LaviGen framework repurposes 3D generative models for autoregressive layout generation, achieving 19% higher physical plausibility on LayoutVLM benchmark.

Haoran Feng, Yifan Niu, Zehuan Huang et al.

CrossMath benchmark reveals VLMs' limitations in visual reasoning; text reasoning outperforms visual.

Yige Xu, Yongjie Wang, Zizhuo Wu et al.

This study systematically evaluates various vision-language models for country-level image geolocalization, revealing their limitations in capturing fine-grained geographic cues.

Siddhant Bharadwaj, Ashish Vashist, Fahimul Aleem et al.

CollideNet enhances time-to-collision forecasting precision by disentangling temporal patterns in multi-scale video representation learning.

Nishq Poorav Desai, Ali Etemad, Michael Greenspan

Proposed a two-stage deep learning framework using YOLOv8n and RexNet-150, achieving 95% accuracy in cheating detection.

Van-Truong Le, Le-Khanh Nguyen, Trong-Doanh Nguyen

SENSE leverages stereo vision and vision-language models to enhance open-vocabulary semantic segmentation, achieving a 2.9% precision improvement on PhraseStereo.

Thomas Campagnolo, Ezio Malis, Philippe Martinet et al.

Introduces OVRSISBenchV2 and Pi-Seg, expanding to 95K images for robust open-vocabulary remote sensing segmentation.

Bingyu Li, Tao Huo, Haocheng Dong et al.

AdaDINO uses task-adaptive NAS to improve edge vision models, boosting accuracy by 7.9% and reducing FLOPs by 74.9%.

Yiwei Zhao, Yi Zheng, Huapeng Su et al.

Proposes ordered 1D tokens for efficient test-time search in autoregressive image generation, improving scalability and quality.

Zhitong Gao, Parham Rezaei, Ali Cy et al.

Bi-CMPStereo framework significantly improves accuracy and generalization in event-frame asymmetric stereo matching.

Ninghui Xu, Fabio Tosi, Lihui Wang et al.

MM-WebAgent uses hierarchical planning and self-reflection to generate consistent multimodal webpages, improving layout and style coherence.

Yan Li, Zezi Zeng, Yifan Yang et al.

RAD-2 scales reinforcement learning in autonomous driving, reducing collision rate by 56% using a generator-discriminator framework.

Hao Gao, Shaoyu Chen, Yifan Zhu et al.

Proposes a multi-stage context enrichment strategy to improve vision-language models' performance in human emotion recognition.

Madhav Agarwal, Sotirios A. Tsaftaris, Laura Sevilla-Lara et al.

SegWithU models uncertainty as perturbation energy for single-forward-pass risk-aware medical image segmentation.

Tianhao Fu, Austin Wang, Charles Chen et al.

Proposes multi-view priors for controllable video object insertion, enhancing identity consistency and scene integration.

Qi Xia, Peishan Cong, Yichen Yao et al.

Proposes LingBot-Map, a geometric context transformer for streaming 3D reconstruction, achieving 20FPS on long sequences.

Lin-Zhuo Chen, Jian Gao, Yihang Chen et al.

Proposed ACPO method significantly reduces audio hallucination in audio-visual language models.

Ami Baid, Zihui Xue, Kristen Grauman

UI-Zoomer enhances GUI grounding with uncertainty-driven adaptive zoom-in, achieving up to 13.4% accuracy improvement.

Fei Tang, Bofan Chen, Zhengxi Lu et al.

Proposed BVE framework achieves high-quality 3D editing using 3D masks and self-constructed data, significantly improving editing performance.

Yizhao Xu, Hongyuan Zhu, Caiyun Liu et al.

Proposes CAMFusion, a multiview transformer for fusing vision-language embeddings, achieving state-of-the-art 3D semantic classification.

Tomas Berriel Martins, Martin R. Oswald, Javier Civera