Guspan Tanadi

A bidirectional pipeline parallelism algorithm for computation-communication overlap in DeepSeek V3/R1 training.

CVPR2023 - Activating More Pixels in Image Super-Resolution Transformer TPAMI - HAT: Hybrid Attention Transformer for Image Restoration

[ICCV 2023] Tracking Anything with Decoupled Video Segmentation

[ICLR24] Official implementation of the paper “MagicDrive: Street View Generation with Diverse 3D Geometry Control”

Codes for "Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models".

[CVPR 2024 Highlight] Putting the Object Back Into Video Object Segmentation

Official implementation of paper "MiniGPT-5: Interleaved Vision-and-Language Generation via Generative Vokens"

[SIGIR'2024] "GraphGPT: Graph Instruction Tuning for Large Language Models"

[CVPR 2023] Official implementation of the paper "One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformer"

Data and code for NeurIPS 2022 Paper "Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering".

[WSDM'2024 Oral] "LLMRec: Large Language Models with Graph Augmentation for Recommendation"