Fabian Paischer

Postdoc@, Johannes Kepler Universität Linz·奥地利·OpenReview

研究方向

Cross-Modal Transfer · Large Language Models · Reinforcement learning under partial observability · Natural Language Processing · Foundation Models · Parameter-efficient Fine-tuning · AI for Physics Simulations

5.5

Physics-Preserving Compression of High-Dimensional Plasma Turbulence Simulations

ICLR 2026Rejected

三作

5.0

From Circuits to Dynamics: Understanding and Stabilizing Failure in 3D Diffusion Transformers

ICLR 2026Rejected

二作

6.0

GyroSwin: 5D Surrogates for Gyrokinetic Plasma Turbulence Simulations

NeurIPS 2025Poster

一作

6.0

Parameter Efficient Fine-tuning via Explained Variance Adaptation

NeurIPS 2025Poster

一作

4.8

One Initialization to Rule them All: Fine-tuning via Explained Variance Adaptation

合作者 (20)

Johannes Brandstetter

Fabian Paischer

Physics-Preserving Compression of High-Dimensional Plasma Turbulence Simulations

From Circuits to Dynamics: Understanding and Stabilizing Failure in 3D Diffusion Transformers

GyroSwin: 5D Surrogates for Gyrokinetic Plasma Turbulence Simulations

Parameter Efficient Fine-tuning via Explained Variance Adaptation

One Initialization to Rule them All: Fine-tuning via Explained Variance Adaptation

Retrieval-Augmented Decision Transformer: External Memory for In-context RL

Unifying Generative and Dense Retrieval for Sequential Recommendation

Preference Discerning in Generative Sequential Recommendation