Knowledge catalogue
arXiv:2605.11130v1 Announce Type: new Abstract: Critical events in multivariate time series, from turbine failures to cardiac arrhythmias, demand accurate prediction, yet labeled data is scarce becaus
arXiv:2605.11208v1 Announce Type: new Abstract: Automated, clinician-grade assessment reports for surgical procedures could reduce documentation burden and provide objective feedback, yet remain chall
arXiv:2605.11195v1 Announce Type: new Abstract: Large language models (LLMs) trained on web-scale corpora can memorize sensitive training data, posing significant privacy risks. Differential privacy (
Interesting paper. What I like about this is that it is a relatively low-commitment attention modification. I.e., one can use it during most of training, switch back to vanilla attention near the end,
arXiv:2603.17510v2 Announce Type: replace Abstract: Robots operating in human-shared environments must not only achieve task-level navigation objectives such as safety and efficiency, but also adapt t
arXiv:2605.12471v1 Announce Type: cross Abstract: We introduce KV-Fold, a simple, training-free long-context inference protocol that treats the key-value (KV) cache as the accumulator in a left fold o
arXiv:2605.11115v1 Announce Type: new Abstract: High Dynamic Range (HDR) generation remains challenging for generative models, which are largely limited to low dynamic range outputs. Recent diffusionb
arXiv:2503.09051v2 Announce Type: replace Abstract: We propose a novel model-level GNN explanation framework that shifts the explanation target from class-wise rule extraction to rule-based logit reco
arXiv:2605.11762v1 Announce Type: new Abstract: Learning robust navigation policies remains a core challenge in robotics. Offline imitation learning suffers from distribution shift and compounding err
arXiv:2605.12492v1 Announce Type: new Abstract: We introduce Pion, a spectrum-preserving optimizer for large language model (LLM) training based on orthogonal equivalence transformation. Unlike additi
arXiv:2605.11506v1 Announce Type: new Abstract: Score-based diffusion models achieve state-of-the-art performance for inverse problems, but their practical deployment is hindered by long inference tim
arXiv:2605.11151v1 Announce Type: cross Abstract: Offline-to-online reinforcement learning (RL) improves sample efficiency by leveraging pre-collected datasets prior to online interaction. A key chall
arXiv:2605.11502v1 Announce Type: new Abstract: Accurately and consistently indexing biomedical literature by publication type and study design is essential for supporting evidence synthesis and knowl
arXiv:2605.11840v1 Announce Type: new Abstract: Radar-camera depth estimation must turn an ultra-sparse, all-weather, metric radar signal into a dense per-pixel depth map. Existing methods -- concaten
arXiv:2605.11854v1 Announce Type: new Abstract: Diffusion Language Models (DLMs) have recently emerged as a promising alternative to autoregressive language models, offering stronger global awareness
arXiv:2605.11547v1 Announce Type: new Abstract: Flow matching models generate samples by numerically integrating a learned velocity field, with each integration step requiring a neural network evaluat
arXiv:2605.11689v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) architectures have become standard in large language models, yet many of their core design choices - expert count, granularit
arXiv:2605.12466v1 Announce Type: cross Abstract: Looped Transformers offer a promising alternative to purely feed-forward computation by iteratively refining latent representations, improving languag
arXiv:2511.07767v2 Announce Type: replace Abstract: Schedule-Free SGD, proposed in [Defazio et al., 2024], achieves optimal convergence rates without requiring the training horizon in advance, by repl
arXiv:2605.11167v1 Announce Type: new Abstract: Existing multi-model and tool-augmented systems communicate by generating text, serializing every exchange through the output vocabulary. Can two pretra
TST has two moving parts that can be ablated independently: the input-side averaging and the output-side multi-hot cross-entropy. Both, on their own, outperform the matched-FLOPs baseline. Their effec
arXiv:2605.12088v1 Announce Type: new Abstract: Multi-reference image generation aims to synthesize images from textual instructions while faithfully preserving subject identities from multiple refere
arXiv:2605.11864v1 Announce Type: cross Abstract: Listwise reranking is a key yet computationally expensive component in vision-centric retrieval and multimodal retrieval-augmented generation (M-RAG)
arXiv:2605.08282v1 Announce Type: cross Abstract: Purpose: We aim to enhance the image quality of point-of-care ultrasound (POCUS) devices using deep learning and a novel paired dataset of POCUS and h
arXiv:2605.10819v1 Announce Type: cross Abstract: Vision-language-action (VLA) models remain constrained by the scarcity of action-labeled robot data, whereas action-free videos provide abundant evide
arXiv:2605.09622v1 Announce Type: cross Abstract: Voxel-wise dose prediction is a critical yet challenging task in practical radiotherapy (RT) planning, as bespoke models trained from scratch often st
arXiv:2603.10126v2 Announce Type: replace-cross Abstract: We propose a standalone autoregressive (AR) Action Expert that generates actions as a continuous causal sequence while conditioning on refresh
arXiv:2605.08173v1 Announce Type: new Abstract: The generalization performance (GP) of deep learning-based arbitrary-scale image super-resolution (ASISR) methods is subject to limited training dataset
arXiv:2605.08663v1 Announce Type: new Abstract: We propose CAST, a dual-stream architecture that utilizes channel-aware spatial transfer learning for isolated sign language recognition addressing the
arXiv:2603.05495v2 Announce Type: replace Abstract: To scale optimization and simulation, prior work has explored training machine-learning surrogates that map problem parameters to solutions inexpens
arXiv:2605.10817v1 Announce Type: new Abstract: Clinical EEG interpretation requires reasoning over full EEG sessions and integrating signal patterns with clinical context. Existing EEG foundation mod
arXiv:2605.09688v1 Announce Type: new Abstract: Feedforward 3D Gaussian Splatting (3DGS) often struggles in trajectory-based sparse-view driving scenes. Existing Gaussian repair methods mainly target
arXiv:2605.09126v1 Announce Type: new Abstract: Asynchronous DiLoCo systems may receive pseudo-gradients computed several outer rounds earlier, yet the standard Nesterov outer optimizer does not expli
arXiv:2605.08960v1 Announce Type: cross Abstract: Crystal generative models mainly learn what stable crystals look like, with little explicit supervision for what makes them stable. We reveal a substa
arXiv:2605.09604v1 Announce Type: new Abstract: Millimeter-wave (mmWave) radar provides privacy-preserving sensing and is valuable for human action recognition (HAR). Existing mmWave point cloud datas
arXiv:2605.10184v1 Announce Type: cross Abstract: We develop a foundation model using 1.2m high resolution satellite images of the Netherlands. By combining a Convolutional Neural Network and a Vision
arXiv:2605.08167v1 Announce Type: cross Abstract: The increasing availability of advanced image editing tools has led to a significant rise in manipulated digital content, posing serious challenges fo
arXiv:2604.05064v2 Announce Type: replace-cross Abstract: Synthetic data is essential for training foundation models for time series (FMTS), but most generators assume static correlations, and are typ
arXiv:2602.03783v2 Announce Type: replace-cross Abstract: Modern AI agents such as large language models are trained on diverse tasks -- translation, code generation, mathematical reasoning, and text
arXiv:2605.08434v1 Announce Type: new Abstract: Vision-language-action (VLA) models provide a promising paradigm for scalable robotic manipulation, yet their reliance on success-only behavioral clonin
arXiv:2605.10439v1 Announce Type: new Abstract: Low-Rank Adaptation (LoRA) has become a widely used mechanism for customizing diffusion models, enabling users to inject new visual concepts or styles t
arXiv:2605.09861v1 Announce Type: cross Abstract: Alignment, the tendency of adjacent weight matrices in deep networks to develop compatible subspace orientations, underlies gradient flow, Neural Coll
arXiv:2605.10302v1 Announce Type: new Abstract: Existing approaches to controllable generation typically rely on fine-tuning, auxiliary networks, or test-time search. We show that flow matching admits
arXiv:2605.10762v1 Announce Type: cross Abstract: Long-video understanding in VLMs is bottlenecked by a single monolithic forward pass over thousands of frames at quadratic attention cost. A common mi
arXiv:2605.08254v1 Announce Type: cross Abstract: As foundation models grow in capability, the ability to efficiently and reliably control their behavior becomes critical. Fine-tuning these models can
arXiv:2605.08577v1 Announce Type: new Abstract: In modern GANs, maintaining an Exponential Moving Average (EMA) of the generator's weights is a standard practice, as such an averaged model consistentl
arXiv:2605.10523v1 Announce Type: new Abstract: The field of image-to-video generation has made remarkable progress. However, challenges such as human limb twisting and facial distortion persist, espe
arXiv:2010.03496v4 Announce Type: replace-cross Abstract: Knowledge Graphs (KG) are of vital importance for multiple applications on the web, including information retrieval, recommender systems, and
arXiv:2605.10727v1 Announce Type: new Abstract: We propose kernel-gradient drifting, a one-step generative modeling framework that replaces the fixed Euclidean displacement direction in drifting model
arXiv:2605.08732v1 Announce Type: cross Abstract: Modern vision-based world models can represent observations as compact yet expressive latent manifolds, but fast goal-oriented planning in these space
arXiv:2605.10186v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly integrated into legal drafting and research workflows, where incorrect citations or fabricated precedent
arXiv:2509.20786v3 Announce Type: replace Abstract: Training deep neural networks with noise and data heterogeneity is a major challenge. We introduce Lightweight Learnable Adaptive Weighting (LiLAW),
arXiv:2605.08777v1 Announce Type: cross Abstract: Mode separation, namely how sharply a distribution fragments into barrier-separated clusters, is a fundamental geometric property of densities, diffic
arXiv:2605.10537v1 Announce Type: new Abstract: Memory consolidation, the process by which transient experiences are transformed into stable, structured representations, is a foundational organizing p
arXiv:2605.09479v1 Announce Type: cross Abstract: We study full-reference image quality assessment from a machine-centric perspective, where images are evaluated by how well they preserve information
arXiv:2603.28254v2 Announce Type: replace Abstract: Orthogonalized-update optimizers such as Muon improve training of matrix-valued parameters, but existing extensions typically either rescale updates
arXiv:2605.09176v1 Announce Type: cross Abstract: Training large language models requires optimization algorithms that are not only statistically effective, but also computationally and memory efficie
arXiv:2605.09991v1 Announce Type: new Abstract: Mode connectivity has been widely studied, yet the role of the optimizer remains underexplored. We revisit it through optimizer-induced implicit regular
arXiv:2605.08516v1 Announce Type: new Abstract: Transparent decision-making is essential for traffic signal control (TSC) systems to earn public trust. However, traditional reinforcement learning-base
arXiv:2605.09503v1 Announce Type: new Abstract: Large-scale visual generative models have achieved remarkable performance. However, their high computational and memory costs make deployment challengin