Analyzing Fine-tuning Representation Shift for Multimodal LLMs Steering Alignment

tl;dr: a new method for understanding and controlling how MLLMs adapt during fine-tuning

by: P. Khayatan, M. Shukor, J. Parekh, A. Dapogny, @matthieucord.bsky.social
📄: arxiv.org/abs/2501.03012

FLOSS: Free Lunch in Open-vocabulary Semantic Segmentation

tl;dr: a simple trick to boost open-vocabulary semantic segmentation by identifying class expert prompt templates

by: Y. Benigmim, M. Fahes, @tuanhungvu.bsky.social, @abursuc.bsky.social, R. de Charette.
📄: arxiv.org/abs/2504.10487

MoSiC: Optimal-Transport Motion Trajectories for Dense Self-Supervised Learning

tl;dr: a self-supervised learning of temporally consistent representations from video w/ motion cues

by: M. Salehi, S. Venkataramanan, I. Simion, E. Gavves, @cgmsnoek.bsky.social, Y. Asano
📄: arxiv.org/abs/2506.08694

GaussRender: Learning 3D Occupancy with Gaussian Rendering

tl;dr: a module for 3D occupancy learning that enforces 2D-3D consistency through differentiable Gaussian rendering

by: L. Chambon, @eloizablocki.bsky.social, @alexandreboulch.bsky.social, M. Chen, M. Cord
📄: arxiv.org/abs/2502.05040

DIP: Unsupervised Dense In-Context Post-training of Visual Representations

@ssirko.bsky.social, @vobeckya.bsky.social, @abursuc.bsky.social , N. Thome, @spyrosgidaris.bsky.social
📄: arxiv.org/abs/2506.18463

bsky.app/profile/ssir...

PPT: Pretraining with Pseudo-Labeled Trajectories for Motion Forecasting

📄 Paper: arxiv.org/abs/2412.06491

by Y. Xu, @yuanyinnn.bsky.social, @eloizablocki.bsky.social, @tuanhungvu.bsky.social , @alexandreboulch.bsky.social, M. Cord

VaViM & VaVAM: Autonomous Driving through Video Generative Modeling

🔗 Project page: valeoai.github.io/vavim-vavam/
📄 Paper: arxiv.org/abs/2502.15672
💻 Code: github.com/valeoai/Vide...

by F. Bartoccioni, E. Ramzi, et al.

@spyrosgidaris.bsky.social @abursuc.bsky.social @vobeckya.bsky.social @matthieucord.bsky.social @ptrkprz.bsky.social