Sepp Hochreiter

papers

692

total citations

papers (20)

TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learning

NEURIPS 2025arXiv

citations

Quantification of Uncertainty with Adversarial Models

NEURIPS 2023arXiv

citations

Improving Uncertainty Estimation through Semantically Diverse Language Generation

ICLR 2025arXiv

citations

Learning to Modulate pre-trained Models in RL

NEURIPS 2023arXiv

citations

Variational Annealing on Graphs for Combinatorial Optimization

NEURIPS 2023arXiv

citations

Contrastive Tuning: A Little Help to Make Masked Autoencoders Forget

AAAI 2024arXiv

citations

Semantic HELM: A Human-Readable Memory for Reinforcement Learning

NEURIPS 2023arXiv

citations

Scalable Discrete Diffusion Samplers: Combinatorial Optimization and Statistical Physics

ICLR 2025arXiv

citations

xLSTM 7B: A Recurrent LLM for Fast and Efficient Inference

ICML 2025arXiv

citations

A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks

ICML 2025arXiv

citations

Tiled Flash Linear Attention: More Efficient Linear RNN and xLSTM Kernels

NEURIPS 2025arXiv

citations

Parameter Efficient Fine-tuning via Explained Variance Adaptation

NEURIPS 2025arXiv

citations

Overcoming Saturation in Density Ratio Estimation by Iterated Regularization

ICML 2024arXiv

citations

Rethinking Losses for Diffusion Bridge Samplers

NEURIPS 2025arXiv

citations

The Disparate Benefits of Deep Ensembles

ICML 2025arXiv

citations

Sepp Hochreiter

papers (20)

Modern Hopfield Networks and Attention for Immune Repertoire Classification

CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP

Vision-LSTM: xLSTM as Generic Vision Backbone

A Diffusion Model Framework for Unsupervised Neural Combinatorial Optimization

Conformal Prediction for Time Series with Modern Hopfield Networks

TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learning

Quantification of Uncertainty with Adversarial Models

Improving Uncertainty Estimation through Semantically Diverse Language Generation

Learning to Modulate pre-trained Models in RL

Variational Annealing on Graphs for Combinatorial Optimization

Contrastive Tuning: A Little Help to Make Masked Autoencoders Forget

Semantic HELM: A Human-Readable Memory for Reinforcement Learning

Scalable Discrete Diffusion Samplers: Combinatorial Optimization and Statistical Physics

xLSTM 7B: A Recurrent LLM for Fast and Efficient Inference

A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks

Tiled Flash Linear Attention: More Efficient Linear RNN and xLSTM Kernels

Parameter Efficient Fine-tuning via Explained Variance Adaptation

Overcoming Saturation in Density Ratio Estimation by Iterated Regularization

Rethinking Losses for Diffusion Bridge Samplers

The Disparate Benefits of Deep Ensembles

papers (20)

Modern Hopfield Networks and Attention for Immune Repertoire Classification

CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP

Vision-LSTM: xLSTM as Generic Vision Backbone

A Diffusion Model Framework for Unsupervised Neural Combinatorial Optimization

Conformal Prediction for Time Series with Modern Hopfield Networks

TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learning

Quantification of Uncertainty with Adversarial Models

Improving Uncertainty Estimation through Semantically Diverse Language Generation

Learning to Modulate pre-trained Models in RL

Variational Annealing on Graphs for Combinatorial Optimization

Contrastive Tuning: A Little Help to Make Masked Autoencoders Forget

Semantic HELM: A Human-Readable Memory for Reinforcement Learning

Scalable Discrete Diffusion Samplers: Combinatorial Optimization and Statistical Physics

xLSTM 7B: A Recurrent LLM for Fast and Efficient Inference

A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks

Tiled Flash Linear Attention: More Efficient Linear RNN and xLSTM Kernels

Parameter Efficient Fine-tuning via Explained Variance Adaptation

Overcoming Saturation in Density Ratio Estimation by Iterated Regularization

Rethinking Losses for Diffusion Bridge Samplers

The Disparate Benefits of Deep Ensembles