Zico Kolter

papers

542

total citations

papers (12)

Finetune Like You Pretrain: Improved Finetuning of Zero-Shot Vision Models

CVPR 2023arXiv

195

citations

Unified Fully and Timestamp Supervised Temporal Action Segmentation via Sequence to Sequence Translation

ECCV 2022arXiv

109

citations

Understanding Augmentation-based Self-Supervised Representation Learning via RKHS Approximation and Regression

ICLR 2024arXiv

citations

Single Image Backdoor Inversion via Robust Smoothed Classifiers

CVPR 2023arXiv

citations

DART: Implicit Doppler Tomography for Radar Novel View Synthesis

CVPR 2024arXiv

citations

From Variance to Veracity: Unbundling and Mitigating Gradient Variance in Differentiable Bundle Adjustment Layers

CVPR 2024arXiv

citations

Contextures: Representations from Contexts

ICML 2025arXiv

citations

Zico Kolter

papers (12)

Finetune Like You Pretrain: Improved Finetuning of Zero-Shot Vision Models

Unified Fully and Timestamp Supervised Temporal Action Segmentation via Sequence to Sequence Translation

Scaling Laws for Data Filtering— Data Curation cannot be Compute Agnostic

Defending Multimodal Fusion Models Against Single-Source Adversaries

Weight ensembling improves reasoning in language models

OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents

Understanding Optimization in Deep Learning with Central Flows

Understanding Augmentation-based Self-Supervised Representation Learning via RKHS Approximation and Regression

Single Image Backdoor Inversion via Robust Smoothed Classifiers

DART: Implicit Doppler Tomography for Radar Novel View Synthesis

From Variance to Veracity: Unbundling and Mitigating Gradient Variance in Differentiable Bundle Adjustment Layers

Contextures: Representations from Contexts

papers (12)

Finetune Like You Pretrain: Improved Finetuning of Zero-Shot Vision Models

Unified Fully and Timestamp Supervised Temporal Action Segmentation via Sequence to Sequence Translation

Scaling Laws for Data Filtering— Data Curation cannot be Compute Agnostic

Defending Multimodal Fusion Models Against Single-Source Adversaries

Weight ensembling improves reasoning in language models

OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents

Understanding Optimization in Deep Learning with Central Flows

Understanding Augmentation-based Self-Supervised Representation Learning via RKHS Approximation and Regression

Single Image Backdoor Inversion via Robust Smoothed Classifiers

DART: Implicit Doppler Tomography for Radar Novel View Synthesis

From Variance to Veracity: Unbundling and Mitigating Gradient Variance in Differentiable Bundle Adjustment Layers

Contextures: Representations from Contexts