representation-learning

Multimodal fusion for heterogeneous biomedical data. NeurIPS 2024.

[ECCV 2024] Pytorch code for our ECCV'24 paper NeRF-MAE: Masked AutoEncoders for Self-Supervised 3D Representation Learning for Neural Radiance Fields

[ICML 2024] The offical Implementation of "DecisionNCE: Embodied Multimodal Representations via Implicit Preference Learning"

[ICLR 2024 Spotlight] This is the official code for the paper "SNIP: Bridging Mathematical Symbolic and Numeric Realms with Unified Pre-training"

Efficient Multimodal Foundation Model Adaptation for Recommendation

ThinkJEPA: Empowering Latent World Models with Large Vision-Language Reasoning Model

This includes the codebase for EntroPE (Entropy-Guided Dynamic Patch Encoder for Time Series Forecasting) paper.

AESTETIK: Convolutional autoencoder for learning spot representations from spatial transcriptomics and morphology data

[NeurIPS 2025] TL;DR: Aligning pretrained unimodal models with the proposed framework using limited paired data yields ~52% gains in cross-modality zero-shot classification and ~92% in retrieval.

Multimodal Integration with Modality-agnostic Autoencoders - Developed by LMIB @ KU Leuven

The source code for our Paper: ''Are Multimodal Embeddings Truly Beneficial for Recommendation? A Deep Dive into Whole vs. Individual Modalities''.

Multimodal data alignment and cell type analysis with coupled autoencoders.