Federated Learning (FL) enables decentralized, privacy-preserving model training but struggles to balance global generalization and local personalization due to non-identical data distributions across clients. Personalized Fine-Tuning (PFT), a popular post-hoc solution, fine-tunes the final global model locally but often overfits to skewed client distributions or fails under domain shifts. We propose adapting Linear Probing followed by full Fine-Tuning (LP-FT), a principled centralized strategy for alleviating feature distortion (Kumar et al., 2022), to the FL setting. Through systematic evaluation across seven datasets and six PFT variants, we demonstrate LP-FT's superiority in balancing personalization and generalization. Our analysis uncovers federated feature distortion, a phenomenon where local fine-tuning destabilizes globally learned features, and theoretically characterizes how LP-FT mitigates this via phased parameter updates. We further establish conditions (e.g., partial feature overlap, covariate-concept shift) under which LP-FT outperforms standard fine-tuning, offering actionable guidelines for deploying robust personalization in FL.

Modeling normal behavior in dynamic, nonlinear time series data is challenging for effective anomaly detection. Traditional methods, such as nearest neighbor and clustering approaches, often depend on rigid assumptions, such as a predefined number of reliable neighbors or clusters, which frequently break down in complex temporal scenarios. To address these limitations, we introduce the Granular-ball One-Class Network (GBOC), a novel approach based on a data-adaptive representation called Granular-ball Vector Data Description (GVDD). GVDD partitions the latent space into compact, high-density regions represented by granular-balls, which are generated through a density-guided hierarchical splitting process and refined by removing noisy structures. Each granular-ball serves as a prototype for local normal behavior, naturally positioning itself between individual instances and clusters while preserving the local topological structure of the sample set. During training, GBOC improves the compactness of representations by aligning samples with their nearest granular-ball centers. During inference, anomaly scores are computed based on the distance to the nearest granular-ball. By focusing on dense, high-quality regions and significantly reducing the number of prototypes, GBOC delivers both robustness and efficiency in anomaly detection. Extensive experiments validate the effectiveness and superiority of the proposed method, highlighting its ability to handle the challenges of time series anomaly detection.

Stock trading strategies play a critical role in investment. However, it is challenging to design a profitable strategy in a complex and dynamic stock market. In this paper, we propose an ensemble strategy that employs deep reinforcement schemes to learn a stock trading strategy by maximizing investment return. We train a deep reinforcement learning agent and obtain an ensemble trading strategy using three actor-critic based algorithms: Proximal Policy Optimization (PPO), Advantage Actor Critic (A2C), and Deep Deterministic Policy Gradient (DDPG). The ensemble strategy inherits and integrates the best features of the three algorithms, thereby robustly adjusting to different market situations. In order to avoid the large memory consumption in training networks with continuous action space, we employ a load-on-demand technique for processing very large data. We test our algorithms on the 30 Dow Jones stocks that have adequate liquidity. The performance of the trading agent with different reinforcement learning algorithms is evaluated and compared with both the Dow Jones Industrial Average index and the traditional min-variance portfolio allocation strategy. The proposed deep ensemble strategy is shown to outperform the three individual algorithms and two baselines in terms of the risk-adjusted return measured by the Sharpe ratio. This work is fully open-sourced at \href{https://github.com/AI4Finance-Foundation/Deep-Reinforcement-Learning-for-Automated-Stock-Trading-Ensemble-Strategy-ICAIF-2020}{GitHub}.

Safety-aligned large language models (LLMs) are becoming increasingly widespread, especially in sensitive applications where fairness is essential and biased outputs can cause significant harm. However, evaluating the fairness of models is a complex challenge, and approaches that do so typically utilize standard question-answer (QA) styled schemes. Such methods often overlook deeper issues by interpreting the model's refusal responses as positive fairness measurements, which creates a false sense of fairness. In this work, we introduce the concept of silenced biases, which are unfair preferences encoded within models' latent space and are effectively concealed by safety-alignment. Previous approaches that considered similar indirect biases often relied on prompt manipulation or handcrafted implicit queries, which present limited scalability and risk contaminating the evaluation process with additional biases. We propose the Silenced Bias Benchmark (SBB), which aims to uncover these biases by employing activation steering to reduce model refusals during QA. SBB supports easy expansion to new demographic groups and subjects, presenting a fairness evaluation framework that encourages the future development of fair models and tools beyond the masking effects of alignment training. We demonstrate our approach over multiple LLMs, where our findings expose an alarming distinction between models' direct responses and their underlying fairness issues.

The overall architecture of CFDT is shown in Figure 1. The base backbone is consistent with the network illustrated in the section of 3.1 Local-Global Cross Fusion. As shown by the red dotted lines in Figure 1, we use 100 det tokens as the additional input to perform self attention in the backbone. The det tokens dimension is also set as 256. Neck is a decoder-only modules, and there are 6 decoder layers in this neck.

On this episode of, guest Brian Merchant walks us through a historical framework he used to analyze whether AI fits the classic signs of an economic bubble--and what that means for all of us. Chatter about an AI bubble has been everywhere lately, and top tech companies like Google, Meta, and Microsoft have doubled down on their AI investments for 2026. But how have analysts in the past accurately identified forming tech bubbles? Hosts Michael Calore and Lauren Goode sit down with Brian Merchant, WIRED contributor and author of the newsletter to break down the four criteria some researchers have used in the past to understand and brace for the worst. Please help us improve by filling out our listener survey . Write to us at uncannyvalley@wired.com . You can always listen to this week's podcast through the audio player on this page, but if you want to subscribe for free to get every episode, here's how: If you're on an iPhone or iPad, open the app called Podcasts, or just tap this link . Hey Lauren, how are you doing? It's earnings season, so a lot of us on the business desk here at WIRED have been tuning into tech companies earnings reports and their earnings calls. And I guess that basically means it's CapEx season. Now that I'm a business desk reporter, I say CapEx. I throw it around at parties. But we are seeing a trend in how tech companies are sleeping on piles of money, but they aren't just sleeping on it. They're sharing big plans to spend on it, and especially to spend on AI infrastructure. And this is all partly what is fueling all of this talk about a bubble, which we touched on a little bit a couple of weeks ago with our colleague Molly Taft.

When you purchase through links in our articles, we may earn a small commission. Google's new AI service turns into your own private tutor With Guided Learning, Google Gemini turns into your own educational tutor. When ChatGPT launched three years ago, it shook the academic world to its core. Suddenly, students could have AI answer questions and even write essays. And because ChatGPT is so articulate, spotting cheaters became increasingly difficult.

As OpenAI expands in every direction, the new CEO of Applications is on a mission to make ChatGPT indispensable and lucrative. In case OpenAI's structure couldn't get any weirder--a nonprofit in charge of a for-profit that's become a public benefit corporation--it now has two CEOs. There's Sam Altman, chief executive of the whole company, who manages research and compute. And as of this summer, there's Fidji Simo, the former CEO of Instacart, who manages everything else. Simo hasn't been seen much at OpenAI's San Francisco office since she began as CEO of Applications in August. But her presence is felt at every level of the company--not least because she's heading up ChatGPT and basically every function that might make OpenAI money. Simo is dealing with a relapse of postural orthostatic tachycardia syndrome (POTS) that makes her prone to fainting if she stands for long periods of time. "Being present from 8 am to midnight every day, responding within five minutes, people feel like I'm there and that they can reach me immediately, that I jump on the phone within five minutes," she tells me. Employees confirm that this is true. OpenAI's famously Slack-driven culture can be overwhelming for new hires. Employees say she is often seen popping into channels and threads, sharing thoughts and asking questions.

Work done as a Research Fellow at Microsoft Research India.