conftrace_

gpt-4v

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

context-sensitive text-rich visual reasoning (1) gemini-pro-vision (1) human-crafted instructions (1) llava-next (1) seeact (1) visuals (1) image-grounded guidance (1) open-source vision models (1) feature router (1) geometrically-grounded vision encoder (1)

Papers

Mitigating Object Hallucination in Large Vision-Language Models via Image-Grounded Guidance ICML 2025 Primitive Vision: Improving Diagram Understanding in MLLMs ICML 2025 ConTextual: Evaluating Context-Sensitive Text-Rich Visual Reasoning in Large Multimodal Models ICML 2024 GPT-4V(ision) is a Generalist Web Agent, if Grounded ICML 2024