paper-with-me

Papers

MVT: Mask-Grounded Vision-Language Models for Taxonomy-Aligned Land-Cover Tagging

2025-09-23 · Siyi Chen, Kai Wang, Weicong Pang, Ruiming Yang, Ziru Chen, Renjun Gao, Alexis Kai Hon Lau, Dasa Gu, Chenchen Zhang, Cheng Li arxiv

Land-cover understanding in remote sensing increasingly demands class-agnostic systems that generalize across datasets while remaining spatially precise and interpretable. We study a geometry-first discovery-and-interpretation setting under domain shift, where candidate regions are delineated class-agnostically and supervision avoids lexical class names via anonymized identifiers. Complementary to open-set recognition and open-world learning, we focus on coupling class-agnostic mask evidence with taxonomy-grounded scene interpretation, rather than unknown rejection or continual class expansion. We propose MVT, a three-stage framework that (i) extracts boundary-faithful region masks using SAM2 with domain adaptation, (ii) performs mask-grounded semantic tagging and scene description generation via dual-step LoRA fine-tuning of multimodal LLMs, and (iii) evaluates outputs with LLM-as-judge scoring calibrated by stratified expert ratings. On cross-dataset segmentation transfer (train on OpenEarthMap, evaluate on LoveDA), domain-adapted SAM2 improves mask quality; meanwhile, dual-step MLLM fine-tuning yields more accurate taxonomy-aligned tags and more informative mask-grounded scene descriptions.

📄 PDF Abstract BibTeX arXiv:2509.18693

Code (0)

등록된 구현이 없습니다.

Tasks

Domain Adaptation

Similar Papers 제목 키워드 기반

GeoMeld: Toward Semantically Grounded Foundation Models for Remote Sensing

2026-04-12 · Maram Hasan, Md Aminur Hossain, Savitra Roy, Souparna Bhowmik 외 arxiv

Effective foundation modeling in remote sensing requires spatially aligned heterogeneous modalities coupled with semantically grounded supervision, yet such resources remain limited at scale. We present GeoMeld, a large-…

Representation Learning

From Masks to Pixels and Meaning: A New Taxonomy, Benchmark, and Metrics for VLM Image Tampering

2026-03-20 · Xinyi Shang, Yi Tang, Jiacheng Cui, Ahmed Elhagry 외 arxiv

Existing tampering detection benchmarks largely rely on object masks, which severely misalign with the true edit signal: many pixels inside a mask are untouched or only trivially modified, while subtle yet consequential …

EiCAP: Beyond Fluency, Probing and Improving Emotional Intelligence in LLMs via Psychologically Grounded Multi-Turn Dialogue

2025-08-08 · Nizi Nazar, Pardis Sadat Zahraei, Dilek Hakkani-Tür, Natasa Milic-Frayling 외 arxiv

Large Language Models increasingly serve in emotionally sensitive roles, including mental health support, education, and crisis response, yet they lack a principled framework for assessing or improving Emotional Intellig…

Emotional Intelligence

LongCrafter: Towards Diverse Long-Context Understanding via Evidence-Graph-Guided Instruction Synthesis

2026-07-07 · Chenhao Yuan, Yinhao Xu, Shuwen Xu, Xizhi Yang 외 arxiv

Synthesizing long-context supervised fine-tuning (SFT) data is a scalable way to enhance the long-context understanding of large language models (LLMs), yet existing approaches share three limitations: narrow task covera…

Long-Context Understanding

Almieyar-Oryx-BloomBench: A Bilingual Multimodal Benchmark for Cognitively Informed Evaluation of Vision-Language Models

2026-06-04 · Mohammad Mahdi Abootorabi, Omid Ghahroodi, Anas Madkoor, Marzia Nouri 외 arxiv

Despite the rapid progress of Vision-Language Models (VLMs), the field lacks benchmarks that rigorously diagnose their true reasoning abilities and chart meaningful progress toward human-like multimodal intelligence. Mos…

Multimodal Reasoning