9 papers
Calibrated Test-Time Guidance for Bayesian Inference
Daniel Geyfman, Felix Draxler, Jan Groeneveld +3
Test-time guidance is a widely used mechanism for steering pretrained diffusion models toward outcomes specified by a reward function. Existing approaches, however, focus on maximi…
Assessing Sample Quality in Conditional Generation under Compositional Shift
Berker Demirel, Valentino Maiorca, Marco Fumero +2
Conditional generators provide a natural tool for controllable generation, including settings where the desired condition is a new composition of observed attributes or experimenta…
Position: agentic AI orchestration should be Bayes-consistent
Theodore Papamarkou, Pierre Alquier, Matthias Bauer +27
LLMs excel at predictive tasks and complex reasoning tasks, but many high-value deployments rely on decisions under uncertainty, for example, which tool to call, which expert to co…
Parallel Token Prediction for Language Models
Felix Draxler, Justus Will, Farrin Marouf Sofian +3
Autoregressive decoding in language models is inherently slow, generating only one token per forward pass. We propose Parallel Token Prediction (PTP), a general-purpose framework f…
Learning Explicit Single-Cell Dynamics Using ODE Representations
Jan-Philipp von Bassewitz, Adeel Pervez, Marco Fumero +3
Modeling the dynamics of cellular differentiation is fundamental to advancing the understanding and treatment of diseases associated with this process, such as cancer. With the rap…
A path towards AI-scale, interoperable biological data
Brian Aevermann, Andrea Califano, Chi-Li Chiu +27
Biology is at the precipice of a new era where AI accelerates and amplifies the ability to study how cells operate, organize, and work as systems, revealing why disease happens and…