[WACV 26] Official code for the paper Safe Vision-Language Models via Unsafe Weights Manipulation

Code repository of the paper: Start Smart: Leveraging Gradients For Enhancing Mask-based XAI Methods. Published at ICLR, 2025.

Official implementation of "Training-free Online Video Step Grounding", NeurIPS 2025

CoNNect repo for connectivity-based pruning of neural networks.

Official implementation of "ConViS-Bench: Estimating Video Similarity Through Semantic Concepts", NeurIPS 2025

Code implementation of DuoGPT (NeurIPS 2025, https://arxiv.org/abs/2506.20194)

Awesome LLM pruning papers all-in-one repository with integrating all useful resources and insights.

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

The official code for the paper "Sparsity-Driven Plasticity in Multi-Task Reinforcement Learning", published in the Transactions on Machine Learning Research (TMLR).

Multi Task RL Baselines

Multi-task reinforcement learning research

Demonstrations of Loss of Plasticity and Implementation of Continual Backpropagation

Official code of the paper "Multi-Task Reinforcement Learning with Mixture of Orthogonal Experts" at ICLR2024

Official repo of the paper "Dynamic Scoring with Enhanced Semantics for Training-Free Human-Object Interaction Detection" (ACMMM2025)

Conditional computing research: hybrid approach for stacked MoE and Early-Exit Neural Networks

Official Implementation of Data Adaptive Pathway Discovery (DAPD) for Online RL

[ICML 2025 oral] Network Sparsity Unlocks the Scaling Potential of Deep Reinforcement Learning

Collections of robotics environments geared towards benchmarking multi-task and meta reinforcement learning

Official codebase for the paper "Training-Free Personalization via Retrieval and Reasoning on Fingerprints"

Github repo for ICLR-2025 paper, Fine-tuning Large Language Models with Sparse Matrices

Automated Identification of Redundant Layer Blocks for Pruning in Large Language Models

Interpretable Multi Agent Reinforcement Learning with a Quality DIversity Approach

Official code for the EMNLP 2024 (main) paper "Retrieval-enriched zero-shot image classification in low-resource domains"

Official implementation of "Can Text-to-Video Generation help Video-Language Alignment?", CVPR 2025

Efficient Expert Pruning for Sparse Mixture-of-Experts Language Models: Enhancing Performance and Reducing Inference Costs

[CVPR'25] Official implementation of the paper "Not Only Text: Exploring Compositionality of Visual Representations in Vision-Language Models".