Peng Shangpin

psp-dada

tencent

·

https://github.com/pspdada

AI & ML interests

Multimodal Large Language Models, Preference Optimization Algorithm, Reinforcement Learning

Recent Activity

upvoted a paper 3 days ago

Beyond Data Scaling: Representation-Centric Continued Pre-training for Vision-Language-Action Models

authored a paper 10 days ago

Beyond Correctness: Benchmarking and Aligning Response Behaviors in Hybrid-Thinking MLLMs

upvoted a paper 10 days ago

Beyond Correctness: Benchmarking and Aligning Response Behaviors in Hybrid-Thinking MLLMs

View all activity

Organizations

psp-dada 's papers 14

arxiv:2608.12781

arxiv:2607.14548

arxiv:2607.04884

arxiv:2606.29905

arxiv:2606.23049

arxiv:2606.14832

arxiv:2606.01348

arxiv:2605.29486

arxiv:2605.11960

arxiv:2605.07630

arxiv:2605.03677

arxiv:2506.10054

arxiv:2511.19575

arxiv:2507.12455