2 papers
cs.LG2026
High-Fidelity Compression of Seismic Velocity Models via SIREN Auto-Decoders
Caiyun Liu, Xiaoxue Luo, Jie Xiong
Implicit Neural Representations (INRs) have emerged as a powerful paradigm for representing continuous signals independently of grid resolution. In this paper, we propose a high-fi…
cs.SD2025
DeCodec: Rethinking Audio Codecs as Universal Disentangled Representation Learners
Xiaoxue Luo, Jinwei Huang, Runyan Yang +4
Universal audio codecs learn entangled representations across audio types, whereas some specific codecs offer decoupled representations but are limited to speech. Real-world audio,…