Task vectors from weight differences allow arithmetic operations to edit pre-trained models, improving multiple tasks simultaneously and enabling analogical inference on unseen tasks.
hub
Learning Transferable Visual Models From Natural Language Supervision
92 Pith papers cite this work. Polarity classification is still indexing.
92
Pith papers citing it
abstract
State-of-the-art computer vision systems are trained to predict a fixed set of predetermined object categories. This restricted form of supervision limits their generality and usability since additional labeled data is needed to specify any other visual concept. Learning directly from raw text about images is a promising alternative which leverages a much broader source of supervision. We demonstrate that the simple pre-training task of predicting which caption goes with which image is an efficient and scalable way to learn SOTA image representations from scratch on a dataset of 400 million (image, text) pairs collected from the internet. After pre-training, natural language is used to reference learned visual concepts (or describe new ones) enabling zero-shot transfer of the model to downstream tasks. We study the performance of this approach by benchmarking on over 30 different existing computer vision datasets, spanning tasks such as OCR, action recognition in videos, geo-localization, and many types of fine-grained object classification. The model transfers non-trivially to most tasks and is often competitive with a fully supervised baseline without the need for any dataset specific training. For instance, we match the accuracy of the original ResNet-50 on ImageNet zero-shot without needing to use any of the 1.28 million training examples it was trained on. We release our code and pre-trained model weights at https://github.com/OpenAI/CLIP.
hub tools
claims ledger
- abstract State-of-the-art computer vision systems are trained to predict a fixed set of predetermined object categories. This restricted form of supervision limits their generality and usability since additional labeled data is needed to specify any other visual concept. Learning directly from raw text about images is a promising alternative which leverages a much broader source of supervision. We demonstrate that the simple pre-training task of predicting which caption goes with which image is an efficient and scalable way to learn SOTA image representations from scratch on a dataset of 400 million (i
co-cited works
representative citing papers
Cross-attention control in text-conditioned models enables localized and global image edits by editing only the input text prompt.
Textual Inversion learns a single embedding vector from a few images to represent personal concepts inside the text embedding space of a frozen text-to-image model, enabling their composition in natural language prompts.
SMA uses a submodular mutual information objective on data sets to deliver competitive zero-shot classification and retrieval performance on CLIP benchmarks with only tens of thousands of samples, orders of magnitude fewer than standard approaches.
PRISM-VL improves VLM performance by grounding on RAW-derived Meas.-XYZ inputs and exposure-bracketed supervision, gaining +0.1074 BLEU and +4.46% LLM-Judge accuracy over an RGB baseline on a held-out benchmark.
FLARE is a new benchmark with 399 long videos, 87k multimodal clips, and 275k user-style queries for testing audiovisual retrieval under caption and query regimes.
UniShield introduces a knowledge-graph-informed multimodal framework that improves unified detection of physical and digital face attacks through instruction tuning and consistency-optimized reasoning.
Classification fields are infinite recursive hierarchical cluster structures generated by a local refinement rule, and a ReLU network predictor learned from finite prefixes can approximate the generator and extend it to deeper levels with exponential convergence in the completed cell metric.
Concept-based abductive and contrastive explanations find minimal high-level concepts that causally determine vision model outcomes on individual images or groups sharing a specified behavior.
OA-WAM uses persistent address vectors and dynamic content vectors in object slots to enable addressable world-action prediction, improving robustness on manipulation benchmarks under scene changes.
TCD-Arena is a new customizable testing framework that runs millions of experiments to map how 33 different assumption violations affect time series causal discovery methods and shows ensembles can boost overall robustness.
The paper introduces the VODA setting for domain adaptation from scratch using vision-language models and presents TS-DRD, which achieves competitive performance on standard benchmarks without source models.
A weighted entropy active learning method for fair brain segmentation reduces group performance disparities by 75-86% versus standard entropy on synthetic biased MRI data.
Oracle Noise optimizes diffusion model noise on a Riemannian hypersphere guided by key prompt words to preserve the Gaussian prior, eliminate norm inflation, and achieve faster semantic alignment than Euclidean methods.
Z²-Sampling implicitly realizes zero-cost zigzag trajectories for curvature-aware semantic alignment in diffusion models by reducing multi-step paths via operator dualities and temporal caching while synthesizing a directional derivative penalty.
MMEB-V3 benchmark shows omni-modality embedding models fail to enforce instruction-specified modality constraints and exhibit asymmetric, query-biased retrieval.
Latent space probing on CogVideoX achieves 97.29% F1 for adult content detection on a new 11k-clip dataset with 4-6ms overhead.
A Semantic Progress Function is defined as a 1D curve of cumulative semantic shifts from frame embeddings, supporting a linearization procedure that retimes video sequences for constant-rate semantic evolution.
StyleID supplies human-perception-aligned benchmarks and fine-tuned encoders that improve facial identity recognition robustness across stylization types and strengths.
A-MAR decomposes art queries into reasoning plans to condition retrieval, leading to improved explanation quality and multi-step reasoning on art benchmarks compared to baselines.
Audio-Contrastive Preference Optimization (ACPO) mitigates audio hallucination in AVLMs via output-contrastive and input-contrastive objectives that enforce faithful audio grounding.
Alignment of vision-language models with human V1-V3 early visual cortex negatively predicts resistance to sycophantic gaslighting attacks.
A framework uses modality-agnostic prompts to adapt SAM for multi-modal camouflaged object detection, with a mask refine module for better boundaries.
Visual token pruning in MLLMs fails on complex reasoning due to Relevant Visual Information Shift during decoding, but the DSTP framework fixes it training-free across models.
citing papers explorer
-
Editing Models with Task Arithmetic
Task vectors from weight differences allow arithmetic operations to edit pre-trained models, improving multiple tasks simultaneously and enabling analogical inference on unseen tasks.
-
Prompt-to-Prompt Image Editing with Cross Attention Control
Cross-attention control in text-conditioned models enables localized and global image edits by editing only the input text prompt.
-
An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion
Textual Inversion learns a single embedding vector from a few images to represent personal concepts inside the text embedding space of a frozen text-to-image model, enabling their composition in natural language prompts.
-
SMA: Submodular Modality Aligner For Data Efficient Multimodal Learning
SMA uses a submodular mutual information objective on data sets to deliver competitive zero-shot classification and retrieval performance on CLIP benchmarks with only tens of thousands of samples, orders of magnitude fewer than standard approaches.
-
Allegory of the Cave: Measurement-Grounded Vision-Language Learning
PRISM-VL improves VLM performance by grounding on RAW-derived Meas.-XYZ inputs and exposure-bracketed supervision, gaining +0.1074 BLEU and +4.46% LLM-Judge accuracy over an RGB baseline on a held-out benchmark.
-
FLARE: Full-Modality Long-Video Audiovisual Retrieval Benchmark with User-Simulated Queries
FLARE is a new benchmark with 399 long videos, 87k multimodal clips, and 275k user-style queries for testing audiovisual retrieval under caption and query regimes.
-
UniShield: Unified Face Attack Detection via KG-Informed Multimodal Reasoning
UniShield introduces a knowledge-graph-informed multimodal framework that improves unified detection of physical and digital face attacks through instruction tuning and consistency-optimized reasoning.
-
Classification Fields: Arbitrarily Fine Recursive Hierarchical Clustering From Few Examples
Classification fields are infinite recursive hierarchical cluster structures generated by a local refinement rule, and a ReLU network predictor learned from finite prefixes can approximate the generator and extend it to deeper levels with exponential convergence in the completed cell metric.
-
Concept-Based Abductive and Contrastive Explanations for Behaviors of Vision Models
Concept-based abductive and contrastive explanations find minimal high-level concepts that causally determine vision model outcomes on individual images or groups sharing a specified behavior.
-
OA-WAM: Object-Addressable World Action Model for Robust Robot Manipulation
OA-WAM uses persistent address vectors and dynamic content vectors in object slots to enable addressable world-action prediction, improving robustness on manipulation benchmarks under scene changes.
-
TCD-Arena: Assessing Robustness of Time Series Causal Discovery Methods Against Assumption Violations
TCD-Arena is a new customizable testing framework that runs millions of experiments to map how 33 different assumption violations affect time series causal discovery methods and shows ensembles can boost overall robustness.
-
Rethinking the Need for Source Models: Source-Free Domain Adaptation from Scratch Guided by a Vision-Language Model
The paper introduces the VODA setting for domain adaptation from scratch using vision-language models and presents TS-DRD, which achieves competitive performance on standard benchmarks without source models.
-
Exploring Entropy-based Active Learning for Fair Brain Segmentation
A weighted entropy active learning method for fair brain segmentation reduces group performance disparities by 75-86% versus standard entropy on synthetic biased MRI data.
-
Oracle Noise: Faster Semantic Spherical Alignment for Interpretable Latent Optimization
Oracle Noise optimizes diffusion model noise on a Riemannian hypersphere guided by key prompt words to preserve the Gaussian prior, eliminate norm inflation, and achieve faster semantic alignment than Euclidean methods.
-
$Z^2$-Sampling: Zero-Cost Zigzag Trajectories for Semantic Alignment in Diffusion Models
Z²-Sampling implicitly realizes zero-cost zigzag trajectories for curvature-aware semantic alignment in diffusion models by reducing multi-step paths via operator dualities and temporal caching while synthesizing a directional derivative penalty.
-
MMEB-V3: Measuring the Performance Gaps of Omni-Modality Embedding Models
MMEB-V3 benchmark shows omni-modality embedding models fail to enforce instruction-specified modality constraints and exhibit asymmetric, query-biased retrieval.
-
Latent Space Probing for Adult Content Detection in Video Generative Models
Latent space probing on CogVideoX achieves 97.29% F1 for adult content detection on a new 11k-clip dataset with 4-6ms overhead.
-
Video Analysis and Generation via a Semantic Progress Function
A Semantic Progress Function is defined as a 1D curve of cumulative semantic shifts from frame embeddings, supporting a linearization procedure that retimes video sequences for constant-rate semantic evolution.
-
StyleID: A Perception-Aware Dataset and Metric for Stylization-Agnostic Facial Identity Recognition
StyleID supplies human-perception-aligned benchmarks and fine-tuned encoders that improve facial identity recognition robustness across stylization types and strengths.
-
A-MAR: Agent-based Multimodal Art Retrieval for Fine-Grained Artwork Understanding
A-MAR decomposes art queries into reasoning plans to condition retrieval, leading to improved explanation quality and multi-step reasoning on art benchmarks compared to baselines.
-
Don't Let the Video Speak: Audio-Contrastive Preference Optimization for Audio-Visual Language Models
Audio-Contrastive Preference Optimization (ACPO) mitigates audio hallucination in AVLMs via output-contrastive and input-contrastive objectives that enforce faithful audio grounding.
-
Gaslight, Gatekeep, V1-V3: Early Visual Cortex Alignment Shields Vision-Language Models from Sycophantic Manipulation
Alignment of vision-language models with human V1-V3 early visual cortex negatively predicts resistance to sycophantic gaslighting attacks.
-
Modality-Agnostic Prompt Learning for Multi-Modal Camouflaged Object Detection
A framework uses modality-agnostic prompts to adapt SAM for multi-modal camouflaged object detection, with a mask refine module for better boundaries.
-
Why and When Visual Token Pruning Fails? A Study on Relevant Visual Information Shift in MLLMs Decoding
Visual token pruning in MLLMs fails on complex reasoning due to Relevant Visual Information Shift during decoding, but the DSTP framework fixes it training-free across models.
-
Bottleneck Tokens for Unified Multimodal Retrieval
Bottleneck Tokens paired with a masked generative objective achieve state-of-the-art unified multimodal retrieval performance among 2B-scale models on the MMEB-V2 benchmark with 78 datasets.
-
CWCD: Category-Wise Contrastive Decoding for Structured Medical Report Generation
CWCD improves structured chest X-ray report generation by using category-wise contrastive decoding to reduce spurious pathology co-occurrences in multi-modal LLMs.
-
WildDet3D: Scaling Promptable 3D Detection in the Wild
WildDet3D is a promptable 3D detector paired with a new 1M-image dataset across 13.5K categories that sets SOTA on open-world and zero-shot 3D detection benchmarks.
-
Revealing Physical-World Semantic Vulnerabilities: Universal Adversarial Patches for Infrared Vision-Language Models
UCGP is a universal physical adversarial patch that compromises cross-modal semantic alignment in IR-VLMs through curved-grid parameterization and representation-space disruption.
-
Self-Directed Task Identification
SDTI lets models identify the correct target variable in datasets in a zero-shot setting using standard neural networks, beating baselines by 14% F1 on synthetic benchmarks.
-
Visual Instruction Tuning
LLaVA is trained on GPT-4 generated visual instruction data to achieve 85.1% relative performance to GPT-4 on synthetic multimodal tasks and 92.53% accuracy on Science QA.
-
BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
BLIP-2 bootstraps vision-language pre-training from frozen image encoders and LLMs via a lightweight two-stage Querying Transformer, delivering SOTA results with 54x fewer trainable parameters than Flamingo80B on zero-shot VQAv2.
-
LAION-5B: An open large-scale dataset for training next generation image-text models
LAION-5B is an openly released dataset of 5.85 billion CLIP-filtered image-text pairs that enables replication of foundational vision-language models.
-
Flamingo: a Visual Language Model for Few-Shot Learning
Flamingo models reach new state-of-the-art few-shot results on image and video tasks by bridging frozen vision and language models with cross-attention layers trained on interleaved web-scale data.
-
Hierarchical Text-Conditional Image Generation with CLIP Latents
A hierarchical prior-decoder model using CLIP latents generates more diverse text-conditional images than direct methods while preserving photorealism and caption fidelity.
-
GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models
A 3.5-billion-parameter diffusion model with classifier-free guidance generates images preferred over DALL-E by human raters and can be fine-tuned for text-guided inpainting.
-
LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs
LAION-400M is a publicly released open dataset of 400 million CLIP-filtered image-text pairs with embeddings and kNN indices for efficient search.
-
Diffusion Models Beat GANs on Image Synthesis
Diffusion models with architecture improvements and classifier guidance achieve superior FID scores to GANs on unconditional and conditional ImageNet image synthesis.
-
EDGER: EDge-Guided with HEatmap Refinement for Generalizable Image Forgery Localization
A dual-branch system using frequency edge cues and CLIP-based synthetic patch detection for accurate, resolution-independent image forgery localization.
-
StereoPolicy: Improving Robotic Manipulation Policies via Stereo Perception
StereoPolicy fuses stereo image pairs via a Stereo Transformer on pretrained 2D encoders to boost robotic manipulation policies, showing gains over monocular, RGB-D, point cloud, and multi-view methods in simulations and real-robot tests.
-
Language-Conditioned Visual Grounding with CLIP Multilingual
Fixing the visual encoder in multilingual CLIP isolates text-branch deficits as the cause of lower visual grounding performance for low-resource languages, with model scaling widening some gaps but not others.
-
CASCADE: Context-Aware Relaxation for Speculative Image Decoding
CASCADE formalizes semantic interchangeability and convergence in target model representations to enable context-aware acceptance relaxation in tree-based speculative decoding, delivering up to 3.6x speedup on text-to-image models without quality loss.
-
Zero-Shot Satellite Image Retrieval through Joint Embeddings: Application to Crisis Response
GeoQuery enables natural-language retrieval of global Sentinel-2 imagery by optimizing text prompts on a 100k proxy subset so that text embeddings correlate with CLAY visual embeddings, then using two-stage text-then-visual search, achieving 31.6% accuracy within 50 km on disaster queries.
-
Catching the Infection Before It Spreads: Foresight-Guided Defense in Multi-Agent Systems
A foresight-based local purification method simulates future agent interactions, detects infections via response diversity across personas, and applies targeted rollback or recursive diagnosis to cut maximum infection rates from over 95% to under 5.47% while preserving benign performance.
-
VisInject: Disruption != Injection -- A Dual-Dimension Evaluation of Universal Adversarial Attacks on Vision-Language Models
Universal adversarial attacks cause output perturbation 90 times more often than precise target injection in VLMs, with only 2 verbatim successes out of 6615 tests.
-
Compared to What? Baselines and Metrics for Counterfactual Prompting
Counterfactual prompting effects on LLMs are often indistinguishable from those caused by meaning-preserving paraphrases, causing most previously reported demographic sensitivities to disappear under proper statistical comparison.
-
Delta Score Matters! Spatial Adaptive Multi Guidance in Diffusion Models
SAMG uses spatially adaptive guidance scales derived from a geometric analysis of classifier-free guidance to resolve the detail-artifact dilemma in diffusion-based image and video generation.
-
Majorization-Guided Test-Time Adaptation for Vision-Language Models under Modality-Specific Shift
MG-MTTA improves VLM accuracy under modality-specific shifts by replacing pure entropy minimization with majorization-guided adaptation that incorporates a reliability-aware gate prior.
-
Only Brains Align with Brains: Cross-Region Alignment Patterns Expose Limits of Normative Models
Alignment pattern analysis reveals that models aligned to individual brain ROIs do not reproduce the stable cross-region alignment profiles observed across human subjects.
-
Using Machine Mental Imagery for Representing Common Ground in Situated Dialogue
Incremental visual scaffolding using multimodal models improves persistent common ground representation in situated dialogue by reducing representational blur compared to text-only approaches, with hybrid text-visual yielding best results on the IndiRef benchmark.
-
MoDAl: Self-Supervised Neural Modality Discovery via Decorrelation for Speech Neuroprosthesis
MoDAl discovers complementary neurolinguistic modalities via contrastive-decorrelation objectives, cutting brain-to-text word error rate from 26.3% to 21.6% by incorporating area 44 signals.