GPTQ-intrinsic LoRA augments GPTQ with intrinsic low-rank compensation via Hessian modification to achieve layer-wise reconstruction bounds that match information-theoretic lower bounds under structural assumptions.
Resnet strikes back: An im- proved training procedure in timm
9 Pith papers cite this work, alongside 33 external citations. Polarity classification is still indexing.
9
Pith papers citing it
33
external citations · external index
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
LAION-C supplies six novel corruptions that stay OOD for web-scale training sets and demonstrates that leading models now rival or exceed human robustness on them.
Q-Align trains LMMs on discrete text-defined levels for visual scoring, achieving SOTA on IQA, IAA, and VQA while unifying the tasks in OneAlign.
SPANetV2 is a vision backbone built around a new spectral-adaptive modulation mixer that outperforms prior models on ImageNet-1K classification, COCO detection, and ADE20K segmentation.
Adding register tokens to Vision Transformers eliminates high-norm background artifacts and raises state-of-the-art performance on dense visual prediction tasks.
SigLIP replaces softmax-based contrastive loss with a simple pairwise sigmoid loss for vision-language pre-training, decoupling batch size from normalization and reaching strong zero-shot performance with limited compute.
SaluNet replaces normalization layers with the SALU activation and reports competitive accuracies on CIFAR-10/100 and ImageNet-1K without normalization.
Weak-to-strong knowledge distillation applied early and then turned off accelerates convergence to target performance in visual learning tasks by factors of 1.7-4.8x.
citing papers explorer
-
GPTQ-intrinsic LoRA: A Near-optimal Algorithm for Low-precision Quantization with Low-rank Adaptation
GPTQ-intrinsic LoRA augments GPTQ with intrinsic low-rank compensation via Hessian modification to achieve layer-wise reconstruction bounds that match information-theoretic lower bounds under structural assumptions.
-
LAION-C: An Out-of-Distribution Benchmark for Web-Scale Vision Models
LAION-C supplies six novel corruptions that stay OOD for web-scale training sets and demonstrates that leading models now rival or exceed human robustness on them.
-
Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels
Q-Align trains LMMs on discrete text-defined levels for visual scoring, achieving SOTA on IQA, IAA, and VQA while unifying the tasks in OneAlign.
-
Spectral-Adaptive Modulation Networks for Visual Perception
SPANetV2 is a vision backbone built around a new spectral-adaptive modulation mixer that outperforms prior models on ImageNet-1K classification, COCO detection, and ADE20K segmentation.
-
Vision Transformers Need Registers
Adding register tokens to Vision Transformers eliminates high-norm background artifacts and raises state-of-the-art performance on dense visual prediction tasks.
-
Sigmoid Loss for Language Image Pre-Training
SigLIP replaces softmax-based contrastive loss with a simple pairwise sigmoid loss for vision-language pre-training, decoupling batch size from normalization and reaching strong zero-shot performance with limited compute.
-
SaluNet: Enabling Total Plasticity in Normalization-Free Deep Networks
SaluNet replaces normalization layers with the SALU activation and reports competitive accuracies on CIFAR-10/100 and ImageNet-1K without normalization.
-
Weak-to-Strong Knowledge Distillation Accelerates Visual Learning
Weak-to-strong knowledge distillation applied early and then turned off accelerates convergence to target performance in visual learning tasks by factors of 1.7-4.8x.
- Rethinking Evaluation Paradigms in IBP-based Certified Training