A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Yue Fan, Xuehai He, Diji Yang, et al.
GRIT trains multimodal LLMs to generate reasoning chains interleaving text and bounding boxes, using RL with robust rewards to achieve data-efficient visual grounding.
Aniri, Jinhe Bi, Peng Liao, et al.
OPD-V introduces a visual on-policy self-distillation paradigm that uses modality-balance trust regions to improve MLLM reasoning while reducing training cost.
Unknown
This paper investigates whether multimodal large language models (MLLMs) can develop visual-spatial intelligence to remember and recall spaces from sequential visual observations, akin to human spatial memory.
Unknown
This survey provides a comprehensive overview of multimodal large language models (MLLMs), covering their frameworks, training strategies, and evaluation methods.
Unknown
A comprehensive survey and guide to multimodal large language models (MLLMs) for vision-language tasks, covering architectures, training, and applications.
Unknown
FlashRAG is a modular toolkit that provides a comprehensive framework for efficient retrieval-augmented generation research, supporting both LLMs and MLLMs.
Zongyi Chen, Yu Liang, Jie Lin, et al.
PathVU is a vision-anchored benchmark for fine-grained multiscale visual understanding in pathology, with 14 VQA tasks, 61,673 images, and 308,070 samples, revealing substantial limitations in current MLLMs.
Kaiyu Li, Zepeng Xin, Zixuan Jiang, et al.
Introduces OVEarth-Bench, a benchmark for open-vocabulary Earth observation with broad category coverage and diverse query types, revealing current method limitations and MLLM superiority.
Tongtong Feng, Xin Wang, Yu-Gang Jiang, et al.
This paper surveys embodied AI from basics to advances, covering LLM-driven and world model-driven approaches, and proposes a joint MLLM-WM architecture for complex physical tasks.
Unknown
This survey reviews the development of multimodal large language models (MLLMs), inspired by the success of large language models.
Unknown
A comprehensive survey of multimodal large language models (MLLMs), their architectures, training methods, and applications.