Hugging Face Trending Papers July 30, 2026

One Patch Is Enough: Reinforcement-Optimized Visual Token Grounding for MLLM-Based Scene Text Spotting

Read the original on Hugging Face Trending Papers →

Scene text spotting requires high-precision alignment between textual recognition and spatial localization. While visual-token grounding has emerged as a promising formulation for Multimodal Large Language Models (MLLMs), the previous multi-patch paradigm often introduces redundant noise and localization ambiguity, particularly for dense or small text instances.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv AI

Jul 31

TraceCLIP: Recovering Local Semantics from Patch-to-CLS Contributions

arXiv:2607. 26107v1 Announce Type: cross Abstract: Dense vision-language understanding, including object localization, region recognition, and open-vocabulary semantic segmentation, requires associating language concepts with spatially grounded visual regions.

By Xinran Liu, Shouqian Shi, Yutong Chen, Ge Wang, Xin-Wei Yao, Sheng Zhong

rag computer-vision multimodal benchmarks safety

arXiv AI

Jun 2

CLIP Tricks You: Training-free Token Pruning for Efficient Pixel Grounding in Large VIsion-Language Models

arXiv:2605. 13178v2 Announce Type: replace-cross Abstract: In large vision-language models, visual tokens typically constitute the majority of input tokens, leading to substantial computational overhead.

By Sangin Lee, Yukyung Choi

llms fine-tuning efficiency multimodal

arXiv AI

Jul 7

Token-Based Affordance Grounding with Large Vision-Language Models

arXiv:2607. 03595v1 Announce Type: cross Abstract: Affordance grounding aims to localize image regions that support a specific action, serving as a core capability for physical intelligence and embodied perception.

By Seung Il Lee, Qinqian Lei, Daguang Xu, Dong Yang, Robby T. Tan, Yixin Chen, Bo Wang

llms robotics multimodal benchmarks

arXiv AI

Jun 11

MultiToP: Learning to Patch Visual Tokens to Mitigate Hallucinations in Video Large Multimodal Models

arXiv:2606. 11792v1 Announce Type: cross Abstract: Video Large Multimodal Models have achieved remarkable progress in video understanding, yet they remain prone to hallucinations, where generated responses are not faithfully supported by the input video.

By Yuansheng Gao, Wenbin Xing, Jiahao Yuan, Kaiwen Zhou, Han Bao, Zonghui Wang, Wenzhi Chen

efficiency multimodal safety

arXiv Machine Learning

Jun 3

Zero-Shot 3D Question Answering via Hierarchical View-to-Token Transportation

arXiv:2606. 03100v1 Announce Type: cross Abstract: Recently, zero-shot 3D scene understanding via 2D Vision-Language Models (VLMs) has gained increasing research interest due to their promising spatial reasoning capabilities.

By Dongsheng Wang, Dawei Su, Hui Huang

llms rag nlp multimodal benchmarks

arXiv AI

Jun 2

A Lightweight Context-Driven Training-Free Network for Scene Text Segmentation and Recognition

arXiv:2503. 15639v2 Announce Type: replace-cross Abstract: Modern scene text recognition systems often depend on large end-to-end architectures that require extensive training and are prohibitively expensive for real-time scenarios.

By Ritabrata Chakraborty, Shivakumara Palaiahnakote, Umapada Pal, Cheng-Lin Liu

computer-vision benchmarks

Related stories

TraceCLIP: Recovering Local Semantics from Patch-to-CLS Contributions

CLIP Tricks You: Training-free Token Pruning for Efficient Pixel Grounding in Large VIsion-Language Models

Token-Based Affordance Grounding with Large Vision-Language Models

MultiToP: Learning to Patch Visual Tokens to Mitigate Hallucinations in Video Large Multimodal Models

Zero-Shot 3D Question Answering via Hierarchical View-to-Token Transportation

A Lightweight Context-Driven Training-Free Network for Scene Text Segmentation and Recognition