🔄 In a Training Loop

Xiangchao Chen

UlyssesXC

·

https://chasechen.xyz

AI & ML interests

Agent Learning / Embodied AI

Recent Activity

upvoted a paper about 18 hours ago

Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models

updated a model 2 months ago

UlyssesXC/verl-agent-alfworld-exp15_aux_ce_1.5b

updated a model 2 months ago

UlyssesXC/rlwm-webshop-qwen25-7b-exp-dualadv-w005

View all activity

Organizations

Papers 4

arxiv:2603.20691

arxiv:2603.16124

arxiv:2510.23642

arxiv:2510.08558

models 28

UlyssesXC/rlwm-webshop-qwen25-7b-exp-dualadv-w005

UlyssesXC/verl-agent-alfworld-exp15_aux_ce_1.5b

UlyssesXC/verl-agent-alfworld-grpo-baseline-no-predict-7b

UlyssesXC/rlwm-webshop-qwen25-3b-exp-dualadv-w005

UlyssesXC/rlwm-webshop-exp-dualadv-w005

Updated May 14 • 1

UlyssesXC/verl-agent-alfworld-exp14_no_wm_from_exp13_step80_3b

UlyssesXC/verl-agent-alfworld-grpo-dualadv-w005-schema-verifier-exp5-fix-7b

UlyssesXC/verl-agent-alfworld-exp13_switch_b16_3b

UlyssesXC/verl-agent-alfworld-grpo-baseline-no-predict-3b

UlyssesXC/rlwm-webshop-exp_dualadv_w005

datasets 0

None public yet