arxiv:2602.22859
Hongrui Jia
hongruijia
AI & ML interests
None yet
Recent Activity
authored
a paper
about 5 hours ago
MaVEn: An Effective Multi-granularity Hybrid Visual Encoding Framework
for Multimodal Large Language Model authored
a paper
about 5 hours ago
SymDPO: Boosting In-Context Learning of Large Multimodal Models with
Symbol Demonstration Direct Preference Optimization authored
a paper
about 5 hours ago
Decoupling Reasoning and Perception: An LLM-LMM Framework for Faithful
Visual Reasoning Organizations
None yet
models 6
hongruijia/Qwen2.5-VL-7B-Instruct_DPE_v3
8B • Updated
• 12 • 5
hongruijia/Qwen2.5-VL-7B-Instruct_DPE_v2
8B • Updated
• 3 • 3
hongruijia/Qwen2.5-VL-7B-Instruct_DPE_v1
8B • Updated
• 4 • 2
hongruijia/Qwen3_VL_8B_Instruct_DPE_v2
9B • Updated
• 3 • 2
hongruijia/Qwen3_VL_8B_Instruct_DPE_v1
9B • Updated
• 3 • 4
hongruijia/Qwen3_VL_8B_Instruct_DPE_v3
9B • Updated
• 6 • 6
datasets 0
None public yet