JingfanChen
JingfanChen
Hi! Thanks for your excellent work! I'm diving into a complex environment, where all the actions are not available at each step. Let's say there are 1000 actions (range from...
Hi! I found that the augmentation "add edge" may not support for the mini-batch graph-level contrastive learning. In my understanding, edges should be added for each graph in the mini-batch...
The research work is exciting! I noticed that you formulate the automated graph contrastive learning as the min-max optimization problem. May I ask that why not use the bi-level optimization...
Hi! Thanks for your great work! I'm a bit confused with the code in 'MGCN_FAUST.py' `for k in range(31, -1, -(32//(K-1))): Win = torch.mm(torch.mm(torch.mm(V, torch.diag(clk[:, k])), torch.t(V)), torch.diag(torch.squeeze(A))) ** 2...
should we change code line 75 : _"estimator.model = None"_ to _"estimator.cost_model"_ and change code line 77: _"estimator.model = self.cost_model.models[I]"_ to _"estimator.cost_model = self.cost_model.models[I]"_ and should we delete delete line...
Thanks for your great work! I wonder how much time it costs to train the Lora on the dataset (1M DiffusionDB + subset of Laion5B) on, for example, 4 GPUs?
Hi, I wonder why the joint names in SMPL_BODY_BONES is different from the official SMPL (e.g., the 'left_hand', 'right_hand' is commented) ? Thanks.
Thank you for your work. When will the bunny-llama3 LoRA weights be released?
### Your current environment I built my flash-attn from the source. The version is 2.6.3 ### 🐛 Describe the bug When runing following code: ``` self.policy_model = LLM( model="OpenGVLab/InternVL2-8B", trust_remote_code=True,...
What is the prompt used for the os environment benchmark? (e.g., Android world, OSworld)