MaVEn: An Effective Multi-granularity Hybrid Visual Encoding Framework for Multimodal Large Language Model
Paper
• 2408.12321 • Published
Hongrui Jia
hongruijia
AI & ML interests
None yet
Recent Activity
authored
a paper
5 days ago
MaVEn: An Effective Multi-granularity Hybrid Visual Encoding Framework
for Multimodal Large Language Model authored
a paper
5 days ago
Decoupling Reasoning and Perception: An LLM-LMM Framework for Faithful
Visual Reasoning Organizations
None yet
authored 5 papers 5 days ago
SymDPO: Boosting In-Context Learning of Large Multimodal Models with Symbol Demonstration Direct Preference Optimization
Paper
• 2411.11909 • Published
• 22
Decoupling Reasoning and Perception: An LLM-LMM Framework for Faithful Visual Reasoning
Paper
• 2509.23322 • Published
• 1
From Blind Spots to Gains: Diagnostic-Driven Iterative Training for Large Multimodal Models
Paper
• 2602.22859 • Published
• 148
OSWorld-MCP: Benchmarking MCP Tool Invocation In Computer-Use Agents
Paper
• 2510.24563 • Published
• 23