Joint Selection for Large-Scale Pre-Training Data via Policy Gradient-based Mask Learning
Stable-DiffCoder is a family of lightweight open-source code DLLMs(diffusion large language models) comprising base and instruct models, developed by ByteDance Seed.
This is a minimal artifact with state-of-the-art speculative decoding as described in the SwiftSpec paper [ASPLOS' 26].
[ICLR 2026] Trace Anything: Representing Any Video in 4D via Trajectory Fields
Official code for VINCIE: Unlocking In-context Image Editing from Video
Sim-to-real and CDM inference code for ManipAsInSim project.
