MulTaBench is a new collection of 40 image-tabular and text-tabular datasets designed to test target-aware representation tuning in multimodal tabular models.
TIPSv2: Advancing Vision-Language Pretraining with Enhanced Patch-Text Alignment
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
abstract
Recent progress in vision-language pretraining has enabled significant improvements to many downstream computer vision applications, such as classification, retrieval, segmentation and depth prediction. However, a fundamental capability that these models still struggle with is aligning dense patch representations with text embeddings of corresponding concepts. In this work, we investigate this critical issue and propose novel techniques to enhance this capability in foundational vision-language models. First, we reveal that a patch-level distillation procedure significantly boosts dense patch-text alignment -- surprisingly, the patch-text alignment of the distilled student model strongly surpasses that of the teacher model. This observation inspires us to consider modifications to pretraining recipes, leading us to propose iBOT++, an upgrade to the commonly-used iBOT masked image objective, where unmasked tokens also contribute directly to the loss. This dramatically enhances patch-text alignment of pretrained models. Additionally, to improve vision-language pretraining efficiency and effectiveness, we modify the exponential moving average setup in the learning recipe, and introduce a caption sampling strategy to benefit from synthetic captions at different granularities. Combining these components, we develop TIPSv2, a new family of image-text encoder models suitable for a wide range of downstream applications. Through comprehensive experiments on 9 tasks and 20 datasets, we demonstrate strong performance, generally on par with or better than recent vision encoder models. Code and models are released via our project page at https://gdm-tipsv2.github.io/ .
citation-role summary
background 1
baseline 1
citation-polarity summary
years
2026 6representative citing papers
LookWhen factorizes video recognition into learning when, where, and what to compute via uniqueness-based token selection and dual-teacher distillation, achieving better accuracy-FLOPs trade-offs than baselines on multiple datasets.
An image generator is instruction-tuned to perform diverse vision tasks by representing task outputs as RGB images, achieving SOTA on segmentation and depth estimation.
Casper3D is a backbone-agnostic variational model that infers stable 3D semantics from noisy 2D embeddings by treating them as observations of a latent 3D state and training via held-out viewpoint prediction.
ReSiReg clusters VLM intermediates into prototypes, derives language descriptors, and reconstructs patches as mixtures to improve spatial consistency in dense language-grounded retrieval for robotics.
EVA01 introduces a Mixture-of-Transformers model that natively adds 3D mesh understanding, generation, and multi-turn editing to MLLMs by decoupling understanding and generation experts with shared global self-attention.
citing papers explorer
-
MulTaBench: Benchmarking Multimodal Tabular Learning with Text and Image
MulTaBench is a new collection of 40 image-tabular and text-tabular datasets designed to test target-aware representation tuning in multimodal tabular models.
-
LookWhen? Fast Video Recognition by Learning When, Where, and What to Compute
LookWhen factorizes video recognition into learning when, where, and what to compute via uniqueness-based token selection and dual-teacher distillation, achieving better accuracy-FLOPs trade-offs than baselines on multiple datasets.
-
Image Generators are Generalist Vision Learners
An image generator is instruction-tuned to perform diverse vision tasks by representing task outputs as RGB images, achieving SOTA on segmentation and depth estimation.
-
Lightweight 3D Feature Pretraining by Bayesian Inversion of 2D Foundation Models
Casper3D is a backbone-agnostic variational model that infers stable 3D semantics from noisy 2D embeddings by treating them as observations of a latent 3D state and training via held-out viewpoint prediction.
-
ReSiReg: Towards Spatially Consistent Semantics in Language-Conditioned Robotic Tasks
ReSiReg clusters VLM intermediates into prototypes, derives language descriptors, and reconstructs patches as mixtures to improve spatial consistency in dense language-grounded retrieval for robotics.
-
EVA01: Unified Native 3D Understanding and Generation via Mixture-of-Transformers
EVA01 introduces a Mixture-of-Transformers model that natively adds 3D mesh understanding, generation, and multi-turn editing to MLLMs by decoupling understanding and generation experts with shared global self-attention.