3 papers
cs.RO2026
OCC4M: Object-Centric 4D Memory for Spatiotemporal Reasoning in Long-Horizon Manipulation
Jack B. Jedlicki, Tanguy Dieudonné, Heng Yang
Long-horizon manipulation often requires reasoning about state absent from the current view, such as a vanished object's location, temporal identity, or the contents of a shuffled…
cs.LG2026
When One Adapter Speaks for Many: Discovering Low-Rank Redundancy in Continual Fine-Tuning
Tanguy Dieudonné, Giulia Lanzillotta, Enis Simsar +2
Low-Rank Adaptation (LoRA) has become the standard tool for parameter-efficient fine-tuning of large pretrained models. When applied sequentially across tasks in Continual Learning…
cs.CL2026
Memorization Dynamics of Fill-in-the-Middle Pretraining
Tobias von Arx, Tanguy Dieudonné
Fill-in-the-middle (FIM) is a pretraining objective widely used to equip causal language models with infilling ability, yet its effect on verbatim memorization remains underexplore…