Large Language Models (LLMs) have shown remarkable capabilities across various tasks, but their deployment in high-stake domains requires consistent performance across multiple interaction rounds. This paper introduces a comprehensive framework for evaluating and improving LLM response consistency, making three key contributions. First, we propose a novel Position-Weighted Consistency (PWC) score that captures both the importance of early-stage stability and recovery patterns in multi-turn interactions. Second, we present a carefully curated benchmark dataset spanning diverse domains and difficulty levels, specifically designed to evaluate LLM consistency under various challenging follow-up scenarios. Third, we introduce Confidence-Aware Response Generation (CARG), a framework that significantly improves response stability by incorporating model confidence signals into the generation process. Empirical results demonstrate that CARG significantly improves response stability without sacrificing accuracy, underscoring its potential for reliable LLM deployment in critical applications.

AI risks are typically framed around physical threats to humanity, a loss of control or an accidental error causing humanity's extinction. However, I argue in line with the gradual disempowerment thesis, that there is an underappreciated risk in the slow and irrevocable decline of human autonomy. As AI starts to outcompete humans in various areas of life, a tipping point will be reached where it no longer makes sense to rely on human decision-making, creativity, social care or even leadership. What may follow is a process of gradual de-skilling, where we lose skills that we currently take for granted. Traditionally, it is argued that AI will gain human skills over time, and that these skills are innate and immutable in humans. By contrast, I argue that humans may lose such skills as critical thinking, decision-making and even social care in an AGI world. The biggest threat to humanity is therefore not that machines will become more like humans, but that humans will become more like machines.

Policy gradient methods are one of the most successful methods for solving challenging reinforcement learning problems. However, despite their empirical successes, many SOTA policy gradient algorithms for discounted problems deviate from the theoretical policy gradient theorem due to the existence of a distribution mismatch. In this work, we analyze the impact of this mismatch on the policy gradient methods. Specifically, we first show that in the case of tabular parameterizations, the methods under the mismatch remain globally optimal. Then, we extend this analysis to more general parameterizations by leveraging the theory of biased stochastic gradient descent. Our findings offer new insights into the robustness of policy gradient methods as well as the gap between theoretical foundations and practical implementations.

Recently, a large amount of work has focused on improving large language models' (LLMs') performance on reasoning benchmarks such as math and logic. However, past work has largely assumed that tasks are well-defined. In the real world, queries to LLMs are often underspecified, only solvable through acquiring missing information. We formalize this as a constraint satisfaction problem (CSP) with missing variable assignments. Using a special case of this formalism where only one necessary variable assignment is missing, we can rigorously evaluate an LLM's ability to identify the minimal necessary question to ask and quantify axes of difficulty levels for each problem. We present QuestBench, a set of underspecified reasoning tasks solvable by asking at most one question, which includes: (1) Logic-Q: Logical reasoning tasks with one missing proposition, (2) Planning-Q: PDDL planning problems with initial states that are partially-observed, (3) GSM-Q: Human-annotated grade school math problems with one missing variable assignment, and (4) GSME-Q: a version of GSM-Q where word problems are translated into equations by human annotators. The LLM is tasked with selecting the correct clarification question(s) from a list of options. While state-of-the-art models excel at GSM-Q and GSME-Q, their accuracy is only 40-50% on Logic-Q and Planning-Q. Analysis demonstrates that the ability to solve well-specified reasoning problems may not be sufficient for success on our benchmark: models have difficulty identifying the right question to ask, even when they can solve the fully specified version of the problem. Furthermore, in the Planning-Q domain, LLMs tend not to hedge, even when explicitly presented with the option to predict ``not sure.'' This highlights the need for deeper investigation into models' information acquisition capabilities.

AI for software engineering has made remarkable progress recently, becoming a notable success within generative AI. Despite this, there are still many challenges that need to be addressed before automated software engineering reaches its full potential. It should be possible to reach high levels of automation where humans can focus on the critical decisions of what to build and how to balance difficult tradeoffs while most routine development effort is automated away. Reaching this level of automation will require substantial research and engineering efforts across academia and industry. In this paper, we aim to discuss progress towards this in a threefold manner. First, we provide a structured taxonomy of concrete tasks in AI for software engineering, emphasizing the many other tasks in software engineering beyond code generation and completion. Second, we outline several key bottlenecks that limit current approaches. Finally, we provide an opinionated list of promising research directions toward making progress on these bottlenecks, hoping to inspire future research in this rapidly maturing field.

Efficient nutrient management and precise fertilization are essential for advancing modern agriculture, particularly in regions striving to optimize crop yields sustainably. The AgroLens project endeavors to address this challenge by develop ing Machine Learning (ML)-based methodologies to predict soil nutrient levels without reliance on laboratory tests. By leveraging state of the art techniques, the project lays a foundation for acionable insights to improve agricultural productivity in resource-constrained areas, such as Africa. The approach begins with the development of a robust European model using the LUCAS Soil dataset and Sentinel-2 satellite imagery to estimate key soil properties, including phosphorus, potassium, nitrogen, and pH levels. This model is then enhanced by integrating supplementary features, such as weather data, harvest rates, and Clay AI-generated embeddings. This report details the methodological framework, data preprocessing strategies, and ML pipelines employed in this project. Advanced algorithms, including Random Forests, Extreme Gradient Boosting (XGBoost), and Fully Connected Neural Networks (FCNN), were implemented and finetuned for precise nutrient prediction. Results showcase robust model performance, with root mean square error values meeting stringent accuracy thresholds. By establishing a reproducible and scalable pipeline for soil nutrient prediction, this research paves the way for transformative agricultural applications, including precision fertilization and improved resource allocation in underresourced regions like Africa.

Artificial Intelligence (AI) has achieved new levels of performance and spread in public usage with the rise of deep neural networks (DNNs). Initially inspired by human neurons and their connections, NNs have become the foundation of AI models for many advanced architectures. However, some of the most integral processes in the human brain, particularly neurogenesis and neuroplasticity in addition to the more spread neuroapoptosis have largely been ignored in DNN architecture design. Instead, contemporary AI development predominantly focuses on constructing advanced frameworks, such as large language models, which retain a static structure of neural connections during training and inference. In this light, we explore how neurogenesis, neuroapoptosis, and neuroplasticity can inspire future AI advances. Specifically, we examine analogous activities in artificial NNs, introducing the concepts of ``dropin'' for neurogenesis and revisiting ``dropout'' and structural pruning for neuroapoptosis. We additionally suggest neuroplasticity combining the two for future large NNs in ``life-long learning'' settings following the biological inspiration. We conclude by advocating for greater research efforts in this interdisciplinary domain and identifying promising directions for future exploration.

Rapid advancements in Visual Language Models (VLMs) have transformed multimodal understanding but are often constrained by generating English responses regardless of the input language. This phenomenon has been termed as Image-induced Fidelity Loss (IFL) and stems from limited multimodal multilingual training data. To address this, we propose a continuous multilingual integration strategy that injects text-only multilingual data during visual instruction tuning, preserving the language model's original multilingual capabilities. Extensive evaluations demonstrate that our approach significantly improves linguistic fidelity across languages without degradation in visual performance. We also explore model merging, which improves language fidelity but comes at the cost of visual performance. In contrast, our core method achieves robust multilingual alignment without trade-offs, offering a scalable and effective path to mitigating IFL for global VLM adoption.

Self-supervised monocular depth estimation (SSMDE) has gained attention in the field of deep learning as it estimates depth without requiring ground truth depth maps. This approach typically uses a photometric consistency loss between a synthesized image, generated from the estimated depth, and the original image, thereby reducing the need for extensive dataset acquisition. However, the conventional photometric consistency loss relies on the Lambertian assumption, which often leads to significant errors when dealing with reflective surfaces that deviate from this model. To address this limitation, we propose a novel framework that incorporates intrinsic image decomposition into SSMDE. Our method synergistically trains for both monocular depth estimation and intrinsic image decomposition. The accurate depth estimation facilitates multi-image consistency for intrinsic image decomposition by aligning different view coordinate systems, while the decomposition process identifies reflective areas and excludes corrupted gradients from the depth training process. Furthermore, our framework introduces a pseudo-depth generation and knowledge distillation technique to further enhance the performance of the student model across both reflective and non-reflective surfaces. Comprehensive evaluations on multiple datasets show that our approach significantly outperforms existing SSMDE baselines in depth prediction, especially on reflective surfaces.

This paper explores the effectiveness of Multimodal Large Language models (MLLMs) as assistive technologies for visually impaired individuals. We conduct a user survey to identify adoption patterns and key challenges users face with such technologies. Despite a high adoption rate of these models, our findings highlight concerns related to contextual understanding, cultural sensitivity, and complex scene understanding, particularly for individuals who may rely solely on them for visual interpretation. Informed by these results, we collate five user-centred tasks with image and video inputs, including a novel task on Optical Braille Recognition. Our systematic evaluation of twelve MLLMs reveals that further advancements are necessary to overcome limitations related to cultural context, multilingual support, Braille reading comprehension, assistive object recognition, and hallucinations. This work provides critical insights into the future direction of multimodal AI for accessibility, underscoring the need for more inclusive, robust, and trustworthy visual assistance technologies.