Knowledge catalogue
arXiv:2605.01229v1 Announce Type: cross Abstract: Cross-attention patterns in neural machine translation (NMT) are widely used to study how multilingual models align linguistic structure. We report a
arXiv:2605.01302v1 Announce Type: new Abstract: Standard Retrieval-Augmented Generation (RAG) systems predominantly rely on semantic relevance as a proxy for utility. However, this assumption collapse
arXiv:2605.01698v1 Announce Type: new Abstract: BIM models provide structured representations of building geometry, semantics, and topology, yet extracting specific information from them remains remar
arXiv:2311.10320v3 Announce Type: replace Abstract: Data collected by different modalities can provide a wealth of complementary information, such as hyperspectral image (HSI) to offer rich spectral-s
arXiv:2605.02263v1 Announce Type: new Abstract: Recent diffusion large language models (dLLMs) have demonstrated both effectiveness and efficiency in reasoning via a block-based semi-autoregressive ge
arXiv:2605.01171v1 Announce Type: new Abstract: Despite recent progress, recovering parametric CAD construction sequences from geometric input, such as meshes or point clouds, is a key challenge for d
arXiv:2507.23386v3 Announce Type: replace Abstract: Decoder-only large language models (LLMs) have been increasingly adopted to build embedding models for diverse tasks. To overcome the inherent limit
arXiv:2603.29184v3 Announce Type: replace Abstract: Nonconvex multi-well energies in cell-induced phase transitions give rise to fine-scale microstructures, low-regularity transition layers and sharp
arXiv:2605.01490v1 Announce Type: new Abstract: Pansharpening aims to generate high-resolution multispectral (HRMS) images by fusing low-resolution multispectral (LRMS) images with high-resolution pan
arXiv:2605.01284v1 Announce Type: cross Abstract: Iterative Retrieval-Augmented Generation (iRAG) has emerged as a powerful paradigm for answering complex multi-hop questions by progressively retrievi
arXiv:2605.02357v1 Announce Type: new Abstract: In 3D point cloud understanding, the core challenge lies in accurately capturing discriminative features within complex neighborhoods, which directly af
arXiv:2605.01634v1 Announce Type: new Abstract: Physics-Informed Neural Networks (PINNs) offer a flexible paradigm for solving differential equations by embedding governing laws into the training obje
arXiv:2605.01298v1 Announce Type: cross Abstract: Backdoor attacks threaten the deep learning supply chain by poisoning a small fraction of the training data so that a model behaves normally on clean
arXiv:2605.01679v1 Announce Type: cross Abstract: Fall detection is a critical task in healthcare, particularly for elderly people. Timely fall detection and treatment can prevent severe injuries. Sen
arXiv:2605.01277v1 Announce Type: new Abstract: Recently, Convolutional Neural Network (CNN) or Transformer architecture based models have been proposed to overcome the limitations of Recurrent Neural
arXiv:2605.01712v1 Announce Type: new Abstract: Pareto set learning (PSL) is an emerging paradigm in multi-objective optimization that trains neural networks to map preference vectors to Pareto optima
arXiv:2605.02159v1 Announce Type: new Abstract: Deep reinforcement learning (DRL) has delivered strong results in domains such as Atari and Go, but it still suffers from high sample cost and weak tran
arXiv:2605.02277v1 Announce Type: new Abstract: Factual Error Correction (FEC) aims to revise inaccurate text into statements that are factually consistent with external evidence. Although recent meth
arXiv:2605.01291v1 Announce Type: new Abstract: Spiking Neural Networks (SNNs) are widely regarded as an energy-efficient paradigm for modeling and processing temporal and event-driven information. In
arXiv:2505.20948v3 Announce Type: replace Abstract: Abductive reasoning in knowledge graphs aims to generate plausible logical hypotheses from observed entities, with broad applications in areas such
arXiv:2508.12535v3 Announce Type: replace Abstract: Sparse Autoencoders (SAEs) can extract interpretable features from large language models (LLMs) without supervision. However, their effectiveness in
arXiv:2605.01675v1 Announce Type: cross Abstract: Constraint Programming (CP) is a powerful paradigm for solving combinatorial problems, yet translating natural language problem descriptions into exec
arXiv:2602.15823v2 Announce Type: replace Abstract: A central challenge in large language model (LLM) editing is capability preservation: methods that successfully change targeted behavior can quietly
arXiv:2605.01309v1 Announce Type: new Abstract: Long-tailed distributions are common in real-world recognition tasks, where a few head classes have many samples while most tail classes have very few.
arXiv:2605.01468v1 Announce Type: new Abstract: Long-tailed data bias decision boundaries toward head classes and degrade tail class accuracy. Diffusion-based generative augmentation address this prob
arXiv:2605.01361v1 Announce Type: new Abstract: Decision-Focused Learning (DFL) trains predictors to improve downstream decision quality, but computing regret gradients typically requires differentiat
arXiv:2605.02348v1 Announce Type: new Abstract: Large language models pick up social biases from the data they are trained on and carry those biases into downstream applications, often reinforcing ste
arXiv:2605.01448v1 Announce Type: cross Abstract: Cross-task generalization is a core challenge in open-world robotic manipulation, and the key lies in extracting transferable manipulation knowledge f
arXiv:2605.01858v1 Announce Type: new Abstract: Streaming video understanding requires processing unbounded video streams with limited memory and computation, posing two key challenges. First, continu
arXiv:2605.01667v1 Announce Type: new Abstract: Orderless encoding methods have shown to improve Convolutional Neural Networks (CNNs) for image classification in the context of limited availability of
arXiv:2602.17205v2 Announce Type: replace-cross Abstract: The detection limit of astronomical imaging observations is limited by several noise sources. Some of that noise is correlated between neighbo
arXiv:2605.01283v1 Announce Type: new Abstract: Plants, crops and their yields are essential to our very existence, but diseases and pests cause large losses every year. As such it is vital to ensure
arXiv:2603.23985v2 Announce Type: replace Abstract: Large language models (LLMs) have demonstrated remarkable capabilities, but their massive scale poses significant challenges for practical deploymen
arXiv:2602.00217v2 Announce Type: replace Abstract: Large language models (LLMs) achieve remarkable performance through ever-increasing parameter counts, but scaling incurs steep computational costs.
arXiv:2605.02752v1 Announce Type: new Abstract: Open-world text-guided class-agnostic counting (CAC) has emerged as a flexible paradigm for counting arbitrary object classes by using natural language
arXiv:2605.01718v1 Announce Type: new Abstract: Unlearnable examples (UEs) aim to compromise model training by injecting imperceptible perturbations to clean samples. However, existing UE schemes exhi
arXiv:2603.19675v2 Announce Type: replace Abstract: Recently, world models have been incorporated into the autonomous driving systems to improve the planning reliability. Existing approaches typically
arXiv:2601.21714v2 Announce Type: replace Abstract: The evolution of Large Language Model (LLM) agents towards System~2 reasoning, characterized by deliberative, high-precision problem-solving, requir
arXiv:2605.00850v1 Announce Type: cross Abstract: Foundation models (FMs) for the Earth system learn statistical relationships between physical variables across massive datasets to enable versatile do
arXiv:2605.02275v1 Announce Type: new Abstract: Place recognition is essential for long-term autonomous navigation, enabling loop closure and consistent mapping. Although deep learning has improved pe
arXiv:2507.03787v2 Announce Type: replace Abstract: Static timing analysis is a crucial stage in the VLSI design flow that verifies the timing correctness of circuits. Timing analysis depends on the p
arXiv:2506.18315v2 Announce Type: replace-cross Abstract: LLMs excel at code generation, yet ensuring the functional correctness of their outputs remains a persistent challenge. While recent studies h
arXiv:2501.19201v2 Announce Type: replace Abstract: Chain-of-Thought (CoT) reasoning has become a powerful framework for improving complex problem-solving capabilities in Multimodal Large Language Mod
arXiv:2605.01372v1 Announce Type: new Abstract: Large language models (LLMs) have been widely explored for embedding generation. While recent studies show that in-context learning (ICL) effectively en
arXiv:2605.00731v1 Announce Type: cross Abstract: While Graph Foundation Models (GFMs) have achieved remarkable success in homogeneous graphs, extending them to multi-domain heterogeneous graphs (MDHG
arXiv:2605.02011v1 Announce Type: new Abstract: Automating the drafting of judgment documents is pivotal to judicial efficiency, yet it remains challenging due to the dual requirements of comprehensiv
arXiv:2605.02378v1 Announce Type: new Abstract: In-context learning (ICL) allows large models to adapt to tasks using a few examples, yet its extension to vision-language models (VLMs) remains fragile
arXiv:2505.01185v3 Announce Type: replace-cross Abstract: Achieving sub-10 m indoor ranging with LoRaWAN is challenging because multipath, human blockage, and micro-climate dynamics induce non-station
arXiv:2605.02519v1 Announce Type: new Abstract: Classic Network Intrusion Detection Systems (NIDS) often rely on manual feature engineering to extract meaningful patterns from network traffic data. Ho
arXiv:2605.01869v1 Announce Type: cross Abstract: Token communication has emerged as a promising framework for efficient wireless transmission by representing source data as compact semantic tokens. H
arXiv:2605.02252v1 Announce Type: new Abstract: Fast prototyping of new SE(3) estimation objectives remains awkward in practice. Modern Lie-group frameworks -- GTSAM, manif, Sophus, SymForce, Ceres --
arXiv:2605.01266v1 Announce Type: new Abstract: Zero-shot vision-language models (VLMs) offer a promptable alternative to task-specific training for gross tumor volume (GTV) delineation in non-small-c
arXiv:2605.02464v1 Announce Type: new Abstract: Single-image HDR reconstruction aims to recover high dynamic range radiance from a single low dynamic range (LDR) input, but remains highly ill-posed du
arXiv:2603.12612v2 Announce Type: replace Abstract: Scaling Maximum Entropy Reinforcement Learning (RL) to high-dimensional humanoid control remains a fundamental challenge, as the ''curse of dimensio
arXiv:2605.02705v1 Announce Type: new Abstract: Mobile crowdsensing (MCS) is a distributed sensing architecture that utilizes existing sensors on mobile units (MUs) to perform sensing tasks. A mobile
arXiv:2605.01567v1 Announce Type: cross Abstract: Large language model (LLM) coding agents increasingly operate over repositories, terminals, tests, and execution traces across long software-engineeri
arXiv:2605.01264v1 Announce Type: cross Abstract: Traditional approaches to test case generation often involve manual effort and incur significant computational overhead. Additionally, these approache
arXiv:2508.15202v2 Announce Type: replace Abstract: Process Reward Models (PRMs) supervise intermediate reasoning steps in large language models (LLMs), but existing PRMs are mainly trained on general
arXiv:2605.01373v1 Announce Type: new Abstract: The iterative denoising paradigm of Diffusion Large Language Models (DLMs) endows them with a distinct advantage in global context modeling. However, cu
arXiv:2605.02764v1 Announce Type: new Abstract: We present FoR-Net, a lightweight architecture for semantic segmentation that focuses on identifying and enhancing hard regions. Instead of relying on h