yukang

Code and documents of LongLoRA and LongAlpaca (ICLR 2024 Oral)

Project Page for "LISA: Reasoning Segmentation via Large Language Model"

Long Video Gen / World Model / World Action Model (Embodied) Infrastructure

Controllable video and image Generation, SVD, Animate Anyone, ControlNet, ControlNeXt, LoRA

Long-RL: Scaling RL to Long Sequences (NeurIPS 2025)

[ICLR 2026]QeRL enables RL for 32B LLMs on a single H100 GPU.