Janus-Series: Unified Multimodal Understanding and Generation Models

[TPAMI'23] Unifying Flow, Stereo and Depth Estimation

[CVPR'23] Universal Instance Perception as Object Discovery and Retrieval

A unified multi-task time series model.

VARGPT: Unified Understanding and Generation in a Visual Autoregressive Multimodal Large Language Model

[ICCV 2025] LangScene-X: Reconstruct Generalizable 3D Language-Embedded Scenes with TriMap Video Diffusion

VARGPT-v1.1: Improve Visual Autoregressive Large Unified Model via Iterative Instruction Tuning and Reinforcement Learning

[ICCV2023] Segment Every Reference Object in Spatial and Temporal Spaces

[ICML 2024] A novel, efficient lightweight approach combining convolutional operations with adaptive spectral analysis as a foundation model for different time series tasks

Uni-CoT: Towards Unified Chain-of-Thought Reasoning Across Text and Vision

ZoomNeXt: A Unified Collaborative Pyramid Network for Camouflaged Object Detection (TPAMI 2024)

CVPR25(Highlight)-Unified Perceptual and Task-Oriented Image Restoration Model Using Diffusion Prior

Code for Sergeev et al. (2020)

Automatic Lidar and Ceilometer Processing Framework (ALCF)

Official repository of the paper "Unlocking Aha Moments via Reinforcement Learning: Advancing Collaborative Visual Comprehension and Generation"

Novel unified representation to solve all the sub-tasks of argumentation mining

Discrete Unification Theory

Progetto Ingegneria del Software - Informatica, Università Sapienza

Code to reproduce figures from Sergeev et al. (2022)

Code to reproduce figures in Sergeev et al. (2018)