Notable data and AI papers

Papers627Labs45

627 papers · 45 labs

Fish Audio S2 Technical Report research paper by Fish Audio, 2026

Fish Audio · Foundation models · Mar 9, 2026 · 24 citations · 40 upvotes · unverified

Read on arXiv

What it shows

Fish Audio S2 is an open-source text-to-speech system with multi-speaker capabilities, multi-turn generation, and instruction-following control through natural-language descriptions, utilizing a multi-stage training approach and production-ready inference engine.

By Shijia Liao, Yuxuan Wang, Songting Liu and 11 more · arXiv 2603.08823 · PDF · Code

UnverifiedHugging Face's summary; not yet checked by hand.

More from Fish Audio

All 2
Multimodal and roboticsUnverifiedOct 13, 2026Fish Audio Drama 3 Technical ReportThis paper introduces an open-source speech generation model capable of multi-turn performance, character-specific voice cloning, and real-time audio editing.Fish Audio26 upvotesRead →

Other foundation models papers

Topic
Foundation modelsOct 11, 2018BERT: Pre-training of Deep Bidirectional Transformers for Language UnderstandingPre-training a Transformer to fill in masked words, then fine-tuning it, beat task-specific models across language understanding tests.Google125k citations33 upvotesRead →Foundation modelsMay 28, 2020Language Models are Few-Shot LearnersGPT-3, a 175B-parameter model, does new tasks from a few examples in the prompt, with no fine-tuning.OpenAI66.4k citations21 upvotesRead →Foundation modelsMar 15, 2023GPT-4 Technical ReportA multimodal model that passes a simulated bar exam with a score around the top 10% of test takers.OpenAI28.4k citations7 upvotesRead →Foundation modelsFeb 27, 2023LLaMA: Open and Efficient Foundation Language ModelsOpen models from 7B to 65B trained only on public data; the 13B model beats GPT-3 on most benchmarks.Meta22.6k citations25 upvotesRead →Foundation modelsJul 31, 2024The Llama 3 Herd of ModelsOpen models up to 405B parameters that match leading closed models on many tasks.Meta20.8k citations119 upvotesRead →Foundation modelsUnverifiedMay 14, 2025Qwen3 Technical ReportQwen3, a unified series of large language models, integrates thinking and non-thinking modes, reduces computational resources, and achieves state-of-the-art performance across various tasks and languages.Alibaba (Qwen)10.1k citations339 upvotesRead →
About this paper
Venue
arXiv.org
Citations
24, 6 influential · Semantic Scholar
Upvotes
40 · Hugging Face
Lab
Fish Audio · on Companies · on Rounds · on labs · on Leaders · on Arena · on newsletters · on Paydays · on Releases · on repos · on socials · on terms

Changes

CitationsNov 9, 2026Citations rose from 23 to 24.
CitationsNov 2, 2026Influential citations rose from 4 to 6.
CitationsNov 2, 2026Citations rose from 20 to 23.
CitationsOct 12, 2026Influential citations rose from 3 to 4.
CitationsOct 12, 2026Citations rose from 19 to 20.
CitationsOct 5, 2026Citations rose from 17 to 19.
CitationsSep 25, 2026A first count of 3 influential citations.
CitationsSep 25, 2026A first count of 17 citations.
New paperSep 25, 2026Found by the weekly Hugging Face scan; not yet checked by hand.