From the 2 of 10 linked papers with an AI index.
10 papers
From Interpretation to Compilation: A Compilation-Based Execution Engine for Semantic Operator Systems
Wenkai Dong, Yifan Wang
Semantic operators extend data processing with natural-language predicates. Existing semantic operator systems commonly execute these operators through interpretation-based executi…
PMMC: Prospective Multimodal Memory Compilation for Long-Term LVLM Agents
Jingyu Sun, Yan Lin, Yuyang Xue +10
Long-term memory is essential for LVLM agents to maintain consistency and integrate information across extended multimodal interactions. Existing agent memory systems, however, oft…
Conan-embedding-v3: Fusing Modality-Specific Models for Omni-Modal Embedding
Shiyu Li, Zhiyuan Hu, Yifan Wang +3
The paper presents Conan-embedding-v3, a framework that trains modality‑specific specialist models, fuses them into a single dense backbone, and then recovers the modality projecto…
From Interpretation to Compilation: Compilation-Based Execution of Semantic Operators [Vision]
Wenkai Dong, Yifan Wang
The paper proposes generating deterministic executable code from LLMs once during a compilation step, enabling faster execution of semantic filter, map, and join operators without…
DECIS: Dual-Evidence Corrective Verification for Interpretable Strabismus Diagnostic Decision-Making
Xikai Tang, Yifan Wang, Jiafan Zhuang +12
Strabismus is a common ocular disorder that requires fine-grained subtype diagnosis for individualized treatment planning. However, existing deep learning methods mainly provide di…
Are Reasoning Vision-Language Models Robust to Semantic Visual Distractions?
Yizheng Sun, Mochuan Zhan, Yanan Ma +10
Reasoning Vision-Language Models (VLMs) achieve strong performance on complex multimodal tasks, but reliable real-world application requires handling visual inputs that are messier…