Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv:2610.33857v1 Announce Type: new Abstract: We introduce TrackTok, an efficient video tokenization framework that produces object-centric tokens, i.e., tokens that consistently encode the same se...
arXiv:2610.33877v1 Announce Type: new Abstract: Catastrophic forgetting in continual learning (CL) manifests not only as accuracy degradation but also as \emph{explanation drift}: models maintain pre...
arXiv:2610.33894v1 Announce Type: new Abstract: Interactive world models hold immense potential for high-stakes applications in robotics, game engines, and immersive digital twins, yet existing bench...
arXiv:2610.34028v1 Announce Type: new Abstract: As Vision-Language Models (VLMs) increasingly enable robots to follow language instructions, understanding their navigation decisions becomes important...
arXiv:2610.34093v1 Announce Type: new Abstract: Open-vocabulary 3D occupancy prediction is important for embodied agents operating in complex environments whose semantic categories extend beyond fixe...
arXiv:2610.34303v1 Announce Type: new Abstract: Recent advances in image editing have enabled fine-grained and highly controllable visual modifications. However, achieving similar levels of controlla...
arXiv:2610.34305v1 Announce Type: new Abstract: Object re-identification requires embeddings that are robust to intra-class variation in viewpoint, illumination, and occlusion, yet preserve sharp sep...
arXiv:2610.34344v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) has become a standard representation for real-time novel-view synthesis. Yet, its quality-efficiency trade-off still relie...
arXiv:2610.35044v1 Announce Type: new Abstract: World models are emerging as a fundamental component of policy learning for real-world agents, enabling agents to predict future world states and plan...
arXiv:2610.35065v1 Announce Type: new Abstract: Tube-wise video completion reconstructs temporal trajectories at spatial locations unobserved in every frame. We propose a two-stage framework combinin...
arXiv:2610.35152v1 Announce Type: new Abstract: Recent studies on generalizable human Gaussian splatting have achieved the notable progress in synthesizing novel views of unseen human subjects from m...
arXiv:2610.35220v1 Announce Type: new Abstract: Medical image segmentation (MIS) remains challenging due to composite degradations and multi-scale geometric variations, which jointly impair lesion-ba...
arXiv:2610.35621v1 Announce Type: new Abstract: Evaluating deformable 3D reconstruction requires ground truth linking camera motion, surface deformation, material correspondence and image appearance....
arXiv:2610.33127v1 Announce Type: cross Abstract: Active speaker detection (ASD) relies on audiovisual correspondence between speech and visible faces, yet this correspondence becomes unreliable in c...
arXiv:2610.33377v1 Announce Type: cross Abstract: Advertisers routinely create multiple duration variants of ads to meet marketing budgets and viewer preferences, a labor-intensive and costly process...
arXiv:2610.33616v1 Announce Type: cross Abstract: High-frequency attenuation can reduce the rate of learned image codecs but also remove object boundaries and fine detail. We propose Semantic-Guided...
arXiv:2610.33966v1 Announce Type: cross Abstract: People have long dreamed of an assistant that is always there to guide them and remind what they forget, from new dishes to lost keys. Powered by mul...
arXiv:2610.35224v1 Announce Type: cross Abstract: We present GaussianSpline, a dynamic 4D Gaussian Splatting method that models per-Gaussian motion using adaptive, non-uniform piecewise cubic B\'ezie...
arXiv:2610.35448v1 Announce Type: cross Abstract: End-to-end driving models perform well on standard benchmarks but collide frequently in safety-critical scenarios. We present a failure-mode analysis...
arXiv:2502.04192v5 Announce Type: replace Abstract: Multiple works have emerged to push the boundaries of multi-modal large language models (MLLMs) towards pixel-level understanding. The current tren...