Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv:2609.09708v2 Announce Type: replace-cross Abstract: 6G wireless technology is poised to adopt higher and wider frequency bands, leveraging highly directional beamforming. However, the vast band...
arXiv:2610.00040v1 Announce Type: new Abstract: Recent advances in 3D Gaussian Splatting have enabled open-vocabulary and referring segmentation by distilling semantic knowledge from 2D foundation mo...
arXiv:2610.00141v1 Announce Type: new Abstract: Vision-based anti-UAV systems must function in poor visibility, yet most benchmarks use only clear-sky footage, and previous robustness studies treat a...
arXiv:2610.00204v1 Announce Type: new Abstract: Visual-token compression for vision--language models is posed almost entirely as a selection problem: decide which tokens to keep and discard the rest....
arXiv:2610.00350v1 Announce Type: new Abstract: Spiking Neural Networks (SNNs) offer an energy-efficient approach to processing event-camera data, yet out-of-distribution (OOD) detection remains chal...
arXiv:2610.00573v1 Announce Type: new Abstract: Query-aware keyframe selection enables multimodal large language models (MLLMs) to process long videos using only a small set of question-relevant fram...
arXiv:2610.00749v1 Announce Type: new Abstract: Standard 3D Gaussian Splatting (3DGS) learns geometry and appearance jointly from RGB supervision, making it difficult to isolate how luminance and chr...
arXiv:2610.00960v1 Announce Type: new Abstract: A video benchmark should reward the capability it claims to measure, yet models can exploit answer options, question text, or partial visual evidence....
arXiv:2610.00994v1 Announce Type: new Abstract: Existing synthetic image evaluators typically provide only a scalar quality score and do not identify the image regions that support it. We introduce V...
arXiv:2610.01022v1 Announce Type: new Abstract: Memory-attention-based Video Instance Segmentation (VIS) methods have demonstrated strong zero-shot tracking capability, yet their substantial memory r...
arXiv:2610.00623v1 Announce Type: new Abstract: Speculative decoding has achieved substantial lossless speedups for LLMs, but remains less effective for large vision-language models (LVLMs), where li...
arXiv:2610.01180v1 Announce Type: new Abstract: Despite the strong performance of Vision-Language Models (VLMs) on a wide range of visual question answering (VQA) tasks, these models consistently str...
arXiv:2610.01201v1 Announce Type: new Abstract: Object permanence, keeping track of an object's identity and position while it is occluded, is central to video representations that track, predict and...
arXiv:2610.01314v1 Announce Type: new Abstract: Dynamic scenes may be captured by a moving camera, multiple video streams, or images taken at different times. These observations reveal complementary...
arXiv:2610.01452v1 Announce Type: new Abstract: While state-of-the-art automated models for medical image segmentation achieve high mean performance, they frequently suffer from localized, catastroph...
arXiv:2610.01544v1 Announce Type: new Abstract: Existing image forgery detectors often suffer from generalization to unseen manipulation methods due to the limited ability to capture transferable for...
arXiv:2610.01741v1 Announce Type: new Abstract: Predictive Vision-Language-Action (VLA) models aim to improve robotic manipulation via future observation or world dynamics forecasting. However, exist...
arXiv:2610.01778v1 Announce Type: new Abstract: Reliable evaluation of image forgery localization (IFL) requires assessing models under diverse distribution changes, yet existing benchmarks often cov...
arXiv:2610.01876v1 Announce Type: new Abstract: A surface photographed under even light presents nearly the same appearance from every angle; the same surface under uneven light does not. Exposure ch...
arXiv:2610.02205v1 Announce Type: new Abstract: Programmable world models separate executable dynamics from visual generation, offering a promising foundation for next-generation game engines. Howeve...