5 papers
Semantic Routing: Exploring Multi-Layer LLM Feature Weighting for Diffusion Transformers
Bozhou Li, Yushuo Guan, Haolin Li +7
Recent DiT-based text-to-image models increasingly adopt LLMs as text encoders, yet text conditioning remains largely static and often utilizes only a single LLM layer, despite pro…
Research on World Models Is Not Merely Injecting World Knowledge into Specific Tasks
Bohan Zeng, Kaixin Zhu, Daili Hua +24
World models have emerged as a critical frontier in AI research, aiming to enhance large models by infusing them with physical dynamics and world knowledge. The core objective is t…
DiaDem: Advancing Dialogue Descriptions in Audiovisual Video Captioning for Multimodal Large Language Models
Xinlong Chen, Weihong Lin, Jingyun Hua +10
Accurate dialogue description in audiovisual video captioning is crucial for downstream understanding and generation tasks. However, existing models generally struggle to produce f…
The Unseen Bias: How Norm Discrepancy in Pre-Norm MLLMs Leads to Visual Information Loss
Bozhou Li, Xinda Xue, Sihan Yang +5
Multimodal Large Language Models (MLLMs), which couple pre-trained vision encoders and language models, have shown remarkable capabilities. However, their reliance on the ubiquitou…
AVoCaDO: An Audiovisual Video Captioner Driven by Temporal Orchestration
Xinlong Chen, Yue Ding, Weihong Lin +9
Audiovisual video captioning aims to generate semantically rich descriptions with temporal alignment between visual and auditory events, thereby benefiting both video understanding…