Language models (LMs) are susceptible to in-context reward hacking, where they exploit flaws in tainted or faulty written specifications or rubrics to achieve high scores without fulfilling the user's true intent. We introduce Specification Self-Correction (SSC), a novel, test-time framework that enables an LM to identify and correct flaws within its own guiding specification. SSC employs a multi-step inference process where the model first generates a response based on a potentially tainted specification, critiques its output, and then revises the specification itself to remove the exploitable loophole. A final, more robust response is then generated using this self-corrected specification. Across experiments spanning creative writing and agentic coding tasks with several LMs, we demonstrate that while models initially game tainted specifications in 50-70\% of cases, the SSC process reduces this vulnerability by over 90\%. This dynamic repair occurs at inference time, requires no weight modification, and leads to more robustly aligned model behavior. Code at https://github.com/vicgalle/specification-self-correction .

A curated dataset of Guitar Pro tablature files (.gp5 format), tailored for tasks involving guitar music generation, sequence modeling, and performance-aware learning is provided. The dataset is derived from MIDI notes in MAESTRO and GiantMIDI which have been adapted into rhythm guitar tracks. These tracks are further processed to include a variety of expression settings typical of guitar performance, such as bends, slides, vibrato, and palm muting, to better reflect the nuances of real-world guitar playing.

As AI-powered image generation improves, a key question is how well human beings can differentiate between "real" and AI-generated or modified images. Using data collected from the online game "Real or Not Quiz.", this study investigates how effectively people can distinguish AI-generated images from real ones. Participants viewed a randomized set of real and AI-generated images, aiming to identify their authenticity. Analysis of approximately 287,000 image evaluations by over 12,500 global participants revealed an overall success rate of only 62\%, indicating a modest ability, slightly above chance. Participants were most accurate with human portraits but struggled significantly with natural and urban landscapes. These results highlight the inherent challenge humans face in distinguishing AI-generated visual content, particularly images without obvious artifacts or stylistic cues. This study stresses the need for transparency tools, such as watermarks and robust AI detection tools to mitigate the risks of misinformation arising from AI-generated content

We present VIBE, a two-stage Transformer that fuses multi-modal video, audio, and text features to predict fMRI activity. Representations from open-source models (Qwen2.5, BEATs, Whisper, SlowFast, V-JEPA) are merged by a modality-fusion transformer and temporally decoded by a prediction transformer with rotary embeddings. Trained on 65 hours of movie data from the CNeuroMod dataset and ensembled across 20 seeds, VIBE attains mean parcel-wise Pearson correlations of 0.3225 on in-distribution Friends S07 and 0.2125 on six out-of-distribution films. An earlier iteration of the same architecture obtained 0.3198 and 0.2096, respectively, winning Phase-1 and placing second overall in the Algonauts 2025 Challenge.

This is a post-peer-review version of an article published in Applied Soft Computing . This manuscript is made available under the Elsevier user license. Published in: Applied Soft Computing, 2025. Abstract Over the past decade, recommender systems have experienced a surge in popularity. Despite notable progress, they grapple with challenging issues, such as high data dimensionality and sparseness. Representing users and items as low-dimensional embeddings learned via neural networks has become a leading solution. However, while recent studies show promising results, many approaches rely on complex architectures or require content data, which may not always be available. This paper presents Interact2Vec, a novel neural network-based model that simultaneously learns distributed embeddings for users and items while demanding only implicit feedback. The model employs state-of-the-art strategies that natural language processing models commonly use to optimize the training phase and enhance the final embeddings. Two types of experiments were conducted regarding the extrinsic and intrinsic quality of the model. In the former, we benchmarked the recommendations generated by Interact2Vec's embeddings in a top-N ranking problem, comparing them with six other recommender algorithms. The model achieved the second or third-best results in 30% of the datasets, being competitive with other recommenders, and has proven to be very efficient with an average training time reduction of 274% compared to other embedding-based models. Later, we analyzed the intrinsic quality of the embeddings through similarity tables. Our findings suggest that Interact2Vec can achieve promising results, especially on the extrinsic task, and is an excellent embedding-generator model for scenarios of scarce computing resources, enabling the learning of item and user embeddings simultaneously and efficiently. Keywords: recommender systems, collaborative filtering, distributed vector representation, embeddings1. Introduction As technology advances and content becomes increasingly accessible, a growing volume of data is generated and shared daily. While this has led to numerous advancements in the modern world, the sheer magnitude of information means that only a fraction is relevant to individual users.

The growing popularity of large language models has raised concerns regarding the potential to misuse AI-generated text (AIGT). It becomes increasingly critical to establish an excellent AIGT detection method with high generalization and robustness. However, existing methods either focus on model generalization or concentrate on robustness. The unified mechanism, to simultaneously address the challenges of generalization and robustness, is less explored. In this paper, we argue that robustness can be view as a specific form of domain shift, and empirically reveal an intrinsic mechanism for model generalization of AIGT detection task. Then, we proposed a novel AIGT detection method (DP-Net) via dynamic perturbations introduced by a reinforcement learning with elaborated reward and action. Experimentally, extensive results show that the proposed DP-Net significantly outperforms some state-of-the-art AIGT detection methods for generalization capacity in three cross-domain scenarios. Meanwhile, the DP-Net achieves best robustness under two text adversarial attacks. The code is publicly available at https://github.com/CAU-ISS-Lab/AIGT-Detection-Evade-Detection/tree/main/DP-Net.

Fox News anchor Bret Baier examines the U.S. power supply on'Special Report.' A new study shows that a third of American teenagers prefer chatting with artificial intelligence companions over having real friends. Common Sense Media's report, titled "Talk, Trust, and Trade-Offs: How and Why Teens Use AI Companions," revealed that the most widespread uses of AI are aged 13-17. The report explained further that the "use of AI companions is not a niche interest, but rather mainstream teen behavior" and that teens "find conversations with AI companions to be as satisfying or more satisfying than those with real-life friends." Common Sense Media's report, titled "Talk, Trust, and Trade-Offs: How and Why Teens Use AI Companions," revealed that the most widespread uses of AI are aged 13-17.

Psychedelic rock band The Velvet Sundown has over a million monthly listeners on Spotify and earns thousands of dollars every month. However, the catch is that it's not a traditional band at all. It's mostly made by artificial intelligence. Their Spotify bio confirms that the group is a synthetic music project, guided by human creative direction but composed, voiced, and visualized using AI. This is a sign of where music may be headed.

Breakthroughs, discoveries, and DIY tips sent every weekday. Since its debut in 2007, the Amazon Kindle has changed reading habits for millions of people. E-readers aren't for everyone, but they mean you can take hundreds of books with you on one device, look up words instantly, get new reading material in seconds, and take advantage of all the other benefits of digital reading. The Amazon Kindle Store is stocked with titles you can purchase, but if you'd rather not spend any money to expand your library, you don't have to. Here are some ways you can load up your Amazon Kindle with free e-books.

MikeroweWorks Foundation founder Mike Rowe joins'The Brian Kilmeade Show' to discuss how AI and robots threaten white-collar jobs, as the nation faces a need for blue-collar workers. 'UNDENIABLE': Mike Rowe is sounding the alarm about the future of white and blue-collar jobs, and is urging young Americans to rethink their career choices due to threats from artificial intelligence. 'ALL IN': President Donald Trump is going all in on artificial intelligence, with a top Meta executive voicing strong support for his bold strategy. Speaking at a tech summit in Washington, Trump outlined his vision for a future driven by American innovation and secured by global artificial intelligence leadership. INNOVATION BOOST: Nvidia CEO Jensen Huang said in an interview Wednesday that the Trump administration's artificial intelligence plan is poised to boost innovation and AI deployment in the U.S. IMMINENT CRISIS: OpenAI CEO Sam Altman warned Wall Street executives that bad actors could exploit digital voice ID authentication to defraud consumers by enabling large money transfers, creating what he describes as an imminent fraud crisis. STARGATE OPENS: Oracle and OpenAI have inked an agreement to further develop the Stargate project as part of a broader pledge to expand Artificial Intelligence (AI) infrastructure in the United States.