From Blind Spots to Gains: Diagnostic-Driven Iterative Training for Large Multimodal Models
Paper
• 2602.22859 • Published
• 142
Hongrui Jia
hongruijia
AI & ML interests
None yet
Recent Activity
authored
a paper
about 7 hours ago
MaVEn: An Effective Multi-granularity Hybrid Visual Encoding Framework
for Multimodal Large Language Model authored
a paper
about 7 hours ago
SymDPO: Boosting In-Context Learning of Large Multimodal Models with
Symbol Demonstration Direct Preference Optimization authored
a paper
about 7 hours ago
Decoupling Reasoning and Perception: An LLM-LMM Framework for Faithful
Visual Reasoning Organizations
None yet