Knowledge catalogue
arXiv:2608.17598v1 Announce Type: new Abstract: Despite the rapid progress of deep neural networks in visual recognition, their adoption in high-risk medical applications remains limited due to reliab
Thoughts About Scaling Law Scaling, but not only of parameters. Every model release now ends with the same question: how many parameters? It isn't a question that can be answered on its own. Parameter
arXiv:2608.17268v1 Announce Type: cross Abstract: Curriculum learning has been widely adopted in the post-training of large language models by organizing training data from easy to hard. However, its
arXiv:2608.17325v1 Announce Type: new Abstract: Tokenization is a fundamental component of language modeling pipelines. Despite its importance, it is often fixed, even though it significantly impacts
arXiv:2608.15984v1 Announce Type: new Abstract: Motion Language Models (MoLMs) typically understand human motions by tokenizing 3D motion and processing the resulting tokens using a language model. Ho
arXiv:2608.14721v1 Announce Type: new Abstract: Vision-language models (VLMs) have been widely employed in understanding and reasoning tasks for unmanned aerial vehicles (UAVs). Existing UAV benchmark
arXiv:2608.15456v1 Announce Type: new Abstract: Remote sensing (RS) foundation models provide transferable Earth observation representations across sensors, resolutions, and geographies, yet most rema
arXiv:2608.15721v1 Announce Type: new Abstract: This report describes our submission to the Big Cross-Modal Attenuation Correction (BIC-MAC) 2026 Challenge for CT-less PET attenuation correction throu
arXiv:2608.16351v1 Announce Type: new Abstract: Dexterous grasp generation that considers arm-related constraints is crucial in real-world scenarios involving arm environment collision avoidance, work
arXiv:2608.16103v1 Announce Type: new Abstract: Open-vocabulary referring segmentation in 3D Gaussian Splatting (3DGS) requires a neural model to select Gaussian primitives according to free-form lang
arXiv:2506.15700v2 Announce Type: replace-cross Abstract: Control contraction metrics (CCMs)-defined by Riemannian metrics under which a closed-loop system is incrementally exponentially stable-offer
arXiv:2608.15790v1 Announce Type: new Abstract: Crevasse mapping from uncrewed aerial vehicle (UAV) imagery matters for glaciological research and for field safety in glaciated terrain. Yet, pixel-lev
arXiv:2608.16310v1 Announce Type: new Abstract: Residents' perception of the urban streetscape is an important factor in public health, active mobility, and social wellbeing. Street view imagery (SVI)
arXiv:2608.16718v1 Announce Type: new Abstract: Identifying cell types directly from routine haematoxylin and eosin (H&E) histology would enable single-cell analysis at scale, but training such models
arXiv:2608.14916v1 Announce Type: cross Abstract: AI-generated music detectors are commonly evaluated against original songs, but real-world uploads are often remixed, re-encoded, pitch-shifted, or ot
arXiv:2608.16161v1 Announce Type: cross Abstract: General-purpose text embedding models are designed to capture semantic similarity but are not optimised for distinguishing entity records that represe
arXiv:2608.16632v1 Announce Type: new Abstract: Deep learning-based object detectors are fundamental to intelligent transportation systems, enabling traffic monitoring, vehicle analytics, and infrastr
arXiv:2608.15282v1 Announce Type: cross Abstract: Earth observation foundation models (EOFMs) are emerging as reusable representation frameworks for data-driven retrieval, prediction and process model
arXiv:2608.15749v1 Announce Type: new Abstract: Existing 3D editing methods have made notable progress in controllability, yet they remain limited in several important ways. Most approaches rely on te
arXiv:2608.16416v1 Announce Type: new Abstract: Automated machine learning (AutoML) systems search for pipelines within a space of preprocessing operators, learners, and hyper-parameters specified in
arXiv:2608.16523v1 Announce Type: new Abstract: Event cameras generate asynchronous, high-frequency data streams offering spatially sparse information at lower latency than traditional cameras.In prin
arXiv:2608.15296v1 Announce Type: new Abstract: Audio-driven 3D facial animation is essential for advancing immersion and interactivity in virtual experiences. Although recent advances have shown prom
arXiv:2608.15651v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) represents 3D content with anisotropic primitives that jointly encode geometry and appearance. Fixed-budget encoders consum
arXiv:2608.16837v1 Announce Type: cross Abstract: Humanoid robots hold great promise as general-purpose agents in human-centered environments, yet generalist vision-language-action (VLA) foundation mo
arXiv:2604.01322v2 Announce Type: replace Abstract: Trampoline gymnastics involves extreme human poses and uncommon viewpoints, on which state-of-the art pose estimation models tend to under-perform.
arXiv:2608.15299v1 Announce Type: cross Abstract: Sparsely-activated Mixture-of-Experts (MoE) Transformers universally fix the same number of routed experts across all layers, a convention that ignore
arXiv:2608.15483v1 Announce Type: new Abstract: Modern deep networks are trained through long update trajectories, yet their temporal organization remains less systematically characterized than archit
arXiv:2602.22431v2 Announce Type: replace-cross Abstract: Millimeter-wave (mmWave) radar captures are band-limited and noisy, making for difficult reconstruction of intelligible full-bandwidth speech.
arXiv:2608.15311v1 Announce Type: new Abstract: Federated instruction fine-tuning enables Large Language Models (LLMs) to adapt to decentralized, privacy-sensitive data without requiring data sharing.
arXiv:2608.14835v1 Announce Type: new Abstract: Dynamic scene graphs (DSGs) capture spatio-temporal interactions across videos as langlesubject, predicate, objectrangle triplets, and underpin downstre
arXiv:2608.14656v1 Announce Type: cross Abstract: Photoplethysmography (PPG) is widely used in consumer wearables because of its low cost and ease of acquisition. However, unlike electrocardiography (
arXiv:2608.15026v1 Announce Type: new Abstract: Post-training of vision-language-action (VLA) models typically relies on expert demonstrations and policy interaction trajectories. However, in long-hor
arXiv:2608.16419v1 Announce Type: cross Abstract: Large language models can describe mechanisms, yet scalable post-training still depends on costly, manually curated biological reasoning traces. Here
arXiv:2608.16198v1 Announce Type: cross Abstract: Dermatology models face distribution shifts in teledermatology settings, where submitted images differ from the training data in lighting, angle, dist
arXiv:2510.07546v2 Announce Type: replace Abstract: We address the task of video style transfer with diffusion models, where the goal is to preserve the context of an input video while rendering it in
arXiv:2608.16289v1 Announce Type: new Abstract: Automated e-commerce poster design requires both high-quality poster generation and flexible editing of existing designs. However, most existing methods
arXiv:2608.14664v1 Announce Type: new Abstract: How can we determine whether a trained neural network is already deep enough? We study this under a fixed function-preserving residual-growth protocol s
arXiv:2608.14947v1 Announce Type: new Abstract: Detecting opioid craving from wearable physiological signals is critical yet difficult, with the potential to support proactive interventions for indivi
arXiv:2608.15680v1 Announce Type: cross Abstract: Vision-language-action (VLA) models improve robotic manipulation but remain vulnerable to compounding errors, scene changes, and off-trajectory states
arXiv:2608.16195v1 Announce Type: new Abstract: Achieving human-level competitive intelligence and physical agility in humanoid robots remains a profound challenge, particularly in contact-rich and hi
arXiv:2608.16287v1 Announce Type: new Abstract: Joint-embedding predictive world models plan by scoring predicted terminal embeddings against a goal embedding using a cost defined on the representatio
arXiv:2608.14922v1 Announce Type: cross Abstract: Mechanistic interpretability has recently expanded to Vision Transformers (ViTs), with Sparse Autoencoders (SAEs) increasingly used as post-hoc tools
arXiv:2608.16585v1 Announce Type: new Abstract: Video Diffusion Transformers (DiTs) spend most of their compute inside the Self-Attention operation, whose cost grows quadratically, O(n^2), with the nu
arXiv:2607.10745v2 Announce Type: replace Abstract: This paper presents the first ChineseBabyLM Challenge, organized as part of NLPCC 2026. The challenge asked participants to train language models fr
arXiv:2608.16245v1 Announce Type: new Abstract: Disentangled representation learning seeks latent representations whose indicidual dimensions each align with a distinct covariate. Unsupervised approac
arXiv:2604.02637v2 Announce Type: replace Abstract: As large language models (LLMs) become increasingly persuasive, there is concern that people's opinions and decisions may be influenced across vario
arXiv:2608.15816v1 Announce Type: new Abstract: As Vision-Language-Action (VLA) models scale toward real-world deployment, contact-rich manipulation exposes a critical blind spot: these policies encod
arXiv:2608.14712v1 Announce Type: cross Abstract: Each row of a transformer's attention matrix is a probability distribution over tokens, and in trained models most of that probability lands on a sing
arXiv:2608.14633v1 Announce Type: cross Abstract: Wolff-Parkinson-White (WPW) syndrome is a congenital cardiac pre-excitation, clinically important and often missed on the resting 12-lead ECG. Detecti
arXiv:2510.18135v2 Announce Type: replace Abstract: Generative world models (WMs) can now simulate worlds with striking visual realism, which naturally raises the question of whether they can endow em
arXiv:2608.13626v1 Announce Type: new Abstract: A hidden state signal can be decodable or causally usable without supporting a reusable action map. We test whether action maps fitted without a source
arXiv:2608.13940v1 Announce Type: new Abstract: AI research agents (AIRA) can now propose, implement, and evaluate their own machine learning experiments, but progress on frontier tasks is throttled b
arXiv:2603.18871v2 Announce Type: replace Abstract: Urban Vehicular Ad-Hoc Networks (VANETs) can become fragmented because buildings obstruct wireless links and vehicle mobility continuously changes t
arXiv:2608.14403v1 Announce Type: new Abstract: Subject-driven image personalization---generating new images that preserve the identity of one or several reference subjects in novel scenes---is a foun
arXiv:2608.13741v1 Announce Type: new Abstract: Synthesizing time series from natural language is emerging as the most expressive form of controllable time series generation. However, existing text-co
arXiv:2608.14428v1 Announce Type: new Abstract: 3D object detection from LiDAR point clouds is a core problem in autonomous driving. Recent advances in self-supervised learning (SSL) enable scalable p
arXiv:2608.13698v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR), often optimized with Group Relative Policy Optimization (GRPO), has become a central recipe for i
arXiv:2608.14290v1 Announce Type: new Abstract: We introduce Mobius-v0, an architecture that comprises a globally shared Memory (FFN) that stores knowledge vectors and multiple Reasoners (Self-Attn) t
arXiv:2602.12314v2 Announce Type: replace-cross Abstract: We present LatentAM, an online 3D Gaussian Splatting (3DGS) mapping framework that builds scalable latent feature maps from streaming RGB-D ob
arXiv:2602.11903v3 Announce Type: replace-cross Abstract: No-reference video quality assessment (NR-VQA) for gaming videos is challenging due to limited human-rated datasets and unique content charact