How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.
Official implementation of NavMorph: A Self-Evolving World Model for Vision-and-Language Navigation in Continuous Environments (ICCV'25).
The main features of feliciaxyao/navmorph are: Embodied World Models, Model Adaptation and Merging.
Projects with overlapping indexed features include: openbmb/minicpm — MiniCPM is a collection of small language models designed for local, on-device deployment in resource-constrained… agibottech/ewmbench — Official code for EWMBench: Evaluating Scene, Motion, and Semantic Quality in Embodied World Models. aidanscannell/dcmpc — This repository is the official implementation of DC-MPC, presented in "Discrete Codebook World Models for Continuous… aignlai/edge — The Code for "The Lie of the Average: How Class Incremental Learning Evaluation Deceives You?". aignlai/gddsg — Xiangkun Wang 1   Junbo Zhang 3   Tianrui Li 4   Xin Yang 1  . adymaharana/adapt-inf — Code for the paper "Adapt - $\infty$: Scalable Lifelong Multimodal Instruction Tuning".
MiniCPM is a collection of small language models designed for local, on-device deployment in resource-constrained environments. The project focuses on running dense Transformer models on consumer hardware, including GPUs, CPUs, and Apple Silicon, without requiring custom code forks. The project distinguishes itself through heavy optimization for edge hardware, utilizing quantized weight compression in GGUF and MLX formats to reduce memory overhead. It implements advanced inference techniques such as speculative sampling and radix-tree prefix caching to accelerate generation speed and throughp
Official code for EWMBench: Evaluating Scene, Motion, and Semantic Quality in Embodied World Models
This repository is the official implementation of DC-MPC, presented in "Discrete Codebook World Models for Continuous Control" at ICLR 2025. DC-MPC is a model-based reinforcement learning algorithm demonstrating the strengths of learning a discrete latent space with discrete codebook encodings.
Code for the paper "Adapt - $\infty$: Scalable Lifelong Multimodal Instruction Tuning"