Girolamo Macaluso

MotionCompositionDiffusion. Official implementation of "Generation of Complex 3D Human Motion by Temporal and Spatial Composition of Diffusion Models" (WACV 2025 Oral)

momask-codes. Official implementation of "MoMask: Generative Masked Modeling of 3D Human Motions (CVPR2024)"

SPEQ. [RLC2025] - Official repository of "SPEQ: Offline Stabilization Phases for Efficient Q-Learning in High Update-To-Data Reinforcement Learning"

OfflineMania. [COG24] - Official repository of "OfflineMania: A Benchmark Environment for Offline Reinforcement Learning in Racing Games"

elastic_feature_consolidation. [ICLR 2024] - Elastic Feature Consolidation for Cold Start Exemplar-Free Incremental Learning

Keyframes-GAN. [IEEE TMM 2023] This is the official repo of the paper "Perceptual Quality Improvement in Videoconferencing using Keyframes-based GAN".

CIRCO. [ICCV 2023] - Composed Image Retrieval on Common Objects in context (CIRCO) dataset

ARNIQA. [WACV 2024 Oral] - ARNIQA: Learning Distortion Manifold for Image Quality Assessment

SEARLE. [ICCV 2023] - Zero-shot Composed Image Retrieval with Textual Inversion

fiftyone. Refine high-quality datasets and visual AI models

RLPD-PyTorch. off-policy algorithm utilizing offline and online data

awesome-comics-understanding. The official repo of the Comics Survey: "A missing piece in Vision and Language: A Survey on Comics Understanding"

racetrack-generation. Unity project for generating closed, arcade-like and highly customizable race tracks.

TAPE. [WACV 2024] - Reference-based Restoration of Digitized Analog Videotapes

ISSUES. [ICCVW 2023] - Mapping Memes to Words for Multimodal Hateful Meme Classification

DiffDefence. Official implementation of the paper DiffDefence: defending against adversarial attacks via diffusion models. ICIAP 2023.

GreenAI. This repository is a companion page for the revision at the 9th International Workshop on Green and Sustainable Software (GREENS’25)

cdf. [MANPU] Framework for mixing Comics datasets, existing and new, with dense and curated annotations.

CoMix-dataset. Repository for "CoMix: Comprehensive Benchmark for Multi-Task Comic Understanding"

DLA_labs. This repository contains the source code for the three laboratory assignments that I completed during the "Deep Learning Applications" course taught by Professor Andrew David Bagdanov

Quantum-DQN. This repository implements a novel approach to the Cart Pole problem by integrating quantum computing principles into the Deep Q Network. Enhance exploration and policy learning for efficient balancing. Dive in and explore the intersection of quantum computing and deep reinforcement learning.

KDPL. [ECCV 2024] - Improving Zero-shot Generalization of Learned Prompts via Unsupervised Knowledge Distillation

sample-factory. High throughput synchronous and asynchronous reinforcement learning

ToDoList_java. Java

iamcl2r. [CVPR 2024 Highlight] - Stationary Representations: Optimally Approximating Compatibility and Implications for Improved Model Replacements (notable top 2.8%)

QualiCLIP. Quality-Aware Image-Text Alignment for Opinion-Unaware Image Quality Assessment

Pearl. A Production-ready Reinforcement Learning AI Agent Library brought by the Applied Reinforcement Learning team at Meta.

gym-super-mario-bros. An OpenAI Gym interface to Super Mario Bros. & Super Mario Bros. 2 (Lost Levels) on The NES

RL-PPO-GAMES. Jupyter Notebook

tmrl. Reinforcement Learning for real-time applications