Hang Guo

MambaIR. [ECCV2024, CVPR2025] MambaIR and MambaIRv2!

Awesome-Mamba-in-Low-Level-Vision. A paper list of recent mamba efforts for low-level vision.

AdaptIR. [NeurIPS2024] Tune your restoration model with one 3090 GPU!

FastVAR. [ICCV2025]Generate one 2K image on single 24GB 3090 GPU!

DummyForcing. Minute-long video generation at 24FPS.

ReFIR. [NeurIPS2024] Overcome hallucination of diffusion restoration models.

LEMMA. [IJCAI2023] Your text images can be clearer!

IntLoRA. [ICML2025] LoRA fine-tune directly on the INT4 models.

OBR. [ICLR2026] The first W4A4KV4 quantized + 50% sparse LLMs!

KD-LTR. [MM2023] An official implement of the paper "One-stage Low-resolution Text Recognition with High-resolution Knowledge Transfer"

MGTR. [ACCV2022] An official implement of the paper "MGTR: End-to-end Mutual Gaze Detection with Transformer".

Awesome-Blind-Image-Super-resolution. Collect papers for recent blind image super-resolution.

Seq2seq_attn. Use the Seq2Seq method to implement machine translation and introduce Attention mechanism to improve the results

NTIRE2026_Dn50_challenge. Python

Awesome-Mamba-Papers. Awesome Papers related to Mamba.

Awesome-Parameter-Efficient-Transfer-Learning. A collection of parameter-efficient transfer learning papers focusing on computer vision and multimodal domains.

llm-course. Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

CUDA-Programming. Sample codes for my CUDA programming book

csguoh.github.io. HTML