Uni-Edit introduces a data synthesis pipeline turning VQA data into reasoning-intensive editing instructions, enabling single-task tuning that boosts all three capabilities in models like BAGEL and Janus-Pro.
Mmbench: Is your multi-modal model an all-around player? InECCV
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
dataset 2
background 1
citation-polarity summary
representative citing papers
G²TR reduces visual tokens and prefill compute by 1.94x in separate-encoder UMMs via generation-guided importance from VAE latent consistency, balanced selection, and merging, while preserving reasoning accuracy and editing quality.
Cambrian-S introduces VSI-SUPER benchmarks for long-horizon spatial recall and counting, shows data scaling yields 30% gains on existing tests, and demonstrates a self-supervised next-latent predictor using surprise outperforms baselines on the new spatial supersensing tasks.
SSL4RL reformulates self-supervised learning objectives into dense, verifiable reward signals for RL-based fine-tuning of vision-language models, yielding performance gains on reasoning benchmarks.
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.
JoyAI-Image unifies visual understanding and generation via an MLLM-MMDiT architecture with spatial training signals to reach competitive benchmark performance and stronger spatial intelligence.
citing papers explorer
-
Uni-Edit: Intelligent Editing Is A General Task For Unified Model Tuning
Uni-Edit introduces a data synthesis pipeline turning VQA data into reasoning-intensive editing instructions, enabling single-task tuning that boosts all three capabilities in models like BAGEL and Janus-Pro.
-
G$^2$TR: Generation-Guided Visual Token Reduction for Separate-Encoder Unified Multimodal Models
G²TR reduces visual tokens and prefill compute by 1.94x in separate-encoder UMMs via generation-guided importance from VAE latent consistency, balanced selection, and merging, while preserving reasoning accuracy and editing quality.
-
Cambrian-S: Towards Spatial Supersensing in Video
Cambrian-S introduces VSI-SUPER benchmarks for long-horizon spatial recall and counting, shows data scaling yields 30% gains on existing tests, and demonstrates a self-supervised next-latent predictor using surprise outperforms baselines on the new spatial supersensing tasks.
-
SSL4RL: Revisiting Self-supervised Learning as Intrinsic Reward for Visual-Language Reasoning
SSL4RL reformulates self-supervised learning objectives into dense, verifiable reward signals for RL-based fine-tuning of vision-language models, yielding performance gains on reasoning benchmarks.
-
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.
-
JoyAI-Image: Awaking Spatial Intelligence in Unified Multimodal Understanding and Generation
JoyAI-Image unifies visual understanding and generation via an MLLM-MMDiT architecture with spatial training signals to reach competitive benchmark performance and stronger spatial intelligence.