arXiv:2608.21762v1 Announce Type: cross Abstract: Vision-language models (VLMs) fail many detail-centric questions for a concrete reason: the answer is visible in the image, yet lost after the image...
The paper introduces the Necessary Tool‑Evidence Path (NTEP) annotation scheme and its associated reward mechanism (NTEP‑R) to better supervise vision‑language models that use external tools. By explicitly specifying which evidence is needed and penalizing redundant tool calls, the authors train an 8B‑parameter model that shows improved accuracy and tool‑use efficiency across seven image‑grounded benchmarks. The approach demonstrates that fine‑grained supervision of tool‑evidence paths is essential for robust agentic VLM performance.
RankGround is a two‑stage framework for GUI grounding that uses a single Vision‑Language Model call per query. It introduces GroundRanker, a lightweight multimodal reranker that selects the most promising crop from a dense candidate set, trained with a two‑stage curriculum on ranking supervision data derived from existing grounding datasets. Experiments show RankGround outperforms strong baselines, achieving 1.4× faster inference and a 5.5% average improvement in localization accuracy over the second‑best method across all backbones and screen scales.
arXiv:2606. 30632v1 Announce Type: cross Abstract: Can the robot use a plate to cut a cake if no knife is available?
PANORAMA introduces a new panoptic grounded captioning framework that jointly generates detailed image captions and associates each phrase with precise pixel-level masks. The authors create PanoCaps, a human‑annotated benchmark with dense captions and near‑complete pixel coverage, and propose a phrase‑mask matching protocol with a generalized Panoptic Quality metric. PANORAMA conditions a pretrained segmenter on contextualized phrase representations, learns to select appropriate masks, and achieves state‑of‑the‑art grounding performance on PanoCaps and other pixel‑level tasks.
arXiv:2510. 19496v3 Announce Type: replace-cross Abstract: Large vision-language models (VLMs) commonly process images at native or high resolution to remain effective across tasks.
arXiv:2512. 23020v3 Announce Type: replace-cross Abstract: 3D visual grounding aims to locate objects based on natural language descriptions in 3D scenes.
Intelligent systems that act in the world require image understanding that is both comprehensive and spatially grounded. Current vision-language models (VLMs) can generate fluent and detailed image ca...
arXiv:2607. 15942v1 Announce Type: cross Abstract: Remote sensing vision-language models are increasingly expected to support open-ended reasoning over Earth Observation data and a variety of tasks.
arXiv:2608.22429v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) capable of thinking with images often rely on external tools for fine-grained perception. However, this relian...
arXiv:2510. 01483v3 Announce Type: replace-cross Abstract: Vision-language models (VLMs) demonstrate strong image-level scene understanding, but reasoning over long egocentric video remains costly: because VLMs maintain no persistent memory or explicit spatial representation, all sampled frames must be re-processed for every new query.
IVSGround introduces a lightweight view selector that learns to choose the most informative camera views for vision‑language model (VLM) based 3D visual grounding, replacing heuristic view selection. The selector is trained via a two‑stage rejection sampling process that uses feedback from a reasoning VLM to generate supervision signals. Experiments on ScanRefer and NR3D demonstrate that IVSGround consistently improves grounding accuracy over existing zero‑shot pipelines, underscoring the importance of selecting where to look for effective 3D visual grounding.