:2604.09405v1 Announce Type: new Abstract: As text-to-image diffusion models grow increasingly prevalent, the ability to remove specific concepts-mostly explicit content and many copyrighted char
arXiv:2511.03122v2 Announce Type: replace-cross Abstract: Designing materials with targeted properties remains challenging due to the vastness of chemical space and the scarcity of property-labeled da
arXiv:2604.09535v1 Announce Type: new Abstract: Large foundation models have made significant advances in embodied intelligence, enabling synthesis and reasoning over egocentric input for household ta
arXiv:2604.07927v2 Announce Type: replace Abstract: Deep research requires reasoning over web evidence to answer open-ended questions, and it is a core capability for AI agents. Yet many deep research
arXiv:2604.09168v1 Announce Type: new Abstract: We introduce Elastic Looped Transformers (ELT), a highly parameter-efficient class of visual generative models based on a recurrent transformer architec
arXiv:2604.08556v1 Announce Type: cross Abstract: What exactly do efficient sequence models gain over simple temporal averaging? We use exponential moving average (EMA) traces, the simplest recurrent
arXiv:2512.22437v2 Announce Type: replace Abstract: An image conveys meaning through both its visual content and emotional tone, jointly shaping human perception. We introduce Controllable Emotional I
arXiv:2604.08589v1 Announce Type: new Abstract: Mental health challenges among young adults, are on the rise, necessitating effective solutions such as digital mental health interventions (DMHIs). Des
arXiv:2604.06816v2 Announce Type: replace-cross Abstract: Conventional multi-image super-resolution (MISR) methods, such as burst and video SR, rely on sequential frames from a single camera. Conseque
arXiv:2604.08931v1 Announce Type: new Abstract: Human cognitive development is shaped not only by individual effort but by structured social interaction, where role-based exchanges such as those betwe
arXiv:2506.09067v2 Announce Type: replace-cross Abstract: Generative medical vision-language models~(Med-VLMs) are primarily designed to generate complex textual information~(e.g., diagnostic reports)
arXiv:2604.09527v1 Announce Type: cross Abstract: Accurately anticipating how complex, diverse scenes will evolve requires models that represent uncertainty, simulate along extended interaction chains
arXiv:2604.09367v1 Announce Type: new Abstract: Ancient inscriptions, as repositories of cultural memory, have suffered from centuries of environmental and human-induced degradation. Restoring their i
arXiv:2604.09130v1 Announce Type: cross Abstract: As SE(3)-equivariant graph neural networks mature as a core tool for 3D atomistic modeling, improving their efficiency, expressivity, and physical con
arXiv:2604.09265v1 Announce Type: new Abstract: Intelligent dialogue systems are increasingly deployed in emotionally and ethically sensitive settings, where failures in either emotional attunement or
arXiv:2604.09523v1 Announce Type: new Abstract: The transition of Multi-Agent Reinforcement Learning (MARL) policies from simulated cyber wargames to operational Security Operations Centers (SOCs) is
arXiv:2604.08708v1 Announce Type: cross Abstract: While Large Language Model-based Multi-Agent Systems (MAS) consistently outperform single-agent systems on complex tasks, their intricate interactions
arXiv:2604.08627v1 Announce Type: cross Abstract: Pretrained models have become standard in both vision and language, yet they typically do not provide reliable measures of confidence. Existing uncert
arXiv:2602.10414v2 Announce Type: replace Abstract: This paper introduces EVOKE (Emotion Vocabulary of Korean and English), a Korean-English parallel dataset of emotion words. The dataset offers compr
arXiv:2604.08698v1 Announce Type: new Abstract: Tokens serve as the basic units of representation in DNA language models (DNALMs), yet their design remains underexplored. Unlike natural language, DNA
arXiv:2511.03913v2 Announce Type: replace-cross Abstract: Deep diffusion models have revolutionized image generation by producing high-quality outputs. However, achieving specific objectives with thes
arXiv:2604.08644v1 Announce Type: new Abstract: This technical report introduces EXAONE 4.5, the first open-weight vision language model released by LG AI Research. EXAONE 4.5 is architected by integr
arXiv:2510.09093v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are now routinely used to autonomously execute complex tasks, from natural language processing to dynamic workflo
arXiv:2604.02598v2 Announce Type: replace-cross Abstract: LLM-generated explanations can make technical content more accessible, but there is a ceiling on what they can support interactively. Because
arXiv:2412.12686v3 Announce Type: replace Abstract: Current large language models (LLMs) often exhibit imbalances in multilingual capabilities and cultural adaptability, largely attributed to their En
arXiv:2602.07142v2 Announce Type: replace-cross Abstract: Collaboration is a cornerstone of 21st-century learning, yet teachers continue to face challenges in supporting productive peer interaction. E
arXiv:2604.08606v1 Announce Type: cross Abstract: One of the impediments to the efficiency of information markets is the inherent information asymmetry present in them, exacerbated by the 'buyer's ins
arXiv:2604.09127v1 Announce Type: new Abstract: Lightweight face recognition is increasingly important for deployment on edge and mobile devices, where strict constraints on latency, memory, and energ
arXiv:2604.09174v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) aims to reduce hallucination by grounding answers in retrieved evidence, yet hallucinated answers remain common eve
arXiv:2604.09249v1 Announce Type: new Abstract: Fashion understanding requires both visual perception and expert-level reasoning about style, occasion, compatibility, and outfit rationale. However, ex
arXiv:2604.06832v2 Announce Type: replace Abstract: Vision-language models (VLMs) predominantly rely on autoregressive decoding, which generates tokens one at a time and fundamentally limits inference
arXiv:2604.08903v1 Announce Type: new Abstract: Pansharpening aims to generate high-resolution multispectral (HRMS) images by fusing low-resolution multispectral (LRMS) and high-resolution panchromati
arXiv:2603.23199v2 Announce Type: replace Abstract: Deep learning-based 3D medical image segmentation methods relies on large-scale labeled datasets, yet acquiring such data is difficult due to privac
arXiv:2604.09064v1 Announce Type: new Abstract: In partial multi-label learning (PML), each instance is associated with a set of candidate labels containing both ground-truth and noisy labels. The pre
arXiv:2604.09094v1 Announce Type: cross Abstract: Abusive speech detection is becoming increasingly important as social media shifts towards voice-based interaction, particularly in multilingual and l