From the 1 of 6 linked papers with an AI index.
6 papers
From Sparse X-rays to 3D CT: Training-Free Reconstruction with Diffusion Priors
Zhenkai Zhang, Markus Hiller, Krista A. Ehinger +1
The paper introduces TF-PRDiT, a training‑free framework that uses a frozen 3D diffusion transformer prior to reconstruct CT volumes from sparse X‑ray projections, and can be appli…
Pixel-Level Residual Diffusion Transformer: Scalable 3D CT Volume Generation
Zhenkai Zhang, Markus Hiller, Krista A. Ehinger +1
Generating high-resolution 3D CT volumes with fine details remains challenging due to substantial computational demands and optimization difficulties inherent to existing generativ…
SVoT: State-aware Visualization-of-Thought for Spatial Reasoning via Reinforcement Learning
Chao Lei, Yanbei Jiang, Markus Hiller +4
Spatial reasoning remains a challenge for Multimodal Large Language Models (MLLMs), as it requires reliable multi-hop inference over both intermediate states and state transitions.…
Active Budget Allocation for Efficient Scaling Law Estimation via Surrogate-Guided Pruning
Viktoria Schram, Markus Hiller, Daniel Beck +1
Predicting model performance at larger scales enables the design of training strategies and architectures tailored to specific performance targets. Empirical scaling law research i…
Zero-Shot Performance Prediction for Probabilistic Scaling Laws
Viktoria Schram, Markus Hiller, Daniel Beck +1
The prediction of learning curves for Natural Language Processing (NLP) models enables informed decision-making to meet specific performance objectives, while reducing computationa…
Perceiving Longer Sequences With Bi-Directional Cross-Attention Transformers
Markus Hiller, Krista A. Ehinger, Tom Drummond
We present a novel bi-directional Transformer architecture (BiXT) which scales linearly with input size in terms of computational cost and memory consumption, but does not suffer t…