Knowledge catalogue
arXiv:2605.04913v1 Announce Type: new Abstract: LLM post-training typically propagates task gradients through the full depth of the model. Although this end-to-end structure is simple and general, it
arXiv:2605.01999v1 Announce Type: new Abstract: Classifying brain tumors using magnetic resonance imaging (MRI) is crucial for early diagnosis and treatment; however, tumor heterogeneity and a dearth
arXiv:2605.01854v1 Announce Type: new Abstract: We propose a method to reconstruct high-fidelity human avatars from multi-view video that can run on mobile devices. Many works can model high-quality G
arXiv:2605.02772v1 Announce Type: new Abstract: While linear-complexity attention mechanisms offer a promising alternative to Softmax attention for overcoming the quadratic bottleneck, training such m
arXiv:2602.04509v4 Announce Type: replace Abstract: Fine-tuning Multimodal Large Language Models (MLLMs) on task-specific data is an effective way to improve performance on downstream applications. Ho
arXiv:2605.01632v1 Announce Type: new Abstract: Models that are indistinguishable on in-distribution data can behave very differently under distribution shift. We introduce Perturb-and-Correct (P&C),
arXiv:2605.01759v1 Announce Type: new Abstract: Scene-level point cloud self-supervised learning (PC-SSL) has demonstrated potential in enhancing the generalization capability of 3D vision models. Des
arXiv:2605.01699v1 Announce Type: new Abstract: Recent attacks show that behavioural unlearning of large language models leaves internal traces recoverable by adversarial probes. We characterise where
arXiv:2605.02589v1 Announce Type: new Abstract: Optical Coherence Tomography (OCT) has become one of the most used imaging modality in ophthalmology. It provides high-resolution, non-invasive visualiz
arXiv:2605.02283v1 Announce Type: new Abstract: Vision foundation models have attracted significant attention for their ability to leverage large-scale unlabeled visual data. This advantage is particu
arXiv:2605.00251v1 Announce Type: cross Abstract: Existing voice deepfake detection and localization models rely heavily on representations extracted from speech foundation models (SFMs). However, dow
arXiv:2603.15988v2 Announce Type: replace-cross Abstract: Dysarthric speech quality assessment (DSQA) is critical for clinical diagnostics and inclusive speech technologies. However, subjective evalua
arXiv:2506.09110v3 Announce Type: replace Abstract: Electroencephalography (EEG) provides real-time insights into brain activity and supports diverse applications in neuroscience. While EEG foundation
arXiv:2604.27263v1 Announce Type: new Abstract: Subword tokenization is an essential part of modern large language models (LLMs), yet its specific contributions to training efficiency and model perfor
arXiv:2604.27178v1 Announce Type: new Abstract: Recent advances in large-scale visual representation learning have significantly improved performance in plant species and plant disease recognition tas
arXiv:2511.12386v2 Announce Type: replace Abstract: Quantum machine learning has emerged as a promising approach for medical image analysis, particularly in settings where compact models and expressiv
arXiv:2604.27889v1 Announce Type: new Abstract: Semantic segmentation and change detection are two fundamental challenges in remote sensing, requiring models to capture either spatial semantics or tem
arXiv:2604.27356v1 Announce Type: cross Abstract: Heterogeneous graphs are widely used to model multi-relational systems, but missing node attributes remain a major bottleneck for downstream learning.
arXiv:2601.08611v2 Announce Type: replace-cross Abstract: The growing scale of online misinformation urgently demands Automated Fact-Checking (AFC). Existing benchmarks for evaluating AFC systems, how
arXiv:2604.25574v1 Announce Type: new Abstract: In autonomous driving, camera-radar fusion offers complementary sensing and low deployment cost. Existing methods perform fusion through input mixing, f
arXiv:2604.25164v1 Announce Type: new Abstract: Recent advances in text-driven human motion generation enable models to synthesize realistic motion sequences from natural language descriptions. Howeve
arXiv:2604.25244v1 Announce Type: cross Abstract: Protein dynamics underlie many biological functions, yet remain difficult to characterize due to the high computational cost of molecular dynamics sim
arXiv:2603.15954v2 Announce Type: replace Abstract: Real-time AI experiences call for on-device large language models (OD-LLMs) optimized for efficient deployment on resource-constrained hardware. The
arXiv:2506.20941v3 Announce Type: replace Abstract: Large language models are trained on massive corpora of web data, which may include private data, copyrighted material, factually inaccurate data, o
arXiv:2604.25316v1 Announce Type: new Abstract: Domain adaptation (DA) addresses the challenge of transferring a machine learning model trained on a source domain to a target domain with a different d
arXiv:2511.21517v2 Announce Type: replace Abstract: Unlike text, speech conveys information about the speaker, such as gender, through acoustic cues like pitch. This gives rise to modality-specific bi
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:2604.24575v1 Announce Type: new Abstract: Diffusion models are primarily trained for image synthesis, yet their denoising trajectories encode rich, spatially aligned visual priors. In this paper
arXiv:2604.23385v1 Announce Type: new Abstract: Transthoracic echocardiography is the reference standard for confirming structural heart disease (SHD), but first-line screening is limited by cost, wor
arXiv:2604.24563v1 Announce Type: cross Abstract: Machine-learning interatomic potentials (MLIPs) have enabled molecular dynamics at near ab initio accuracy, yet remain limited to energies and forces
arXiv:2604.24469v1 Announce Type: cross Abstract: Content-based image retrieval (CBIR) systems enable users to search images based on visual content instead of relying on metadata. The text domain has
arXiv:2604.22817v1 Announce Type: cross Abstract: Recent advances in speech-aware language models have coupled strong acoustic encoders with large language models, enabling systems that move beyond tr
arXiv:2604.22832v1 Announce Type: cross Abstract: Microscopy-based phenotypic profiling is scalable for drug discovery but lacks the mechanistic depth of transcriptomics, which remains costly and scar
arXiv:2604.22938v1 Announce Type: cross Abstract: The promise of data-driven materials discovery remains constrained by the scarcity of large, high-quality, and accessible experimental datasets. Here,
arXiv:2604.23604v1 Announce Type: new Abstract: Understanding the surrounding environment is fundamental in autonomous driving and robotic perception. Distinguishing between known classes and previous
arXiv:2603.19451v2 Announce Type: replace-cross Abstract: Fine-grained representation learning is crucial for retrieval and phrase grounding in chest X-rays, where clinically relevant findings are oft
arXiv:2604.24715v1 Announce Type: new Abstract: Hybrid sequence models that combine efficient Transformer components with linear sequence modeling blocks are a promising alternative to pure Transforme
arXiv:2604.23627v1 Announce Type: new Abstract: Resources for Grammatical Error Correction (GEC) in non-English languages are scarce, while available spellcheckers in these languages are mostly limite
arXiv:2503.05587v3 Announce Type: replace-cross Abstract: Robustness has become a critical attribute for the deployment of RAG systems in real-world applications. Existing research focuses on robustne
arXiv:2604.24597v1 Announce Type: cross Abstract: We provide evidence of quantum kernel advantage under noiseless simulation in binary insurance classification on MIMIC-CXR chest radiographs using qua
arXiv:2604.24543v1 Announce Type: new Abstract: RGB-Thermal (T) crowd counting aims to integrate visible-spectrum and thermal infrared information to improve the robustness of crowd density estimation
arXiv:2604.23073v1 Announce Type: new Abstract: Vision-language-action (VLA) models can learn to perform diverse manipulation skills 'out of the box,' but achieving the precision and speed that real-w
arXiv:2303.14897v4 Announce Type: replace Abstract: Imagining the future trajectory is the key for robots to make sound planning and successfully reach their goals. Therefore, text-conditioned video p
arXiv:2604.22825v1 Announce Type: cross Abstract: Large segmentation foundation models such as the Segment Anything Model (SAM) have reshaped promptable segmentation in natural images, and recent effo
arXiv:2604.22826v1 Announce Type: new Abstract: Industrial CAD workflows require robust, generalizable 3D geometric representations supporting accuracy and explainability. We introduce Shape, a self-s
arXiv:2511.17411v2 Announce Type: replace-cross Abstract: Robotic Foundation Models (RFMs) hold great promise as generalist, end-to-end systems for robot control. Yet their ability to generalize acros
arXiv:2604.23750v1 Announce Type: cross Abstract: Hypernetwork-based methods such as Doc-to-LoRA internalize a document into an LLM's weights in a single forward pass, but they fail systematically on
arXiv:2604.22529v1 Announce Type: new Abstract: Self-supervised learning has achieved remarkable success in learning visual representations from clean data, yet remains challenging when clean observat
arXiv:2604.22167v1 Announce Type: cross Abstract: Language models are increasingly capable and are being rapidly deployed on a population-level scale. As a result, the safety of these models is increa
arXiv:2602.06019v2 Announce Type: replace Abstract: Existing techniques for accelerating language model inference, such as speculative decoding, require training auxiliary speculator models and buildi
arXiv:2604.22753v1 Announce Type: new Abstract: Scaling laws are used to plan multi-million-dollar training runs, but fitting those laws can itself cost millions. In modern large-scale workflows, asse
arXiv:2604.21921v1 Announce Type: new Abstract: We present Omni, a unified multimodal model natively trained on diverse modalities, including text, images, videos, 3D geometry, and hidden representati
arXiv:2604.20909v1 Announce Type: new Abstract: Downhole drilling telemetry presents a fundamental labeling asymmetry: surface sensor data are generated continuously at 1~Hz, while labeled downhole me
arXiv:2604.21668v1 Announce Type: new Abstract: The world knowledge and reasoning capabilities of text-based large language models (LLMs) are advancing rapidly, yet current approaches to human motion
arXiv:2604.21265v1 Announce Type: new Abstract: We show that pre-training a Transformer on music before language significantly accelerates language acquisition. Using piano performances (MAESTRO datas
arXiv:2604.21076v1 Announce Type: cross Abstract: Medication reconciliation at clinical handoffs is a high-stakes, error-prone process. Large language models are increasingly proposed to assist with t
arXiv:2604.21395v1 Announce Type: cross Abstract: We prove that empirical risk minimisation (ERM) imposes a necessary geometric constraint on learned representations: any encoder that minimises superv
arXiv:2604.21148v1 Announce Type: new Abstract: Studies on bias in Automatic Speech Recognition (ASR) tend to focus on reporting error rates for speakers of underrepresented dialects, yet less researc
arXiv:2604.20051v1 Announce Type: new Abstract: Self-play has recently emerged as a promising paradigm to train Large Language Models (LLMs). In self-play, the target LLM creates the task input (e.g.,
arXiv:2509.03740v3 Announce Type: replace-cross Abstract: Vision-language models (VLMs) like CLIP have shown impressive zero-shot and few-shot learning capabilities across diverse applications. Howeve