Operationalising the Superficial Alignment Hypothesis via Task Complexity

The superficial alignment hypothesis (SAH) posits that large language models learn most of their knowledge during pre-training, and that post-training merely surfaces this knowledge. The SAH, however, lacks a precise definition, which has led to (i) different and seemingly orthogonal arguments supporting it, and (ii) important critiques to it. We propose a new metric called task complexity: the length of the shortest program that achieves a target performance on a task. In this framework, the SAH simply claims that pre-trained models drastically reduce the complexity of achieving high performance on many tasks. Our definition unifies prior arguments supporting the SAH, interpreting them as different strategies to find such short programs. Experimentally, we estimate the task complexity of mathematical reasoning, machine translation, and instruction following; we then show that these complexities can be remarkably low when conditioned on a pre-trained model. Further, we find that pre-training enables access to strong performances on our tasks, but it can require programs of gigabytes of length to access them. Post-training, on the other hand, collapses the complexity of reaching this same performance by several orders of magnitude. Overall, our results highlight that task adaptation often requires surprisingly little information -- often just a few kilobytes.

Stabilizing Test-Time Adaptation of High-Dimensional Simulation Surrogates via D-Optimal Statistics

Machine learning surrogates are increasingly used in engineering to accelerate costly simulations, yet distribution shifts between training and deployment often cause severe performance degradation (e.g., unseen geometries or configurations). Test-Time Adaptation (TTA) can mitigate such shifts, but existing methods are largely developed for lower-dimensional classification with structured outputs and visually aligned input-output relationships, making them unstable for the high-dimensional, unstructured and regression problems common in simulation. We address this challenge by proposing a TTA framework based on storing maximally informative (D-optimal) statistics, which jointly enables stable adaptation and principled parameter selection at test time. When applied to pretrained simulation surrogates, our method yields up to 7% out-of-distribution improvements at negligible computational cost. To the best of our knowledge, this is the first systematic demonstration of effective TTA for high-dimensional simulation regression and generative design optimization, validated on the SIMSHIFT and EngiBench benchmarks.

Enhancing Building Semantics Preservation in AI Model Training with Large Language Model Encodings

Accurate representation of building semantics, encompassing both generic object types and specific subtypes, is essential for effective AI model training in the architecture, engineering, construction, and operation (AECO) industry. Conventional encoding methods (e.g., one-hot) often fail to convey the nuanced relationships among closely related subtypes, limiting AI's semantic comprehension. To address this limitation, this study proposes a novel training approach that employs large language model (LLM) embeddings (e.g., OpenAI GPT and Meta LLaMA) as encodings to preserve finer distinctions in building semantics. We evaluated the proposed method by training GraphSAGE models to classify 42 building object subtypes across five high-rise residential building information models (BIMs). Various embedding dimensions were tested, including original high-dimensional LLM embeddings (1,536, 3,072, or 4,096) and 1,024-dimensional compacted embeddings generated via the Matryoshka representation model. Experimental results demonstrated that LLM encodings outperformed the conventional one-hot baseline, with the llama-3 (compacted) embedding achieving a weighted average F1-score of 0.8766, compared to 0.8475 for one-hot encoding. The results underscore the promise of leveraging LLM-based encodings to enhance AI's ability to interpret complex, domain-specific building semantics. As the capabilities of LLMs and dimensionality reduction techniques continue to evolve, this approach holds considerable potential for broad application in semantic elaboration tasks throughout the AECO industry.

Context-aware Skin Cancer Epithelial Cell Classification with Scalable Graph Transformers

Whole-slide images (WSIs) from cancer patients contain rich information that can be used for medical diagnosis or to follow treatment progress. To automate their analysis, numerous deep learning methods based on convolutional neural networks and Vision Transformers have been developed and have achieved strong performance in segmentation and classification tasks. However, due to the large size and complex cellular organization of WSIs, these models rely on patch-based representations, losing vital tissue-level context. We propose using scalable Graph Transformers on a full-WSI cell graph for classification. We evaluate this methodology on a challenging task: the classification of healthy versus tumor epithelial cells in cutaneous squamous cell carcinoma (cSCC), where both cell types exhibit very similar morphologies and are therefore difficult to differentiate for image-based approaches. We first compared image-based and graph-based methods on a single WSI. Graph Transformer models SGFormer and DIFFormer achieved balanced accuracies of $85.2 \pm 1.5$ ($\pm$ standard error) and $85.1 \pm 2.5$ in 3-fold cross-validation, respectively, whereas the best image-based method reached $81.2 \pm 3.0$. By evaluating several node feature configurations, we found that the most informative representation combined morphological and texture features as well as the cell classes of non-epithelial cells, highlighting the importance of the surrounding cellular context. We then extended our work to train on several WSIs from several patients. To address the computational constraints of image-based models, we extracted four $2560 \times 2560$ pixel patches from each image and converted them into graphs. In this setting, DIFFormer achieved a balanced accuracy of $83.6 \pm 1.9$ (3-fold cross-validation), while the state-of-the-art image-based model CellViT256 reached $78.1 \pm 0.5$.

GLM-5: from Vibe Coding to Agentic Engineering

We present GLM-5, a next-generation foundation model designed to transition the paradigm of vibe coding to agentic engineering. Building upon the agentic, reasoning, and coding (ARC) capabilities of its predecessor, GLM-5 adopts DSA to significantly reduce training and inference costs while maintaining long-context fidelity. To advance model alignment and autonomy, we implement a new asynchronous reinforcement learning infrastructure that drastically improves post-training efficiency by decoupling generation from training. Furthermore, we propose novel asynchronous agent RL algorithms that further improve RL quality, enabling the model to learn from complex, long-horizon interactions more effectively. Through these innovations, GLM-5 achieves state-of-the-art performance on major open benchmarks. Most critically, GLM-5 demonstrates unprecedented capability in real-world coding tasks, surpassing previous baselines in handling end-to-end software engineering challenges. Code, models, and more information are available at https://github.com/zai-org/GLM-5.

Beyond Labels: Information-Efficient Human-in-the-Loop Learning using Ranking and Selection Queries

Integrating human expertise into machine learning systems often reduces the role of experts to labeling oracles, a paradigm that limits the amount of information exchanged and fails to capture the nuances of human judgment. We address this challenge by developing a human-in-the-loop framework to learn binary classifiers with rich query types, consisting of item ranking and exemplar selection. We first introduce probabilistic human response models for these rich queries motivated by the relationship experimentally observed between the perceived implicit score of an item and its distance to the unknown classifier. Using these models, we then design active learning algorithms that leverage the rich queries to increase the information gained per interaction. We provide theoretical bounds on sample complexity and develop a tractable and computationally efficient variational approximation. Through experiments with simulated annotators derived from crowdsourced word-sentiment and image-aesthetic datasets, we demonstrate significant reductions on sample complexity. We further extend active learning strategies to select queries that maximize information rate, explicitly balancing informational value against annotation cost. This algorithm in the word sentiment classification task reduces learning time by more than 57\% compared to traditional label-only active learning.

Causal Effect Estimation with Latent Textual Treatments

Understanding the causal effects of text on downstream outcomes is a central task in many applications. Estimating such effects requires researchers to run controlled experiments that systematically vary textual features. While large language models (LLMs) hold promise for generating text, producing and evaluating controlled variation requires more careful attention. In this paper, we present an end-to-end pipeline for the generation and causal estimation of latent textual interventions. Our work first performs hypothesis generation and steering via sparse autoencoders (SAEs), followed by robust causal estimation. Our pipeline addresses both computational and statistical challenges in text-as-treatment experiments. We demonstrate that naive estimation of causal effects suffers from significant bias as text inherently conflates treatment and covariate information. We describe the estimation bias induced in this setting and propose a solution based on covariate residualization. Our empirical results show that our pipeline effectively induces variation in target features and mitigates estimation error, providing a robust foundation for causal effect estimation in text-as-treatment settings.

Random Wavelet Features for Graph Kernel Machines

Node embeddings map graph vertices into low-dimensional Euclidean spaces while preserving structural information. They are central to tasks such as node classification, link prediction, and signal reconstruction. A key goal is to design node embeddings whose dot products capture meaningful notions of node similarity induced by the graph. Graph kernels offer a principled way to define such similarities, but their direct computation is often prohibitive for large networks. Inspired by random feature methods for kernel approximation in Euclidean spaces, we introduce randomized spectral node embeddings whose dot products estimate a low-rank approximation of any specific graph kernel. We provide theoretical and empirical results showing that our embeddings achieve more accurate kernel approximations than existing methods, particularly for spectrally localized kernels. These results demonstrate the effectiveness of randomized spectral constructions for scalable and principled graph representation learning.

Proactive Conversational Assistant for a Procedural Manual Task based on Audio and IMU

Real-time conversational assistants for procedural tasks often depend on video input, which can be computationally expensive and compromise user privacy. For the first time, we propose a real-time conversational assistant that provides comprehensive guidance for a procedural task using only lightweight privacy-preserving modalities such as audio and IMU inputs from a user's wearable device to understand the context. This assistant proactively communicates step-by-step instructions to a user performing a furniture assembly task, and answers user questions. We construct a dataset containing conversations where the assistant guides the user in performing the task. On observing that an off-the-shelf language model is a very talkative assistant, we design a novel User Whim Agnostic (UWA) LoRA finetuning method which improves the model's ability to suppress less informative dialogues, while maintaining its tendency to communicate important instructions. This leads to >30% improvement in the F-score. Finetuning the model also results in a 16x speedup by eliminating the need to provide in-context examples in the prompt. We further describe how such an assistant is implemented on edge devices with no dependence on the cloud.

The Next Paradigm Is User-Centric Agent, Not Platform-Centric Service

Modern digital services have evolved into indispensable tools, driving the present large-scale information systems. Yet, the prevailing platform-centric model, where services are optimized for platform-driven metrics such as engagement and conversion, often fails to align with users' true needs. While platform technologies have advanced significantly-especially with the integration of large language models (LLMs)-we argue that improvements in platform service quality do not necessarily translate to genuine user benefit. Instead, platform-centric services prioritize provider objectives over user welfare, resulting in conflicts against user interests. This paper argues that the future of digital services should shift from a platform-centric to a user-centric agent. These user-centric agents prioritize privacy, align with user-defined goals, and grant users control over their preferences and actions. With advancements in LLMs and on-device intelligence, the realization of this vision is now feasible. This paper explores the opportunities and challenges in transitioning to user-centric intelligence, presents a practical device-cloud pipeline for its implementation, and discusses the necessary governance and ecosystem structures for its adoption.