11 papers
Dynamo: Dynamic Skill-Tool Evolution for Vision-Language Agents
Yutao Sun, Yanting Miao, Hao-Xuan Ma +8
Improving vision-language models (VLMs) on visual reasoning typically requires retraining or hand-designed prompts and tools. We present Dynamo, a training-free framework that adap…
REKEY: Metadata-Grounded Visual-Key Regeneration for Contamination-Resilient VQA Evaluation
Tengjie Lin, Yutao Sun, Jingwei Ni +7
Static visual question answering (VQA) benchmarks age quickly: Once the items leak into training corpora, scores can reflect memorization rather than genuine visual ability, thus o…
Which Pretraining Paradigm Better Serves Spatial Intelligence? An Empirical Comparison of Vision-Language and Video Generation Models
Haozhan Shen, Tiancheng Zhao, Kangjia Zhao +1
Spatial intelligence requires visual representations that capture both semantic objects and geometric structure in the physical world. To support this, two major pre-training schem…
Geo-R1: Improving Few-Shot Geospatial Referring Expression Understanding with Reinforcement Fine-Tuning
Zilun Zhang, Zian Guan, Tiancheng Zhao +7
Referring expression understanding in remote sensing poses unique challenges, as it requires reasoning over complex object-context relationships. While supervised fine-tuning (SFT)…
DetailCLIP: Injecting Image Details into CLIP's Feature Space
Zilun Zhang, Cuifeng Shen, Yuan Shen +4
Although CLIP-like Visual Language Models provide a functional joint feature space for image and text, due to the limitation of the CILP-like model's image input size (e.g., 224),…
MM-CondChain: A Programmatically Verified Benchmark for Visually Grounded Deep Compositional Reasoning
Haozhan Shen, Shilin Yan, Hongwei Xue +5
Multimodal Large Language Models (MLLMs) are increasingly used to carry out visual workflows such as navigating GUIs, where the next step depends on verified visual compositional c…