CORE improves compositional reasoning in multimodal language models by distilling a cross‑attentive reranker’s fine‑grained judgments into the embedding model. It generates candidate lists across five compositional matching levels and trains with a Rank‑KL objective to replicate the reranker’s ranking. Experiments on COLA, SUGARCREPE++, and NEGBENCH show CORE‑RERANKER‑8B outperforms Jina‑Reranker by 10.7 points, while CORE‑EMBED‑8B achieves the best overall average among evaluated embeddings, with gains also transferring to the MCMR benchmark without harming COCO or Flickr30K retrieval.
By Tingyu Song, Mingxin Li, Yanzhao Zhang, Dingkun Long, Chu Liu, Pengjun Xie, Yilun Zhao, Shu Wu
arXiv:2606. 00910v1 Announce Type: cross Abstract: Composed Video Retrieval (CoVR) seeks the target video that results from applying a free-form textual modification to a reference video.
By Ali Alavi
arXiv:2511.14086v2 Announce Type: replace-cross
Abstract: Despite recent progress in 3D-LLMs, they remain limited in accurately grounding language to visual and spatial elements in 3D environments. T...
By Yue Zhang, Zun Wang, Han Lin, Jialu Li, Jianing Yang, Yonatan Bitton, Idan Szpektor, Mohit Bansal
arXiv:2608.29604v1 Announce Type: cross
Abstract: Vision-language retrieval with CLIP-style dual encoders achieves strong cross-modal performance, yet practical accuracy often hinges on localized sem...
By Siyi Liu, Xiaorong Zhu, Enjun Du, Xinyu Zuo, Lisheng Duan, Haijin Liang, Jin Ma, Junfu Pu, Yongqi Zhang
arXiv:2606. 05142v1 Announce Type: cross Abstract: Recent developments in multi-view image editing with generative models have brought us a step closer toward general 3D content generation and customization.
By Josef Bengtson, Yaroslava Lochman, Fredrik Kahl
arXiv:2609.10008v1 Announce Type: new
Abstract: Composed video retrieval (CoVR) searches a gallery for the target video that realizes a natural-language modification of a source clip. However, at gal...
By Dmitry Demidov, Muhammad Zaigham Zaheer, Omkar Thawakar, Abdelrahman Mohamed Shaker, Rao Anwer
arXiv:2602. 07774v5 Announce Type: replace-cross Abstract: Recent studies increasingly explore Large Language Models (LLMs) as a new paradigm for recommendation systems due to their scalability and world knowledge.
By Mingfu Liang, Yufei Li, Jay Xu, Kavosh Asadi, Xi Liu, Shuo Gu, Kaushik Rangadurai, Frank Shyu, Shuaiwen Wang, Song Yang, Zhijing Li, Jiang Liu, Mengying Sun, Fei Tian, Xiaohan Wei, Chonglin Sun, Jacob Tao, Shike Mei, Wenlin Chen, Santanu Kolay, Sandeep Pandey, Hamed Firooz, Luke Simon
ScenePilot introduces a retrieval‑augmented Grow‑and‑Repair framework for text‑driven 3D indoor scene generation. It uses a Hierarchical Retrieval‑Augmented Planning module to fetch room, group, and anchor layout priors, then incrementally inserts object groups with a base generator, while a Reinforcement Multimodal Repair module performs lightweight local corrections after each insertion and a final global repair. The approach is trained on a new SceneReverse‑17k dataset of perturbed scenes, enabling the policy to predict structured move‑rotate‑scale actions from rendered views, scene state, retrieved priors, and edit history, thereby improving physical plausibility, functional coherence, and controllability without heavy full‑scene optimization.
By Jiawei Zhang, Hongsong Wang, Pan Zhou
The paper introduces RSMEB, a unified benchmark for remote‑sensing multimodal retrieval that evaluates both cross‑modal and interleaved retrieval across 21 tasks under a single ranking protocol. It also presents VLM2GeoVec, an instruction‑conditioned single‑encoder model that embeds image, text, bounding‑box, and geo‑coordinate tokens into one sequence and achieves state‑of‑the‑art performance on region‑caption, referring‑expression, and semantic geo‑aware retrieval while remaining competitive on conventional tasks. The authors provide code, checkpoints, and data on GitHub to facilitate reproducibility.
By Emanuel S\'anchez Aimar, Gulnaz Zhambulova, Fahad Shahbaz Khan, Yonghao Xu, Michael Felsberg
Vision-language models (VLMs) achieve strong semantic understanding but remain unreliable in metric spatial reasoning, particularly when queries require comparing multiple instances of the same object category. We study this problem through the Closest-Instance Distance Query (CIDQ), where a model must identify the nearest visible candidate to a unique reference object and estimate their gravity-aligned floor-plane distance.
GeoStore is a new benchmark for fine‑grained point‑of‑interest (POI) localization that matches close‑up storefront photos against large geo‑tagged street‑view images, a task distinct from traditional visual place recognition. The paper shows that global‑descriptor methods designed for symmetric matching perform poorly on this asymmetric problem, and introduces GLAM, a Global‑to‑Local Asymmetric Matching approach that combines a global retrieval anchor with a lightweight local re‑ranking using pooled region tokens. GLAM achieves higher Recall@1/5/10 and mAP than strong baselines while using far fewer re‑ranking features and significantly lower per‑pair matching cost.
By Lu Han, Xiting Sun, Hao Wang, Zhiqiang Cao, Ruihuan Du, Ziquan Zeng, Chunlong Lv
arXiv:2609.14899v1 Announce Type: new
Abstract: Neural 3D scene editing is often evaluated by semantic alignment alone, although a convincing result may alter unrelated content or become inconsistent...
By Sariah Patro, Arjun Mehra, Nikhil Bhatia