Knowledge catalogue
arXiv:2605.26734v1 Announce Type: new Abstract: Existing Multi-Turn Composed Image Retrieval (MTCIR) datasets lack dialogue-history consistency and are restricted to the fashion domain. To address the
arXiv:2410.00995v3 Announce Type: replace Abstract: The automatic synthesis of analog circuits presents significant challenges. Most existing approaches formulate the problem as a single-objective opt
arXiv:2605.26524v1 Announce Type: cross Abstract: Maritime intelligent transportation systems (MITS) are essential for ensuring navigation safety and efficiency in busy waterways. However, accurate ve
arXiv:2605.26967v1 Announce Type: new Abstract: Existing video captioning methods struggle to balance visual fidelity and redundancy: holistic captions are compact but lose fine-grained evidence, wher
arXiv:2603.07211v2 Announce Type: replace Abstract: Direct Preference Optimization (DPO) has become a standard framework for safety alignment, but its reliance on pairwise preference updates makes tra
arXiv:2603.21563v2 Announce Type: replace Abstract: Collaborative multi-agent large language models (LLMs) can solve complex reasoning tasks by decomposing roles, but reinforcement learning for such s
arXiv:2605.27116v1 Announce Type: new Abstract: Open-vocabulary object detection (OVD) has made significant progress, enabling detectors to generalize from seen to unseen categories. However, real-wor
arXiv:2605.26445v1 Announce Type: new Abstract: Physicians learn primarily about illicit drugs from clinical overdose cases, limiting their understanding of real-world usage. Meanwhile, drug users sha
arXiv:2605.26286v1 Announce Type: cross Abstract: Real-world multi-agent reinforcement learning (MARL) systems must often operate under stale observations, stochastic communication delays, and intermi
arXiv:2605.26358v1 Announce Type: cross Abstract: Turbulence is ubiquitous in engineering and science, yet direct simulation is prohibitively expensive. The Reynolds-averaged Navier-Stokes (RANS) equa
arXiv:2602.18907v2 Announce Type: replace-cross Abstract: We introduce DeepInterestGR, a novel framework that integrates deep interest mining into the generative recommendation pipeline. This addresse
arXiv:2605.27130v1 Announce Type: cross Abstract: We present DEI: Diversity in Evolutionary Inference, a distributed Quality-Diversity (QD) search framework that assigns heterogeneous large language m
arXiv:2605.26629v1 Announce Type: new Abstract: Novel-view synthesis and 3D reconstruction from sparse posed images are central to robotics and AR/VR. Yet, feed-forward 3D Gaussian reconstruction fail
arXiv:2605.26382v1 Announce Type: new Abstract: Deploying high-performing 3D medical image segmenters (e.g., nnU-Net) is often limited by memory footprint and inference latency. Compression is therefo
arXiv:2605.26938v1 Announce Type: new Abstract: Alignment-based conformance checking is the state-of-the-art approach for comparing observed process executions with normative process models. The stand
arXiv:2602.08586v3 Announce Type: replace Abstract: Multi-agent LLM systems consistently outperform single-agent baselines, yet practitioners still cannot predict which design works for a new task or
arXiv:2605.26569v1 Announce Type: new Abstract: We present Distribution-aware Conformal Prediction (DCP), a unified framework integrating probabilistic predictors like Monte Carlo dropout, deep ensemb
arXiv:2505.18603v2 Announce Type: replace Abstract: Document understanding aims to perform question answering and information extraction over document images, where the visual content is highly inform
arXiv:2605.26656v1 Announce Type: new Abstract: Multimodal large language models are typically trained end-to-end to predict ground-truth answers, yet supervision signals are applied exclusively to te
arXiv:2605.26680v1 Announce Type: cross Abstract: Recent video multimodal large language models (MLLMs) increasingly couple step-by-step reasoning with on-demand visual evidence retrieval, allowing mo
arXiv:2605.26119v1 Announce Type: cross Abstract: Industrial Edge AI programs often begin with the model and only later confront the platform. That sequencing is attractive because it allows early dem
arXiv:2605.26910v1 Announce Type: cross Abstract: Large EEG Foundation Models (FMs) have shown great potential for decoding EEG signals across diverse cognitive tasks. However, existing EEG-FM studies
arXiv:2605.26952v1 Announce Type: new Abstract: Agentic reinforcement learning (RL) has proven effective for training LLM-based agents with external tool-use capabilities. However, we identify that ag
arXiv:2601.01668v2 Announce Type: replace-cross Abstract: Clinicians routinely navigate fragmented electronic health record (EHR) interfaces to assemble a coherent picture of a patient's problems, med
arXiv:2605.26355v1 Announce Type: cross Abstract: Standard transformer attention computes pairwise token similarity but treats all tokens as equally salient and all positions as equally local, regardl
arXiv:2605.26166v1 Announce Type: cross Abstract: The rapid proliferation of Internet of Things (IoT) devices has created an urgent demand for adaptive, resource-efficient Intrusion Detection Systems
arXiv:2605.27016v1 Announce Type: cross Abstract: Large language models (LLMs) are prone to hallucinations, i.e., statements unsupported by the input or training data, hindering reliable deployment. I
arXiv:2509.04310v4 Announce Type: replace Abstract: Recent research on Chain-of-Thought (CoT) reasoning in Large Language Models (LLMs) has demonstrated that agents can engage in extit{complex}, extit
arXiv:2605.26371v1 Announce Type: new Abstract: Hierarchical Reinforcement Learning (HRL) promises to solve long-horizon Reinforcement Learning (RL) tasks more efficiently than non-hierarchical counte
arXiv:2605.27045v1 Announce Type: new Abstract: The democratization of LLMs has accelerated the generation and circulation of highly fluent disinformation, making traditional syntax-semantic verificat
arXiv:2605.27286v1 Announce Type: cross Abstract: Time series foundation models (TSFMs) are transforming the forecasting paradigm through large-scale cross-domain pretraining. However, most existing T
arXiv:2603.13282v2 Announce Type: replace-cross Abstract: Federated Learning (FL) with Low-Rank Adaptation (LoRA) has become a standard for privacy-preserving LLM fine-tuning. However, existing person
arXiv:2605.27351v1 Announce Type: new Abstract: 3D editing is a fundamental capability for scalable 3D content creation. While image editing has rapidly evolved toward large-scale feedforward generati
arXiv:2605.27284v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models are increasingly expected to not only complete robot tasks, but also follow human instructions about how those tas
arXiv:2603.17685v3 Announce Type: replace Abstract: Balancing policy expressiveness with the exploration-exploitation trade-off is a core challenge in online Reinforcement Learning (RL). While Stochas
arXiv:2602.01941v2 Announce Type: replace-cross Abstract: Autoregressive learning of time-stepping operators provides an effective approach to data-driven partial differential equation (PDE) simulatio
arXiv:2605.27178v1 Announce Type: cross Abstract: We address the challenging task of 3D object segmentation in complex scene point clouds without relying on any scene-level human annotations during tr
arXiv:2605.25570v2 Announce Type: replace Abstract: Estimating continuous optical flow is a fundamental yet challenging problem in dynamic visual perception. Event-based cameras, with microsecond late
arXiv:2604.04948v2 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) systems depend critically on the quality of document preprocessing, yet no prior study has evaluated PDF
arXiv:2605.26601v1 Announce Type: new Abstract: Vision-language models have progressed rapidly, but Tibetan remains a severely underserved low-resource language due to the lack of reproducible trainin
arXiv:2605.26184v1 Announce Type: cross Abstract: Hybrid post-training usually combines supervised fine-tuning and reinforcement learning, but fixed mixing schedules cannot adapt when the relative noi
arXiv:2605.27295v1 Announce Type: new Abstract: We introduce Gemini Embedding 2, a native multimodal embedding model that allows embedding video, audio, image, and text modalities in a unified represe
arXiv:2605.26893v1 Announce Type: cross Abstract: Chain-of-Thought (CoT) reasoning has advanced large language models (LLMs), but outcome-based supervision leads to pervasive post-hoc rationalization,
arXiv:2603.08413v2 Announce Type: replace-cross Abstract: Deep neural networks for image classification often exhibit overconfidence on out-of-distribution (OOD) samples. To address this, we introduce
arXiv:2605.26600v1 Announce Type: cross Abstract: Standard Self-Supervised Learning (SSL) for Automatic Modulation Recognition (AMR) struggles with ineffective isotropic augmentations, spectral instab
arXiv:2605.26230v1 Announce Type: new Abstract: Multi-view 3D reconstruction has achieved remarkable progress with the advent of feed-forward 3D reconstruction models. However, these models are typica
arXiv:2603.09551v2 Announce Type: replace Abstract: While Vision-Language Models (VLMs) have significantly advanced remote sensing interpretation, enabling them to perform complex, step-by-step reason
arXiv:2602.16449v2 Announce Type: replace-cross Abstract: Generative model evaluation commonly relies on high-dimensional embedding spaces to compute distances between samples. We show that dataset re
arXiv:2411.02355v4 Announce Type: replace-cross Abstract: Quantization is a powerful tool for accelerating large language model (LLM) inference, but the accuracy-performance trade-offs across differen
arXiv:2603.11479v2 Announce Type: replace-cross Abstract: Time Series Event Detection (TSED) aims to localize semantically meaningful events in time series data, with critical applications in high-sta
arXiv:2605.26620v1 Announce Type: new Abstract: Natural language conveys information at varying levels of granularity, from fine-grained references to broad descriptions. While granularity is fundamen
arXiv:2602.02518v2 Announce Type: replace-cross Abstract: Large language models (LLMs) increasingly rely on external knowledge to improve factuality, yet many real-world knowledge sources are organize
arXiv:2602.22190v2 Announce Type: replace-cross Abstract: Open-source native GUI agents still lag behind closed-source systems on long-horizon navigation tasks. This gap stems from two limitations: a
arXiv:2601.01608v2 Announce Type: replace Abstract: Diffusion models deliver high quality in image synthesis but remain expensive during training and inference. Recent works have leveraged the inheren
arXiv:2504.08593v5 Announce Type: replace-cross Abstract: This work tackles the challenge of continuous sign language segmentation, a key task with huge implications for sign language translation and
arXiv:2605.26835v1 Announce Type: new Abstract: LLM-based multi-agent systems have been widely adopted for knowledge retrieval and report generation, synthesizing known information through web search
arXiv:2510.01336v2 Announce Type: replace-cross Abstract: Speculative decoding accelerates LLM inference by using a smaller draft model to speculate tokens that a larger target model verifies. Verific
arXiv:2605.27310v1 Announce Type: new Abstract: Cross-view spatial reasoning remains a weak spot for vision-language models (VLMs): they often reason in language and lose the fine-grained geometry nee
arXiv:2605.26421v1 Announce Type: new Abstract: The rapid evolution of generative models has precipitated a proliferation of fabricated content, posing significant challenges to existing Synthetic Ima
arXiv:2605.26715v1 Announce Type: new Abstract: Major data protection regulations all mention the 'right to be forgotten,' and that's what pushed federated unlearning (FU) techniques forward. But one