What will happen if we train a Q function for digital agents?
HAO BAI
JackBAI
AI & ML interests
Representation learning, language models.
Recent Activity
authored a paper 1 day ago
Enabling Token-wise Importance Sampling in Off-Policy RLVR with Proximal KL Regularization submitted a paper 1 day ago
Enabling Token-wise Importance Sampling in Off-Policy RLVR with Proximal KL Regularization upvoted a paper 10 days ago
MotorMind: Scaffolding General Vision Language Models for Zero-Shot Robot ManipulationOrganizations
models 21
JackBAI/tti-new
Updated
JackBAI/webvoyager_allresults
Updated
JackBAI/short-to-long
Updated • 1
JackBAI/aitw-general-digiq-agent
Updated
JackBAI/aitw-webshop-digiq-agent
Updated
JackBAI/llava-v1.5-7b-sfted-pad-inputtext
Updated
JackBAI/CRATE-GPT-12L-Pile-600000steps
Updated
JackBAI/webshop-off2on-filteredbc
Updated
JackBAI/general-off2on-filteredbc
Updated • 1
JackBAI/general-off2on-digirl
Updated • 2
datasets 9
JackBAI/jack-latest-vllm-stack
Updated • 9
JackBAI/tinytlp
Viewer • Updated • 30k • 119
JackBAI/eval_data
Viewer • Updated • 9.64k • 32
JackBAI/autoui-zeroshot-trajectories
Preview • Updated • 178
JackBAI/pile_uncopyrighted_bin
Updated • 15
JackBAI/bert_pretrain_datasets
Viewer • Updated • 80.5M • 574 • 1
JackBAI/redbajama-sampled
Viewer • Updated • 24.3M • 1.98k
JackBAI/merged_roberta_dataset
Updated • 4
JackBAI/chatgpt-woi-finetune
Preview • Updated • 88 • 4