8 papers
LatentOmni: Rethinking Omni-Modal Understanding via Unified Audio-Visual Latent Reasoning
Yifan Dai, Zhenhua Wu, Bohan Zeng +18
Joint audio-visual reasoning is essential for omnimodal understanding, yet current multimodal large language models (MLLMs) still struggle when reasoning requires fine-grained evid…
OmniSIFT: Modality-Asymmetric Token Compression for Efficient Omni-modal Large Language Models
Yue Ding, Yiyan Ji, Jungang Li +12
Omni-modal Large Language Models (Omni-LLMs) have demonstrated strong capabilities in audio-video understanding tasks. However, their reliance on long multimodal token sequences le…
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…
GRAN-TED: Generating Robust, Aligned, and Nuanced Text Embedding for Diffusion Models
Bozhou Li, Sihan Yang, Yushuo Guan +6
The text encoder is a critical component of text-to-image and text-to-video diffusion models, fundamentally determining the semantic fidelity of the generated content. However, its…
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…
Mavors: Multi-granularity Video Representation for Multimodal Large Language Model
Yang Shi, Jiaheng Liu, Yushuo Guan +12
Long-context video understanding in multimodal large language models (MLLMs) faces a critical challenge: balancing computational efficiency with the retention of fine-grained spati…