From the 1 of 6 linked papers with an AI index.
6 papers
VLZip: Unified Visual and Textual Compression for Interleaved Long-Context Modeling
Yuqi Zhang, Cheng Chen, Yuyu Guo +6
Vision Language Models (VLMs) face significant challenges with ultra-long, interleaved image-text sequences due to the quadratic complexity of self-attention. Current solutions eit…
SOLAR: Self-supervised Joint Learning for Symmetric Multimodal Retrieval
Wenjie Yang, Hang Yu, Yuyu Guo +1
The paper introduces SOLAR, a self‑supervised two‑stage framework for symmetric multimodal‑to‑multimodal retrieval that learns intersection masks from large unlabeled image‑text pa…
From One-to-One to Many-to-Many: Dynamic Cross-Layer Injection for Deep Vision-Language Fusion
Cheng Chen, Yuyu Guo, Pengpeng Zeng +4
Vision-Language Models (VLMs) create a severe visual feature bottleneck by using a crude, asymmetric connection that links only the output of the vision encoder to the input of the…
Multimodal Continuous Reasoning via Asymmetric Mutual Variational Learning
Shijie Li, Yilin Gao, Siyuan Yang +7
Multimodal Large Language Models (MLLMs) are often constrained by a language-space bottleneck, forcing complex visual reasoning into discrete tokens which can lose perceptual nuanc…
Janus-LoRA: A Balanced Low-Rank Adaptation for Continual Learning
Cheng Chen, Pengpeng Zeng, Yuyu Guo +3
Low-Rank Adaptation (LoRA) has emerged as a promising paradigm for Continual Learning. It independently updates its low-rank factors ( and ), creating a composite update to t…
OpAgent: Operator Agent for Web Navigation
Yuyu Guo, Wenjie Yang, Siyuan Yang +12
To fulfill user instructions, autonomous web agents must contend with the inherent complexity and volatile nature of real-world websites. Conventional paradigms predominantly rely…