4 papers
MASRA: MLLM-Assisted Semantic-Relational Consistent Alignment for Video Temporal Grounding
Ran Ran, Jiwei Wei, Shuchang Zhou +5
Video Temporal Grounding (VTG) faces a cross-modal semantic gap that often leads to background features being incorrectly aligned with the query, while directly matching the query…
MM-R1: Unleashing the Power of Unified Multimodal Large Language Models for Personalized Image Generation
Qian Liang, Yujia Wu, Kuncheng Li +4
Multimodal Large Language Models (MLLMs) with unified architectures excel across a wide range of vision-language tasks, yet aligning them with personalized image generation remains…
Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025
Zonghao Ying, Siyang Wu, Run Hao +44
Multimodal Large Language Models (MLLMs) have enabled transformative advancements across diverse applications but remain susceptible to safety threats, especially jailbreak attacks…
LoLDU: Low-Rank Adaptation via Lower-Diag-Upper Decomposition for Parameter-Efficient Fine-Tuning
Yiming Shi, Jiwei Wei, Yujia Wu +4
The rapid growth of model scale has necessitated substantial computational resources for fine-tuning. Existing approach such as Low-Rank Adaptation (LoRA) has sought to address the…