Rongrong Ji

11 papers Xiamen University, China

• Accelerating Multimodal Large Language Models via Dynamic Visual-Token Exit and the Empirical Findings
• CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models
• DAMamba: Vision State Space Model with Dynamic Adaptive Scan
• Discovering Important Experts for Mixture-of-Experts Models Pruning Through a Theoretical Perspective
• LTD-Bench: Evaluating Large Language Models by Letting Them Draw
• MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models
• Spotlight Attention: Towards Efficient LLM Generation via Non-linear Hashing-based KV Cache Retrieval
• VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction
• VITA-Audio: Fast Interleaved Audio-Text Token Generation for Efficient Large Speech-Language Model
• Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension
• Zooming from Context to Cue: Hierarchical Preference Optimization for Multi-Image MLLMs