From the 2 of 5 linked papers with an AI index.
5 papers
Rethinking Multimodal Fusion for Time Series: Text Modalities Need Constrained Fusion
Seunghan Lee, Jun Seo, Jaehoon Lee +7
The paper investigates how naive multimodal fusion can hurt time series forecasting performance and proposes a Controlled Fusion Adapter that uses low‑rank adapters to filter irrel…
Not All Retrievals are Useful: Cross-Attention for Input-Aware RAG in Time Series Forecasting
Seunghan Lee, Jaehoon Lee, Jun Seo +7
The paper introduces Cross-RAG, a retrieval-augmented generation framework for zero-shot time series forecasting that uses query‑retrieval cross‑attention to selectively attend to…
AdaTKG: Adaptive Memory for Temporal Knowledge Graph Reasoning
Seunghan Lee, Jun Seo, Jaehoon Lee +7
Temporal knowledge graphs (TKGs) represent time-stamped relational facts and support a wide range of reasoning tasks over evolving events. However, existing methods produce entity…
ReSpec: Relevance and Specificity Grounded Online Filtering for Learning on Video-Text Data Streams
Chris Dongjoo Kim, Jihwan Moon, Sangwoo Moon +7
The rapid growth of video-text data presents challenges in storage and computation during training. Online learning, which processes streaming data in real-time, offers a promising…
MASH-VLM: Mitigating Action-Scene Hallucination in Video-LLMs through Disentangled Spatial-Temporal Representations
Kyungho Bae, Jinhyung Kim, Sihaeng Lee +3
In this work, we tackle action-scene hallucination in Video Large Language Models (Video-LLMs), where models incorrectly predict actions based on the scene context or scenes based…