Molmo VLMs trained on newly collected PixMo open datasets achieve state-of-the-art performance among open-weight models and surpass multiple proprietary VLMs including Claude 3.5 Sonnet and Gemini 1.5 Pro.
hub
xgen-mm (blip-3): A family of open large multimodal models
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
hub tools
citation-role summary
background 1
baseline 1
dataset 1
other 1
citation-polarity summary
representative citing papers
Gromov-Wasserstein distance between modalities provides a stronger, inference-only predictor of final VLM performance than conventional encoder metrics, backed by theory linking it to cross-modal learnability and verified across 60+ training runs.
Thinking with Drafting reconceptualizes visual reasoning as optical decompression by forcing models to draft mental models into executable DSL code for deterministic self-verification on the VisAlg benchmark.
PPLLaVA uses CLIP-based alignment and prompt-guided convolution-style pooling to reduce visual tokens 18x in Video LLMs, achieving SOTA results on captioning, QA, and long-form reasoning benchmarks with higher throughput.
GR-3 is a VLA model that generalizes to novel objects, environments, and abstract instructions, outperforms the π0 baseline, and integrates with the new ByteMini bi-manual mobile robot.
BAGEL is a unified decoder-only model that develops emerging complex multimodal reasoning abilities after pretraining on large-scale interleaved data and outperforms prior open-source unified models.
BLIP3-o uses a diffusion transformer to generate CLIP image features and a sequential pretraining strategy to build open models that perform strongly on both image understanding and generation benchmarks.
Modality-mutual attention (MMA) is introduced to replace causal attention in MLLMs, enabling mutual attention between image and text tokens and claiming SOTA results on 12 multimodal benchmarks with no extra parameters.
VideoLLaMA3 uses a vision-centric training paradigm and token-reduction design to reach competitive results on image and video benchmarks.
citing papers explorer
-
Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models
Molmo VLMs trained on newly collected PixMo open datasets achieve state-of-the-art performance among open-weight models and surpass multiple proprietary VLMs including Claude 3.5 Sonnet and Gemini 1.5 Pro.
-
Rethinking Model Selection in VLM Through the Lens of Gromov-Wasserstein Distance
Gromov-Wasserstein distance between modalities provides a stronger, inference-only predictor of final VLM performance than conventional encoder metrics, backed by theory linking it to cross-modal learnability and verified across 60+ training runs.
-
Thinking with Drafting: Optical Decompression via Logical Reconstruction
Thinking with Drafting reconceptualizes visual reasoning as optical decompression by forcing models to draft mental models into executable DSL code for deterministic self-verification on the VisAlg benchmark.
-
PPLLaVA: Varied Video Sequence Understanding With Prompt Guidance
PPLLaVA uses CLIP-based alignment and prompt-guided convolution-style pooling to reduce visual tokens 18x in Video LLMs, achieving SOTA results on captioning, QA, and long-form reasoning benchmarks with higher throughput.
-
GR-3 Technical Report
GR-3 is a VLA model that generalizes to novel objects, environments, and abstract instructions, outperforms the π0 baseline, and integrates with the new ByteMini bi-manual mobile robot.
-
Emerging Properties in Unified Multimodal Pretraining
BAGEL is a unified decoder-only model that develops emerging complex multimodal reasoning abilities after pretraining on large-scale interleaved data and outperforms prior open-source unified models.
-
BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset
BLIP3-o uses a diffusion transformer to generate CLIP image features and a sequential pretraining strategy to build open models that perform strongly on both image understanding and generation benchmarks.
-
Seeing is Understanding: Unlocking Causal Attention into Modality-Mutual Attention for Multimodal LLMs
Modality-mutual attention (MMA) is introduced to replace causal attention in MLLMs, enabling mutual attention between image and text tokens and claiming SOTA results on 12 multimodal benchmarks with no extra parameters.
-
VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding
VideoLLaMA3 uses a vision-centric training paradigm and token-reduction design to reach competitive results on image and video benchmarks.
- FineBench: Benchmarking and Enhancing Vision-Language Models for Fine-grained Human Activity Understanding