activity
20242026
collaborators

7 papers

cs.LG2026

Text-Conditional JEPA for Learning Semantically Rich Visual Representations

Chen Huang, Xianhang Li, Vimal Thilak +2

Image-based Joint-Embedding Predictive Architecture (I-JEPA) offers a promising approach to visual self-supervised learning through masked feature prediction. However with the inhe…

cs.LG2026

Path-Constrained Mixture-of-Experts

Zijin Gu, Tatiana Likhomanenko, Vimal Thilak +2

Sparse Mixture-of-Experts (MoE) architectures route each token through a subset of experts at each layer independently. We propose viewing MoE computation through the lens of \emph…

cs.CV2025

How PARTs assemble into wholes: Learning the relative composition of images

Melika Ayoughi, Samira Abnar, Chen Huang +10

The composition of objects and their parts, along with object-object positional relationships, provides a rich source of information for representation learning. Hence, spatial-awa…

cs.LG2025

Rethinking JEPA: Compute-Efficient Video SSL with Frozen Teachers

Xianhang Li, Chen Huang, Chun-Liang Li +4

Video Joint Embedding Predictive Architectures (V-JEPA) learn generalizable off-the-shelf video representation by predicting masked regions in latent space with an exponential movi…

cs.LG2025

Parameters vs FLOPs: Scaling Laws for Optimal Sparsity for Mixture-of-Experts Language Models

Samira Abnar, Harshay Shah, Dan Busbridge +3

Scaling the capacity of language models has consistently proven to be a reliable approach for improving performance and unlocking new capabilities. Capacity can be primarily define…

eess.AS2025

Towards Automatic Assessment of Self-Supervised Speech Models using Rank

Zakaria Aldeneh, Vimal Thilak, Takuya Higuchi +2

This study explores using embedding rank as an unsupervised evaluation metric for general-purpose speech encoders trained via self-supervised learning (SSL). Traditionally, assessi…