Knowledge catalogue
arXiv:2604.01597v2 Announce Type: replace Abstract: Traditional RL algorithms like Proximal Policy Optimization (PPO) typically train on the entire rollout buffer, operating under the assumption that
arXiv:2608.23943v1 Announce Type: cross Abstract: High-fidelity image-to-3D generation requires a 3D representation that captures both geometry and appearance. To support relighting and integration in
arXiv:2608.24342v1 Announce Type: cross Abstract: Synthetic image generation is a promising strategy to address data scarcity and the underrepresentation of clinically important phenotypes in medical
arXiv:2608.24340v1 Announce Type: cross Abstract: The prediction of student engagement from the online tutoring videos is difficult because engagement is a multidimensional construct comprising distin
arXiv:2608.24486v1 Announce Type: cross Abstract: Purpose: To quantify how evaluation annotations influence measured pulmonary embolism (PE) segmentation performance relative to model training changes
arXiv:2608.24026v1 Announce Type: new Abstract: Recent end-to-end neural motion planners generate trajectories from raw sensor observations, avoiding the privileged geometric models required by classi
arXiv:2411.15209v3 Announce Type: replace Abstract: The expansion of time-series data from sensors and monitoring systems has made compact representations increasingly important. Such representations
arXiv:2608.24263v1 Announce Type: new Abstract: Change data synthesis provides a cost-effective solution for expanding training data and improving the performance of change detection models. However,
arXiv:2608.23930v1 Announce Type: new Abstract: Single-image 3D scene reconstruction must complete partially observed objects and place them coherently in a shared observation-aligned scene frame. Obj
arXiv:2608.24555v1 Announce Type: cross Abstract: Prehospital stroke assessment aims to accurately identify stroke symptoms and make rapid decisions through standardized procedures within an extremely
arXiv:2608.23582v1 Announce Type: cross Abstract: We present the Transformer Accelerator (TFA), a synthesizable, parameterizable INT8 memory-to-memory engine for transformer inference. One time-multip
arXiv:2608.24756v1 Announce Type: new Abstract: Seagrass meadows are crucial blue-carbon habitats, and mapping their extent is a prerequisite for coastal management and carbon inventory. Optical satel
arXiv:2608.24563v1 Announce Type: new Abstract: Imaging factor disentanglement in text-to-image generation aims to independently control image acquisition properties such as types of camera lenses, se
arXiv:2608.23261v1 Announce Type: new Abstract: Event extraction is fundamental to information extraction. Prior approaches often separate event detection and argument extraction or depend on dataset-
arXiv:2608.22313v1 Announce Type: new Abstract: Learning multi-label image classification with incomplete annotations is a challenging task that has been widely studied for its superior trade-off betw
arXiv:2608.21926v1 Announce Type: new Abstract: Unmanned aerial vehicle (UAV) navigation in modern low-altitude environments requires more accurate pose alignment in the final approach stage for targe
arXiv:2607.10358v2 Announce Type: replace-cross Abstract: Foundation models are increasingly used as image feature extractors for mammography, but their robustness under external domain shift remains
arXiv:2608.22294v1 Announce Type: new Abstract: World models for physical interaction are typically trained to predict future observations or latent features; however, a planning-oriented model must a
arXiv:2606.09590v2 Announce Type: replace Abstract: Medical language models (LMs) can memorize and reproduce protected health information, but privacy evaluations often focus on recovery of training t
arXiv:2608.23114v1 Announce Type: cross Abstract: Predicting transcriptome-wide responses to unseen genetic perturbations remains a major computational challenge because accurate prediction requires r
arXiv:2608.22819v1 Announce Type: new Abstract: Text-conditioned image-to-video (I2V) generation has advanced rapidly, yet generating videos with multiple subjects remains challenging. A model must si
arXiv:2409.16183v2 Announce Type: replace Abstract: Radiology is a vital and complex component of modern clinical workflow and covers many tasks. Recently, vision-language (VL) foundation models in me
arXiv:2608.23549v1 Announce Type: new Abstract: Rendering views using 3D scene representations such as Gaussian Splatting (3DGS), Neural Radiance Fields (NeRF), meshes, or even point clouds produces a
arXiv:2608.23000v1 Announce Type: new Abstract: Fully online embodied learning requires synaptic adaptation to acquire new behaviors while preserving previously learned dynamics during ongoing interac
arXiv:2608.23204v1 Announce Type: new Abstract: Decision-making in high-dimensional, nonlinear systems remains a central challenge in robotics. While model-based methods like Model Predictive Control
arXiv:2512.21076v2 Announce Type: replace-cross Abstract: The growing availability of books and textual materials in digital learning environments necessitates reliable semantic organization to suppor
arXiv:2608.21446v1 Announce Type: cross Abstract: We study whether the loss design of High-Fidelity Generative Image Compression (HiFiC), a GAN-based neural codec originally built for natural photogra
arXiv:2608.21811v1 Announce Type: new Abstract: Reinforcement learning for vision-language math reasoning starves under sparse reward: on a pool of 20,830 visual-math problems where Qwen2-VL-2B answer
arXiv:2608.22879v1 Announce Type: new Abstract: Task-specific lightweight models for surgical phase recognition excel at capturing temporal dynamics but generalize poorly under domain shift. Conversel
arXiv:2608.22403v1 Announce Type: new Abstract: Human video is playing an increasingly central role in training World Action Models (WAMs), owing to its diversity and low collection cost relative to t
arXiv:2607.16327v2 Announce Type: replace Abstract: Medical image segmentation is essential for modern computer-aided medicine. Recently, text-guided segmentation has shown promise by incorporating cl
arXiv:2511.18980v2 Announce Type: replace-cross Abstract: Foundation models (FM) are transforming artificial intelligence by enabling generalizable, data-efficient solutions across different domains f
arXiv:2608.23238v1 Announce Type: new Abstract: We present Mover360, a controllable object manipulation framework for 360{eg} images. Unlike perspective images, 360{eg} images in equirectangular proje
arXiv:2608.22273v1 Announce Type: cross Abstract: Pathological and more broadly non-canonical speech present significant challenges for automatic phoneme recognition due to systematic deviations from
arXiv:2412.04806v2 Announce Type: replace-cross Abstract: Adapting Large Language Models (LLMs) trained on discrete text data, to forecast continuous time series signals is challenging. While finetuni
arXiv:2608.23476v1 Announce Type: new Abstract: Narrow fine-tuning on small, domain-specific datasets can produce broad and surprising changes in model behavior-a phenomenon called weird generalizatio
arXiv:2601.17885v2 Announce Type: replace-cross Abstract: Bimanual manipulation in cluttered scenes requires policies that remain stable under occlusions, viewpoint changes and scene variations. Exist
arXiv:2608.21367v1 Announce Type: cross Abstract: Protein-peptide interactions are central to cellular regulation and peptide-based drug discovery, yet existing computational methods mainly focus on i
arXiv:2608.22359v1 Announce Type: cross Abstract: Automatically analyzing hours-long egocentric video is increasingly essential for progress monitoring, quality control, and safety in logistics, const
arXiv:2608.22636v1 Announce Type: new Abstract: Q-learning with linear function approximation can be unstable because an arbitrary approximation architecture need not preserve the Bellman contraction.
arXiv:2503.09130v2 Announce Type: replace-cross Abstract: This paper presents InteractEdit, a novel framework for reference-free Human-Object Interaction (HOI) editing that tackles the challenging tas
arXiv:2608.21414v1 Announce Type: cross Abstract: Autonomous driving risk identification aims to determine which observed object is likely to become safety-critical to the ego vehicle. Existing approa
arXiv:2608.22419v1 Announce Type: cross Abstract: Query-based Vision-Language-Action (VLA) models offer low-latency inference that is attractive for bimanual robotic manipulation, but we observe that
arXiv:2508.03077v2 Announce Type: replace Abstract: Feedforward 3D Gaussian Splatting (3DGS) overcomes the limitations of optimization-based 3DGS by enabling fast and high-quality reconstruction witho
arXiv:2608.22300v1 Announce Type: new Abstract: Co-registration underlies nearly every multi-temporal and multi-sensor use of optical satellite imagery, and operational products still carry documented
arXiv:2608.22532v1 Announce Type: new Abstract: Domain shift across imaging modalities and acquisition sites remains a significant barrier to the clinical deployment of segmentation models. Source-fre
arXiv:2608.22594v1 Announce Type: new Abstract: Tabular foundation models (TFMs) have recently emerged as a promising paradigm for machine learning on tabular data, offering the ability to generalize
arXiv:2608.23358v1 Announce Type: new Abstract: The performance gap between low- and high-resource languages in LLMs is widely known, but it remains unclear which internal model factors drive these di
arXiv:2608.23102v1 Announce Type: new Abstract: Composed Image Retrieval (CIR) is an emerging paradigm in content-based image retrieval that enables users to formulate compositional queries by combini
arXiv:2608.22586v1 Announce Type: cross Abstract: External hand forces are important inputs to biomechanical analyses of occupational physical exposure and injury risk, yet continuous force measuremen
arXiv:2608.21761v1 Announce Type: new Abstract: Large collections of street-view imagery provide rich visual information about urban environments, but extracting fine-grained geographic information fr
arXiv:2608.22591v1 Announce Type: new Abstract: Robot policies receive heterogeneous observations at each decision step, yet sequence models differ in how they organize these inputs over time. We intr
arXiv:2608.21186v1 Announce Type: new Abstract: Surgical procedures such as laparoscopic appendectomy are complex, high-stakes processes, yet formalizing their workflows for decision support remains a
arXiv:2608.20497v1 Announce Type: new Abstract: Deploying high-accuracy neural networks on resource-constrained edge devices remains challenging, as existing approaches treat training, compression, an
arXiv:2608.20427v1 Announce Type: cross Abstract: Dense causal attention remains expensive at long context even when implemented with highly optimized exact kernels. We study BF1, a deterministic bloc
arXiv:2601.21948v2 Announce Type: replace Abstract: Neural visual decoding is a central problem in brain-computer interface research, aiming to reconstruct human visual perception and to elucidate the
arXiv:2608.20830v1 Announce Type: cross Abstract: Evaluating mobility interventions at tourist destinations requires predicting visitor behavior under varying conditions. Traditional methods struggle
arXiv:2608.21174v1 Announce Type: new Abstract: Attention masks are relation-level controls: they specify which query--source pairs may interact. They do not provide a representation-carried token sta
In the fight to defend openness in AI, the Marin project is a precious demonstration of openness in model training, with open code, data, recipes, even experimental results. Releasing AI research open
arXiv:2608.20969v1 Announce Type: new Abstract: Multimodal clinical AI is limited by weakly aligned inputs and the absence of domain-specific interpretable representations, particularly when learning