Product
Help
Pricing
About
Jobs
Log in
Get started
Author
Add to collection
Florent Draye
Observed name:
Draye, Florent
Institutions:
Max Planck Society,
Intelligent Systems Research (United States),
H.W. & J. Hector Stiftung,
Max Planck Institute for Intelligent Systems
Observed institutions:
Max Planck Society,
University of Oxford,
Intelligent Systems Research (United States),
H.W. & J. Hector Stiftung,
Max Planck Institute for Intelligent Systems
OpenAlex ID:
A5120409390
Decode-gLM: Tools to Interpret, Audit, and Steer Genomic Language Models
2025
·
Aaron Maiwald
, Piotr Jedryszek
, et al.
·
bioRxiv (Cold Spring Harbor Laboratory)
·
3
PDF
When Forgetting is not Catastrophic: On the Mechanics of Spurious Forgetting
2026
·
Palit, Vedant
, Draye, Florent
, et al.
·
arXiv (Cornell University)
PDF
ABC: Advantage-Based Control Variates for Reinforcement Learning with Verifiable Rewards
2026
·
Pan, Hsiao-Ru
, Draye, Florent
, et al.
·
arXiv (Cornell University)
PDF
RAPTOR: Role-Aware Private Training for Mixture-of-Experts
2026
·
Dm, Duc
, Le-Duc, Khai
, et al.
·
arXiv (Cornell University)
PDF
STRIDE: Training Data Attribution via Sparse Recovery from Subset Perturbations
2026
·
Dagli, Rishit
, Harrasse, Abir
, et al.
·
arXiv (Cornell University)
PDF
Superposition Without Interference? Towards Isolated Interventions via Almost Orthogonal Features in Language Models
2026
·
Miller, Moritz
, Draye, Florent
, et al.
·
arXiv (Cornell University)
PDF
Tracing Multilingual Representations in LLMs with Cross-Layer Transcoders
2026
·
Abir Harrasse
, Florent Draye
, et al.
·
Conference on Empirical Methods in Natural Language Processing (EMNLP)
PDF
CLT-Forge: A Scalable Library for Cross-Layer Transcoders and Attribution Graphs
2026
·
Florent Draye
, Vedant Palit
, et al.
·
Conference on Empirical Methods in Natural Language Processing: System Demonstrations (EMNLP)
PDF
PruneGround: Plug-and-play Spatial Pruning for 3D Visual Grounding
2026
·
Duc Cao Dinh
, Khai Le-Duc
, et al.
·
Conference on Empirical Methods in Natural Language Processing (EMNLP)
PDF
How Does Alignment Tuning Shape Representations of Sycophancy and Related Cue-Induced Biases in LLMs?
2026
·
Prakhar Gupta
, Terry Jingchen Zhang
, et al.
·
Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)
PDF
How Do Linear Probes Emerge? A Circuit-Tracing Framework with Concept-Targeted Attribution
2026
·
Vedant Palit
, Florent Draye
, et al.
·
Conference on Empirical Methods in Natural Language Processing (EMNLP)
PDF
Intrinsically Interpretable Attention via Sparse Post-Training
2025
·
Draye, Florent
, Lei, Anson
, et al.
·
arXiv (Cornell University)
PDF
Show more works
View as search
Works count:
12
Citation count:
3
H-index:
1
I10-index:
Year
Topic
Type
