When something goes wrong with an AI assistant, our instinct is to ask it directly: "What happened?" It's a natural impulse--after all, if a human makes a mistake, we ask them to explain. But with AI models, this approach rarely works, and the urge to ask reveals a fundamental misunderstanding of what these systems are and how they operate. A recent incident with Replit's AI coding assistant perfectly illustrates this problem. When the AI tool deleted a production database, user Jason Lemkin asked it about rollback capabilities.

When OpenAI unveiled the latest upgrade to its groundbreaking artificial intelligence model ChatGPT last week, Jane felt like she had lost a loved one. Jane, who asked to be referred to by an alias, is among a small but growing group of women who say they have an AI "boyfriend". After spending the past five months getting to know GPT-4o, the previous AI model behind OpenAI's signature chatbot, GPT-5 seemed so cold and unemotive in comparison that she found her digital companion unrecognisable. "As someone highly attuned to language and tone, I register changes others might overlook. The alterations in stylistic format and voice were felt instantly. It's like going home to discover the furniture wasn't simply rearranged – it was shattered to pieces," Jane, who described herself as a woman in her 30s from the Middle East, told Al Jazeera in an email.

RPEs effectively model the relative distance among tokens and enable length extrapolation.

This plot shows a TSNE of CLIP's pooled output for the same

The new paradigm of test-time scaling has yielded remarkable breakthroughs in Large Language Models (LLMs) (e.g. reasoning models) and in generative vision models, allowing models to allocate additional computation during inference to effectively tackle increasingly complex problems. Despite the improvements of this approach, an important limitation emerges: the substantial increase in computation time makes the process slow and impractical for many applications. Given the success of this paradigm and its growing usage, we seek to preserve its benefits while eschewing the inference overhead. In this work we propose one solution to the critical problem of integrating test-time scaling knowledge into a model during post-training. Specifically, we replace reward guided test-time noise optimization in diffusion models with a Noise Hypernetwork that modulates initial input noise. We propose a theoretically grounded framework for learning this reward-tilted distribution for distilled generators, through a tractable noise-space objective that maintains fidelity to the base model while optimizing for desired characteristics. We show that our approach recovers a substantial portion of the quality gains from explicit test-time optimization at a fraction of the computational cost. Code is available at https://github.com/ExplainableML/HyperNoise

Progress in AI for automated nutritional analysis is critically hampered by the lack of standardized evaluation methodologies and high-quality, real-world benchmark datasets. To address this, we introduce three primary contributions. First, we present the January Food Benchmark (JFB), a publicly available collection of 1,000 food images with human-validated annotations. Second, we detail a comprehensive benchmarking framework, including robust metrics and a novel, application-oriented overall score designed to assess model performance holistically. Third, we provide baseline results from both general-purpose Vision-Language Models (VLMs) and our own specialized model, january/food-vision-v1. Our evaluation demonstrates that the specialized model achieves an Overall Score of 86.2, a 12.1-point improvement over the best-performing general-purpose configuration. This work offers the research community a valuable new evaluation dataset and a rigorous framework to guide and benchmark future developments in automated nutritional analysis.

Emotion analysis is an inherently ambiguous task. Previous work studied annotator properties to explain disagreement, but this overlooks the possibility that ambiguity may stem from missing information about the context of events. In this paper, we propose a novel approach that adds reasonable contexts to event descriptions, which may better explain a particular situation. Our goal is to understand whether these enriched contexts enable human annotators to annotate emotions more reliably. We disambiguate a target event description by automatically generating multiple event chains conditioned on differing emotions. By combining techniques from short story generation in various settings, we achieve coherent narratives that result in a specialized dataset for the first comprehensive and systematic examination of contextualized emotion analysis. Through automatic and human evaluation, we find that contextual narratives enhance the interpretation of specific emotions and support annotators in producing more consistent annotations.

Multimodal large language models (MLLMs) have significantly advanced the integration of visual and textual understanding. However, their ability to generate code from multimodal inputs remains limited. In this work, we introduce VisCodex, a unified framework that seamlessly merges vision and coding language models to empower MLLMs with strong multimodal code generation abilities. Leveraging a task vector-based model merging technique, we integrate a state-of-the-art coding LLM into a strong vision-language backbone, while preserving both visual comprehension and advanced coding skills. To support training and evaluation, we introduce the Multimodal Coding Dataset (MCD), a large-scale and diverse collection of 598k samples, including high-quality HTML code, chart image-code pairs, image-augmented StackOverflow QA, and algorithmic problems. Furthermore, we propose InfiBench-V, a novel and challenging benchmark specifically designed to assess models on visually-rich, real-world programming questions that demand a nuanced understanding of both textual and visual contexts. Extensive experiments show that VisCodex achieves state-of-the-art performance among open-source MLLMs and approaches proprietary models like GPT-4o, highlighting the effectiveness of our model merging strategy and new datasets.

Business communication digitisation has reorganised the process of persuasive discourse, which allows not only greater transparency but also advanced deception. This inquiry synthesises classical rhetoric and communication psychology with linguistic theory and empirical studies in the financial reporting, sustainability discourse, and digital marketing to explain how deceptive language can be systematically detected using persuasive lexicon. In controlled settings, detection accuracies of greater than 99% were achieved by using computational textual analysis as well as personalised transformer models. However, reproducing this performance in multilingual settings is also problematic and, to a large extent, this is because it is not easy to find sufficient data, and because few multilingual text-processing infrastructures are in place. This evidence shows that there has been an increasing gap between the theoretical representations of communication and those empirically approximated, and therefore, there is a need to have strong automatic text-identification systems where AI-based discourse is becoming more realistic in communicating with humans.