Knowledge catalogue
arXiv:2604.10297v1 Announce Type: cross Abstract: Composed Image Retrieval (CIR) retrieves target images using a reference image paired with modification text. Despite rapid advances, all existing met
arXiv:2604.10275v1 Announce Type: new Abstract: Real-time image denoising is essential for modern mobile photography but remains challenging due to the strict latency and power constraints of edge dev
arXiv:2508.17431v3 Announce Type: replace-cross Abstract: Person re-identification (re-ID) is a fundamental task in intelligent surveillance and public safety. Federated learning (FL) provides a priva
arXiv:2604.10678v1 Announce Type: new Abstract: Social bot detection is critical to the stability and security of online social platforms. However, current state-of-the-art bot detection models are la
arXiv:2604.10391v1 Announce Type: cross Abstract: Vision foundation models (VFMs) and Bird's Eye View (BEV) representation have advanced visual perception substantially, yet their internal spatial rep
arXiv:2604.11083v1 Announce Type: cross Abstract: Text-to-motion generation is driven by learning motion representations for semantic alignment with language. Existing methods rely on either continuou
arXiv:2604.09989v1 Announce Type: cross Abstract: Recently, synthetic palmprints have been increasingly used as substitutes for real data to train recognition models. To be effective, such synthetic d
arXiv:2603.22911v2 Announce Type: replace-cross Abstract: Due to the great saving of computation and memory overhead, token compression has become a research hot-spot for MLLMs and achieved remarkable
arXiv:2604.10512v1 Announce Type: new Abstract: The development of generalizable Novel View Synthesis (NVS) models is critically limited by the scarcity of large-scale training data featuring diverse
arXiv:2604.10332v1 Announce Type: new Abstract: We present the progress of the GPT family from GPT-3 through GPT-3.5, GPT-4, GPT-4 Turbo, GPT-4o, GPT-4.1, and the GPT-5 family. Our work is comparative
arXiv:2603.23964v2 Announce Type: replace Abstract: The remarkable progress of reinforcement learning (RL) is intrinsically tied to the environments used to train and evaluate artificial agents. Movin
arXiv:2604.11041v1 Announce Type: new Abstract: Semiconductor supply chains face unprecedented resilience challenges amidst global geopolitical turbulence. Conventional Large Language Model (LLM) plan
arXiv:2604.11104v1 Announce Type: new Abstract: This paper presents an empirical study of a multi-model zero-shot pipeline for knowledge graph construction and exploitation, executed entirely through
arXiv:2509.20624v5 Announce Type: replace-cross Abstract: Autoregressive language models (ARMs) deliver strong likelihoods, but are inherently serial: they generate one token per forward pass, which l
arXiv:2601.08209v3 Announce Type: replace Abstract: In domains such as materials science, biomedicine, and finance, high-stakes deployment of large language models (LLMs) requires injecting private, d
arXiv:2604.11786v1 Announce Type: new Abstract: Modeling open-play soccer tactics is a formidable challenge due to the stochastic, multi-agent nature of the game. Existing computational approaches typ
arXiv:2602.09932v2 Announce Type: replace Abstract: Building height (BH) and footprint (BF) are fundamental urban morphological parameters required by climate modelling, disaster-risk assessment, and
arXiv:2604.11344v1 Announce Type: cross Abstract: Embedding-as-a-Service (EaaS) has become an important semantic infrastructure for natural language and multimedia applications, but it is highly vulne
arXiv:2604.10094v1 Announce Type: new Abstract: Anthropogenic methane (CH4) point sources drive near-term climate forcing, safety hazards, and system inefficiencies. Space-based imaging spectroscopy i
arXiv:2604.11404v1 Announce Type: cross Abstract: We present GlobalCY, a JAX-based framework for globally defined and symmetry-aware neural Kahler-potential models on projective hypersurface Calabi--Y
arXiv:2505.17022v2 Announce Type: replace-cross Abstract: Visual generation models have made remarkable progress in creating realistic images from text prompts, yet struggle with complex prompts that
arXiv:2604.10658v1 Announce Type: new Abstract: Institutional decisions -- regulatory compliance, clinical triage, prior authorization appeal -- require a different AI architecture than general-purpos
arXiv:2510.22329v2 Announce Type: replace Abstract: The Capacitated Vehicle Routing Problem with Time Windows (CVRPTW) is a fundamental NP-hard optimization problem in logistics. Solving large-scale i
arXiv:2604.10073v1 Announce Type: cross Abstract: Long-horizon Flexible Job-Shop Scheduling~(FJSP) presents a formidable combinatorial challenge due to complex, interdependent decisions spanning exten
arXiv:2604.11751v1 Announce Type: cross Abstract: In Model Predictive Control (MPC), world models predict the future outcomes of various action proposals, which are then scored to guide the selection
arXiv:2604.11218v1 Announce Type: new Abstract: Superpixels offer a compact image representation by grouping pixels into coherent regions. Recent methods have reached a plateau in terms of segmentatio
arXiv:2604.10665v1 Announce Type: new Abstract: HeceTokenizer is a syllable-based tokenizer for Turkish that exploits the deterministic six-pattern phonological structure of the language to construct
arXiv:2604.10560v1 Announce Type: new Abstract: Profiled Sparse Networks (PSN) replace uniform connectivity with deterministic, heterogeneous fan-in profiles defined by continuous, nonlinear functions
arXiv:2604.09679v1 Announce Type: cross Abstract: Multi-Agent Debate (MAD) is a collaborative framework in which multiple agents iteratively refine solutions through the generation of reasoning and al
arXiv:2604.10836v1 Announce Type: new Abstract: Generating realistic 3D hand-object interactions (HOI) is a fundamental challenge in computer vision and robotics, requiring both temporal coherence and
arXiv:2604.04385v3 Announce Type: replace-cross Abstract: This paper localizes the policy routing mechanism in alignment-trained language models. An intermediate-layer attention gate reads detected co
arXiv:2604.11133v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly being explored for clinical question answering and decision support, yet safe deployment critically requir
arXiv:2604.10917v1 Announce Type: new Abstract: Enabling large language models to scale and reliably use hundreds of tools is critical for real-world applications, yet challenging due to the inefficie
arXiv:2604.09670v1 Announce Type: cross Abstract: Intelligent systems must maintain and manipulate task-relevant information online to adapt to dynamic environments and changing goals. This capacity,
arXiv:2604.10955v1 Announce Type: new Abstract: Hypergraph neural networks (HGNNs) have shown remarkable potential in modeling high-order relationships that naturally arise in many real-world data dom
arXiv:2601.17755v2 Announce Type: replace Abstract: Graph Retrieval-Augmented Generation (GraphRAG) has emerged as a promising paradigm that organizes external knowledge into structured graphs of enti
arXiv:2604.09697v1 Announce Type: cross Abstract: Test-time augmentation (TTA)--aggregating predictions over multiple augmented copies of a test input--is widely assumed to improve classification accu
arXiv:2604.09702v1 Announce Type: cross Abstract: Precise segmentation of objects with highly similar shapes remains a challenging problem in dense prediction, especially in scenarios with ambiguous b
arXiv:2507.00748v3 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) perform well in single-image visual grounding but struggle with real-world tasks that demand cross-image re
arXiv:2305.16272v5 Announce Type: replace Abstract: Collaborative learning techniques have the potential to enable training machine learning models that are superior to models trained on a single enti
arXiv:2604.10703v1 Announce Type: new Abstract: Transformer architectures are designed by trial and error: the number of attention heads, the depth, and the head size are fixed before training begins,
arXiv:2509.22887v2 Announce Type: replace Abstract: Theory of Mind (ToM)-an understanding of the mental states of others-is a key aspect of human social intelligence, yet, chatbots and LLM-based socia
arXiv:2604.07209v2 Announce Type: replace Abstract: Building world models with spatial consistency and real-time interactivity remains a fundamental challenge in computer vision. Current video generat
arXiv:2604.10448v1 Announce Type: new Abstract: Instruction tuning relies on large instruction-response corpora whose quality and composition strongly affect downstream performance. We propose Answer
arXiv:2501.19227v2 Announce Type: replace-cross Abstract: In this paper, we propose a novel active learning approach integrated with an improved semi-supervised learning framework to reduce the cost o
arXiv:2509.26306v4 Announce Type: replace Abstract: Existing multi-agent learning approaches have developed interactive training environments to explicitly promote collaboration among multiple Large L
arXiv:2604.11035v1 Announce Type: new Abstract: Diffusion language models promise parallel generation, yet still lag behind autoregressive (AR) models in quality. We stem this gap to a failure of intr
arXiv:2604.10707v1 Announce Type: new Abstract: While appearance-based gaze estimation has achieved significant improvements in accuracy and domain adaptation, the fairness of these systems across dif
arXiv:2604.09626v1 Announce Type: cross Abstract: A significant gap exists in datasets regarding post-COVID-19 vaccination experiences, particularly ``vaccine buyer's remorse''. Understanding the prev
arXiv:2604.10326v1 Announce Type: cross Abstract: Large language models remain vulnerable to jailbreak attacks -- inputs designed to bypass safety mechanisms and elicit harmful responses -- despite ad
arXiv:2602.09667v2 Announce Type: replace Abstract: Integrating domain knowledge into neural networks is a central challenge in scientific machine learning. Three paradigms have emerged -- data-driven
arXiv:2406.13621v2 Announce Type: replace Abstract: Commonsense reasoning often requires both textual and visual knowledge, yet Large Language Models (LLMs) trained solely on text lack visual groundin
arXiv:2604.10417v1 Announce Type: new Abstract: In recent years, aspect-based sentiment analysis (ABSA) has made rapid progress and shown strong practical value. However, existing research and benchma
arXiv:2604.11091v1 Announce Type: new Abstract: Prompt-based class-incremental learning methods typically construct a prompt pool consisting of multiple trainable key-prompts and perform instance-leve
arXiv:2604.09955v1 Announce Type: new Abstract: Video Unsupervised Domain Adaptation (VUDA) poses a significant challenge in action recognition, requiring the adaptation of a model from a labeled sour
arXiv:2604.11365v1 Announce Type: new Abstract: Monte Carlo Tree Search (MCTS) has been widely used for automated reasoning data exploration, but current supervision extraction methods remain ineffici
arXiv:2604.10150v1 Announce Type: new Abstract: Generative listwise reranking leverages global context for superior retrieval but is plagued by intrinsic position bias, where models exhibit structural
arXiv:2604.11473v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) architectures offer a scalable path for Graph Neural Networks (GNNs) in node classification tasks but typically rely on static
arXiv:2604.10783v1 Announce Type: new Abstract: Designing reward functions remains a central challenge in reinforcement learning (RL) for healthcare, where outcomes are sparse, delayed, and difficult
arXiv:2603.11346v2 Announce Type: replace Abstract: Humanoid robotics has strong potential to transform daily service and caregiving applications. Although recent advances in general motion tracking w