VGR introduces a visual-grounded reasoning MLLM that detects and replays image regions during inference, achieving gains on visual benchmarks with 30% fewer image tokens than the LLaVA-NeXT-7B baseline.
Reconstructive visual instruction tuning
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 7verdicts
UNVERDICTED 7roles
background 1polarities
background 1representative citing papers
HYDRA-X presents the first unified multimodal model using a single ViT for holistic image-video tokenization, with ablations on attention and compression plus a latent-level editing improvement.
VIF is a new inference-time module that maintains visual grounding in MLLMs by directly bridging pure visual representations to the output space throughout generation.
SWIM aligns cross-attention maps from object nouns to ground-truth masks during training on the new NL-Refer dataset to enable text-only fine-grained video object understanding in MLLMs.
A latent denoising objective with saliency-aware corruption and contrastive distillation improves visual alignment and corruption robustness in large multimodal models.
DriveVLA-W0 adds world modeling to predict future images in VLA models, overcoming sparse action supervision and amplifying data scaling laws on NAVSIM benchmarks and a large in-house dataset.
Semantic Generative Tuning applies segmentation-based generative proxies during post-training to align and improve both understanding and generation in unified multimodal models.
citing papers explorer
-
VGR: Visual Grounded Reasoning
VGR introduces a visual-grounded reasoning MLLM that detects and replays image regions during inference, achieving gains on visual benchmarks with 30% fewer image tokens than the LLaVA-NeXT-7B baseline.
-
HYDRA-X: Native Unified Multimodal Models with Holistic Visual Tokenizers
HYDRA-X presents the first unified multimodal model using a single ViT for holistic image-video tokenization, with ablations on attention and compression plus a latent-level editing improvement.
-
Vision Inference Former: Sustaining Visual Consistency in Multimodal Large Language Models
VIF is a new inference-time module that maintains visual grounding in MLLMs by directly bridging pure visual representations to the output space throughout generation.
-
See What I Mean: Aligning Vision and Language Representations for Video Fine-grained Object Understanding
SWIM aligns cross-attention maps from object nouns to ground-truth masks during training on the new NL-Refer dataset to enable text-only fine-grained video object understanding in MLLMs.
-
Latent Denoising Improves Visual Alignment in Large Multimodal Models
A latent denoising objective with saliency-aware corruption and contrastive distillation improves visual alignment and corruption robustness in large multimodal models.
-
DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Driving
DriveVLA-W0 adds world modeling to predict future images in VLA models, overcoming sparse action supervision and amplifying data scaling laws on NAVSIM benchmarks and a large in-house dataset.
-
Semantic Generative Tuning for Unified Multimodal Models
Semantic Generative Tuning applies segmentation-based generative proxies during post-training to align and improve both understanding and generation in unified multimodal models.