Tomas Pfister

papers

4,574

total citations

papers (24)

Consistency-based Semi-supervised Active Learning: Towards Minimizing Labeling Cost

ECCV 2020arXiv

230

citations

TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting

ICLR 2024arXiv

225

citations

Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding

ICLR 2024arXiv

209

citations

Pic2Word: Mapping Pictures to Words for Zero-Shot Composed Image Retrieval

CVPR 2023arXiv

185

citations

Learning Fast Sample Re-Weighting Without Reward Data

ICCV 2021arXiv

103

citations

Interpretable Sequence Learning for Covid-19 Forecasting

NEURIPS 2020arXiv

citations

Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting

ICLR 2025arXiv

citations

Large Language Models Can Automatically Engineer Features for Few-Shot Tabular Learning

ICML 2024arXiv

citations

Controlling Neural Networks with Rule Representations

NEURIPS 2021arXiv

citations

Mitigating Object Hallucination in MLLMs via Data-augmented Phrase-level Alignment

ICLR 2025arXiv

citations

Prefix Conditioning Unifies Language and Label Supervision

CVPR 2023arXiv

citations

Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence

ICML 2025arXiv

citations

SPADE: Semi-supervised Anomaly Detection under Distribution Mismatch

ICLR 2024arXiv

citations

Learning Instance-Specific Adaptation for Cross-Domain Segmentation

ECCV 2022arXiv

citations

Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systems

NEURIPS 2025arXiv

citations

MLE-STAR: Machine Learning Engineering Agent via Search and Targeted Refinement

NEURIPS 2025arXiv

citations

Learning to Transfer Learn: Reinforcement Learning-Based Selection for Adaptive Transfer Learning

ECCV 2020arXiv

citations

Distilling Effective Supervision From Severe Label Noise

CVPR 2020arXiv

citations

Towards Compute-Optimal Many-Shot In-Context Learning

COLM 2025arXiv

citations

Differentiable Top-k with Optimal Transport

NEURIPS 2020

citations

Tomas Pfister

papers (24)

Learning To Prompt for Continual Learning

CutPaste: Self-Supervised Learning for Anomaly Detection and Localization

DualPrompt: Complementary Prompting for Rehearsal-Free Continual Learning

On Completeness-aware Concept-Based Explanations in Deep Neural Networks

Consistency-based Semi-supervised Active Learning: Towards Minimizing Labeling Cost

TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting

Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding

Pic2Word: Mapping Pictures to Words for Zero-Shot Composed Image Retrieval

Learning Fast Sample Re-Weighting Without Reward Data

Interpretable Sequence Learning for Covid-19 Forecasting

Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting

Large Language Models Can Automatically Engineer Features for Few-Shot Tabular Learning

Controlling Neural Networks with Rule Representations

Mitigating Object Hallucination in MLLMs via Data-augmented Phrase-level Alignment

Prefix Conditioning Unifies Language and Label Supervision

Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence

SPADE: Semi-supervised Anomaly Detection under Distribution Mismatch

Learning Instance-Specific Adaptation for Cross-Domain Segmentation

Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systems

MLE-STAR: Machine Learning Engineering Agent via Search and Targeted Refinement

Learning to Transfer Learn: Reinforcement Learning-Based Selection for Adaptive Transfer Learning

Distilling Effective Supervision From Severe Label Noise

Towards Compute-Optimal Many-Shot In-Context Learning

Differentiable Top-k with Optimal Transport

papers (24)

Learning To Prompt for Continual Learning

CutPaste: Self-Supervised Learning for Anomaly Detection and Localization

DualPrompt: Complementary Prompting for Rehearsal-Free Continual Learning

On Completeness-aware Concept-Based Explanations in Deep Neural Networks

Consistency-based Semi-supervised Active Learning: Towards Minimizing Labeling Cost

TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting

Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding

Pic2Word: Mapping Pictures to Words for Zero-Shot Composed Image Retrieval

Learning Fast Sample Re-Weighting Without Reward Data

Interpretable Sequence Learning for Covid-19 Forecasting

Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting

Large Language Models Can Automatically Engineer Features for Few-Shot Tabular Learning

Controlling Neural Networks with Rule Representations

Mitigating Object Hallucination in MLLMs via Data-augmented Phrase-level Alignment

Prefix Conditioning Unifies Language and Label Supervision

Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence

SPADE: Semi-supervised Anomaly Detection under Distribution Mismatch

Learning Instance-Specific Adaptation for Cross-Domain Segmentation

Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systems

MLE-STAR: Machine Learning Engineering Agent via Search and Targeted Refinement

Learning to Transfer Learn: Reinforcement Learning-Based Selection for Adaptive Transfer Learning

Distilling Effective Supervision From Severe Label Noise

Towards Compute-Optimal Many-Shot In-Context Learning

Differentiable Top-k with Optimal Transport