Large Language Models (LLMs) such as OpenAI's GPT-4 and Meta's LLaMA offer a promising approach for scalable personality assessment from open-ended language. However, inferring personality traits remains challenging, and earlier work often relied on synthetic data or social media text lacking psychometric validity. We introduce a real-world benchmark of 555 semi-structured interviews with BFI-10 self-report scores for evaluating LLM-based personality inference. Three state-of-the-art LLMs (GPT-4.1 Mini, Meta-LLaMA, and DeepSeek) were tested using zero-shot prompting for BFI-10 item prediction and both zero-shot and chain-of-thought prompting for Big Five trait inference. All models showed high test-retest reliability, but construct validity was limited: correlations with ground-truth scores were weak (max Pearson's $r = 0.27$), interrater agreement was low (Cohen's $κ< 0.10$), and predictions were biased toward moderate or high trait levels. Chain-of-thought prompting and longer input context modestly improved distributional alignment, but not trait-level accuracy. These results underscore limitations in current LLM-based personality inference and highlight the need for evidence-based development for psychological applications.

Parameter efficient fine tuning (PEFT) is a versatile and extensible approach for adapting a Large Language Model (LLM) for newer tasks. One of the most prominent PEFT approaches, Low Rank Adaptation (LoRA), primarily focuses on adjusting the attention weight matrices within individual decoder blocks of a Generative Pre trained Transformer (GPT2). In contrast, we introduce Solo Connection a novel method that adapts the representation at the decoder-block level rather than modifying individual weight matrices. Not only does Solo Connection outperform LoRA on E2E natural language generation benchmarks, but it also reduces the number of trainable parameters by 59% relative to LoRA and by more than 99% compared to full fine-tuning of GPT2, an early version of Large Language Models (LLMs). Solo Connection is also motivated by homotopy theory: we introduce a trainable linear transformation that gradually interpolates between a zero vector and the task-specific representation, enabling smooth and stable adaptation over time. While skip connections in the original 12 layer GPT2 are typically confined to individual decoder blocks, subsequent GPT2 variants scale up to 48 layers, and even larger language models can include 128 or more decoder blocks. These expanded architectures underscore the need to revisit how skip connections are employed during fine-tuning. This paper focuses on long skip connections that link outputs of different decoder blocks, potentially enhancing the model's ability to adapt to new tasks while leveraging pre-trained knowledge.

Brain foundation models represent a new frontier in AI: instead of processing text or images, these models interpret real-time neural signals from EEG, fMRI, and other neurotechnologies. When integrated with brain-computer interfaces (BCIs), they may enable transformative applications-from thought controlled devices to neuroprosthetics-by interpreting and acting on brain activity in milliseconds. However, these same systems pose unprecedented risks, including the exploitation of subconscious neural signals and the erosion of cognitive liberty. Users cannot easily observe or control how their brain signals are interpreted, creating power asymmetries that are vulnerable to manipulation. This paper proposes embedding fiduciary duties-loyalty, care, and confidentiality-directly into BCI-integrated brain foundation models through technical design. Drawing on legal traditions and recent advancements in AI alignment techniques, we outline implementable architectural and governance mechanisms to ensure these systems act in users' best interests. Placing brain foundation models on a fiduciary footing is essential to realizing their potential without compromising self-determination.

Language models have become increasingly powerful tools for formal mathematical reasoning. However, most existing approaches rely exclusively on either large general-purpose models or smaller specialized models, each with distinct limitations, while training specialized large models still requires significant computational resources. This paper introduces ProofCompass, a novel hybrid methodology that achieves remarkable computational efficiency by strategically guiding existing specialized prover methods, such as DeepSeek-Prover-v1.5-RL (DSP-v1.5) with a Large Language Model (LLM) without requiring additional model training. The LLM provides natural language proof strategies and analyzes failed attempts to select intermediate lemmas, enabling effective problem decomposition. On the miniF2F benchmark, ProofCompass demonstrates substantial resource efficiency: it outperforms DSP-v1.5 ($54.9\% \rightarrow 55.3\%$) while using 25x fewer attempts ($3200 \rightarrow 128$). Our synergistic approach paves the way for simultaneously improving computational efficiency and accuracy in formal theorem proving.

Recent methods for customizing Large Vision Language Models (LVLMs) for domain-specific tasks have shown promising results in scientific chart comprehension. However, existing approaches face two major limitations: First, they rely on paired data from only a few chart types, limiting generalization to wide range of chart types. Secondly, they lack targeted pre-training for chart-data alignment, which hampers the model's understanding of underlying data. In this paper, we introduce ChartScope, an LVLM optimized for in-depth chart comprehension across diverse chart types. We propose an efficient data generation pipeline that synthesizes paired data for a wide range of chart types, along with a novel Dual-Path training strategy that enabling the model to succinctly capture essential data details while preserving robust reasoning capabilities by incorporating reasoning over the underlying data. Lastly, we establish ChartDQA, a new benchmark for evaluating not only question-answering at different levels but also underlying data understanding. Experimental results demonstrate that ChartScope significantly enhances comprehension on a wide range of chart types. The code and data are available at https://davidhalladay.github.io/chartscope_demo.

The rapid development of autonomous web agents powered by Large Language Models (LLMs), while greatly elevating efficiency, exposes the frontier risk of taking unintended or harmful actions. This situation underscores an urgent need for effective safety measures, akin to access controls for human users. To address this critical challenge, we introduce WebGuard, the first comprehensive dataset designed to support the assessment of web agent action risks and facilitate the development of guardrails for real-world online environments. In doing so, WebGuard specifically focuses on predicting the outcome of state-changing actions and contains 4,939 human-annotated actions from 193 websites across 22 diverse domains, including often-overlooked long-tail websites. These actions are categorized using a novel three-tier risk schema: SAFE, LOW, and HIGH. The dataset includes designated training and test splits to support evaluation under diverse generalization settings. Our initial evaluations reveal a concerning deficiency: even frontier LLMs achieve less than 60% accuracy in predicting action outcomes and less than 60% recall in lagging HIGH-risk actions, highlighting the risks of deploying current-generation agents without dedicated safeguards. We therefore investigate fine-tuning specialized guardrail models using WebGuard. We conduct comprehensive evaluations across multiple generalization settings and find that a fine-tuned Qwen2.5VL-7B model yields a substantial improvement in performance, boosting accuracy from 37% to 80% and HIGH-risk action recall from 20% to 76%. Despite these improvements, the performance still falls short of the reliability required for high-stakes deployment, where guardrails must approach near-perfect accuracy and recall.

Materials discovery relies on high-throughput, high-fidelity simulation techniques such as Density Functional Theory (DFT), which require years of training, extensive parameter fine-tuning and systematic error handling. To address these challenges, we introduce the DFT-based Research Engine for Agentic Materials Screening (DREAMS), a hierarchical, multi-agent framework for DFT simulation that combines a central Large Language Model (LLM) planner agent with domain-specific LLM agents for atomistic structure generation, systematic DFT convergence testing, High-Performance Computing (HPC) scheduling, and error handling. In addition, a shared canvas helps the LLM agents to structure their discussions, preserve context and prevent hallucination. We validate DREAMS capabilities on the Sol27LC lattice-constant benchmark, achieving average errors below 1\% compared to the results of human DFT experts. Furthermore, we apply DREAMS to the long-standing CO/Pt(111) adsorption puzzle, demonstrating its long-term and complex problem-solving capabilities. The framework again reproduces expert-level literature adsorption-energy differences. Finally, DREAMS is employed to quantify functional-driven uncertainties with Bayesian ensemble sampling, confirming the Face Centered Cubic (FCC)-site preference at the Generalized Gradient Approximation (GGA) DFT level. In conclusion, DREAMS approaches L3-level automation - autonomous exploration of a defined design space - and significantly reduces the reliance on human expertise and intervention, offering a scalable path toward democratized, high-throughput, high-fidelity computational materials discovery.

--Generative AI is gaining increasing attention in software engineering, where testing remains an indispensable reliability mechanism. According to the widely adopted testing pyramid, unit tests constitute the majority of test cases and are often schematic, requiring minimal domain expertise. Automatically generating such tests under the supervision of software engineers can significantly enhance productivity during the development phase of the software lifecycle. This paper investigates the impact of code context and prompting strategies on the quality and adequacy of unit tests generated by various large language models (LLMs) across several families. The results show that including docstrings notably improves code adequacy, while further extending context to the full implementation yields definitely smaller gains. Notably, the chain-of-thought prompting strategy -- applied even to'reasoning' models -- achieves the best results, with up to 96.3% branch coverage, a 57% average mutation score, and near-perfect compilation success rate. Among the evaluated models, M5 (Gemini 2.5 Pro) demonstrated superior performance in both mutation score and branch coverage being still in top in terms of compilation success rate. ECENT years have brought significant advancements in artificial intelligence (AI), particularly in the areas of performance and productivity enhancement. However, AI -- and particularly large language models (LLMs) -- still suffer from several weaknesses. Among them, convincing but senseless content generation ('hallucination'), safety misalignment ('ethicality') [1], unfairness [2], and limited processing context are the most critical. In spite of these restrictions, and bearing in mind the limited and merely apparent creativity of LLMs [3], they have become versatile tools already widely used across a variety of domains (creative industries [4], entertainment, reporting, and software engineering [5] are just cases in point) for multiple tasks.

Unlocking the potential of nanomaterials in medicine and environmental science hinges on understanding their interactions with proteins, a complex decision space where AI is poised to make a transformative impact. However, progress has been hindered by limited datasets and the restricted generalizability of existing models. Here, we propose NanoPro-3M, the largest nanomaterial-protein interaction dataset to date, comprising over 3.2 million samples and 37,000 unique proteins. Leveraging this, we present NanoProFormer, a foundational model that predicts nanomaterial-protein affinities through multimodal representation learning, demonstrating strong generalization, handling missing features, and unseen nanomaterials or proteins. We show that multimodal modeling significantly outperforms single-modality approaches and identifies key determinants of corona formation. Furthermore, we demonstrate its applicability to a range of downstream tasks through zero-shot inference and fine-tuning. Together, this work establishes a solid foundation for high-performance and generalized prediction of nanomaterial-protein interaction endpoints, reducing experimental reliance and accelerating various in vitro applications.

While Artificial Intelligence (AI) is not a new field, recent developments, especially with the release of generative tools like ChatGPT, have brought it to the forefront of the minds of industry workers and academic folk alike. There is currently much talk about AI and its ability to reshape many everyday processes as we know them through automation. It also allows users to expand their ideas by suggesting things they may not have thought of on their own and provides easier access to information. However, not all of the changes this technology will bring or has brought so far are positive; this is why it is extremely important for all modern people to recognize and understand the risks before using these tools and allowing them to cause harm. This work takes a position on better understanding many equity concerns and the spread of misinformation that result from new AI, in this case, specifically ChatGPT and deepfakes, and encouraging collaboration with law enforcement, developers, and users to reduce harm. Considering many academic sources, it warns against these issues, analyzing their cause and impact in fields including healthcare, education, science, academia, retail, and finance. Lastly, we propose a set of future-facing guidelines and policy considerations to solve these issues while still enabling innovation in these fields, this responsibility falling upon users, developers, and government entities.