visual comprehension

SpatialMath: Spatial Comprehension-Infused Symbolic Reasoning for Mathematical Problem-Solving EACL 2026 ViCToR: Improving Visual Comprehension via Token Reconstruction for Pretraining LMMs AAAI 2026 CoSpace: Benchmarking Continuous Space Perception Ability for Vision-Language Models CVPR 2025 LIRA: Inferring Segmentation in Large Multi-modal Models with Local Interleaved Region Assistance ICCV 2025 Q-Frame: Query-aware Frame Selection and Multi-Resolution Adaptation for Video-LLMs ICCV 2025 Scaling Inference-Time Search with Vision Value Model for Improved Visual Comprehension ICCV 2025 Unsupervised Visual Chain-of-Thought Reasoning via Preference Optimization ICCV 2025 Unveiling the Ignorance of MLLMs: Seeing Clearly, Answering Incorrectly CVPR 2025 Auto-Encoding Morph-Tokens for Multimodal LLM ICML 2024 Beyond Text: Frozen Large Language Models in Visual Signal Comprehension CVPR 2024 CODIS: Benchmarking Context-dependent Visual Comprehension for Multimodal Large Language Models ACL 2024 Evaluating and Analyzing Relationship Hallucinations in Large Vision-Language Models ICML 2024 Vitron: A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, Editing NeurIPS 2024 GPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction NeurIPS 2023 Semantic Guided Latent Parts Embedding for Few-Shot Learning WACV 2023 Improving the Visual Comprehension of Point Sets CVPR 2013