AVA-Bench evaluates vision foundation models by disentangling 14 atomic visual abilities with aligned training-test distributions to reveal precise ability fingerprints.
Sigmoid loss for language image pre-training
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 2
method 1
citation-polarity summary
representative citing papers
GenLIP pretrains ViTs to generate language tokens from images via LM objective without contrastive batches or extra decoders, matching baselines on less data and improving on OCR after multi-resolution continued pretraining.
UniDomain extracts atomic PDDL domains from 12,393 robot videos to create a unified domain of 3137 operators and 2875 predicates, then retrieves and fuses relevant parts to enable zero-shot planning on unseen real-world tasks.
Mogao presents a causal unified model with deep fusion, dual encoders, and interleaved position embeddings that achieves strong performance on multi-modal understanding, text-to-image generation, and coherent interleaved outputs including zero-shot editing.
SenseNova-U1 presents native unified multimodal models that match top understanding VLMs while delivering strong performance in image generation, infographics, and interleaved tasks via the NEO-unify architecture.
UniWorld-V1 shows that semantic features from large multimodal models enable unified visual understanding and generation, achieving strong results on perception and manipulation tasks with only 2.7 million training samples.
citing papers explorer
-
AVA-Bench: Atomic Visual Ability Benchmark for Vision Foundation Models
AVA-Bench evaluates vision foundation models by disentangling 14 atomic visual abilities with aligned training-test distributions to reveal precise ability fingerprints.
-
Let ViT Speak: Generative Language-Image Pre-training
GenLIP pretrains ViTs to generate language tokens from images via LM objective without contrastive batches or extra decoders, matching baselines on less data and improving on OCR after multi-resolution continued pretraining.
-
UniDomain: Pretraining a Unified PDDL Domain from Real-World Demonstrations for Generalizable Robot Task Planning
UniDomain extracts atomic PDDL domains from 12,393 robot videos to create a unified domain of 3137 operators and 2875 predicates, then retrieves and fuses relevant parts to enable zero-shot planning on unseen real-world tasks.
-
Mogao: An Omni Foundation Model for Interleaved Multi-Modal Generation
Mogao presents a causal unified model with deep fusion, dual encoders, and interleaved position embeddings that achieves strong performance on multi-modal understanding, text-to-image generation, and coherent interleaved outputs including zero-shot editing.
-
SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture
SenseNova-U1 presents native unified multimodal models that match top understanding VLMs while delivering strong performance in image generation, infographics, and interleaved tasks via the NEO-unify architecture.
-
UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation
UniWorld-V1 shows that semantic features from large multimodal models enable unified visual understanding and generation, achieving strong results on perception and manipulation tasks with only 2.7 million training samples.
- Modality Gap-Driven Subspace Alignment Training Paradigm For Multimodal Large Language Models