Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv:2609.15171v1 Announce Type: new Abstract: Airborne optical tracking of uncrewed aerial vehicle (UAV) swarms is challenging due to extremely small target scales, rapid viewpoint changes, and clu...
arXiv:2609.15224v1 Announce Type: new Abstract: We present LOVER, a \underline{L}ong to sh\underline{O}rt \underline{V}ideo \underline{E}vidence \underline{R}einforced model for grounded question ans...
arXiv:2609.15228v1 Announce Type: new Abstract: Unsupervised registration of large-scale LiDAR point clouds remains challenging due to the geometric ambiguity inherent in outdoor scenes, which degrad...
arXiv:2603.13966v3 Announce Type: replace Abstract: Vision-Language-Action (VLA) models are increasingly evaluated across multiple simulation benchmarks, yet adding each benchmark to an evaluation pi...
arXiv:2609.15484v1 Announce Type: new Abstract: We report on the continued development of CatchMonitor, resulting in a prototype computer vision system designed to automatically quantify discarded fi...
arXiv:2609.15683v1 Announce Type: new Abstract: While In-Context Learning (ICL) enables models to adapt from exemplars without parameter updates, multimodal ICL remains largely underexplored, particu...
arXiv:2609.15810v1 Announce Type: new Abstract: Diffusion Transformers deliver state-of-the-art video generation, but their long spatiotemporal sequences make attention the dominant deployment cost,...
arXiv:2609.15833v1 Announce Type: new Abstract: Cultural heritage documentation increasingly relies on image-based 3D surface reconstruction, with photogrammetry software making such workflows access...
arXiv:2609.13659v1 Announce Type: cross Abstract: Underwater Acoustic Target Recognition (UATR) of ships is well-suited for machine learning, yet its progress is hindered by the lack of large, divers...
arXiv:2609.15550v1 Announce Type: cross Abstract: X-ray coronary angiography is the clinical gold standard for coronary artery disease during real-time cardiac interventions, but provides only 2D pro...
The paper introduces a modular correction framework for large language models that uses Activated LoRA adapters and a context-aware routing mechanism to mitigate harmful outputs. By allowing expert adapters to activate mid-sequence without invalidating the KV cache, the system achieves low-latency, targeted correction during generation. Experiments show improved alignment on safety benchmarks while maintaining task performance, presenting a lightweight, scalable approach to safer LLM deployments.
arXiv:2512.07776v2 Announce Type: replace Abstract: Monitoring critically endangered western lowland gorillas is currently hampered by the immense manual effort required to re-identify individuals fr...
arXiv:2609.14145v1 Announce Type: cross Abstract: Kinship verification is a task involving determining whether two individuals share a first-order kin relation. To tackle this task, we propose CONVTR...
arXiv:2512.15971v2 Announce Type: replace Abstract: Multispectral object detection is critical for safety-sensitive applications such as autonomous driving and surveillance, where robust perception u...
arXiv:2603.02790v2 Announce Type: replace Abstract: Foundation models are changing the way we develop medical artificial intelligence. By learning broadly generalizable features across diverse data m...
arXiv:2605.27310v2 Announce Type: replace Abstract: Cross-view spatial reasoning remains a weak spot for vision-language models (VLMs): they reason in language and discard the fine-grained geometry t...
arXiv:2605.28173v2 Announce Type: replace Abstract: End-to-end manga generation is a structured visual storytelling task that requires story decomposition, recurring character and scene grounding, pa...
arXiv:2606.08906v2 Announce Type: replace Abstract: In many binary segmentation tasks, most multimodal methods rely on fixed feature concatenation for cross-modal interaction and straightforward deco...
arXiv:2508.13488v2 Announce Type: replace-cross Abstract: Loop closure detection is important for simultaneous localization and mapping (SLAM), which associates current observations with historical k...
arXiv:2604.00634v3 Announce Type: replace-cross Abstract: Panoptic segmentation is a key enabler for robotic perception, as it unifies semantic understanding with object-level reasoning. However, the...