Understanding the context of crash occurrence in complex driving environments is essential for improving traffic safety and advancing automated driving. Previous studies have used statistical models and deep learning to predict crashes based on semantic, contextual, or vehicle kinematic features, but none have examined the combined influence of these factors. In this study, we term the integration of these features ``roadway complexity''. This paper introduces a two-stage framework that integrates roadway complexity features for crash prediction. In the first stage, an encoder extracts hidden contextual information from these features, generating complexity-infused features. The second stage uses both original and complexity-infused features to predict crash likelihood, achieving an accuracy of 87.98\% with original features alone and 90.15\% with the added complexity-infused features. Ablation studies confirm that a combination of semantic, kinematic, and contextual features yields the best results, which emphasize their role in capturing roadway complexity. Additionally, complexity index annotations generated by the Large Language Model outperform those by Amazon Mechanical Turk, highlighting the potential of AI-based tools for accurate, scalable crash prediction systems.

The increasing presence of AI-generated content on the internet raises a critical question: What happens when generative machine learning models are pretrained on web-scale datasets containing data created by earlier models? Some authors prophesy \textit{model collapse} under a `{\it replace}' scenario: a sequence of models, the first trained with real data and each later one trained {\it only on} synthetic data from its preceding model. In this scenario, models successively degrade. Others see collapse as avoidable; in an `{\it accumulate}' scenario, a sequence of models is trained, but each training uses all real and synthetic data generated so far. In this work, we deepen and extend the study of these contrasting scenarios. First, collapse versus avoidance of collapse is studied by comparing the replace and accumulate scenarios on each of three prominent generative modeling settings; we find the same contrast emerges in all three settings. Second, we study a compromise scenario; the available data remains the same as in the {\it accumulate} scenario -- but unlike {\it accumulate} and like {\it replace}, each model is trained using a fixed compute budget; we demonstrate that model test loss on real data is larger than in the {\it accumulate} scenario, but apparently plateaus, unlike the divergence seen with {\it replace}. Third, we study the relative importance of cardinality and proportion of real data for avoiding model collapse. Surprisingly, we find a non-trivial interaction between real and synthetic data, where the value of synthetic data for reducing test loss depends on the absolute quantity of real data. Our insights are particularly important when forecasting whether future frontier generative models will collapse or thrive, and our results open avenues for empirically and mathematically studying the context-dependent value of synthetic data.

Despite the significant strides made by generative AI in just a few short years, its future progress is constrained by the challenge of building modular and robust systems. This capability has been a cornerstone of past technological revolutions, which relied on combining components to create increasingly sophisticated and reliable systems. Cars, airplanes, computers, and software consist of components-such as engines, wheels, CPUs, and libraries-that can be assembled, debugged, and replaced. A key tool for building such reliable and modular systems is specification: the precise description of the expected behavior, inputs, and outputs of each component. However, the generality of LLMs and the inherent ambiguity of natural language make defining specifications for LLM-based components (e.g., agents) both a challenging and urgent problem. In this paper, we discuss the progress the field has made so far-through advances like structured outputs, process supervision, and test-time compute-and outline several future directions for research to enable the development of modular and reliable LLM-based systems through improved specifications.

Large models (LMs) have immense potential in Internet of Things (IoT) systems, enabling applications such as intelligent voice assistants, predictive maintenance, and healthcare monitoring. However, training LMs on edge servers raises data privacy concerns, while deploying them directly on IoT devices is constrained by limited computational and memory resources. We analyze the key challenges of training LMs in IoT systems, including energy constraints, latency requirements, and device heterogeneity, and propose potential solutions such as dynamic resource management, adaptive model partitioning, and clustered collaborative training. Furthermore, we propose a split knowledge distillation framework to efficiently distill LMs into smaller, deployable versions for IoT devices while ensuring raw data remains local. This framework integrates knowledge distillation and split learning to minimize energy consumption and meet low model training delay requirements. A case study is presented to evaluate the feasibility and performance of the proposed framework.

Mixture-of-Experts (MoE) models, though highly effective for various machine learning tasks, face significant deployment challenges on memory-constrained devices. While GPUs offer fast inference, their limited memory compared to CPUs means not all experts can be stored on the GPU simultaneously, necessitating frequent, costly data transfers from CPU memory, often negating GPU speed advantages. To address this, we present DAOP, an on-device MoE inference engine to optimize parallel GPU-CPU execution. DAOP dynamically allocates experts between CPU and GPU based on per-sequence activation patterns, and selectively pre-calculates predicted experts on CPUs to minimize transfer latency. This approach enables efficient resource utilization across various expert cache ratios while maintaining model accuracy through a novel graceful degradation mechanism. Comprehensive evaluations across various datasets show that DAOP outperforms traditional expert caching and prefetching methods by up to 8.20x and offloading techniques by 1.35x while maintaining accuracy.

Large Language Models (LLMs) have shown promising potential in the medical domain, assisting with tasks like clinical note generation and patient communication. However, current LLMs are limited to text-based communication, hindering their ability to interact with diverse forms of information in clinical environments. Despite clinical agents succeeding in diverse signal interaction, they are oriented to a single clinical scenario and hence fail for broader applications. To evaluate clinical agents holistically, we propose ClinicalAgent Bench~(CAB), a comprehensive medical agent benchmark consisting of 18 tasks across five key realistic clinical dimensions. Building on this, we introduce ReflecTool, a novel framework that excels at utilizing domain-specific tools within two stages. The first optimization stage progressively enlarges a long-term memory by saving successful solving processes and tool-wise experience of agents in a tiny pre-defined training set. In the following inference stage, ReflecTool can search for supportive successful demonstrations from already built long-term memory to guide the tool selection strategy, and a verifier improves the tool usage according to the tool-wise experience with two verification methods--iterative refinement and candidate selection. Extensive experiments on ClinicalAgent Benchmark demonstrate that ReflecTool surpasses the pure LLMs with more than 10 points and the well-established agent-based methods with 3 points, highlighting its adaptability and effectiveness in solving complex clinical tasks.

The text-to-SQL task aims to convert natural language into Structured Query Language (SQL) without bias. Recently, text-to-SQL methods based on large language models (LLMs) have garnered significant attention. The core of mainstream text-to-SQL frameworks is schema linking, which aligns user queries with relevant tables and columns in the database. Previous methods focused on schema linking while neglecting to enhance LLMs' understanding of database schema. The complex coupling relationships between tables in the database constrain the SQL generation capabilities of LLMs. To tackle this issue, this paper proposes a simple yet effective strategy called view-based schema. This strategy aids LLMs in understanding the database schema by decoupling tightly coupled tables into low-coupling views. We then introduce V-SQL, a view-based two-stage text-to-SQL framework. V-SQL involves the view-based schema strategy to enhance LLMs' understanding of database schema. Results on the authoritative datasets Bird indicate that V-SQL achieves competitive performance compared to existing state-of-the-art methods.

Large Language Models (LLMs) have become increasingly powerful and ubiquitous, but their stochastic nature poses challenges to the reliability of their outputs. While deterministic settings can improve consistency, they do not guarantee reliability, as a single sample from the model's probability distribution can still be misleading. Building upon the concept of LLM-as-a-judge, we introduce a novel framework for rigorously evaluating the reliability of LLM judgments, leveraging McDonald's omega. We evaluate the reliability of LLMs when judging the outputs of other LLMs on standard single-turn and multi-turn benchmarks, simultaneously investigating the impact of temperature on reliability. By analyzing these results, we demonstrate the limitations of fixed randomness and the importance of considering multiple samples, which we show has significant implications for downstream applications. Our findings highlight the need for a nuanced understanding of LLM reliability and the potential risks associated with over-reliance on single-shot evaluations. This work provides a crucial step towards building more trustworthy and reliable LLM-based systems and applications.

Attention heads are one of the building blocks of large language models (LLMs). Prior work on investigating their operation mostly focused on analyzing their behavior during inference for specific circuits or tasks. In this work, we seek a comprehensive mapping of the operations they implement in a model. We propose MAPS (Mapping Attention head ParameterS), an efficient framework that infers the functionality of attention heads from their parameters, without any model training or inference. We showcase the utility of MAPS for answering two types of questions: (a) given a predefined operation, mapping how strongly heads across the model implement it, and (b) given an attention head, inferring its salient functionality. Evaluating MAPS on 20 operations across 6 popular LLMs shows its estimations correlate with the head's outputs during inference and are causally linked to the model's predictions. Moreover, its mappings reveal attention heads of certain operations that were overlooked in previous studies, and valuable insights on function universality and architecture biases in LLMs. Next, we present an automatic pipeline and analysis that leverage MAPS to characterize the salient operations of a given head. Our pipeline produces plausible operation descriptions for most heads, as assessed by human judgment, while revealing diverse operations.

Generating Chain-of-Thought (CoT) before deriving the answer can effectively improve the reasoning capabilities of large language models (LLMs) and significantly improve the accuracy of the generated answer. However, in most cases, the length of the generated CoT is much longer than the desired final answer, which results in additional decoding costs. Furthermore, existing research has discovered that shortening the reasoning steps in CoT, even while preserving the key information, diminishes LLMs' abilities. These phenomena make it difficult to use LLMs and CoT in many real-world applications that only require the final answer and are sensitive to latency, such as search and recommendation. To reduce the costs of model decoding and shorten the length of the generated CoT, this paper presents $\textbf{C}$onditioned $\textbf{C}$ompressed $\textbf{C}$hain-of-$\textbf{T}$hought (C3oT), a CoT compression framework that involves a compressor to compress an original longer CoT into a shorter CoT while maintaining key information and interpretability, a conditioned training method to train LLMs with both longer CoT and shorter CoT simultaneously to learn the corresponding relationships between them, and a conditioned inference method to gain the reasoning ability learned from longer CoT by generating shorter CoT. We conduct experiments over four datasets from arithmetic and commonsense scenarios, showing that the proposed method is capable of compressing the length of generated CoT by up to more than 50% without compromising its effectiveness.