Knowledge catalogue
arXiv:2609.32060v1 Announce Type: new Abstract: How many bits does a network need before its accuracy collapses, and how does this grow with depth? We study the precision floor, the perturbation level
arXiv:2609.32193v1 Announce Type: new Abstract: Vision Language Action (VLA) models condition actions directly on current visual and language context, without an explicit account of how the scene evol
arXiv:2609.34286v1 Announce Type: new Abstract: World models for manipulation are typically trained from video, yet the events that determine how manipulation unfolds, such as making and releasing con
arXiv:2609.34724v1 Announce Type: new Abstract: Learning dexterous humanoid loco-manipulation from human demonstrations requires transferring not only human motion, but also the coordinated interactio
arXiv:2609.32363v1 Announce Type: new Abstract: Probabilistic time series forecasting requires modeling and predicting complex and time-varying distributions. Recently, Denoising Diffusion Probabilist
arXiv:2609.34651v1 Announce Type: new Abstract: Generating high-quality UV textures for 3D meshes remains challenging. Multi-view projection pipelines suffer from occlusion and view inconsistency, and
arXiv:2609.33527v1 Announce Type: new Abstract: Parameter space symmetries are important for understanding neural networks' loss landscape, training dynamics, and generalization. However, systematical
arXiv:2609.33148v1 Announce Type: new Abstract: World-action models give visual navigation agents a way to anticipate how candidate actions will change future observations and to act from the predicte
arXiv:2609.34893v1 Announce Type: new Abstract: Learning-based manipulation policies relying on RGB cameras often suffer from degraded observations under extreme exposure. Event cameras mitigate this
arXiv:2609.35570v1 Announce Type: cross Abstract: Vision-language navigation (VLN) models perform well but target compute-rich platforms, limiting deployment on memory- and power-constrained robotic e
arXiv:2609.31657v1 Announce Type: new Abstract: Remote-sensing foundation models offer strong representations for SAR imagery, but their behavior under severe long-tail class imbalance is still not we
arXiv:2602.06187v2 Announce Type: replace Abstract: Federated learning (FL) enables collaborative training while keeping raw data on clients. Deletion requests and the discovery of poisoned data creat
arXiv:2609.32555v1 Announce Type: new Abstract: Dynamic contrast enhanced breast MRI (DCE-MRI) is a powerful clinical tool for breast cancer detection, providing high resolution anatomical detail toge
arXiv:2609.35728v1 Announce Type: new Abstract: We present FlowAct-R2, a framework for interactive humanoid video generation that combines continuous multimodal control with proactive agent planning.
arXiv:2609.34716v1 Announce Type: new Abstract: Clinical CT and UHRCT cannot resolve individual trabeculae, whereas synchrotron radiation microCT (SR{mu}CT) provides 3.2{mu}m high-resolution reference
arXiv:2609.31755v1 Announce Type: new Abstract: Panoramic 360^irc scene understanding increasingly relies on icosphere transformers, but a state-of-the-art spherical model loses more than half of its
arXiv:2609.35734v1 Announce Type: new Abstract: Novel view synthesis from sparse images must reconcile faithful reconstruction of observed regions with plausible completion of unseen content, while ma
arXiv:2609.32788v1 Announce Type: new Abstract: Deep learning has transformed symbolic music generation by borrowing the training paradigms of large language models, with systems such as NotaGen now p
arXiv:2609.32355v1 Announce Type: cross Abstract: Model-internal features can be studied through both their ability to identify a specified concept and their causal effect when manipulated, e.g., thro
arXiv:2609.33977v1 Announce Type: new Abstract: Semi-structured pruning compresses large language models (LLMs) while keeping a regular sparse structure, but the prevailing N:M pattern fixes the same
arXiv:2609.32117v1 Announce Type: new Abstract: Smartphone motion sensors support interactive applications, but their readings may also reveal touchscreen input beyond their intended use. Assuming kno
arXiv:2609.33093v1 Announce Type: new Abstract: Linear attention replaces the growing key--value (KV) cache of standard attention with a fixed-size recurrent state, substantially reducing memory growt
arXiv:2609.35751v1 Announce Type: new Abstract: Looped Transformers reuse one block of layers several times: by spending extra computation they push a model of fixed size further, and so use its param
arXiv:2609.34798v1 Announce Type: cross Abstract: Recent medical multimodal models have benefited from larger corpora, broader modality coverage, and stronger reasoning-oriented training, yet effectiv
arXiv:2609.35743v1 Announce Type: new Abstract: World-space hand motion estimation from egocentric video requires recovering 3D articulated hand geometry while tracking camera egomotion. Existing appr
arXiv:2609.33647v1 Announce Type: new Abstract: Many indoor environments in which robots operate, such as warehouses, offices, and hospitals, already have cameras installed. They observe parts of the
arXiv:2609.31665v1 Announce Type: new Abstract: Action anticipation predicts future human actions from partial video under incomplete context and temporal uncertainty. Recent systems introduce large l
arXiv:2609.33407v1 Announce Type: cross Abstract: De novo crystal generation (DNG) models decide where to search in composition space and how to generate structures with one set of weights. We argue t
arXiv:2609.34375v1 Announce Type: new Abstract: Compact JEPA world models enable efficient latent-space planning, but low-dimensional representation trained under reward-free self-supervision must enc
arXiv:2609.33769v1 Announce Type: new Abstract: Quantitative evaluation of generative models for radiology remains challenging. Clinically relevant structures are often small and infrequent, feature s
arXiv:2609.35658v1 Announce Type: new Abstract: Real-world capture is heterogeneous: perspective, fisheye, and 360^irc panoramic images can coexist within a single reconstruction task, yet most feed-f
arXiv:2609.35652v1 Announce Type: new Abstract: Mobile manipulation extends robot interaction beyond a fixed kinematic workspace by making the reachable region itself controllable. This flexibility in
arXiv:2609.31700v1 Announce Type: new Abstract: Compressed-domain video captioning avoids full video decoding by operating directly on I-frames, motion vectors and residuals, trading a small amount of
arXiv:2609.31669v1 Announce Type: new Abstract: We present NanoForecast v0.5, a 6.5M-parameter forecaster that competes with models 31x its size (TimesFM, 200M parameters) after training pipeline fixe
arXiv:2603.24458v3 Announce Type: replace Abstract: While proprietary systems such as Seedance-2.0 have achieved remarkable success in omni-capable video generation, the academic research community la
arXiv:2609.31947v1 Announce Type: new Abstract: Hybrid transformer architectures that replace most softmax attention layers with linear attention offer transformer-level quality at a fraction of the m
arXiv:2609.34301v1 Announce Type: new Abstract: Drug design couples property evaluation, conditional generation, structure-based design, and local optimization, yet machine learning systems typically
arXiv:2609.32897v1 Announce Type: new Abstract: Sampling-based motion planners guided by diffusion models produce high-quality trajectories in a single run, yet the stochastic diversity available at i
arXiv:2609.34487v1 Announce Type: new Abstract: Radiology report generation (RRG) increasingly incorporates heterogeneous clinical evidence, such as multi-view radiographs and previous reports, whose
arXiv:2609.32634v1 Announce Type: new Abstract: Reinforcement Fine-Tuning~(RFT) has emerged as a promising paradigm for improving Vision-Language-Action~(VLA) policies, yet sparse task-level outcomes
arXiv:2609.34054v1 Announce Type: new Abstract: Multi-LoRA agent systems enable efficient role specialization by sharing a common backbone model. However, each agent repeatedly processes the growing s
arXiv:2609.32908v1 Announce Type: new Abstract: Neural theorem provers must both propose tactics and decide which valid successor states to explore. We study whether one-step Lean transitions provide
arXiv:2609.33765v1 Announce Type: new Abstract: Generative robot policies provide expressive behavior priors, but updating a large diffusion or flow-matching model through online interaction is costly
arXiv:2609.34299v1 Announce Type: new Abstract: Dataset distillation (DD) condenses a large original dataset into a small distilled dataset with high training utility. Decoupled statistical matching m
arXiv:2609.32681v1 Announce Type: new Abstract: 4D radar provides geometric and motion cues that complement visual semantics, but integrating it into vision-language-action (VLA) models requires both
arXiv:2609.33202v1 Announce Type: new Abstract: Flow-matching models generate high-quality images and videos, but repeated neural network evaluations make sampling expensive. Skipping evaluations redu
arXiv:2609.33854v1 Announce Type: new Abstract: Driving policies require capabilities of scene understanding and future evolution prediction. To achieve this goal, current end-to-end models typically
arXiv:2609.32068v1 Announce Type: new Abstract: Motion retargeting transfers motion across characters with different skeletal structures while preserving semantic intent and physical plausibility. Des
arXiv:2609.35764v1 Announce Type: new Abstract: Sparse inertial pose estimation promises camera-free motion capture from consumer devices, but consumer sensors are unreliable: firmware-fused orientati
arXiv:2609.33217v1 Announce Type: new Abstract: Generative models learn visual structure through denoising, yet their internal states are entangled with both noise level and network depth, making it d
arXiv:2609.32755v1 Announce Type: cross Abstract: Audio autoencoders compress waveforms into compact latent representations that serve as the interface between raw audio and downstream models. Current
arXiv:2609.35292v1 Announce Type: new Abstract: Recent representation alignment (REPA) methods accelerate diffusion transformer training by aligning projections of the transformer's hidden states with
arXiv:2609.33694v1 Announce Type: new Abstract: Vision-language models (VLMs) answer visual questions by combining visual information extraction with downstream problem solving. We investigate a funda
arXiv:2609.34235v1 Announce Type: new Abstract: Medical image segmentation remains challenging in practical deployment, as models often struggle to generalize beyond the distributions covered by their
arXiv:2609.32268v1 Announce Type: new Abstract: Standard autoencoder (AE) inference uses a single encoder-decoder pass, though the latent may not be optimal for each sample under a fixed decoder. We a
arXiv:2609.31801v1 Announce Type: new Abstract: Complex systems such as vehicles, patients, or genomes emit discrete event sequences whose operative question is causal, not predictive: which events ca
arXiv:2607.11196v2 Announce Type: replace Abstract: Deploying object-centric models for real-world scene understanding typically requires complex pipelines to achieve both robust scene decomposition a
arXiv:2506.07932v2 Announce Type: replace-cross Abstract: We propose Squeeze3D, a novel framework that leverages implicit prior knowledge learnt by existing pre-trained encoders and decoders to compre
arXiv:2609.33546v1 Announce Type: new Abstract: Current grasp diffusion models provide rich priors for generation, yet their object-centric approach can violate the kinematic and collision constraints
arXiv:2609.31881v1 Announce Type: new Abstract: Dynamic text-attributed graphs (DTAGs), where nodes, edges, and textual attributes evolve over time, are crucial in applications such as social networks