2 26 2

Runpeng Dai PRO

Leo-Dai

AI & ML interests

None yet

Recent Activity

liked a Space about 24 hours ago

EfficientReasoning/efficient_reasoning_online_judgement

upvoted a paper 3 days ago

Training Data Efficiency in Multimodal Process Reward Models

authored a paper 5 days ago

Parallel-Probe: Towards Efficient Parallel Thinking via 2D Probing

View all activity

Organizations

Collections 2

Papers 6

models 17

datasets 5

Leo-Dai/APO_combine

Viewer • Updated May 30, 2025 • 1.92k • 3

Leo-Dai/APO_AMC23

Viewer • Updated May 29, 2025 • 40 • 4

Leo-Dai/dapo-math-17k_dedup

Viewer • Updated May 29, 2025 • 17.9k • 4

Leo-Dai/APO_AIME24

Viewer • Updated May 29, 2025 • 30 • 5

Leo-Dai/APO_AIME25

Viewer • Updated May 29, 2025 • 30 • 1

Runpeng Dai PRO

AI & ML interests

Recent Activity

Organizations

Collections 2

Offline Actor-Critic Reinforcement Learning Scales to Large Models

The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits

kiendt/llama3-8b-math

aaditya/Llama3-OpenBioLLM-8B

ruslanmv/Medical-Llama3-8B

Offline Actor-Critic Reinforcement Learning Scales to Large Models

The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits

kiendt/llama3-8b-math

aaditya/Llama3-OpenBioLLM-8B

ruslanmv/Medical-Llama3-8B

Papers 6

models 17

Leo-Dai/PPO_BL_250_critic

Leo-Dai/PPO_BL_200_critic

Leo-Dai/PPO_BL_300_actor

Leo-Dai/PPO_BL_250_actor

Leo-Dai/PPO_BL_300_critic

Leo-Dai/GRPO_BL_40

Leo-Dai/GRPO_BL_30

Leo-Dai/GRPO_BL_20

Leo-Dai/GRPO_BL_400

Leo-Dai/GRPO_BL_10

datasets 5

Leo-Dai/APO_combine

Leo-Dai/APO_AMC23

Leo-Dai/dapo-math-17k_dedup

Leo-Dai/APO_AIME24

Leo-Dai/APO_AIME25

Runpeng Dai PRO

AI & ML interests

Recent Activity

Organizations

Collections 2

Papers 6

models 17 Sort: Recently updated

datasets 5 Sort: Recently updated

models 17

datasets 5