Large language models (LLMs) have become indispensable, but the most celebrated efficiency methods -- mixture-of-experts (MoE), speculative decoding, and complex retrieval-augmented generation (RAG) -- were built for hyperscale providers with vast infrastructure and elite teams. Outside that context, their benefits collapse into overhead, fragility, and wasted carbon. The result is that a handful of Big Tech companies benefit, while thousands of hospitals, schools, governments, and enterprises are left without viable options. We argue that the next frontier is not greater sophistication at scale, but robust simplicity: efficiency that thrives under modest resources and minimal expertise. We propose a new research agenda: retrofitting pretrained models with more efficient architectures without retraining, inventing lightweight fine-tuning that preserves alignment, making reasoning economical despite long chains of thought, enabling dynamic knowledge management without heavy RAG pipelines, and adopting Overhead-Aware Efficiency (OAE) as a standard benchmark. By redefining efficiency to include adoption cost, sustainability, and fairness, we can democratize LLM deployment -- ensuring that optimization reduces inequality and carbon waste rather than amplifying them.

The integration of artificial intelligence (AI) into video lecture production has the potential to transform higher education by streamlining content creation and enhancing accessibility. This paper investigates a semi -automated workflow that combines Google Gemini for script generation, Amazon Polly for voice synthesis, and Microsoft PowerPoint for video assembly. Unlike fully automated text -to -video platforms, this hybrid approach preserves pedagogical intent while ensuring script -slide synchronization, narrative coherence, and customization. Case studies demonstrate the effectiveness of Gemini in generating accurate and context - sensitive scripts for visually rich academic presentations, while Polly provides natural - sounding narration with controllable pac ing. A two-course pilot study was conducted to evaluate AI -generated instructional videos (AIIV) against human instructional videos (HIV). Both qualitative and quantitative results indicate that AIIVs are comparable to HIVs in terms of learning outcomes, w ith students reporting high levels of clarity, coherence, and usability. However, limitations remain, particularly regarding audio quality and the absence of human - like avatars. The findings suggest that AI - assisted video production can reduce instructor workload, improve scalability, and deliver effective learning resources, while future improvements in synthetic voices and avatars may further enhance learner engagement.

Developing intelligent agents that possess human-level intelligence is a key goal in the field of human-computer interaction (HCI) and general artificial intelligence[2]. A crucial aspect of achieving this goal is the incorporation of emotional intelligence, which is essential for human cognition and social interaction, into these intelligent agents. Emotional intelligence encompasses three interrelated capabilities: 1) emotion understanding, which involves accurately detecting and understanding affective signals, such as recognizing individuals' emotional states during interactions; 2) emotion elicitation and experiences, which refers to interpreting the causes, context, and implications of emotions for both the individual and the interaction; and 3) emotion expression, which encompasses the capacity to generate, modulate, and convey appropriate emotional responses in a socially meaningful manner. Affective Computing, coined by Rosalind Picard [1], emerged as a discipline dedicated to equipping machines with emotional intelligence, enabling them to recognize, interpret, and respond to human emotions. By embedding emotional intelligence into intelligent agents, affective computing facilitates more naturalistic, adaptive, and socially competent interactions, which in turn enhances user trust, engagement, and satisfaction [209]. Such emotionally intelligent systems not only improve usability but also enable advanced functionalities, including personalized assistance, empathetic dialogue, and context-aware decision-making. In Figure 1, an overview of the emotional intelligence capabilities in intelligent agents is presented. The process of emotional intelligence begins with analyzing the emotional aspects of the user input, enabling the agent to identify the user's affective state during interactions [259][306]. The next step is affective cognition, where the agent evaluates the observed emotional events using cognitive mental states to ensure accurate interpretation.

The development of web-based geospatial dashboards for risk analysis and decision support is often challenged by the difficulty in visualization of big, multi-dimensional environmental data, implementation complexity, and limited automation. We introduce a generative AI framework that harnesses Large Language Models (LLMs) to automate the creation of interactive geospatial dashboards from user-defined inputs including UI wireframes, requirements, and data sources. By incorporating a structured knowledge graph, the workflow embeds domain knowledge into the generation process and enable accurate and context-aware code completions. A key component of our approach is the Context-Aware Visual Prompting (CAVP) mechanism, which extracts encodes and interface semantics from visual layouts to guide LLM driven generation of codes. The new framework also integrates a self-validation mechanism that uses an agent-based LLM and Pass@k evaluation alongside semantic metrics to assure output reliability. Dashboard snippets are paired with data visualization codebases and ontological representations, enabling a pipeline that produces scalable React-based completions using the MVVM architectural pattern. Our results demonstrate improved performance over baseline approaches and expanded functionality over third party platforms, while incorporating multi-page, fully functional interfaces. We successfully developed a framework to implement LLMs, demonstrated the pipeline for automated code generation, deployment, and performed chain-of-thought AI agents in self-validation. This integrative approach is guided by structured knowledge and visual prompts, providing an innovative geospatial solution in enhancing risk analysis and decision making.

Large language models (LLMs) are increasingly used to answer high-stakes study-abroad questions about admissions, visas, scholarships, and eligibility. Yet it remains unclear how reliably they advise students, and how often otherwise helpful answers drift into unsupported claims (``hallucinations''). This work provides a clear, domain-grounded overview of how current LLMs behave in this setting. Using realistic questions set drawn from ApplyBoard's advising workflows -- an EdTech platform that supports students from discovery to enrolment -- we evaluate two essentials side by side: accuracy (is the information correct and complete?) and hallucination (does the model add content not supported by the question or domain evidence). These questions are categorized by domain scope which can be a single-domain or multi-domain -- when it must integrate evidence across areas such as admissions, visas, and scholarships. To reflect real advising quality, we grade answers with a simple rubric which is correct, partial, or wrong. The rubric is domain-coverage-aware: an answer can be partial if it addresses only a subset of the required domains, and it can be over-scoped if it introduces extra, unnecessary domains; both patterns are captured in our scoring as under-coverage or reduced relevance/hallucination. We also report measures of faithfulness and answer relevance, alongside an aggregate hallucination score, to capture relevance and usefulness. All models are tested with the same questions for a fair, head-to-head comparison. Our goals are to: (1) give a clear picture of which models are most dependable for study-abroad advising, (2) surface common failure modes -- where answers are incomplete, off-topic, or unsupported, and (3) offer a practical, reusable protocol for auditing LLMs before deployment in education and advising contexts.

The increasing trust in large language models (LLMs), especially in the form of chatbots, is often undermined by the lack of their extrinsic evaluation. This holds particularly true in nutrition, where randomised controlled trials (RCTs) are the gold standard, and experts demand them for evidence-based deployment. LLMs have shown promising results in this field, but these are limited to intrinsic setups. We address this gap by running the first RCT involving LLMs for nutrition. We augment a rule-based chatbot with two LLM-based features: (1) message rephrasing for conversational variety and engagement, and (2) nutritional counselling through a fine-tuned model. In our seven-week RCT (n=81), we compare chatbot variants with and without LLM integration. We measure effects on dietary outcome, emotional well-being, and engagement. Despite our LLM-based features performing well in intrinsic evaluation, we find that they did not yield consistent benefits in real-world deployment. These results highlight critical gaps between intrinsic evaluations and real-world impact, emphasising the need for interdisciplinary, human-centred approaches.\footnote{We provide all of our code and results at: \\ \href{https://github.com/saeshyra/diet-chatbot-trial}{https://github.com/saeshyra/diet-chatbot-trial}}

The Adam optimizer is a cornerstone of modern deep learning, yet the empirical necessity of each of its individual components is often taken for granted. This paper presents a focused investigation into the role of bias-correction, a feature whose contribution remains poorly understood. Through a series of systematic ablations on vision and language modelling tasks, we demonstrate that the conventional wisdom surrounding bias correction is misleading. In particular, we demonstrate that in the optimal hyper-parameter configuration, the inclusion of bias correction leads to no improvement in final test performance. Moreover, unless appropriate learning rate scheduling is implemented, the inclusion of bias correction can sometimes be detrimental to performance. We further reinterpret bias correction as a form of implicit learning rate scheduling whose behaviour is strongly dependent on the choice of smoothing hyper-parameters $β_1, β_2 \in [0,1)$. Our findings challenge the universal inclusion of this component.

Molecule generation using generative AI is vital for drug discovery, yet class-specific datasets often contain fewer than 100 training examples. While fragment-based models handle limited data better than atom-based approaches, existing heuristic fragmentation limits diversity and misses key fragments. Additionally, model tuning typically requires slow, indirect collaboration between medicinal chemists and AI engineers. We introduce FRAGMENTA, an end-to-end framework for drug lead optimization comprising: 1) a novel generative model that reframes fragmentation as a "vocabulary selection" problem, using dynamic Q-learning to jointly optimize fragmentation and generation; and 2) an agentic AI system that refines objectives via conversational feedback from domain experts. This system removes the AI engineer from the loop and progressively learns domain knowledge to eventually automate tuning. In real-world cancer drug discovery experiments, FRAGMENTA's Human-Agent configuration identified nearly twice as many high-scoring molecules as baselines. Furthermore, the fully autonomous Agent-Agent system outperformed traditional Human-Human tuning, demonstrating the efficacy of agentic tuning in capturing expert intent.

Reasoning based on Large Language Models (LLMs) has garnered increasing attention due to outstanding performance of these models in mathematical and complex logical tasks. Beginning with the Chain-of-Thought (CoT) prompting technique, numerous reasoning methods have emerged that decompose problems into smaller, sequential steps (or thoughts). However, existing reasoning models focus on conventional problem-solving and do not necessarily generate creative solutions by ``creative reasoning''. In domains where the solution space is expansive and conventional solutions are suboptimal, such as drug discovery or business strategization, creative reasoning to discover innovative solutions is crucial. To address this gap, first we introduce a computational framework for creative reasoning inspired by established cognitive science principles. With this framework, we propose three core creative reasoning paradigms, namely, \textit{combinational}, \textit{exploratory}, and \textit{transformative} reasoning, where each offers specific directions for systematic exploration of the universe of thoughts to generate creative solutions. Next, to materialize this framework using LLMs, we introduce the \textit{Universe of Thoughts} (or \textit{UoT}, for short), a novel set of methods to implement the aforementioned three creative processes. Finally, we introduce three novel tasks that necessitate creative problem-solving, along with an evaluation benchmark to assess creativity from three orthogonal perspectives: feasibility as constraint, and utility and novelty as metrics. With a comparative analysis against the state-of-the-art (SOTA) reasoning techniques as well as representative commercial models with reasoning capability, we show that UoT demonstrates superior performance in creative reasoning.

Normalizing flows (NFs) are end-to-end likelihood-based generative models for continuous data, and have recently regained attention with encouraging progress on image generation. Yet in the video generation domain, where spatiotemporal complexity and computational cost are substantially higher, state-of-the-art systems almost exclusively rely on diffusion-based models. In this work, we revisit this design space by presenting STARFlow-V, a normalizing flow-based video generator with substantial benefits such as end-to-end learning, robust causal prediction, and native likelihood estimation. Building upon the recently proposed STARFlow, STARFlow-V operates in the spatiotemporal latent space with a global-local architecture which restricts causal dependencies to a global latent space while preserving rich local within-frame interactions. This eases error accumulation over time, a common pitfall of standard autoregressive diffusion model generation. Additionally, we propose flow-score matching, which equips the model with a light-weight causal denoiser to improve the video generation consistency in an autoregressive fashion. To improve the sampling efficiency, STARFlow-V employs a video-aware Jacobi iteration scheme that recasts inner updates as parallelizable iterations without breaking causality. Thanks to the invertible structure, the same model can natively support text-to-video, image-to-video as well as video-to-video generation tasks. Empirically, STARFlow-V achieves strong visual fidelity and temporal consistency with practical sampling throughput relative to diffusion-based baselines. These results present the first evidence, to our knowledge, that NFs are capable of high-quality autoregressive video generation, establishing them as a promising research direction for building world models. Code and generated samples are available at https://github.com/apple/ml-starflow.