6 papers
OpenAttention: One Percent Is Enough with Tail Proxies
Hyunwoo Yu, Jongbeom Lee, Hyunbin Kim +8
Sparse attention reads only a small subset of the key-value cache, and how to treat the unread tail remains a key challenge. Discarding the tail biases the output, and sampling it…
SparSTAR: Sparse Attention for SpaceTime AutoRegressive Video Synthesis
Jongbeom Lee, Hyunwoo Yu, Jincheol Yang +2
InfinityStar extends visual autoregressive generation to video through a sequence of image and clip pyramids. Its changing scale and cross-clip context, however, leave late-scale a…
Dual Anchors, Do It Better: Hierarchical Group Merging for Zero-Shot Anomaly Detection
Jimin Roh, DongKyu Kim, Suk-Ju Kang
Zero-shot anomaly detection (ZSAD) aims to identify anomalies in unseen domains, a setting that is particularly critical for industrial and medical applications where domain shifts…
Enhancing Retrieval for ESGLLM via ESG-CID -- A Disclosure Content Index Finetuning Dataset for Mapping GRI and ESRS
Shafiuddin Rehan Ahmed, Ankit Parag Shah, Quan Hung Tran +5
Climate change has intensified the need for transparency and accountability in organizational practices, making Environmental, Social, and Governance (ESG) reporting increasingly c…
MetaSeg: MetaFormer-based Global Contexts-aware Network for Efficient Semantic Segmentation
Beoungwoo Kang, Seunghun Moon, Yubin Cho +2
Beyond the Transformer, it is important to explore how to exploit the capacity of the MetaFormer, an architecture that is fundamental to the performance improvements of the Transfo…
Embedding-Free Transformer with Inference Spatial Reduction for Efficient Semantic Segmentation
Hyunwoo Yu, Yubin Cho, Beoungwoo Kang +3
We present an Encoder-Decoder Attention Transformer, EDAFormer, which consists of the Embedding-Free Transformer (EFT) encoder and the all-attention decoder leveraging our Embeddin…