Estimating piano dynamic from audio recordings is a fundamental challenge in computational music analysis. In this paper, we propose an efficient multi-task network that jointly predicts dynamic levels, change points, beats, and downbeats from a shared latent representation. These four targets form the metrical structure of dynamics in the music score. Inspired by recent vocal dynamic research, we use a multi-scale network as the backbone, which takes Bark-scale specific loudness as the input feature. Compared to log-Mel as input, this reduces model size from 14.7 M to 0.5 M, enabling long sequential input. We use a 60-second audio length in audio segmentation, which doubled the length of beat tracking commonly used. Evaluated on the public MazurkaBL dataset, our model achieves state-of-the-art results across all tasks. This work sets a new benchmark for piano dynamic estimation and delivers a powerful and compact tool, paving the way for large-scale, resource-efficient analysis of musical expression.

We study whether self-learning can scale LLM-based agents without relying on human-curated datasets or predefined rule-based rewards. Through controlled experiments in a search-agent setting, we identify two key determinants of scalable agent training: the source of reward signals and the scale of agent task data. We find that rewards from a Generative Reward Model (GRM) outperform rigid rule-based signals for open-domain learning, and that co-evolving the GRM with the policy further boosts performance. Increasing the volume of agent task data-even when synthetically generated-substantially enhances agentic capabilities. Building on these insights, we propose \textbf{Agentic Self-Learning} (ASL), a fully closed-loop, multi-role reinforcement learning framework that unifies task generation, policy execution, and evaluation within a shared tool environment and LLM backbone. ASL coordinates a Prompt Generator, a Policy Model, and a Generative Reward Model to form a virtuous cycle of harder task setting, sharper verification, and stronger solving. Empirically, ASL delivers steady, round-over-round gains, surpasses strong RLVR baselines (e.g., Search-R1) that plateau or degrade, and continues improving under zero-labeled-data conditions, indicating superior sample efficiency and robustness. We further show that GRM verification capacity is the main bottleneck: if frozen, it induces reward hacking and stalls progress; continual GRM training on the evolving data distribution mitigates this, and a small late-stage injection of real verification data raises the performance ceiling. This work establishes reward source and data scale as critical levers for open-domain agent learning and demonstrates the efficacy of multi-role co-evolution for scalable, self-improving agents. The data and code of this paper are released at https://github.com/forangel2014/Towards-Agentic-Self-Learning

Finetuning (pretrained) language models is a standard approach for updating their internal parametric knowledge and specializing them to new tasks and domains. However, the corresponding model weight changes ("weight diffs") are not generally interpretable. While inspecting the finetuning dataset can give a sense of how the model might have changed, these datasets are often not publicly available or are too large to work with directly. Towards the goal of comprehensively understanding weight diffs in natural language, we introduce Diff Interpretation Tuning (DIT), a method that trains models to describe their own finetuning-induced modifications. Our approach uses synthetic, labeled weight diffs to train a DIT-adapter, which can be applied to a compatible finetuned model to make it describe how it has changed. We demonstrate in two proof-of-concept settings (reporting hidden behaviors and summarizing finetuned knowledge) that our method enables models to describe their finetuning-induced modifications using accurate natural language descriptions.

OpenAI has unveiled ChatGPT Atlas, a long-anticipated artificial intelligence-powered web browser built around its popular chatbot, in a direct challenge to Google Chrome's dominance. OpenAI on Tuesday unveiled ChatGPT Atlas, a long-anticipated artificial intelligence-powered web browser built around its popular chatbot, in a direct challenge to Google Chrome's dominance. The launch marks OpenAI's latest move to capitalize on 800 million weekly active ChatGPT users, as it expands into more aspects of users' online lives by collecting data about consumers' browser behavior. It could accelerate a broader shift toward AI-driven search, as users increasingly turn to conversational tools that synthesize information instead of relying on traditional keyword-based results from Google -- intensifying competition between OpenAI and Google. Shares of Alphabet, which owns the Chrome browser, were down 1.8% in afternoon trading.

This material may not be published, broadcast, rewritten, or redistributed. Quotes displayed in real-time or delayed by at least 15 minutes. Market data provided by Factset . Powered and implemented by FactSet Digital Solutions . Mutual Fund and ETF data provided by Refinitiv Lipper .

Your Apple phone has some new AI powers with iOS 26 and Visual Intelligence. Breakthroughs, discoveries, and DIY tips sent every weekday. By now you should've upgraded to iOS 26 on your iPhone, and the update is a big one. In addition to rolling out an entirely new look (called Liquid Glass), iOS 26 introduces a host of new and upgraded features, from a new battery saving mode to a mobile version of the classic Preview Mac app . Another change ushered in by iOS 26 is the introduction of an expanded Visual Intelligence tool, part of Apple Intelligence.

Fear isn't just personal--it spreads through sight, smell, and even subconsciously. Horror movies may be scarier in a crowded movie theater. Breakthroughs, discoveries, and DIY tips sent every weekday. We've all felt it: heart racing, palms sweating, stomach clenching--the iron grip of fear. Whether it's the sudden threat of an out-of-control vehicle or the nervous wait before a job interview, we all have felt fear's sudden grip.

This material may not be published, broadcast, rewritten, or redistributed. Quotes displayed in real-time or delayed by at least 15 minutes. Market data provided by Factset . Powered and implemented by FactSet Digital Solutions . Mutual Fund and ETF data provided by Refinitiv Lipper .

Trump henchman's'Nazi texts' emerge as racist message crisis tears through White House Kate and William lead bid to exile Andrew and Fergie from Royal Lodge as public anger grows at his taxpayer-funded luxury: Waleses'can't abide' Prince and are pushing for him to leave, author claims Meghan's hit a trashy new low. JILLIAN MICHAELS: The trans trend is reversing. Now it's time to admit what's really been driving this extremist fad all along Napa tycoon is accused of slamming Rolls Royce into women because he couldn't find a parking spot... now his scandalous divorce secrets are exposed I know why Prince Harry and Andrew were'cut so much slack' by the late Queen - it's to do with her father and sister, reveals ROBERT HARDMAN The Prince Harry interview that left the Royals reeling and resumed the war against them, with even Downing Street forced to issue a statement! Married Congressman had alleged affair with aide... before she set herself on fire: Bombshell revelation as police block release of 911 call and other evidence Trapped on death island: 'Marooned' Russian troops are starving to death and 5,000 have died after being cut off from other Russian forces in Ukraine Apple Martin's music debut is likened to an'off-key, drunken karaoke performance' and proof that'nepotism is killing art' - as she attempts to follow in Coldplay star dad Chris' footsteps Fox News host Jesse Watters stunned as he admits his MOM joined millions protesting Trump at'No Kings' rally RFK Jr's desperate proposition to Cheryl Hines after his sexting fiasco pushed their marriage to the brink'Woke to blame for Louvre robbery': Female museum security chief accused of being a'diversity hire' comes under fire as politicians say heist has made France'the laughing stock of the world' Bombshell twist in Nicole Kidman and Keith Urban's divorce: 'She'd get back with him in a heartbeat,' says insider who's known her for years - as her inner circle reacts to'girlfriend' rumours Bella Hadid under fire over'offensive' social media posts she made as a teenager: 'Should've known better' Ellen Greenberg's parents reveal harrowing final phone call with daughter's ex fiancé after shock suicide ruling The new drug obsessions of the posh'wines and lines' mums: They scoff at cocaine now - but these three vices are the talk of the private school gate: JANA HOCKING Channel your inner John Wayne! 'Tough guy' walk used by western movie heroes makes you appear more powerful When it comes to swagger, nobody does it quite like John Wayne. His distinctive wide-based walk helped solidify his'tough guy' persona that became iconic in his western films.

You are on slide 3 of chapter 7. Use right arrow to continue. Alternatively, use the open square bracket key and close square bracket key to navigate, and disable left arrow and right arrow key navigation.