Slot-MLLM introduces a slot-attention-based object-centric visual tokenizer with Q-Former encoder, diffusion decoder, and residual vector quantization for improved local visual comprehension and generation in multimodal LLMs.
Visual genome: Connecting language and vision using crowdsourced dense image annotations.International journal of computer vision, 123:32–73, 2017
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2025 2verdicts
UNVERDICTED 2representative citing papers
LENS is a new multi-level benchmark dataset for evaluating MLLMs on perception-to-reasoning tasks using the same images across all levels with recent social media content.
citing papers explorer
-
Slot-MLLM: Object-Centric Visual Tokenization for Multimodal LLM
Slot-MLLM introduces a slot-attention-based object-centric visual tokenizer with Q-Former encoder, diffusion decoder, and residual vector quantization for improved local visual comprehension and generation in multimodal LLMs.
-
LENS: Multi-level Evaluation of Multimodal Reasoning with Large Language Models
LENS is a new multi-level benchmark dataset for evaluating MLLMs on perception-to-reasoning tasks using the same images across all levels with recent social media content.