AnchorSeg uses ordered query banks of latent reasoning tokens plus a spatial anchor token and a Token-Mask Cycle Consistency loss to achieve 67.7% gIoU and 68.1% cIoU on the ReasonSeg benchmark.
arXiv preprint arXiv:2311.03356 (2024)
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
method 1
citation-polarity summary
fields
cs.CV 5polarities
background 2representative citing papers
OmniSch is the first benchmark exposing gaps in LMMs for PCB schematic visual grounding, topology-to-graph parsing, geometric weighting, and tool-augmented reasoning.
MINGLE is a modular pipeline that combines off-the-shelf detection tools with VLM reasoning to localize socially connected groups in urban scenes and is supported by a new 100K-image dataset.
MoE-LLaVA applies mixture-of-experts sparsity to LVLMs via MoE-Tuning, delivering LLaVA-1.5-7B level visual understanding and better hallucination resistance with only ~3B active parameters.
This survey organizes the architectures, training strategies, data, evaluation methods, extensions, and challenges of Multimodal Large Language Models.
citing papers explorer
-
AnchorSeg: Language Grounded Query Banks for Reasoning Segmentation
AnchorSeg uses ordered query banks of latent reasoning tokens plus a spatial anchor token and a Token-Mask Cycle Consistency loss to achieve 67.7% gIoU and 68.1% cIoU on the ReasonSeg benchmark.
-
OmniSch: A Multimodal PCB Schematic Benchmark For Structured Diagram Visual Reasoning
OmniSch is the first benchmark exposing gaps in LMMs for PCB schematic visual grounding, topology-to-graph parsing, geometric weighting, and tool-augmented reasoning.
-
MINGLE: VLMs for Semantically Complex Region Detection in Urban Scenes
MINGLE is a modular pipeline that combines off-the-shelf detection tools with VLM reasoning to localize socially connected groups in urban scenes and is supported by a new 100K-image dataset.
-
MoE-LLaVA: Mixture of Experts for Large Vision-Language Models
MoE-LLaVA applies mixture-of-experts sparsity to LVLMs via MoE-Tuning, delivering LLaVA-1.5-7B level visual understanding and better hallucination resistance with only ~3B active parameters.
-
A Survey on Multimodal Large Language Models
This survey organizes the architectures, training strategies, data, evaluation methods, extensions, and challenges of Multimodal Large Language Models.