RaptorMai / CompBench
CompBench evaluates the comparative reasoning of multimodal large language models (MLLMs) with 40K image pairs and questions across 8 dimensions of relative comparison: visual attribute, existence, state, emotion, temporality, spatiality, quantity, and quality. CompBench covers diverse visual domains, including animals, fashion, sports, and scen…
☆31Updated 3 months ago
Related projects ⓘ
Alternatives and complementary repositories for CompBench
- ☆14Updated last month
- Lessons Learned from a Unifying Empirical Study of Parameter-Efficient Transfer Learning (PETL) in Visual Recognition☆24Updated 2 weeks ago
- Code for Continuously Changing Corruptions (CCC) benchmark + evaluation☆29Updated 2 months ago
- ☆37Updated last year
- Test-Time Adaptation via Conjugate Pseudo-Labels☆38Updated last year
- ☆41Updated last year
- PyTorch implementation of POEM (Out-of-distribution detection with posterior sampling), ICML 2022☆28Updated last year
- ☆24Updated last year
- (Pytorch) Training ResNets on ImageNet-100 data☆52Updated 2 years ago
- PyTorch implementation of CIDER (How to exploit hyperspherical embeddings for out-of-distribution detection), ICLR 2023☆54Updated last year
- Official Implementation of LADS (Latent Augmentation using Domain descriptionS)☆49Updated last year
- LANCE: Stress-testing Visual Models by Generating Language-guided Counterfactual Images☆28Updated 11 months ago
- This repo implements the CVPR23 paper Trainable Projected Gradient Method for Robust Fine-tuning☆24Updated 11 months ago
- [NeurIPS21] TTT++: When Does Self-supervised Test-time Training Fail or Thrive?☆58Updated 2 years ago
- Official Code for Dataset Distillation using Neural Feature Regression (NeurIPS 2022)☆46Updated 2 years ago
- Hierarchical Decomposition of Prompt-Based Continual Learning: Rethinking Obscured Sub-optimality (NeurIPS 2023, Spotlight)☆74Updated 9 months ago
- Code for the paper "Representational Continuity for Unsupervised Continual Learning" (ICLR 22)☆93Updated last year
- Respect to the input tensor instead of paramters of NN☆15Updated 2 years ago
- ☆105Updated last year
- Official PyTorch implementation of "Dataset Condensation via Efficient Synthetic-Data Parameterization" (ICML'22)☆104Updated last year
- source code for NeurIPS'23 paper "Dream the Impossible: Outlier Imagination with Diffusion Models"☆61Updated 2 weeks ago
- ☆47Updated last year
- ☆15Updated 2 years ago
- source code for ICLR'23 paper "Non-parametric Outlier Synthesis"☆53Updated last year
- List of papers that combine self-supervision and continual learning☆59Updated this week
- Test-time Prompt Tuning (TPT) for zero-shot generalization in vision-language models (NeurIPS 2022))☆145Updated 2 years ago
- Official Code for NeurIPS 2022 Paper: How Mask Matters: Towards Theoretical Understandings of Masked Autoencoders☆55Updated 11 months ago
- Official implementation for 'Class-Balancing Diffusion Models'☆46Updated 5 months ago
- ☆58Updated last year
- Augmenting with Language-guided Image Augmentation (ALIA)☆63Updated last year