Li Haozhan PRO
Haozhan72
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
10 days ago
FlowRL: Matching Reward Distributions for LLM Reasoning
upvoted
a
paper
16 days ago
TTRL: Test-Time Reinforcement Learning
authored
a paper
17 days ago
SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning
Organizations
models
37
Haozhan72/rdt_twin2_stack_bowls_two_sft_seed1000
Updated
•
8
Haozhan72/twin2_place_empty_cup_seed1k_sft10k_batch64_rl_seed1000_step40_chunk12
8B
•
Updated
•
8
Haozhan72/twin2_click_bell_sft20k_batch32_rl_seed1000_step40_chunk12
8B
•
Updated
•
5
Haozhan72/twin2_move_can_pot_seed1k_sft20k_batch64_rl_seed1000_step40_chunk12
8B
•
Updated
•
4
Haozhan72/twin2_handover_block_seed1k_sft20k_batch64_rl_seed1000_step40_chunk12
8B
•
Updated
•
3
Haozhan72/twin2_pick_dual_bottles_seed1k_sft10k_batch64_rl_seed1000_step40_chunk12
8B
•
Updated
•
8
Haozhan72/twin2_beat_block_hammer_seed1k_sft10k_batch64_rl_seed1000_step40
8B
•
Updated
•
4
Haozhan72/robotwin2_beat_block_hammer_seed1k_sft_aloha_25chunks_10k
8B
•
Updated
•
5
Haozhan72/twin2_place_empty_cup_seed1k_sft10k_batch64_rl_seed1000_step20
8B
•
Updated
•
4
Haozhan72/twin2_place_container_plate_seed1k_sft10k_batch64_rl_seed1000_step20
8B
•
Updated
•
4