Takin-VC: Zero-shot Voice Conversion via Jointly Hybrid Content and Memory-Augmented Context-Aware Timbre Modeling

Kavli Affiliate: Xiang Zhang | First 5 Authors: Yuguang Yang, Yu Pan, Jixun Yao, Xiang Zhang, Jianhao Ye | Summary: Zero-shot voice conversion (VC) aims to transform the source speaker timbre into an arbitrary unseen one without altering the original speech content.While recent advancements in zero-shot VC methods have shown remarkable progress, there still remains […]


Continue.. Takin-VC: Zero-shot Voice Conversion via Jointly Hybrid Content and Memory-Augmented Context-Aware Timbre Modeling

Harnessing micro-Fabry-Perot reference cavities in photonic integrated circuits

Kavli Affiliate: Kerry J. Vahala | First 5 Authors: Haotian Cheng, Chao Xiang, Naijun Jin, Igor Kudelin, Joel Guo | Summary: Compact photonic systems that offer high frequency stability and low noise are of increasing importance to applications in precision metrology, quantum computing, communication, and advanced sensing technologies. However, on-chip resonators comprised of dielectrics cannot […]


Continue.. Harnessing micro-Fabry-Perot reference cavities in photonic integrated circuits

Efficient, broadly-tunable source of megawatt pulses for multiphoton microscopy based on self-phase modulation in argon-filled hollow-core fiber

Kavli Affiliate: Frank Wise | First 5 Authors: Yishai Eisenberg, Wenchao Wang, Shitong Zhao, Eric S. Hebert, Yi-Hao Chen | Summary: An exciting recent development for deep-tissue imaging with cellular resolution is three-photon fluorescence microscopy (3PM) with excitation at long wavelengths (1300 and 1700 nm). In the last few years, long-wavelength 3PM has driven rapid […]


Continue.. Efficient, broadly-tunable source of megawatt pulses for multiphoton microscopy based on self-phase modulation in argon-filled hollow-core fiber

Efficient, broadly-tunable source of megawatt pulses for multiphoton microscopy based on self-phase modulation in argon-filled hollow-core fiber

Kavli Affiliate: Chris Xu | First 5 Authors: Yishai Eisenberg, Wenchao Wang, Shitong Zhao, Eric S. Hebert, Yi-Hao Chen | Summary: An exciting recent development for deep-tissue imaging with cellular resolution is three-photon fluorescence microscopy (3PM) with excitation at long wavelengths (1300 and 1700 nm). In the last few years, long-wavelength 3PM has driven rapid […]


Continue.. Efficient, broadly-tunable source of megawatt pulses for multiphoton microscopy based on self-phase modulation in argon-filled hollow-core fiber

Edge and bulk states in a three-site Kitaev chain

Kavli Affiliate: Michael Wimmer | First 5 Authors: Sebastiaan L. D. ten Haaf, Yining Zhang, Qingzhen Wang, Alberto Bordin, Chun-Xiao Liu | Summary: A chain of quantum dots (QDs) coupled via semiconductor-superconductor hybrid regions can form an artificial Kitaev chain hosting Majorana bound states (MBSs). These zero-energy states are expected to be localised on the […]


Continue.. Edge and bulk states in a three-site Kitaev chain

Cooling and Squeezing a Microwave Cavity State with Magnons Using a Beam Splitter Interaction

Kavli Affiliate: Gregory D. Fuchs | First 5 Authors: Qin Xu, Gregory D. Fuchs, , , | Summary: We propose two geometries to realize a significant beam splitter interaction (XZ coupling) between magnons and a 2D microwave cavity mode. In both setups the cavity is analogous to the mechanical oscillator in a conventional optomechanical setup. […]


Continue.. Cooling and Squeezing a Microwave Cavity State with Magnons Using a Beam Splitter Interaction

PEAR: Position-Embedding-Agnostic Attention Re-weighting Enhances Retrieval-Augmented Generation with Zero Inference Overhead

Kavli Affiliate: Feng Wang | First 5 Authors: Tao Tan, Yining Qian, Ang Lv, Hongzhan Lin, Songhao Wu | Summary: Large language models (LLMs) enhanced with retrieval-augmented generation (RAG) have introduced a new paradigm for web search. However, the limited context awareness of LLMs degrades their performance on RAG tasks. Existing methods to enhance context […]


Continue.. PEAR: Position-Embedding-Agnostic Attention Re-weighting Enhances Retrieval-Augmented Generation with Zero Inference Overhead

PEAR: Position-Embedding-Agnostic Attention Re-weighting Enhances Retrieval-Augmented Generation with Zero Inference Overhead

Kavli Affiliate: Feng Wang | First 5 Authors: Tao Tan, Yining Qian, Ang Lv, Hongzhan Lin, Songhao Wu | Summary: Large language models (LLMs) enhanced with retrieval-augmented generation (RAG) have introduced a new paradigm for web search. However, the limited context awareness of LLMs degrades their performance on RAG tasks. Existing methods to enhance context […]


Continue.. PEAR: Position-Embedding-Agnostic Attention Re-weighting Enhances Retrieval-Augmented Generation with Zero Inference Overhead

Multimodal Misinformation Detection by Learning from Synthetic Data with Multimodal LLMs

Kavli Affiliate: Wei Gao | First 5 Authors: Fengzhu Zeng, Wenqian Li, Wei Gao, Yan Pang, | Summary: Detecting multimodal misinformation, especially in the form of image-text pairs, is crucial. Obtaining large-scale, high-quality real-world fact-checking datasets for training detectors is costly, leading researchers to use synthetic datasets generated by AI technologies. However, the generalizability of […]


Continue.. Multimodal Misinformation Detection by Learning from Synthetic Data with Multimodal LLMs

Fracture Characterization of Bioinspired Irregular Network Reinforced Composites

Kavli Affiliate: Chiara Daraio | First 5 Authors: Chelsea Fox, Tommaso Magrini, Chiara Daraio, , | Summary: The mechanical behavior of composite materials is significantly influenced by their structure and constituent materials. One emerging class of composite materials is irregular network reinforced composites (NRC’s), whose reinforcing phase is generated by a stochastic algorithm. Although design […]


Continue.. Fracture Characterization of Bioinspired Irregular Network Reinforced Composites