Frame Rate

Follow this topic Ask about this topic

Momentum

5 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 20

All topics

Q-SPT: Learnable Query-Based Compression for Low-Frame-Rate Speech Tokenization
Oct 1, 2026Jeeyoung Yun, Seohwan Yun, Sungwoong KimNeural Speech Codecs Audio Tokenizers
Korea University, Seoul, Republic of Korea
Where Memory Belongs: Ledger, an Object Ledger for Memory-Augmented VLAs
Sep 28, 2026Tanguy Dieudonné, Jack B. Jedlicki, Heng YangRobotic Manipulation Persistent State
Harvard University · ETH Zürich
Joint Analysis of Latent Dimensionality and Frame Rate in Continuous Audio Encoders
Sep 24, 2026Kyudan Jung, Sehyun Lee, Son-ha Jo +2Opencode Frame Rate
KAIST AI · Seoul National University · NAVER Cloud
LACE: Layer-Wise Compression for Dynamic Frame Rate Codecs
Sep 15, 2026Thanapat Trachu, Samuele Cornell, William Chen +1Frame Rate Video Coding
Language Technologies Institute, Carnegie Mellon University, Pittsburgh, USA
Do Input-Level Defenses Transfer to Observation-Level Attacks on VideoLLMs?
Sep 8, 2026Bangshuo Zhu, Wei Song, Yuxin Cao +4LLM Defense Mechanisms Frame Rate
School of Computer Science and Engineering, University of New South Wales, New South Wales 2052, Australia · School of Information and Communication Technology, Griffith University, Queensland 4111, Australia · School of Computing, National University of Singapore, Singapore 117417, Singapore +2
StreamDAM: Presence-Aware Memory for Real-Time Streaming Video Object Segmentation
Aug 4, 2026Xiang ChenVideo Object Segmentation Streaming Video Understanding
Global College Shanghai Jiaotong University Shanghai, China
Evaluating the Effect of Frame Rate in Sequence-Based Classification of Autism-Related Self-Stimulatory Hand Idiosyncrasies
Jul 8, 2026Raunak Mondal, Peter WashingtonAutism Spectrum Disorder Self-Supervised Learning
School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, USA · Department of Information and Computer Sciences, University of Hawaiʻi at Mānoa, Honolulu, HI, USA
DTM-Codec: Dynamic Token Masking for VFR Speech Coding with Efficient Boundary Selection
Jun 28, 2026Hoyeol Sohn, Juhan NamNeural Speech Codecs Frame Rate
Graduate School of Cultural Technology, KAIST, South Korea
Elastic Time: Dynamic Frame Rate Bottlenecks for Neural Audio Coding
Jun 25, 2026Dimitrios Bralios, Paris Smaragdis, Minje KimNeural Audio Codecs Frame Rate
University of Illinois Urbana-Champaign, Urbana, IL, USA · Massachusetts Institute of Technology, Cambridge, MA, USA
OnDeFog: Online Decision Transformer under Frame Dropping
Jun 18, 2026Daiki Yotsufuji, Kenta Nishihara, Shoma Shimizu +2Fog Frame Rate
Yokohama National University, Kanagawa, Japan
Probing Low Frame Rate Degradation in Neural Audio Codecs
Jun 15, 2026Alex Gichamba, Moise BusogiNeural Audio Codecs Frame Rate
Carnegie Mellon University Africa, Rwanda
Which Speech Representation Better Matches Text-Native Reasoning? A Study of Speech-Text Alignment on Frame Rate and Representation
Jun 10, 2026Zhen Ye, Xu Tan, Yiming Li +10Speech-To-Text Alignment Large Audio Language Models
Hong Kong University of Science and Technology, Hong Kong SAR · Tencent, China · Independent Researcher +4
PEEK: Picking Essential frames via Efficient Knowledge distillation
May 29, 2026Killian Steunou, Anas Filali Razzouki, Khalil Guetari +2Video-Language Models Frame Rate
Télécom SudParis — SAMOVAR Institut Polytechnique de Paris Palaiseau, France · Moments Lab 69 Avenue Pierre Grenier Boulogne-Billancourt, France
NeuroLiDAR: Adaptive Frame Rate Depth Sensing via Neuromorphic Event-LiDAR Fusion
May 16, 2026Darshana Rathnayake, Dulanga Weerakoon, Meera Radhakrishnan +1Two-Dimensional Light Detection And Ranging Lidar
Singapore Management University, Singapore · Singapore-MIT Alliance for Research and Technology Centre, Singapore · University of Technology Sydney, Australia
3DGS $^3$ : Joint Super Sampling and Frame Interpolation for Real-Time Large-Scale 3DGS Rendering
May 12, 2026Yibo Zhao, Fan Gao, Youcheng Cai +1Dynamic 3D Gaussian Splatting High-Fidelity
University of Science and Technology of China
LDDR: Linear-DPP-Based Dynamic-Resolution Frame Sampling for Video MLLMs
May 12, 2026Jingfeng Chen, Jiawen Qian, Wendi Deng +5Video Understanding Frame Rate
1Carnegie Mellon University · 2Individual Researcher · 3National University Singapore +2
Towards Compact Sign Language Translation: Frame Rate and Model Size Trade-offs
May 10, 2026Kuanwei Chen, Mengfeng TsaiGloss-Free Sign Language Translation Sign Language Translation
Computer Science and Information Engineering, National Central University, Zhongli, Taiwan
Streaming of rendered content with adaptive frame rate and resolution
May 9, 2026Yaru Liu, Joseph G. March, Rafal K. MantiukFrame Rate Streaming
University of Cambridge, UK
Image Compression with Bubble-Aware Frame Rate Adaptation for Energy-Efficient Video Capsule Endoscopy
Apr 28, 2026Oliver Bause, Jörg Gamerdinger, Julia Werner +1Colonoscopy Frame Rate
University of Tübingen, Faculty of Science, Department of Computer Science, Embedded Systems Group
Instant Expressive Gaussian Head Avatars at Over 100 FPS
Dec 18, 2025Kaiwen Jiang, Xueting Li, Seonwook Park +3Animatable 3D Human Avatars Facial Expression Recognition
University of California, San Diego, United States · NVIDIA, United States

Oct 1, 2026, cs.SDJ/K move · Enter open · S save

Q-SPT: Learnable Query-Based Compression for Low-Frame-Rate Speech Tokenization

Jeeyoung Yun, Seohwan Yun, Sungwoong Kim

Korea University, Seoul, Republic of Korea

Neural Speech Codecs Audio Tokenizers Token Compression Speech Language Models Tokenizer Task-Aware Compression+3

Open paper AskPDF arXiv

Neural speech codecs increasingly serve as tokenizers for speech language models (SLMs). Lowering the frame rate reduces the computational and memory costs of SLMs, but makes it difficult to preserve both linguistic information and acoustic detail. Existing approaches rely on rule-based compression: average pooling can discard linguistic information, whereas similarity-based merging uses a fixed threshold on adjacent-frame similarity and applies the resulting boundaries to the acoustic stream. We propose Q-SPT, a low-frame-rate dual-stream speech tokenizer with separate, context-aware, learnable query-based compressors specialized for semantic and acoustic representations. In particular, queries at a fixed rate independently attend to the semantic and acoustic streams as separate key-value sources, enabling stream-specific, context-aware aggregation through two separately learned compressors. In addition, an autoregressive text loss explicitly supervises the semantic compressor to preserve linguistic information. Experimental results show that Q-SPT achieves the best reconstruction among the evaluated codecs at the same frame rate. In downstream SLMs, it yields the best speech recognition accuracy and text-to-speech perceptual quality with competitive intelligibility.

Momentum

Related topics

Latest papers 20