SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction

Kavli Affiliate: Wei Gao | First 5 Authors: Xuan Zhang, Cunxiao Du, Chao Du, Tianyu Pang, Wei Gao | Summary: Recent advancements in large language models (LLMs) have extended their capabilities to handle long contexts. However, increasing the number of model layers and the length of input sequences significantly escalates the memory required to store […]


Continue.. SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction

LightTransfer: Your Long-Context LLM is Secretly a Hybrid Model with Effortless Adaptation

Kavli Affiliate: Wei Gao | First 5 Authors: Xuan Zhang, Fengzhuo Zhang, Cunxiao Du, Chao Du, Tianyu Pang | Summary: Scaling language models to handle longer contexts introduces substantial memory challenges due to the growing cost of key-value (KV) caches. Motivated by the efficiency gains of hybrid models and the broad availability of pretrained large […]


Continue.. LightTransfer: Your Long-Context LLM is Secretly a Hybrid Model with Effortless Adaptation

On “Inconsistencies of metalens performance and comparison with conventional diffractive optics”

Kavli Affiliate: Andrei Faraon | First 5 Authors: Amir Arbabi, Andrei Faraon, , , | Summary: It was recently claimed1 that reported focusing efficiency values of high numerical aperture metalenses are inconsistent with a theoretical bound, and their measurement results are incorrectly interpreted. We review the article and conclude that these claims are not well […]


Continue.. On “Inconsistencies of metalens performance and comparison with conventional diffractive optics”

Distribution Guidance Network for Weakly Supervised Point Cloud Semantic Segmentation

Kavli Affiliate: Wei Gao | First 5 Authors: Zhiyi Pan, Wei Gao, Shan Liu, Ge Li, | Summary: Despite alleviating the dependence on dense annotations inherent to fully supervised methods, weakly supervised point cloud semantic segmentation suffers from inadequate supervision signals. In response to this challenge, we introduce a novel perspective that imparts auxiliary constraints […]


Continue.. Distribution Guidance Network for Weakly Supervised Point Cloud Semantic Segmentation

Distribution Guidance Network for Weakly Supervised Point Cloud Semantic Segmentation

Kavli Affiliate: Wei Gao | First 5 Authors: Zhiyi Pan, Wei Gao, Shan Liu, Ge Li, | Summary: Despite alleviating the dependence on dense annotations inherent to fully supervised methods, weakly supervised point cloud semantic segmentation suffers from inadequate supervision signals. In response to this challenge, we introduce a novel perspective that imparts auxiliary constraints […]


Continue.. Distribution Guidance Network for Weakly Supervised Point Cloud Semantic Segmentation

Perceptual Quality Assessment of Octree-RAHT Encoded 3D Point Clouds

Kavli Affiliate: Wei Gao | First 5 Authors: Dongshuai Duan, Honglei Su, Qi Liu, Hui Yuan, Wei Gao | Summary: No-reference bitstream-layer point cloud quality assessment (PCQA) can be deployed without full decoding at any network node to achieve real-time quality monitoring. In this work, we focus on the PCQA problem dedicated to Octree-RAHT encoding […]


Continue.. Perceptual Quality Assessment of Octree-RAHT Encoded 3D Point Clouds

Perceptual Quality Assessment of Octree-RAHT Encoded 3D Point Clouds

Kavli Affiliate: Wei Gao | First 5 Authors: Dongshuai Duan, Honglei Su, Qi Liu, Hui Yuan, Wei Gao | Summary: No-reference bitstream-layer point cloud quality assessment (PCQA) can be deployed without full decoding at any network node to achieve real-time quality monitoring. In this work, we focus on the PCQA problem dedicated to Octree-RAHT encoding […]


Continue.. Perceptual Quality Assessment of Octree-RAHT Encoded 3D Point Clouds

Perceptual Quality Assessment of Trisoup-Lifting Encoded 3D Point Clouds

Kavli Affiliate: Wei Gao | First 5 Authors: Juncheng Long, Honglei Su, Qi Liu, Hui Yuan, Wei Gao | Summary: No-reference bitstream-layer point cloud quality assessment (PCQA) can be deployed without full decoding at any network node to achieve real-time quality monitoring. In this work, we develop the first PCQA model dedicated to Trisoup-Lifting encoded […]


Continue.. Perceptual Quality Assessment of Trisoup-Lifting Encoded 3D Point Clouds

Perceptual Quality Assessment of Trisoup-Lifting Encoded 3D Point Clouds

Kavli Affiliate: Wei Gao | First 5 Authors: Juncheng Long, Honglei Su, Qi Liu, Hui Yuan, Wei Gao | Summary: No-reference bitstream-layer point cloud quality assessment (PCQA) can be deployed without full decoding at any network node to achieve real-time quality monitoring. In this work, we develop the first PCQA model dedicated to Trisoup-Lifting encoded […]


Continue.. Perceptual Quality Assessment of Trisoup-Lifting Encoded 3D Point Clouds

Direction Modulation Design for UAV Assisted by IRS with discrete phase shift

Kavli Affiliate: Wei Gao | First 5 Authors: Maolin Li, Wei Gao, Qi Wu, Feng Shu, Cunhua Pan | Summary: As a physical layer security technology, directional modulation (DM) can be combined with intelligent reflect-ing surface (IRS) to improve the security of drone communications. In this paper, a directional modulation scheme assisted by the IRS […]


Continue.. Direction Modulation Design for UAV Assisted by IRS with discrete phase shift