MIT’s new ‘recursive’ framework lets LLMs process 10 million tokens without context rot

While standard models suffer from context rot as data grows, MIT’s new Recursive Language Model (RLM) framework treats ...
GitHub

DMesh++: An Efficient Differentiable Mesh for Complex Shapes

DMesh++ is a probabilistic approach for 2D and 3D mesh, which computes existence probability for faces efficiently and thus handles complex shapes effectively. Please refer to our paper and project ...