4 papers
Where-OPD: Spatially Guided On-Policy Self-Distillation of MLLMs with Synthetic Scenes
Sophia Sirko-Galouchenko, Monika Wysoczanska, Andrei Bursuc +2
On-policy self-distillation has recently emerged as an effective approach for improving language-model reasoning by supervising students with a frozen or EMA version of themselves…
V-GIFT: Boosting Visual Instruction Tuning with Self-Supervised Guidance
Sophia Sirko-Galouchenko, Monika Wysoczanska, Andrei Bursuc +2
Multimodal large language models (MLLMs) perform well on many vision-language tasks but often struggle with vision-centric problems that require fine-grained visual perception. Rec…
DIP: Unsupervised Dense In-Context Post-training of Visual Representations
Sophia Sirko-Galouchenko, Spyros Gidaris, Antonin Vobecky +2
We introduce DIP, a novel unsupervised post-training method designed to enhance dense image representations in large-scale pretrained vision encoders for in-context scene understan…
OccFeat: Self-supervised Occupancy Feature Prediction for Pretraining BEV Segmentation Networks
Sophia Sirko-Galouchenko, Alexandre Boulch, Spyros Gidaris +4
We introduce a self-supervised pretraining method, called OccFeat, for camera-only Bird's-Eye-View (BEV) segmentation networks. With OccFeat, we pretrain a BEV network via occupanc…