Perturbation screens hold the potential to systematically map regulatory processes at single-cell resolution, yet modeling and predicting transcriptome-wide responses to perturbations remains a major computational challenge. Existing methods often underperform simple baselines, fail to disentangle measurement noise fro...
Lars Lorch, Jia-Qi Zhang, Charlotte Bunne et al.· Proceedings of the National...· 7 citations· ⚡2
This work presents LAION-BVD, a large-scale open video dataset for multimodal learning, which contains 1.3B platform-specific video URLs collected from CommonCrawl, and explores video frames as an alternative source of image-text data by extracting scene-changing frames.
Andreas Hochlehnert, Marianna Nezhurina, M. Cherti et al.· 0 citations
This work proves that the answer is negative: drawing from incomplete contract theory, it is formally shown that when contracts cannot distinguish all relevant future contingencies, there is a strictly positive welfare loss that no realistic mechanism can eliminate.
Xuanqi Huang, Charlie Tharas, Samuele G. Marro et al.· arXiv.org· 2 citations
This first release of Prior Labs in relational learning opens-source three pieces of software that expect to accelerate research in the field towards meaningful real-world impact and releases an initial version of RPI, an open-source, model-agnostic interface that enables early adopters to easily define problems on new...
A. Hayler, Klemens Flöge, Alan Arazi et al.· 3 citations· ⚡1
This work introduces RAPTOR - a Role-Aware Private Training framework, which alternates shared and expert optimization and targets each failure directly, using expert-specific clipping and noise together with a public expected-owner denominator and a count-independent update schedule that avoids conditioning on private...
Duc Dm, Khai Le-Duc, D. Nguyen et al.· 0 citations
This framework identifies which law each loss in the literature actually optimizes, recovering MDM, UDM, SEDD, and GIDD as special cases; explains why denoiser and cavity coincide for masked diffusion but not for uniform diffusion; proves that a denoiser parameterization makes the uniform ELBO diverge at initialization...
Rodrigo Casado Noguerales, B. Schölkopf, Thomas Hofmann et al.· arXiv.org· 1 citation
Cue-induced bias is best understood not as a single flaw in LLMs but as a family of causally effective linear directions that are largely shaped by alignment tuning.
Prakhar Gupta, Terry Jingchen Zhang, Florent Draye et al.· arXiv.org· 1 citation
This work studies raw pixels, SD-VAE latents and DINOv2 as well as MAE representation-autoencoder features within a unified masked autoregressive rectified-flow model and shows that compression, reconstruction fidelity, token dimensionality, and visible semantic clustering do not individually predict generative behavio...
Marcel Plocher, B. Schölkopf, Andreas Geiger et al.· 0 citations
Concept-Targeted Attribution (CTA) provides a framework for moving from behavioral probe accuracy to mechanistic explanations of probe performance, enabling more detailed audits of internal concept representations, including safety-critical ones.
V. Palit, Florent Draye, Terry Jingchen Zhang et al.· 0 citations
Recent advances in foundation models have transformed AI for Science, enabling remarkably accurate predictive performance across domains ranging from protein folding to weather forecasting. Yet prediction alone does not constitute scientific discovery. Scientific understanding depends on uncovering the reusable explana...
Ingmar Posner, A. Lei, B. Schölkopf· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
