Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv:2611.06180v1 Announce Type: new Abstract: We present the Rohbau3D-Semantics dataset, which adds dense semantic and instance-level labels to laser scans of the previously released Rohbau3D domai...
arXiv:2611.06195v1 Announce Type: new Abstract: Object detection research remains constrained by high annotation costs and the closed-set assumptions of supervised models, limiting scalability to nov...
arXiv:2611.06203v1 Announce Type: new Abstract: We estimate the quality of a specific target region (e.g., a train body) in an image, rather than the whole image. This differs fundamentally from whol...
arXiv:2611.06422v1 Announce Type: new Abstract: This work presents UGD-FM, a novel unaligned image guided denoising framework based on cross-modal conditional flow matching. Unlike previous approache...
arXiv:2611.06624v1 Announce Type: new Abstract: Reconstructing cell lineages from 3D time-lapse microscopy requires distinguishing cell motion from division and inferring temporally consistent connec...
arXiv:2611.06635v1 Announce Type: new Abstract: Unmanned aerial vehicle (UAV)-based collaborative perception enables multiple agents to share complementary perceptual information, overcoming limitati...
arXiv:2611.06685v1 Announce Type: new Abstract: Online reasoning video segmentation (Online RVS) requires a model to segment query-referred objects as a video streams in, using only the frames observ...
arXiv:2611.06701v1 Announce Type: new Abstract: Deep learning methods for pathology are constrained by the limited availability and high cost of large-scale pixel-level annotations. Synthetic data ca...
arXiv:2611.06781v1 Announce Type: new Abstract: Sign language generation (SLG) maps written sentences into signing motion while preserving both lexical content and fine-grained articulation. This req...
arXiv:2611.06796v1 Announce Type: new Abstract: Few-step distillation offers efficient generation with diffusion and flow models, but preserving quality with only a few sampling steps remains challen...
arXiv:2611.06901v1 Announce Type: new Abstract: JEPA-style world models learn action-conditioned latent dynamics without reconstructing observations, but distributional regularization alone does not...
arXiv:2611.05843v1 Announce Type: cross Abstract: Existing generative model-based approaches to linear inverse problems typically use the acquired noisy measurement to condition or guide sampling in...
arXiv:2611.05847v1 Announce Type: cross Abstract: Joint-Embedding Predictive Architectures (JEPAs) support planning by comparing predicted latent states with an encoded goal. For this comparison to g...
arXiv:2611.06453v1 Announce Type: cross Abstract: Closed-loop driving benchmarks in CARLA rank agents by a driving score that multiplies route completion by an infraction penalty. This score does not...
arXiv:2503.15846v4 Announce Type: replace Abstract: Dynamic Scene Graph Generation (DSGG) aims to capture objects and their evolving relations in videos. Despite recent progress, the practicality and...
arXiv:2511.17481v2 Announce Type: replace Abstract: World models learn to predict the temporal evolution of visual observations given a control signal, potentially enabling agents to reason about env...
arXiv:2512.10888v4 Announce Type: replace Abstract: Table extraction (TE) is a key challenge in document understanding. Traditional approaches detect tables first, then recognize their structure. Rec...
arXiv:2605.10334v2 Announce Type: replace Abstract: Recent deepfake detection methods demonstrate improved cross-dataset generalization, yet the underlying mechanisms remain underexplored. We introdu...
arXiv:2606.00386v3 Announce Type: replace Abstract: Accurately modeling soft boundaries, e.g., hair and defocus blur, is a fundamental challenge in stereo conversion due to the ambiguous blending of...
arXiv:2606.09788v2 Announce Type: replace Abstract: Large-scale document processing requires contextually aware table extraction (TE) that is both accurate and efficient. Yet current approaches requi...