We propose a flexible deep neural network (DNN) framework for modeling survival data within a partially linear regression structure. The approach preserves interpretability through a parametric linear component for covariates of primary interest, while a nonparametric DNN component captures complex time-covariate interactions among nuisance variables. We refer to the method as FLEXI-Haz, a flexible hazard model with a partially linear structure. In contrast to existing DNN approaches for partially linear Cox models, FLEXI-Haz does not rely on the proportional hazards assumption. We establish theoretical guarantees: the neural network component attains minimax-optimal convergence rates based on composite Holder classes, and the linear estimator is root-n consistent, asymptotically normal, and semiparametrically efficient. Extensive simulations and real-data analyses demonstrate that FLEXI-Haz provides accurate estimation of the linear effect, offering a principled and interpretable alternative to modern methods based on proportional hazards. Code for implementing FLEXI-Haz, as well as scripts for reproducing data analyses and simulations, is available at: https://github.com/AsafBanana/FLEXI-Haz

This paper introduces a new probabilistic framework for supervised learning in neural systems. It is designed to model complex, uncertain systems whose random outputs are strongly non-Gaussian given deterministic inputs. The architecture itself is a random object stochastically generated by a latent anisotropic Gaussian random field defined on a compact, boundaryless, multiply-connected manifold. The goal is to establish a novel conceptual and mathematical framework in which neural architectures are realizations of a geometry-aware, field-driven generative process. Both the neural topology and synaptic weights emerge jointly from a latent random field. A reduced-order parameterization governs the spatial intensity of an inhomogeneous Poisson process on the manifold, from which neuron locations are sampled. Input and output neurons are identified via extremal evaluations of the latent field, while connectivity is established through geodesic proximity and local field affinity. Synaptic weights are conditionally sampled from the field realization, inducing stochastic output responses even for deterministic inputs. To ensure scalability, the architecture is sparsified via percentile-based diffusion masking, yielding geometry-aware sparse connectivity without ad hoc structural assumptions. Supervised learning is formulated as inference on the generative hyperparameters of the latent field, using a negative log-likelihood loss estimated through Monte Carlo sampling from single-observation-per-input datasets. The paper initiates a mathematical analysis of the model, establishing foundational properties such as well-posedness, measurability, and a preliminary analysis of the expressive variability of the induced stochastic mappings, which support its internal coherence and lay the groundwork for a broader theory of geometry-driven stochastic learning.

The proliferation of Large Language Models (LLMs) necessitates valid evaluation methods to guide downstream applications and actionable future improvements. The Item Response Theory (IRT) has recently emerged as a promising framework for evaluating LLMs via their response accuracy. Beyond simple response accuracy, LLMs' chain of thought (CoT) lengths serve as a vital indicator of their reasoning ability. To leverage the CoT length information to assist the evaluation of LLMs, we propose Latency-Response Theory (LaRT) to jointly model the response accuracy and CoT length by introducing the latent ability, latent speed, and a key correlation parameter between them. We derive an efficient estimation algorithm and establish rigorous identifiability results for the population parameters to ensure the statistical validity of estimation. Theoretical asymptotic analyses and simulation studies demonstrate LaRT's advantages over IRT in terms of higher estimation accuracy and shorter confidence intervals for latent traits. A key finding is that the asymptotic estimation precision of the latent ability under LaRT exceeds that of IRT whenever the latent ability and latent speed are correlated. We collect real responses from diverse LLMs on popular benchmark datasets. The application of LaRT reveals a strong negative correlation between the latent ability and latent speed in all benchmarks, with stronger correlation for more difficult benchmarks. This finding supports the intuition that higher reasoning ability correlates with slower speed and longer response latency. LaRT yields different LLM rankings than IRT and outperforms IRT across multiple key evaluation metrics including predictive power, item efficiency, ranking validity, and LLM evaluation efficiency. Code and data are available at https://github.com/Toby-X/Latency-Response-Theory-Model.

We investigate how LLMs encode sociodemographic attributes of human conversational partners inferred from indirect cues such as names and occupations. We show that LLMs develop linear representations of user demographics within activation space, wherein stereotypically associated attributes are encoded along interpretable geometric directions. We first probe residual streams across layers of four open transformer-based LLMs (Magistral 24B, Qwen3 14B, GPT-OSS 20B, OLMo2-1B) prompted with explicit demographic disclosure. We show that the same probes predict demographics from implicit cues: names activate census-aligned gender and race representations, while occupations trigger representations correlated with real-world workforce statistics. These linear representations allow us to explain demographic inferences implicitly formed by LLMs during conversation. We demonstrate that these implicit demographic representations actively shape downstream behavior, such as career recommendations. Our study further highlights that models that pass bias benchmark tests may still harbor and leverage implicit biases, with implications for fairness when applied at scale.

The O-RAN architecture is transforming cellular networks by adopting RAN softwarization and disaggregation concepts to enable data-driven monitoring and control of the network. Such management is enabled by RICs, which facilitate near-real-time and non-real-time network control through xApps and rApps. However, they face limitations, including latency overhead in data exchange between the RAN and RIC, restricting real-time monitoring, and the inability to access user plain data due to privacy and security constraints, hindering use cases like beamforming and spectrum classification. In this paper, we leverage the dApps concept to enable real-time RF spectrum classification with LibIQ, a novel library for RF signals that facilitates efficient spectrum monitoring and signal classification by providing functionalities to read I/Q samples as time-series, create datasets and visualize time-series data through plots and spectrograms. Thanks to LibIQ, I/Q samples can be efficiently processed to detect external RF signals, which are subsequently classified using a CNN inside the library. To achieve accurate spectrum analysis, we created an extensive dataset of time-series-based I/Q samples, representing distinct signal types captured using a custom dApp running on a 5G deployment over the Colosseum network emulator and an OTA testbed. We evaluate our model by deploying LibIQ in heterogeneous scenarios with varying center frequencies, time windows, and external RF signals. In real-time analysis, the model classifies the processed I/Q samples, achieving an average accuracy of approximately 97.8% in identifying signal types across all scenarios. We pledge to release both LibIQ and the dataset created as a publicly available framework upon acceptance.

Trustworthiness has become a key requirement for the deployment of artificial intelligence systems in safety-critical applications. Conventional evaluation metrics, such as accuracy and precision, fail to appropriately capture uncertainty or the reliability of model predictions, particularly under adversarial or degraded conditions. This paper introduces the Parallel Trust Assessment System (PaTAS), a framework for modeling and propagating trust in neural networks using Subjective Logic (SL). PaTAS operates in parallel with standard neural computation through Trust Nodes and Trust Functions that propagate input, parameter, and activation trust across the network. The framework defines a Parameter Trust Update mechanism to refine parameter reliability during training and an Inference-Path Trust Assessment (IPTA) method to compute instance-specific trust at inference. Experiments on real-world and adversarial datasets demonstrate that PaTAS produces interpretable, symmetric, and convergent trust estimates that complement accuracy and expose reliability gaps in poisoned, biased, or uncertain data scenarios. The results show that PaTAS effectively distinguishes between benign and adversarial inputs and identifies cases where model confidence diverges from actual reliability. By enabling transparent and quantifiable trust reasoning within neural architectures, PaTAS provides a foundation for evaluating model reliability across the AI lifecycle.

It is widely recognized that reinforcement learning (RL) fine-tuning of large language models often leads to diversity collapse, where outputs lack variety. Prior work has proposed a range of heuristics to counteract this effect, but these methods are ad hoc: they frequently trade off correctness for diversity, their effectiveness varies across tasks, and in some cases they even contradict one another. In this work, we place these observations on a rigorous foundation. We first provide a formal proof of why RL fine-tuning exhibits diversity collapse via a selection and reinforcement bias. Next, we make a key observation that any reward modification to address diversity collapse only needs to be applied on the correct trajectories. Building directly on this analysis, we introduce a principled method -- differential smoothing -- that provably improves both correctness and diversity, outperforming vanilla RL as well as widely used entropy-based heuristics. Our theory precisely characterizes when existing heuristics help and why they fail, while showing that differential smoothing is universally superior. Extensive experiments with models from 1B to 7B parameters, across domains including CountDown and real-world mathematical reasoning, demonstrate consistent gains. Differential smoothing improves both Pass@1 and Pass@k, with up to 6.7% improvements on AIME24 dataset.

Depression is one of the most prevalent mental health disorders globally. In recent years, multi-modal data, such as speech, video, and transcripts, has been increasingly used to develop AI-assisted depression assessment systems. Large language models have further advanced this field due to their strong language understanding and generalization capabilities. However, conventional LLMs remain text-centric and cannot process the rich non-verbal cues found in audio and visual modalities, which are critical components in mental health evaluation. While multi-modal LLMs offer a promising direction, few are tailored for psychological applications. In this study, we propose a novel multi-modal LLM framework for depression detection. This fine-grained alignment improves modeling of temporal dynamics across modalities while reducing the need for extensive training data and computational resources. Experiments on the DAIC-WoZ dataset demonstrate that our model outperforms both single-modality approaches and previous multi-modal methods. Moreover, the proposed framework can be extended to incorporate additional physiological signals, paving the way for broader clinical applications beyond mental health. Depression has emerged as a critical concern in the field of mental health, affecting a broad population across various age groups. Particularly, the incidence of depression among adolescents has surged over the past decade, raising significant social and public health concerns (Thapar et al., 2022).

This paper presents HunyuanOCR, a commercial-grade, open-source, and lightweight (1B parameters) Vision-Language Model (VLM) dedicated to OCR tasks. The architecture comprises a Native Vision Transformer (ViT) and a lightweight LLM connected via an MLP adapter. HunyuanOCR demonstrates superior performance, outperforming commercial APIs, traditional pipelines, and larger models (e.g., Qwen3-VL-4B). Specifically, it surpasses current public solutions in perception tasks (Text Spotting, Parsing) and excels in semantic tasks (IE, Text Image Translation), securing first place in the ICDAR 2025 DIMT Challenge (Small Model Track). Furthermore, it achieves state-of-the-art (SOTA) results on OCRBench among VLMs with fewer than 3B parameters. HunyuanOCR achieves breakthroughs in three key aspects: 1) Unifying Versatility and Efficiency: We implement comprehensive support for core capabilities including spotting, parsing, IE, VQA, and translation within a lightweight framework. This addresses the limitations of narrow "OCR expert models" and inefficient "General VLMs". 2) Streamlined End-to-End Architecture: Adopting a pure end-to-end paradigm eliminates dependencies on pre-processing modules (e.g., layout analysis). This fundamentally resolves error propagation common in traditional pipelines and simplifies system deployment. 3) Data-Driven and RL Strategies: We confirm the critical role of high-quality data and, for the first time in the industry, demonstrate that Reinforcement Learning (RL) strategies yield significant performance gains in OCR tasks. HunyuanOCR is officially open-sourced on HuggingFace. We also provide a high-performance deployment solution based on vLLM, placing its production efficiency in the top tier. We hope this model will advance frontier research and provide a solid foundation for industrial applications.

In this work, we define Foresight Intelligence as the capability to anticipate and interpret future events-an ability essential for applications such as autonomous driving, yet largely overlooked by existing research. To bridge this gap, we introduce FSU-QA, a new Visual Question-Answering (VQA) dataset specifically designed to elicit and evaluate Foresight Intelligence. Using FSU-QA, we conduct the first comprehensive study of state-of-the-art Vision-Language Models (VLMs) under foresight-oriented tasks, revealing that current models still struggle to reason about future situations. Beyond serving as a benchmark, FSU-QA also enables the assessment of world models by measuring the semantic coherence of their generated predictions, quantified through performance gains when VLMs are augmented with such outputs. Our experiments further demonstrate that FSU-QA can effectively enhance foresight reasoning: even small VLMs fine-tuned on FSU-QA surpass much larger, advanced models by a substantial margin. Together, these findings position FSU-QA as a principled foundation for developing next-generation models capable of truly anticipating and understanding future events.