ViperGPT generates executable Python code to compose pre-trained vision-and-language modules into programs that answer visual queries, reaching state-of-the-art results with no additional training.
InThirty-fifth Conference on Neural Infor- mation Processing Systems Datasets and Benchmarks Track (Round 2)
4 Pith papers cite this work, alongside 10 external citations. Polarity classification is still indexing.
4
Pith papers citing it
10
external citations · external index
verdicts
UNVERDICTED 4representative citing papers
Proposes the first unified incomplete video-language model that processes missing modalities and serves as a plug-and-play module to boost existing VLMs on multi-modal tasks.
LanguageBind aligns video, infrared, depth, and audio to a frozen language encoder via contrastive learning on the new VIDAL-10M dataset, extending video-language pretraining to N modalities.
mPLUG-Owl introduces a two-stage modular training paradigm that aligns images with text in LLMs via frozen visual modules followed by LoRA fine-tuning, achieving strong multimodal instruction following.
citing papers explorer
-
ViperGPT: Visual Inference via Python Execution for Reasoning
ViperGPT generates executable Python code to compose pre-trained vision-and-language modules into programs that answer visual queries, reaching state-of-the-art results with no additional training.
-
Towards Unified Vision-Language Models with Incomplete Multi-Modal Inputs
Proposes the first unified incomplete video-language model that processes missing modalities and serves as a plug-and-play module to boost existing VLMs on multi-modal tasks.
-
LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment
LanguageBind aligns video, infrared, depth, and audio to a frozen language encoder via contrastive learning on the new VIDAL-10M dataset, extending video-language pretraining to N modalities.
-
mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality
mPLUG-Owl introduces a two-stage modular training paradigm that aligns images with text in LLMs via frozen visual modules followed by LoRA fine-tuning, achieving strong multimodal instruction following.