🎵 Audio Streaming - matmat · Scour

Subjective and Objective Quality-of-Experience Evaluation Study for Live Video Streaming 🎥Streaming Codecs

DASB -- Discrete Audio and Speech Benchmark 👁️Perceptual Coding

Stream2LLM: Overlap Context Streaming and Prefill for Reduced TTFT ⚡LZ4 Streaming

LLM-Codec: Neural Audio Codec Meets Language Model Objectives 🎧Learned Audio

Suffix Random Access via Function Inversion: A Key for Asymmetric Streaming String Algorithms 🌊Streaming Compression

Reducing the Offline-Streaming Gap for Unified ASR Transducer with Consistency Regularization 🗣️CMU Pronouncing

Video-Robin: Autoregressive Diffusion Planning for Intent-Grounded Video-to-Music Generation 🎧Learned Audio

Temporal Contrastive Decoding: A Training-Free Method for Large Audio-Language Models 🎧Learned Audio

APRVOS: 1st Place Winner of 5th PVUW MeViS-Audio Track 🎧WAV Metadata

NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR 🎙️Whisper

Predicting LLM Compression Degradation from Spectral Statistics 🧠Learned Codecs

Audio-DeepThinker: Progressive Reasoning-Aware Reinforcement Learning for High-Quality Chain-of-Thought Emergence in Audio Language Models 🎧Learned Audio

LLM-AUG: Robust Wireless Data Augmentation with In-Context Learning in Large Language Models 💻Local LLMs

Hierarchical Codec Diffusion for Video-to-Speech Generation 🧠Learned Codecs

Sequential KV Cache Compression via Probabilistic Language Tries: Beyond the Per-Vector Shannon Limit 🌊Streaming Compression

arxiv.org·5d·Hacker News

SAW-INT4: System-Aware 4-Bit KV-Cache Quantization for Real-World LLM Serving 🖥️Hardware Architecture

arxiv.org·3d·Hacker News

No more posts from matmat's subscribed feeds.

Scour all 24374 feeds Learn more about Feeds

Log in to enable infinite scrolling