Pinned Repositories
M3
[ICLR 2024] Towards Robust Multi-Modal Reasoning via Model Selection
unilm
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
modelscope-agent
ModelScope-Agent: An agent framework connecting models in ModelScope with the world
auto-code-rover
A project structure aware autonomous software engineer aiming for autonomous program improvement. Resolved 30.67% tasks (pass@1) in SWE-bench lite with each task costs less than $0.7.
HunyuanDiT
Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding
HunyuanDiT
Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding
M3
[Preprint] Towards Robust Multi-Modal Reasoning via Model Selection
modelscope-agent
ModelScope-Agent(开源版GPTs): An agent framework connecting models in ModelScope with the world
ODMT
[ACM'MM 2023 Oral] Online Distillation-enhanced Multi-modal Transformer for Sequential Recommendation
SWE-agent
SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It solves 12.47% of bugs in the SWE-bench evaluation set and takes just 1.5 minutes to run.
xyliugo's Repositories
xyliugo/ODMT
[ACM'MM 2023 Oral] Online Distillation-enhanced Multi-modal Transformer for Sequential Recommendation
xyliugo/HunyuanDiT
Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding
xyliugo/M3
[Preprint] Towards Robust Multi-Modal Reasoning via Model Selection
xyliugo/modelscope-agent
ModelScope-Agent(开源版GPTs): An agent framework connecting models in ModelScope with the world
xyliugo/SWE-agent
SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It solves 12.47% of bugs in the SWE-bench evaluation set and takes just 1.5 minutes to run.