Iterated reference games - in which players repeatedly pick out novel referents using language - present a test case for agents' ability to perform context-sensitive pragmatic reasoning in multi-turn linguistic environments. We tested humans and vision-language models on trials from iterated reference games, varying the given context in terms of amount, order, and relevance. Without relevant context, models were above chance but substantially worse than humans. However, with relevant context, model performance increased dramatically over trials. Few-shot reference games with abstract referents remain a difficult task for machine learning models.

Food logging, both self-directed and prescribed, plays a critical role in uncovering correlations between diet, medical, fitness, and health outcomes. Through conversations with nutritional experts and individuals who practice dietary tracking, we find current logging methods, such as handwritten and app-based journaling, are inflexible and result in low adherence and potentially inaccurate nutritional summaries. These findings, corroborated by prior literature, emphasize the urgent need for improved food logging methods. In response, we propose SnappyMeal, an AI-powered dietary tracking system that leverages multimodal inputs to enable users to more flexibly log their food intake. SnappyMeal introduces goal-dependent follow-up questions to intelligently seek missing context from the user and information retrieval from user grocery receipts and nutritional databases to improve accuracy. We evaluate SnappyMeal through publicly available nutrition benchmarks and a multi-user, 3-week, in-the-wild deployment capturing over 500 logged food instances. Users strongly praised the multiple available input methods and reported a strong perceived accuracy. These insights suggest that multimodal AI systems can be leveraged to significantly improve dietary tracking flexibility and context-awareness, laying the groundwork for a new class of intelligent self-tracking applications.

Hallucination mitigation remains a persistent challenge for large language models (LLMs), even as model scales grow. Existing approaches often rely on external knowledge sources, such as structured databases or knowledge graphs, accessed through prompting or retrieval. However, prompt-based grounding is fragile and domain-sensitive, while symbolic knowledge integration incurs heavy retrieval and formatting costs. Motivated by knowledge graphs, we introduce Graph-Retrieved Adaptive Decoding (GRAD), a decoding-time method that grounds generation in corpus-derived evidence without retraining. GRAD constructs a sparse token transition graph by accumulating next-token logits across a small retrieved corpus in a single forward pass. During decoding, graph-retrieved logits are max-normalized and adaptively fused with model logits to favor high-evidence continuations while preserving fluency. Across three models and a range of question-answering benchmarks spanning intrinsic, extrinsic hallucination, and factuality tasks, GRAD consistently surpasses baselines, achieving up to 9.7$\%$ higher intrinsic accuracy, 8.6$\%$ lower hallucination rates, and 6.9$\%$ greater correctness compared to greedy decoding, while attaining the highest truth--informativeness product score among all methods. GRAD offers a lightweight, plug-and-play alternative to contrastive decoding and knowledge graph augmentation, demonstrating that statistical evidence from corpus-level token transitions can effectively steer generation toward more truthful and verifiable outputs.

Abstract--Large language models (LLMs) are now widely used to draft and refactor code, but code that works is not necessarily secure. We evaluate secure code generation using the Instruct Prime, which eliminated compliance-required prompts and cue contamination, and evaluate five instruction-tuned code LLMs using a zero-shot baseline and a three-round reflexion prompting approach. Security is measured using the Insecure Code Detector (ICD), and results are reported by measuring Repair, Regression, and NetGain metrics, considering the programming language and CWE family. Python yields the highest secure rates; C and C# are the lowest, with Java, JS, PHP, and C++ in the middle. Reflexion prompting improves security for all models, improving average accuracy from 70.74% at t The trends with Repair, Regression, and NetGain metrics show that applying one to two rounds produces most of the benefits. A replication package is available at https://doi.org/10.5281/zenodo.17065846. LLMs such as GitHub Copilot, Codex, and DeepSeekCoder have made LLM-assisted coding common. Early studies focused on functionality and correctness [1], [2]: can models produce code that compiles and passes tests? Y et LLMs learn from large codebases that also contain design flaws. Recent work shows that low-quality code [3], [4] and vulnerabilities [5] can carry over into generated code.

Accurate geometric modeling of the aortic valve from 3D CT images is essential for biomechanical analysis and patient-specific simulations to assess valve health or make a preoperative plan. However, it remains challenging to generate aortic valve meshes with both high-quality and consistency across different patients. Traditional approaches often produce triangular meshes with irregular topologies, which can result in poorly shaped elements and inconsistent correspondence due to inter-patient anatomical variation. In this work, we address these challenges by introducing a template-fitting pipeline with deep neural networks to generate structured quad (i.e., quadrilateral) meshes from 3D CT images to represent aortic valve geometries. By remeshing aortic valves of all patients with a common quad mesh template, we ensure a uniform mesh topology with consistent node-to-node and element-to-element correspondence across patients. This consistency enables us to simplify the learning objective of the deep neural networks, by employing a loss function with only two terms (i.e., a geometry reconstruction term and a smoothness regularization term), which is sufficient to preserve mesh smoothness and element quality. Our experiments demonstrate that the proposed approach produces high-quality aortic valve surface meshes with improved smoothness and shape quality, while requiring fewer explicit regularization terms compared to the traditional methods. These results highlight that using structured quad meshes for the template and neural network training not only ensures mesh correspondence and quality but also simplifies the training process, thus enhancing the effectiveness and efficiency of aortic valve modeling.

Social and collaborative platforms emit multivariate time-series traces in which early interactions--such as views, likes, or downloads--are followed, sometimes months or years later, by higher impact like citations, sales, or reviews. We formalize this setting as Lead-Lag Forecasting (LLF): given an early usage channel (the lead), predict a correlated but temporally shifted outcome channel (the lag). Despite the ubiquity of such patterns, LLF has not been treated as a unified forecasting problem within the time-series community, largely due to the absence of standardized datasets. To anchor research in LLF, here we present two high-volume benchmark datasets--arXiv (accesses citations of 2.3M papers) and GitHub (pushes/stars forks of 3M repositories)--and outline additional domains with analogous lead-lag dynamics, including Wikipedia (page-views edits), Spotify (streams concert attendance), e-commerce (click-throughs purchases), and LinkedIn profile (views messages). Our datasets provide ideal testbeds for lead-lag forecasting, by capturing long-horizon dynamics across years, spanning the full spectrum of outcomes, and avoiding sur-vivorship bias in sampling. We documented all technical details of data cura-tion and cleaning, verified the presence of lead-lag dynamics through statistical and classification tests, and benchmarked parametric and non-parametric baselines for regression. Our study establishes LLF as a novel forecasting paradigm and lays an empirical foundation for its systematic exploration in social and usage data. The success of human activities is often measured by their collective impact, ranging from music streams and movie box office revenues to product sales and social media popularity. These impact metrics typically follow heavy-tailed distributions (Clauset et al., 2009) and slow decay patterns across timescales (Candia et al., 2019), making early identification of future hits fundamentally challenging (Cheng et al., 2014; Martin et al., 2016). At the same time, digital platforms increasingly log online user interactions--searches, views, downloads, likes, and shares--that often precede these long-term dynamics. These temporal lead-lag dynamics are remarkably ubiquitous, spanning domains as diverse as science (Haque & Ginsparg, 2009), economics (Wu & Brynjolfsson, 2015), arts (Goel et al., 2010), culture (Gruhl et al., 2005), and social movements (Johnson et al., 2016). A systematic understanding of such lead-lag dynamics is not only crucial for anticipating and optimizing impact in digital ecosystems, but also essential for designing effective strategies that identify and promote emerging innovations and products.

Multimodal Large Language Models (MLLMs) are reshaping how modern agentic systems reason over sequential user-behavior data. However, whether textual or image representations of user behavior data are more effective for maximizing MLLM performance remains underexplored. We present \texttt{BehaviorLens}, a systematic benchmarking framework for assessing modality trade-offs in user-behavior reasoning across six MLLMs by representing transaction data as (1) a text paragraph, (2) a scatter plot, and (3) a flowchart. Using a real-world purchase-sequence dataset, we find that when data is represented as images, MLLMs next-purchase prediction accuracy is improved by 87.5% compared with an equivalent textual representation without any additional computational cost.

The response-only model class selection capability of a novel deep convolutional neural network method is examined herein in a simple, yet effective, manner. Specifically, the responses from a unique degree of freedom along with their class information train and validate a one-dimensional convolutional neural network. In doing so, the network selects the model class of new and unlabeled signals without the need of the system input information, or full system identification. An optional physics-based algorithm enhancement is also examined using the Kalman filter to fuse the system response signals using the kinematics constraints of the acceleration and displacement data. Importantly, the method is shown to select the model class in slight signal variations attributed to the damping behavior or hysteresis behavior on both linear and nonlinear dynamic systems, as well as on a 3D building finite element model, providing a powerful tool for structural health monitoring applications.

Large language models (LLMs) offer a powerful opportunity to simulate the results of social science experiments. In this work, we demonstrate that finetuning LLMs directly on individual-level responses from past experiments meaningfully improves the accuracy of such simulations across diverse social science domains. We construct SocSci210 via an automatic pipeline, a dataset comprising 2.9 million responses from 400,491 participants in 210 open-source social science experiments. Through finetuning, we achieve multiple levels of generalization. In completely unseen studies, our strongest model, Socrates-Qwen-14B, produces predictions that are 26% more aligned with distributions of human responses to diverse outcome questions under varying conditions relative to its base model (Qwen2.5-14B), outperforming GPT-4o by 13%. By finetuning on a subset of conditions in a study, generalization to new unseen conditions is particularly robust, improving by 71%. Since SocSci210 contains rich demographic information, we reduce demographic parity difference, a measure of bias, by 10.6% through finetuning. Because social sciences routinely generate rich, topic-specific datasets, our findings indicate that finetuning on such data could enable more accurate simulations for experimental hypothesis screening. We release our data, models and finetuning code at stanfordhci.github.io/socrates.

We demonstrate that unstructured sparsity significantly improves KV cache compression for LLMs, enabling sparsity levels up to 70% without compromising accuracy or requiring fine-tuning. We conduct a systematic exploration of pruning strategies and find per-token magnitude-based pruning as highly effective for both Key and Value caches under unstructured sparsity, surpassing prior structured pruning schemes. The Key cache benefits from prominent outlier elements, while the Value cache surprisingly benefits from a simple magnitude-based pruning despite its uniform distribution. KV cache size is the major bottleneck in decode performance due to high memory overhead for large context lengths. To address this, we use a bitmap-based sparse format and a custom attention kernel capable of compressing and directly computing over compressed caches pruned to arbitrary sparsity patterns, significantly accelerating memory-bound operations in decode computations and thereby compensating for the overhead of runtime pruning and compression. Our custom attention kernel coupled with the bitmap-based format delivers substantial compression of KV cache upto 45% of dense inference and thereby enables longer context length and increased tokens/sec throughput of upto 2.23x compared to dense inference. Our pruning mechanism and sparse attention kernel is available at https://github.com/dhjoo98/mustafar.