junmingyang's picture

junmingyang

jmyang

·

https://junming-yang.github.io/

junming-yang

AI & ML interests

LLM Alignment, VLM

Recent Activity

authored a paper 3 days ago

Preference Orchestrator: Prompt-Aware Multi-Objective Alignment for Large Language Models

authored a paper 3 days ago

SpatialWorld: Benchmarking Interactive Spatial Reasoning of Multimodal Agents in Real-World Tasks

upvoted a paper 3 days ago

SlimSearcher: Training Efficiency-Aware Web Agents via Adaptive Reward Gating

View all activity

Organizations

None yet

jmyang 's models 6

jmyang/MetaAPO-Qwen2.5-7B

0.5B • Updated Feb 28 • 3 • 1

jmyang/Qwen2.5-7B-rm

1B • Updated Feb 28

jmyang/Qwen2.5-7B-DPO

8B • Updated Jan 6 • 1

jmyang/MetaAPO-Llama3.1-8B

0.5B • Updated Jan 2 • 2 • 2

jmyang/llama3.1-8b-rm-ultrafeedback

8B • Updated Nov 15, 2025 • 3

jmyang/llama3.1-8b-dpo-ultrafeedback

8B • Updated Nov 15, 2025