(JAIR'2022) A mini-scale reproduction code of the AlphaStar program. Note: the original AlphaStar is the AI proposed by DeepMind to play StarCraft II. JAIR = Journal of Artificial Intelligence Rese…

一键将 Markdown 和网页 AI 对话（ChatGPT/DeepSeek等）完美粘贴到 Word、WPS 和 Excel 的效率工具 | One-click paste Markdown and AI responses (ChatGPT/DeepSeek) into Word, WPS, and Excel perfectly.

Unofficial implementation for the paper "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"

The official repo for the paper "Adaptive Layer-skipping in Pre-trained LLMs"

[ICML 2025] Official implementation of the paper "SkipGPT: Dynamic Layer Pruning Reinvented with Token Awareness and Module Decoupling". (By Anhao Zhao)

Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation (NeurIPS 2025)

The open-source Mixture of Depths code and the official implementation of the paper "Router-Tuning: A Simple and Effective Approach for Enabling Dynamic Depth in Transformers. (EMNLP 2025)"

Code for "LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding", ACL 2024

[NeurIPS'25 Spotlight🔥] Official Implementation of RobustMerge: Parameter-Efficient Model Merging for MLLMs with Direction Robustness

[ICLR 2025] The official pytorch implement of "Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Context Sparsification".

ICLR 2025

The official implementation of paper: Progressive LoRA for Multimodal Continual Instruction Tuning. (ACL 2025 Findings)

REAP: Router-weighted Expert Activation Pruning for SMoE compression

[ICLR 2025] Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer Models

Implementation for NeurIPS 2024 paper "SAFE: Slow and Fast Parameter-Efficient Tuning for Continual Learning with Pre-Trained Models" (https://arxiv.org/abs/2411.02175)

[CVPR 2025] Mono-InternVL: Pushing the Boundaries of Monolithic Multimodal Large Language Models with Endogenous Visual Pre-training

[ICCV 2025] Official Implementation of Federated Continual Instruction Tuning

[NeurIPS 2025] An official source code for paper "Continual Multimodal Contrastive Learning"

The official repository of CVPR2025 paper "Enhancing Online Continual Learning with Plug-and-Play State Space Model and Class-Conditional Mixture of Discretization"

[CVPR 2025] Crab: A Unified Audio-Visual Scene Understanding Model with Explicit Cooperation

[NeurIPS 2025] Unsupervised Post-Training for Multi-Modal LLM Reasoning via GRPO

Official Implementation of our ICML 2025 paper: "D-MoLE: Dynamic Mixture of Curriculum LoRA Experts for Continual Multimodal Instruction Tuning".

[ICCV 2025] Official code of paper "Dynamic Multi-Layer Null Space Projection for Vision-Language Continual Learning"

ICCV25 highlight

Official repository of "CoMP: Continual Multimodal Pre-training for Vision Foundation Models"

[ECCV 2024] Mind the Interference: Retaining Pre-trained Knowledge in Parameter Efficient Continual Learning of Vision-Language Models

This is the official repo of MLLM-CL.

MCITlib: Multimodal Continual Instruction Tuning Library and Benchmark

PyCIL: A Python Toolbox for Class-Incremental Learning

[ACL'25 Main] Official Implementation of HiDe-LLaVA: Hierarchical Decoupling for Continual Instruction Tuning of Multimodal Large Language Model