# Research Papers — 2025-12 · bundle page 11 of 175 > Full-text markdown of papers #501–550 of 8703 published in 2025-12, newest first. AI-readable mirrors of the full 8703-paper 2025-12 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2025-12/page/11 [← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/10.md) [Next bundle →](https://aipod.dev/papers/archive/2025-12/page/12.md) ### You Only Need Your Transformer 25% of the Time: Meaning-First Execution for Eliminating Unnecessary Inference Authors: Ryan Shamim Published: 2025-12-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.00847v1 Modern AI inference systems treat transformer execution as mandatory, conflating model capability with execution necessity. We reframe inference as a control-plane decision problem: determining when execution is necessary versus when correctness can be preserved through alternative pathways. We introduce Meaning-First Execution (MFEE), a control-plane architecture implementing this framework, selectively invoking transformer inference only when required. MFEE operates as a gating layer above existing stacks without modifying models, weights, or parameters. Across 1,000 diverse prompts under deterministic decoding, MFEE achieves 78.1% execution reduction while maintaining 100% exact-match equivalence for invoked executions. Comparative evaluation reveals pattern-based routers achieve at most 53.3% avoidance with correctness failures, while MFEE reaches 100% avoidance with zero failures through semantic analysis. We prove this limitation via Theorem 1: any router operating solely on finite feature maps cannot simultaneously guarantee zero false skips and positive avoidance on feature-collision pairs. These results establish execution governance as a foundational layer in ML systems infrastructure, orthogonal to model-level optimization techniques. --- ### Enhancing Temporal Awareness in LLMs for Temporal Point Processes Authors: Lili Chen, Wensheng Gan, Shuang Liang, Philip S. Yu Published: 2025-12-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.00845v1 Temporal point processes (TPPs) are crucial for analyzing events over time and are widely used in fields such as finance, healthcare, and social systems. These processes are particularly valuable for understanding how events unfold over time, accounting for their irregularity and dependencies. Despite the success of large language models (LLMs) in sequence modeling, applying them to temporal point processes remains challenging. A key issue is that current methods struggle to effectively capture the complex interaction between temporal information and semantic context, which is vital for accurate event modeling. In this context, we introduce TPP-TAL (Temporal Point Processes with Enhanced Temporal Awareness in LLMs), a novel plug-and-play framework designed to enhance temporal reasoning within LLMs. Rather than using the conventional method of simply concatenating event time and type embeddings, TPP-TAL explicitly aligns temporal dynamics with contextual semantics before feeding this information into the LLM. This alignment allows the model to better perceive temporal dependencies and long-range interactions between events and their surrounding contexts. Through comprehensive experiments on several benchmark datasets, it is shown that TPP-TAL delivers substantial improvements in temporal likelihood estimation and event prediction accuracy, highlighting the importance of enhancing temporal awareness in LLMs for continuous-time event modeling. The code is made available at https://github.com/chenlilil/TPP-TAL --- ### From Clay to Code: Typological and Material Reasoning in AI Interpretations of Iranian Pigeon Towers Authors: Abolhassan Pishahang, Maryam Badiei Published: 2025-12-29 Categories: cs.AI, cs.CV arXiv: https://arxiv.org/abs/2601.00029v1 This study investigates how generative AI systems interpret the architectural intelligence embedded in vernacular form. Using the Iranian pigeon tower as a case study, the research tests three diffusion models, Midjourney v6, DALL-E 3, and DreamStudio based on Stable Diffusion XL (SDXL), across three prompt stages: referential, adaptive, and speculative. A five-criteria evaluation framework assesses how each system reconstructs typology, materiality, environment, realism, and cultural specificity. Results show that AI reliably reproduces geometric patterns but misreads material and climatic reasoning. Reference imagery improves realism yet limits creativity, while freedom from reference generates inventive but culturally ambiguous outcomes. The findings define a boundary between visual resemblance and architectural reasoning, positioning computational vernacular reasoning as a framework for analyzing how AI perceives, distorts, and reimagines traditional design intelligence. --- ### Scaling Remote Sensing Foundation Models: Data Domain Tradeoffs at the Peta-Scale Authors: Charith Wickrema, Eliza Mace, Hunter Brown, Heidys Cabrera, Nick Krall, Matthew O'Neill, Shivangi Sarkar, Lowell Weissman, Eric Hughes, Guido Zarrella Published: 2025-12-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.23903v2 We explore the scaling behaviors of artificial intelligence to establish practical techniques for training foundation models on high-resolution electro-optical (EO) datasets that exceed the current state-of-the-art scale by orders of magnitude. Modern multimodal machine learning (ML) applications, such as generative artificial intelligence (GenAI) systems for image captioning, search, and reasoning, depend on robust, domain-specialized encoders for non-text modalities. In natural image domains where internet-scale data is plentiful, well-established scaling laws help optimize the joint scaling of model capacity, training compute, and dataset size. Unfortunately, these relationships are much less well understood in high-value domains like remote sensing (RS). Using over a quadrillion pixels of commercial satellite EO data and MITRE's Federal AI Sandbox, we train progressively larger vision transformer (ViT) backbones, report successes and failure modes observed at peta-scale, and analyze implications for bridging domain gaps across additional RS modalities. We observe that even at this scale, performance is consistent with a data-limited regime rather than a model parameter-limited one. These practical insights are intended to inform data collection strategies, compute budgets, and optimization schedules that advance the future development of frontier scale RS foundation models. --- ### Efficient Deep Learning for Short-Term Solar Irradiance Time Series Forecasting: A Benchmark Study in Ho Chi Minh City Authors: Tin Hoang Published: 2025-12-29 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.23898v1 Reliable forecasting of Global Horizontal Irradiance (GHI) is essential for mitigating the variability of solar energy in power grids. This study presents a comprehensive benchmark of ten deep learning architectures for short-term (1-hour ahead) GHI time series forecasting in Ho Chi Minh City, leveraging high-resolution NSRDB satellite data (2011-2020) to compare established baselines (e.g. LSTM, TCN) against emerging state-of-the-art architectures, including Transformer, Informer, iTransformer, TSMixer, and Mamba. Experimental results identify the Transformer as the superior architecture, achieving the highest predictive accuracy with an R^2 of 0.9696. The study further utilizes SHAP analysis to contrast the temporal reasoning of these architectures, revealing that Transformers exhibit a strong "recency bias" focused on immediate atmospheric conditions, whereas Mamba explicitly leverages 24-hour periodic dependencies to inform predictions. Furthermore, we demonstrate that Knowledge Distillation can compress the high-performance Transformer by 23.5% while surprisingly reducing error (MAE: 23.78 W/m^2), offering a proven pathway for deploying sophisticated, low-latency forecasting on resource-constrained edge devices. --- ### MRI-to-CT Synthesis With Cranial Suture Segmentations Using A Variational Autoencoder Framework Authors: Krithika Iyer, Austin Tapp, Athelia Paulli, Gabrielle Dickerson, Syed Muhammad Anwar, Natasha Lepore, Marius George Linguraru Published: 2025-12-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.23894v1 Quantifying normative pediatric cranial development and suture ossification is crucial for diagnosing and treating growth-related cephalic disorders. Computed tomography (CT) is widely used to evaluate cranial and sutural deformities; however, its ionizing radiation is contraindicated in children without significant abnormalities. Magnetic resonance imaging (MRI) offers radiation free scans with superior soft tissue contrast, but unlike CT, MRI cannot elucidate cranial sutures, estimate skull bone density, or assess cranial vault growth. This study proposes a deep learning driven pipeline for transforming T1 weighted MRIs of children aged 0.2 to 2 years into synthetic CTs (sCTs), predicting detailed cranial bone segmentation, generating suture probability heatmaps, and deriving direct suture segmentation from the heatmaps. With our in-house pediatric data, sCTs achieved 99% structural similarity and a Frechet inception distance of 1.01 relative to real CTs. Skull segmentation attained an average Dice coefficient of 85% across seven cranial bones, and sutures achieved 80% Dice. Equivalence of skull and suture segmentation between sCTs and real CTs was confirmed using two one sided tests (TOST p < 0.05). To our knowledge, this is the first pediatric cranial CT synthesis framework to enable suture segmentation on sCTs derived from MRI, despite MRI's limited depiction of bone and sutures. By combining robust, domain specific variational autoencoders, our method generates perceptually indistinguishable cranial sCTs from routine pediatric MRIs, bridging critical gaps in non invasive cranial evaluation. --- ### How Large Language Models Systematically Misrepresent American Climate Opinions Authors: Sola Kim, Jieshu Wang, Marco A. Janssen, John M. Anderies Published: 2025-12-29 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2512.23889v2 Federal agencies and researchers increasingly use large language models to analyze and simulate public opinion. When AI mediates between the public and policymakers, accuracy across intersecting identities becomes consequential; inaccurate group-level estimates may mislead outreach, consultation, and policy design. While research examines intersectionality in LLM outputs, few studies have compared these outputs against real human responses across intersecting identities. Climate policy is one such domain, and this is particularly urgent for climate change, where opinion is contested and diverse. We investigate how LLMs represent demographic and intersectional patterns in U.S. climate opinions. We prompted six LLMs with profiles of 978 respondents from a nationally representative U.S. climate opinion survey and compared AI-generated responses to actual human answers across 20 questions. We find that LLMs appear to compress the diversity of American climate opinions, predicting less-concerned groups as more concerned and vice versa. This compression is intersectional: LLMs appear to apply uniform gender assumptions that match reality for White and Hispanic Americans but may misrepresent Black Americans, where actual gender patterns differ. These patterns, which may be invisible to standard auditing approaches, could undermine equitable climate governance. --- ### Autoregressive long-horizon prediction of plasma edge dynamics Authors: Hunor Csala, Sebastian De Pascuale, Paul Laiu, Jeremy Lore, Jae-Sun Park, Pei Zhang Published: 2025-12-29 Categories: physics.plasm-ph, cs.AI arXiv: https://arxiv.org/abs/2512.23884v1 Accurate modeling of scrape-off layer (SOL) and divertor-edge dynamics is vital for designing plasma-facing components in fusion devices. High-fidelity edge fluid/neutral codes such as SOLPS-ITER capture SOL physics with high accuracy, but their computational cost limits broad parameter scans and long transient studies. We present transformer-based, autoregressive surrogates for efficient prediction of 2D, time-dependent plasma edge state fields. Trained on SOLPS-ITER spatiotemporal data, the surrogates forecast electron temperature, electron density, and radiated power over extended horizons. We evaluate model variants trained with increasing autoregressive horizons (1-100 steps) on short- and long-horizon prediction tasks. Longer-horizon training systematically improves rollout stability and mitigates error accumulation, enabling stable predictions over hundreds to thousands of steps and reproducing key dynamical features such as the motion of high-radiation regions. Measured end-to-end wall-clock times show the surrogate is orders of magnitude faster than SOLPS-ITER, enabling rapid parameter exploration. Prediction accuracy degrades when the surrogate enters physical regimes not represented in the training dataset, motivating future work on data enrichment and physics-informed constraints. Overall, this approach provides a fast, accurate surrogate for computationally intensive plasma edge simulations, supporting rapid scenario exploration, control-oriented studies, and progress toward real-time applications in fusion devices. --- ### Breaking Audio Large Language Models by Attacking Only the Encoder: A Universal Targeted Latent-Space Audio Attack Authors: Roee Ziv, Raz Lapid, Moshe Sipper Published: 2025-12-29 Categories: cs.SD, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2512.23881v1 Audio-language models combine audio encoders with large language models to enable multimodal reasoning, but they also introduce new security vulnerabilities. We propose a universal targeted latent space attack, an encoder-level adversarial attack that manipulates audio latent representations to induce attacker-specified outputs in downstream language generation. Unlike prior waveform-level or input-specific attacks, our approach learns a universal perturbation that generalizes across inputs and speakers and does not require access to the language model. Experiments on Qwen2-Audio-7B-Instruct demonstrate consistently high attack success rates with minimal perceptual distortion, revealing a critical and previously underexplored attack surface at the encoder level of multimodal systems. --- ### CASCADE: Cumulative Agentic Skill Creation through Autonomous Development and Evolution Authors: Xu Huang, Junwu Chen, Yuxing Fei, Zhuohan Li, Philippe Schwaller, Gerbrand Ceder Published: 2025-12-29 Categories: cs.AI, cond-mat.mtrl-sci arXiv: https://arxiv.org/abs/2512.23880v2 Large language model (LLM) agents currently depend on predefined tools or early-stage tool generation, limiting their adaptability and scalability to complex scientific tasks. We introduce CASCADE, a self-evolving agentic framework representing an early instantiation of the transition from "LLM + tool use" to "LLM + skill acquisition". CASCADE enables agents to master complex external tools and codify knowledge through two meta-skills: continuous learning via web search, code extraction, and memory utilization; self-reflection via introspection, knowledge graph exploration, and others. We evaluate CASCADE on SciSkillBench, a benchmark of 116 materials science and chemistry research tasks. CASCADE achieves a 93.3% success rate using GPT-5, compared to 35.4% without evolution mechanisms. We further demonstrate real-world applications in computational analysis, autonomous laboratory experiments, and selective reproduction of published papers. Along with human-agent collaboration and memory consolidation, CASCADE accumulates executable skills that can be shared across agents and scientists, moving toward scalable AI-assisted scientific research. --- ### Max-Entropy Reinforcement Learning with Flow Matching and A Case Study on LQR Authors: Yuyang Zhang, Yang Hu, Bo Dai, Na Li Published: 2025-12-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.23870v1 Soft actor-critic (SAC) is a popular algorithm for max-entropy reinforcement learning. In practice, the energy-based policies in SAC are often approximated using simple policy classes for efficiency, sacrificing the expressiveness and robustness. In this paper, we propose a variant of the SAC algorithm that parameterizes the policy with flow-based models, leveraging their rich expressiveness. In the algorithm, we evaluate the flow-based policy utilizing the instantaneous change-of-variable technique and update the policy with an online variant of flow matching developed in this paper. This online variant, termed importance sampling flow matching (ISFM), enables policy update with only samples from a user-specified sampling distribution rather than the unknown target distribution. We develop a theoretical analysis of ISFM, characterizing how different choices of sampling distributions affect the learning efficiency. Finally, we conduct a case study of our algorithm on the max-entropy linear quadratic regulator problems, demonstrating that the proposed algorithm learns the optimal action distribution. --- ### Learning to Feel the Future: DreamTacVLA for Contact-Rich Manipulation Authors: Guo Ye, Zexi Zhang, Xu Zhao, Shang Wu, Haoran Lu, Shihan Lu, Han Liu Published: 2025-12-29 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2512.23864v4 Vision-Language-Action (VLA) models have shown remarkable generalization by mapping web-scale knowledge to robotic control, yet they remain blind to physical contact. Consequently, they struggle with contact-rich manipulation tasks that require reasoning about force, texture, and slip. While some approaches incorporate low-dimensional tactile signals, they fail to capture the high-resolution dynamics essential for such interactions. To address this limitation, we introduce DreamTacVLA, a framework that grounds VLA models in contact physics by learning to feel the future. Our model adopts a hierarchical perception scheme in which high-resolution tactile images serve as micro-vision inputs coupled with wrist-camera local vision and third-person macro vision. To reconcile these multi-scale sensory streams, we first train a unified policy with a Hierarchical Spatial Alignment (HSA) loss that aligns tactile tokens with their spatial counterparts in the wrist and third-person views. To further deepen the model's understanding of fine-grained contact dynamics, we finetune the system with a tactile world model that predicts future tactile signals. To mitigate tactile data scarcity and the wear-prone nature of tactile sensors, we construct a hybrid large-scale dataset sourced from both high-fidelity digital twin and real-world experiments. By anticipating upcoming tactile states, DreamTacVLA acquires a rich model of contact physics and conditions its actions on both real observations and imagined consequences. Across contact-rich manipulation tasks, it outperforms state-of-the-art VLA baselines, achieving up to 95% success, highlighting the importance of understanding physical contact for robust, touch-aware robotic agents. --- ### Probing the Limits of Compressive Memory: A Study of Infini-Attention in Small-Scale Pretraining Authors: Ruizhe Huang, Kexuan Zhang, Yihao Fang, Baifeng Yu Published: 2025-12-29 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2512.23862v1 This study investigates small-scale pretraining for Small Language Models (SLMs) to enable efficient use of limited data and compute, improve accessibility in low-resource settings and reduce costs. To enhance long-context extrapolation in compact models, we focus on Infini-attention, which builds a compressed memory from past segments while preserving local attention. In our work, we conduct an empirical study using 300M-parameter LLaMA models pretrained with Infini-attention. The model demonstrates training stability and outperforms the baseline in long-context retrieval. We identify the balance factor as a key part of the model performance, and we found that retrieval accuracy drops with repeated memory compressions over long sequences. Even so, Infini-attention still effectively compensates for the SLM's limited parameters. Particularly, despite performance degradation at a 16,384-token context, the Infini-attention model achieves up to 31% higher accuracy than the baseline. Our findings suggest that achieving robust long-context capability in SLMs benefits from architectural memory like Infini-attention. --- ### Lifelong Domain Adaptive 3D Human Pose Estimation Authors: Qucheng Peng, Hongfei Xue, Pu Wang, Chen Chen Published: 2025-12-29 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.23860v2 3D Human Pose Estimation (3D HPE) is vital in various applications, from person re-identification and action recognition to virtual reality. However, the reliance on annotated 3D data collected in controlled environments poses challenges for generalization to diverse in-the-wild scenarios. Existing domain adaptation (DA) paradigms like general DA and source-free DA for 3D HPE overlook the issues of non-stationary target pose datasets. To address these challenges, we propose a novel task named lifelong domain adaptive 3D HPE. To our knowledge, we are the first to introduce the lifelong domain adaptation to the 3D HPE task. In this lifelong DA setting, the pose estimator is pretrained on the source domain and subsequently adapted to distinct target domains. Moreover, during adaptation to the current target domain, the pose estimator cannot access the source and all the previous target domains. The lifelong DA for 3D HPE involves overcoming challenges in adapting to current domain poses and preserving knowledge from previous domains, particularly combating catastrophic forgetting. We present an innovative Generative Adversarial Network (GAN) framework, which incorporates 3D pose generators, a 2D pose discriminator, and a 3D pose estimator. This framework effectively mitigates domain shifts and aligns original and augmented poses. Moreover, we construct a novel 3D pose generator paradigm, integrating pose-aware, temporal-aware, and domain-aware knowledge to enhance the current domain's adaptation and alleviate catastrophic forgetting on previous domains. Our method demonstrates superior performance through extensive experiments on diverse domain adaptive 3D HPE datasets. --- ### Seeking Late Night Life Lines: Experiences of Conversational AI Use in Mental Health Crisis Authors: Leah Hope Ajmani, Arka Ghosh, Benjamin Kaveladze, Eugenia Kim, Keertana Namuduri, Theresa Nguyen, Ebele Okoli, Jessica Schleider, Denae Ford, Jina Suh Published: 2025-12-29 Categories: cs.HC, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2512.23859v1 Online, people often recount their experiences turning to conversational AI agents (e.g., ChatGPT, Claude, Copilot) for mental health support -- going so far as to replace their therapists. These anecdotes suggest that AI agents have great potential to offer accessible mental health support. However, it's unclear how to meet this potential in extreme mental health crisis use cases. In this work, we explore the first-person experience of turning to a conversational AI agent in a mental health crisis. From a testimonial survey (n = 53) of lived experiences, we find that people use AI agents to fill the in-between spaces of human support; they turn to AI due to lack of access to mental health professionals or fears of burdening others. At the same time, our interviews with mental health experts (n = 16) suggest that human-human connection is an essential positive action when managing a mental health crisis. Using the stages of change model, our results suggest that a responsible AI crisis intervention is one that increases the user's preparedness to take a positive action while de-escalating any intended negative action. We discuss the implications of designing conversational AI agents as bridges towards human-human connection rather than ends in themselves. --- ### Yggdrasil: Bridging Dynamic Speculation and Static Runtime for Latency-Optimal Tree-Based LLM Decoding Authors: Yue Guan, Changming Yu, Shihan Fang, Weiming Hu, Zaifeng Pan, Zheng Wang, Zihan Liu, Yangjie Zhou, Yufei Ding, Minyi Guo, Jingwen Leng Published: 2025-12-29 Categories: cs.LG, cs.PL arXiv: https://arxiv.org/abs/2512.23858v1 Speculative decoding improves LLM inference by generating and verifying multiple tokens in parallel, but existing systems suffer from suboptimal performance due to a mismatch between dynamic speculation and static runtime assumptions. We present Yggdrasil, a co-designed system that enables latency-optimal speculative decoding through context-aware tree drafting and compiler-friendly execution. Yggdrasil introduces an equal-growth tree structure for static graph compatibility, a latency-aware optimization objective for draft selection, and stage-based scheduling to reduce overhead. Yggdrasil supports unmodified LLMs and achieves up to $3.98\times$ speedup over state-of-the-art baselines across multiple hardware setups. --- ### Flow Matching Neural Processes Authors: Hussen Abu Hamad, Dan Rosenbaum Published: 2025-12-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.23853v1 Neural processes (NPs) are a class of models that learn stochastic processes directly from data and can be used for inference, sampling and conditional sampling. We introduce a new NP model based on flow matching, a generative modeling paradigm that has demonstrated strong performance on various data modalities. Following the NP training framework, the model provides amortized predictions of conditional distributions over any arbitrary points in the data. Compared to previous NP models, our model is simple to implement and can be used to sample from conditional distributions using an ODE solver, without requiring auxiliary conditioning methods. In addition, the model provides a controllable tradeoff between accuracy and running time via the number of steps in the ODE solver. We show that our model outperforms previous state-of-the-art neural process methods on various benchmarks including synthetic 1D Gaussian processes data, 2D images, and real-world weather data. --- ### Trellis: Learning to Compress Key-Value Memory in Attention Models Authors: Mahdi Karami, Ali Behrouz, Praneeth Kacham, Vahab Mirrokni Published: 2025-12-29 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2512.23852v1 Transformers, while powerful, suffer from quadratic computational complexity and the ever-growing Key-Value (KV) cache of the attention mechanism. This paper introduces Trellis, a novel Transformer architecture with bounded memory that learns how to compress its key-value memory dynamically at test time. Trellis replaces the standard KV cache with a fixed-size memory and train a two-pass recurrent compression mechanism to store new keys and values into memory. To achieve this, it leverages an online gradient descent procedure with a forget gate, enabling the compressed memory to be updated recursively while learning to retain important contextual information from incoming tokens at test time. Extensive experiments on language modeling, common-sense reasoning, recall-intensive tasks, and time series show that the proposed architecture outperforms strong baselines. Notably, its performance gains increase as the sequence length grows, highlighting its potential for long-context applications. --- ### TinyHistory: Lightweight Video History Embeddings via Two-Stage Context Learning Authors: Lvmin Zhang, Shengqu Cai, Muyang Li, Chong Zeng, Beijia Lu, Anyi Rao, Song Han, Gordon Wetzstein, Maneesh Agrawala Published: 2025-12-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.23851v6 History context is central to autoregressive video generation, driving consistency and storytelling for both commercial models and personal use cases. For example, personal users, offline workflows, and individual-scale finetuning need to encode longer video histories under tight compute and memory budgets. We observe that content and identity consistency is an essential requirement, and that complete, uninterrupted history coverage together with content query and interpretation capabilities is broadly desired. We present TinyHistory, a lightweight history embedding learned through two-stage context learning. In the first stage, we pretrain the encoder on large-scale video data with a randomized frame query objective; in the second stage, we repurpose the pretrained encoder within an autoregressive video diffusion model to learn content-level consistency. As a result, we show that the learned lightweight embeddings achieve consistency comparable (by VLM, VBench, ELO, etc) to heavier alternatives, while reducing training overhead and extending the encodable history length within a given memory budget. We conduct ablation studies to analyze the influence and trade-offs of each component. --- ### The Drill-Down and Fabricate Test (DDFT): A Protocol for Measuring Epistemic Robustness in Language Models Authors: Rahul Baxi Published: 2025-12-29 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2512.23850v2 Current language model evaluations measure what models know under ideal conditions but not how robustly they know it under realistic stress. Static benchmarks like MMLU and TruthfulQA cannot distinguish a model that lacks knowledge from one whose verification mechanisms collapse when information degrades or adversaries probe for weaknesses. We introduce the Drill-Down and Fabricate Test (DDFT), a protocol that measures epistemic robustness: a model's ability to maintain factual accuracy under progressive semantic compression and adversarial fabrication. We propose a two-system cognitive model comprising a Semantic System that generates fluent text and an Epistemic Verifier that validates factual accuracy. Our findings, based on evaluating 9 frontier models across 8 knowledge domains at 5 compression levels (1,800 turn-level evaluations), reveal that epistemic robustness is orthogonal to conventional design paradigms. Neither parameter count (r=0.083, p=0.832) nor architectural type (r=0.153, p=0.695) significantly predicts robustness, suggesting it emerges from training methodology and verification mechanisms distinct from current approaches. Error detection capability strongly predicts overall robustness (rho=-0.817, p=0.007), indicating this is the critical bottleneck. We find that flagship models exhibit brittleness despite their scale, while smaller models can achieve robust performance, challenging assumptions about the relationship between model size and reliability. The DDFT framework provides both theoretical foundation and practical tools for assessing epistemic robustness before deployment in critical applications. --- ### Security Without Detection: Economic Denial as a Primitive for Edge and IoT Defense Authors: Samaresh Kumar Singh, Joyjit Roy, Sriharsha Anand Pushkala Published: 2025-12-29 Categories: cs.CR, cs.AI, cs.DC, cs.LG arXiv: https://arxiv.org/abs/2512.23849v2 Sophisticated attackers can evade detection-based security by using encryption, stealth tactics, and low-rate attack patterns. This challenge is particularly acute in Internet of Things (IoT) and edge environments, where limited resources make ML-based intrusion detection systems impractical. Hereby, we present Economic Denial Security (EDS), a framework that renders attacks economically infeasible rather than trying to detect them. EDS exploits a fundamental asymmetry. Defenders control their own environment, whereas attackers do not. The four mechanisms in this framework amplify attack costs superlinearly. These mechanisms include adaptive computational puzzles, decoy-driven interaction entropy, temporal stretching, and bandwidth taxation. This paper uses game theory to mathematically prove the optimal configuration of EDS, and we found that combining multiple safety mechanisms usually costs 2.1 times as much as using them separately, a key trade-off to consider during design. The good news is that EDS is extremely efficient, using less than 12 KB of memory, making it practical to run on small embedded devices like microcontrollers rather than on expensive servers. EDS is tested on 20 different IoT devices under four attack scenarios. The results showed that attacks slow down significantly, costs become asymmetric, attack success rates drop, and the system adds only 20 ms of latency with no false positive results. When tested against real malware (Mirai, Torii, and Hajime), combining EDS with machine learning detection improved protection from 67 % to 88 %. Adding both techniques together reached 94 % protection, a 27 % improvement overall. Unlike traditional detection-based approaches, EDS operates independently, without requiring attack identification, making it practical for resource-limited IoT devices where other methods simply don't work. --- ### Integrating Domain Knowledge for Financial QA: A Multi-Retriever RAG Approach with LLMs Authors: Yukun Zhang, Stefan Elbl Droguett, Samyak Jain Published: 2025-12-29 Categories: cs.CL, cs.CE, cs.LG arXiv: https://arxiv.org/abs/2512.23848v1 This research project addresses the errors of financial numerical reasoning Question Answering (QA) tasks due to the lack of domain knowledge in finance. Despite recent advances in Large Language Models (LLMs), financial numerical questions remain challenging because they require specific domain knowledge in finance and complex multi-step numeric reasoning. We implement a multi-retriever Retrieval Augmented Generators (RAG) system to retrieve both external domain knowledge and internal question contexts, and utilize the latest LLM to tackle these tasks. Through comprehensive ablation experiments and error analysis, we find that domain-specific training with the SecBERT encoder significantly contributes to our best neural symbolic model surpassing the FinQA paper's top model, which serves as our baseline. This suggests the potential superior performance of domain-specific training. Furthermore, our best prompt-based LLM generator achieves the state-of-the-art (SOTA) performance with significant improvement (>7%), yet it is still below the human expert performance. This study highlights the trade-off between hallucinations loss and external knowledge gains in smaller models and few-shot examples. For larger models, the gains from external facts typically outweigh the hallucination loss. Finally, our findings confirm the enhanced numerical reasoning capabilities of the latest LLM, optimized for few-shot learning. --- ### Detecting Lookahead Bias in LLM Forecasts Authors: Zhenyu Gao, Wenxi Jiang, Yutong Yan Published: 2025-12-29 Categories: q-fin.GN, cs.LG, q-fin.TR arXiv: https://arxiv.org/abs/2512.23847v2 We develop a statistical procedure to detect lookahead bias in economic forecasts generated by large language models (LLMs). Using a date-only recall query for a firm-date pair, we estimate the probability that the LLM has internalized information about the realized outcome, a statistic we term Lookahead Propensity (LAP). LAP is materially positive throughout the in-sample period and collapses essentially to zero right after the training-data cutoff. We show that a positive interaction between LAP and the LLM forecast in an accuracy regression indicates lookahead-bias contamination, and apply the test to two forecasting tasks: news headlines predicting stock returns and earnings call transcripts predicting capital expenditures. In both applications, the LLM forecast's predictive power is amplified on high-LAP firm-date pairs, and the interaction loses significance on post-training-cutoff samples. Our test provides a cost-efficient, diagnostic tool for assessing the validity and reliability of LLM-generated forecasts. --- ### From Correctness to Collaboration: Toward a Human-Centered Framework for Evaluating AI Agent Behavior in Software Engineering Authors: Tao Dong, Harini Sampath, Ja Young Lee, Sherry Y. Shi, Andrew Macvean Published: 2025-12-29 Categories: cs.SE, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2512.23844v1 As Large Language Models (LLMs) evolve from code generators into collaborative partners for software engineers, our methods for evaluation are lagging. Current benchmarks, focused on code correctness, fail to capture the nuanced, interactive behaviors essential for successful human-AI partnership. To bridge this evaluation gap, this paper makes two core contributions. First, we present a foundational taxonomy of desirable agent behaviors for enterprise software engineering, derived from an analysis of 91 sets of user-defined agent rules. This taxonomy defines four key expectations of agent behavior: Adhere to Standards and Processes, Ensure Code Quality and Reliability, Solving Problems Effectively, and Collaborating with the User. Second, recognizing that these expectations are not static, we introduce the Context-Adaptive Behavior (CAB) Framework. This emerging framework reveals how behavioral expectations shift along two empirically-derived axes: the Time Horizon (from immediate needs to future ideals), established through interviews with 15 expert engineers, and the Type of Work (from enterprise production to rapid prototyping, for example), identified through a prompt analysis of a prototyping agent. Together, these contributions offer a human-centered foundation for designing and evaluating the next generation of AI agents, moving the field's focus from the correctness of generated code toward the dynamics of true collaborative intelligence. --- ### Adversarial Lens: Exploiting Attention Layers to Generate Adversarial Examples for Evaluation Authors: Kaustubh Dhole Published: 2025-12-29 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.23837v1 Recent advances in mechanistic interpretability suggest that intermediate attention layers encode token-level hypotheses that are iteratively refined toward the final output. In this work, we exploit this property to generate adversarial examples directly from attention-layer token distributions. Unlike prompt-based or gradient-based attacks, our approach leverages model-internal token predictions, producing perturbations that are both plausible and internally consistent with the model's own generation process. We evaluate whether tokens extracted from intermediate layers can serve as effective adversarial perturbations for downstream evaluation tasks. We conduct experiments on argument quality assessment using the ArgQuality dataset, with LLaMA-3.1-Instruct-8B serving as both the generator and evaluator. Our results show that attention-based adversarial examples lead to measurable drops in evaluation performance while remaining semantically similar to the original inputs. However, we also observe that substitutions drawn from certain layers and token positions can introduce grammatical degradation, limiting their practical effectiveness. Overall, our findings highlight both the promise and current limitations of using intermediate-layer representations as a principled source of adversarial examples for stress-testing LLM-based evaluation pipelines. --- ### Retrieval Augmented Question Answering: When Should LLMs Admit Ignorance? Authors: Dingmin Wang, Ji Ma, Shankar Kumar Published: 2025-12-29 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.23836v1 The success of expanded context windows in Large Language Models (LLMs) has driven increased use of broader context in retrieval-augmented generation. We investigate the use of LLMs for retrieval augmented question answering. While longer contexts make it easier to incorporate targeted knowledge, they introduce more irrelevant information that hinders the model's generation process and degrades its performance. To address the issue, we design an adaptive prompting strategy which involves splitting the retrieved information into smaller chunks and sequentially prompting a LLM to answer the question using each chunk. Adjusting the chunk size allows a trade-off between incorporating relevant information and reducing irrelevant information. Experimental results on three open-domain question answering datasets demonstrate that the adaptive strategy matches the performance of standard prompting while using fewer tokens. Our analysis reveals that when encountering insufficient information, the LLM often generates incorrect answers instead of declining to respond, which constitutes a major source of error. This finding highlights the need for further research into enhancing LLMs' ability to effectively decline requests when faced with inadequate information. --- ### Explaining News Bias Detection: A Comparative SHAP Analysis of Transformer Model Decision Mechanisms Authors: Himel Ghosh Published: 2025-12-29 Categories: cs.CL, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2512.23835v1 Automated bias detection in news text is heavily used to support journalistic analysis and media accountability, yet little is known about how bias detection models arrive at their decisions or why they fail. In this work, we present a comparative interpretability study of two transformer-based bias detection models: a bias detector fine-tuned on the BABE dataset and a domain-adapted pre-trained RoBERTa model fine-tuned on the BABE dataset, using SHAP-based explanations. We analyze word-level attributions across correct and incorrect predictions to characterize how different model architectures operationalize linguistic bias. Our results show that although both models attend to similar categories of evaluative language, they differ substantially in how these signals are integrated into predictions. The bias detector model assigns stronger internal evidence to false positives than to true positives, indicating a misalignment between attribution strength and prediction correctness and contributing to systematic over-flagging of neutral journalistic content. In contrast, the domain-adaptive model exhibits attribution patterns that better align with prediction outcomes and produces 63\% fewer false positives. We further demonstrate that model errors arise from distinct linguistic mechanisms, with false positives driven by discourse-level ambiguity rather than explicit bias cues. These findings highlight the importance of interpretability-aware evaluation for bias detection systems and suggest that architectural and training choices critically affect both model reliability and deployment suitability in journalistic contexts. --- ### Artificial Intelligence for All? Brazilian Teachers on Ethics, Equity, and the Everyday Challenges of AI in Education Authors: Bruno Florentino, Camila Sestito, Wellington Cruz, André de Carvalho, Robson Bonidia Published: 2025-12-29 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2512.23834v2 This study examines the perceptions of Brazilian K-12 education teachers regarding the use of AI in education, specifically General Purpose AI. This investigation employs a quantitative analysis approach, extracting information from a questionnaire completed by 346 educators from various regions of Brazil regarding their AI literacy and use. Educators vary in their educational level, years of experience, and type of educational institution. The analysis of the questionnaires shows that although most educators had only basic or limited knowledge of AI (80.3\%), they showed a strong interest in its application, particularly for the creation of interactive content (80.6%), lesson planning (80.2%), and personalized assessment (68.6%). The potential of AI to promote inclusion and personalized learning is also widely recognized (65.5%). The participants emphasized the importance of discussing ethics and digital citizenship, reflecting on technological dependence, biases, transparency, and responsible use of AI, aligning with critical education and the development of conscious students. Despite enthusiasm for the pedagogical potential of AI, significant structural challenges were identified, including a lack of training (43.4%), technical support (41.9%), and limitations of infrastructure, such as low access to computers, reliable Internet connections, and multimedia resources in schools. The study shows that Brazil is still in a bottom-up model for AI integration, missing official curricula to guide its implementation and structured training for teachers and students. Furthermore, effective implementation of AI depends on integrated public policies, adequate teacher training, and equitable access to technology, promoting ethical, inclusive, and contextually grounded adoption of AI in Brazilian K-12 education. --- ### Exploiting the Prior of Generative Time Series Imputation Authors: YuYang Miao, Chang Li, Zehua Chen Published: 2025-12-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.23832v1 Time series imputation, i.e., filling the missing values of a time recording, finds various applications in electricity, finance, and weather modelling. Previous methods have introduced generative models such as diffusion probabilistic models and Schrodinger bridge models to conditionally generate the missing values from Gaussian noise or directly from linear interpolation results. However, as their prior is not informative to the ground-truth target, their generation process inevitably suffer increased burden and limited imputation accuracy. In this work, we present Bridge-TS, building a data-to-data generation process for generative time series imputation and exploiting the design of prior with two novel designs. Firstly, we propose expert prior, leveraging a pretrained transformer-based module as an expert to fill the missing values with a deterministic estimation, and then taking the results as the prior of ground truth target. Secondly, we explore compositional priors, utilizing several pretrained models to provide different estimation results, and then combining them in the data-to-data generation process to achieve a compositional priors-to-target imputation process. Experiments conducted on several benchmark datasets such as ETT, Exchange, and Weather show that Bridge-TS reaches a new record of imputation accuracy in terms of mean square error and mean absolute error, demonstrating the superiority of improving prior for generative time series imputation. --- ### Deep learning methods for inverse problems using connections between proximal operators and Hamilton-Jacobi equations Authors: Oluwatosin Akande, Gabriel P. Langlois, Akwum Onwunta Published: 2025-12-29 Categories: math.NA, cs.LG arXiv: https://arxiv.org/abs/2512.23829v3 Inverse problems are important mathematical problems that seek to recover model parameters from noisy data. Since inverse problems are often ill-posed, they require regularization or incorporation of prior information about the underlying model or unknown variables. Proximal operators, ubiquitous in nonsmooth optimization, are central to this because they encode priors and yield efficient iterative algorithms. They have also recently become key to modern machine learning methods, e.g., plug-and-play methods with learned denoisers and deep neural architectures for learning priors of proximal operators. The latter was developed partly due to recent work characterizing proximal operators of nonconvex priors as subdifferentials of convex potentials. In this work, we propose to leverage connections between proximal operators and Hamilton--Jacobi partial differential equations (HJ PDEs) to develop deep learning architectures for learning the prior. In contrast to other existing methods, we learn the prior directly without recourse to inverting the prior after training. We present numerical results in dimensions up to $64$, where the recovered prior is evaluated in a single forward pass. --- ### MS-SSM: A Multi-Scale State Space Model for Efficient Sequence Modeling Authors: Mahdi Karami, Ali Behrouz, Peilin Zhong, Razvan Pascanu, Vahab Mirrokni Published: 2025-12-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.23824v1 State-space models (SSMs) have recently attention as an efficient alternative to computationally expensive attention-based models for sequence modeling. They rely on linear recurrences to integrate information over time, enabling fast inference, parallelizable training, and control over recurrence stability. However, traditional SSMs often suffer from limited effective memory, requiring larger state sizes for improved recall. Moreover, existing SSMs struggle to capture multi-scale dependencies, which are essential for modeling complex structures in time series, images, and natural language. This paper introduces a multi-scale SSM framework that addresses these limitations by representing sequence dynamics across multiple resolution and processing each resolution with specialized state-space dynamics. By capturing both fine-grained, high-frequency patterns and coarse, global trends, MS-SSM enhances memory efficiency and long-range modeling. We further introduce an input-dependent scale-mixer, enabling dynamic information fusion across resolutions. The proposed approach significantly improves sequence modeling, particularly in long-range and hierarchical tasks, while maintaining computational efficiency. Extensive experiments on benchmarks, including Long Range Arena, hierarchical reasoning, time series classification, and image recognition, demonstrate that MS-SSM consistently outperforms prior SSM-based models, highlighting the benefits of multi-resolution processing in state-space architectures. --- ### Video-Based Performance Evaluation for ECR Drills in Synthetic Training Environments Authors: Surya Rayala, Marcos Quinones-Grueiro, Naveeduddin Mohammed, Ashwin T S, Benjamin Goldberg, Randall Spain, Paige Lawton, Gautam Biswas Published: 2025-12-29 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.23819v1 Effective urban warfare training requires situational awareness and muscle memory, developed through repeated practice in realistic yet controlled environments. A key drill, Enter and Clear the Room (ECR), demands threat assessment, coordination, and securing confined spaces. The military uses Synthetic Training Environments that offer scalable, controlled settings for repeated exercises. However, automatic performance assessment remains challenging, particularly when aiming for objective evaluation of cognitive, psychomotor, and teamwork skills. Traditional methods often rely on costly, intrusive sensors or subjective human observation, limiting scalability and accuracy. This paper introduces a video-based assessment pipeline that derives performance analytics from training videos without requiring additional hardware. By utilizing computer vision models, the system extracts 2D skeletons, gaze vectors, and movement trajectories. From these data, we develop task-specific metrics that measure psychomotor fluency, situational awareness, and team coordination. These metrics feed into an extended Cognitive Task Analysis (CTA) hierarchy, which employs a weighted combination to generate overall performance scores for teamwork and cognition. We demonstrate the approach with a case study of real-world ECR drills, providing actionable, domain specific metrics that capture individual and team performance. We also discuss how these insights can support After Action Reviews with interactive dashboards within Gamemaster and the Generalized Intelligent Framework for Tutoring (GIFT), providing intuitive and understandable feedback. We conclude by addressing limitations, including tracking difficulties, ground-truth validation, and the broader applicability of our approach. Future work includes expanding analysis to 3D video data and leveraging video analysis to enable scalable evaluation within STEs. --- ### Energy-Tweedie: Score meets Score, Energy meets Energy Authors: Andrej Leban Published: 2025-12-29 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2512.23818v2 Denoising and score estimation are classically linked through Tweedie's formula, which relates the posterior mean under Gaussian noise to the Stein score of the noisy marginal. In this work, we extend this perspective beyond Gaussian noise to a broad class of Gibbs (energy-based) noise distributions, with the generalized Gaussian family as the running example. We derive the Energy-Tweedie identity: when the denoising posterior is viewed through the lens of scoring rules, the path derivative of a kernel scoring rule defined by the noise potential recovers the Stein score of the noisy marginal. The rule's propriety is determined by the noise potential alone. Thus, the familiar correspondence between Gaussian noise, posterior means, squared loss, and Tweedie's formula is lifted to a distributional correspondence between Gibbs noise distributions, full posterior laws, kernel scoring rules, and the Energy-Tweedie identity, yielding one Tweedie-style relation for each noise potential. Among its consequences, this identity gives a posterior-samples-to-score route to score estimation, yields a principled criterion for estimating unknown noise parameters, and enables diffusion-style sampling along user-chosen paths through the noise-parameter space, supplying the score-based perspective on recent generative methods trained with scoring rules. --- ### Quantum Error Mitigation with Attention Graph Transformers for Burgers Equation Solvers on NISQ Hardware Authors: Seyed Mohamad Ali Tousi, Adib Bazgir, Yuwen Zhang, G. N. DeSouza Published: 2025-12-29 Categories: quant-ph, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.23817v1 We present a hybrid quantum-classical framework augmented with learned error mitigation for solving the viscous Burgers equation on noisy intermediate-scale quantum (NISQ) hardware. Using the Cole-Hopf transformation, the nonlinear Burgers equation is mapped to a diffusion equation, discretized on uniform grids, and encoded into a quantum state whose time evolution is approximated via Trotterized nearest-neighbor circuits implemented in Qiskit. Quantum simulations are executed on noisy Aer backends and IBM superconducting quantum devices and are benchmarked against high-accuracy classical solutions obtained using a Krylov-based solver applied to the corresponding discretized Hamiltonian. From measured quantum amplitudes, we reconstruct the velocity field and evaluate physical and numerical diagnostics, including the L2 error, shock location, and dissipation rate, both with and without zero-noise extrapolation (ZNE). To enable data-driven error mitigation, we construct a large parametric dataset by sweeping viscosity, time step, grid resolution, and boundary conditions, producing matched tuples of noisy, ZNE-corrected, hardware, and classical solutions together with detailed circuit metadata. Leveraging this dataset, we train an attention-based graph neural network that incorporates circuit structure, light-cone information, global circuit parameters, and noisy quantum outputs to predict error-mitigated solutions. Across a wide range of parameters, the learned model consistently reduces the discrepancy between quantum and classical solutions beyond what is achieved by ZNE alone. We discuss extensions of this approach to higher-dimensional Burgers systems and more general quantum partial differential equation solvers, highlighting learned error mitigation as a promising complement to physics-based noise reduction techniques on NISQ devices. --- ### Improved Bounds for Private and Robust Alignment Authors: Wenqian Weng, Yi He, Xingyu Zhou Published: 2025-12-29 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.23816v2 In this paper, we study the private and robust alignment of language models from a theoretical perspective by establishing upper bounds on the suboptimality gap in both offline and online settings. We consider preference labels subject to privacy constraints and/or adversarial corruption, and analyze two distinct interplays between them: privacy-first and corruption-first. For the privacy-only setting, we show that log loss with an MLE-style algorithm achieves near-optimal rates, in contrast to conventional wisdom. For the joint privacy-and-corruption setting, we first demonstrate that existing offline algorithms in fact provide stronger guarantees -- simultaneously in terms of corruption level and privacy parameters -- than previously known, which further yields improved bounds in the corruption-only regime. In addition, we also present the first set of results for private and robust online alignment. Our results are enabled by new uniform convergence guarantees for log loss and square loss under privacy and corruption, which we believe have broad applicability across learning theory and statistics. --- ### StressRoBERTa: Cross-Condition Transfer Learning from Depression, Anxiety, and PTSD to Stress Detection Authors: Amal Alqahtani, Efsun Kayi, Mona Diab Published: 2025-12-29 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.23813v1 The prevalence of chronic stress represents a significant public health concern, with social media platforms like Twitter serving as important venues for individuals to share their experiences. This paper introduces StressRoBERTa, a cross-condition transfer learning approach for automatic detection of self-reported chronic stress in English tweets. The investigation examines whether continual training on clinically related conditions (depression, anxiety, PTSD), disorders with high comorbidity with chronic stress, improves stress detection compared to general language models and broad mental health models. RoBERTa is continually trained on the Stress-SMHD corpus (108M words from users with self-reported diagnoses of depression, anxiety, and PTSD) and fine-tuned on the SMM4H 2022 Task 8 dataset. StressRoBERTa achieves 82% F1-score, outperforming the best shared task system (79% F1) by 3 percentage points. The results demonstrate that focused cross-condition transfer from stress-related disorders (+1% F1 over vanilla RoBERTa) provides stronger representations than general mental health training. Evaluation on Dreaddit (81% F1) further demonstrates transfer from clinical mental health contexts to situational stress discussions. --- ### Zero-Trust Agentic Federated Learning for Secure IIoT Defense Systems Authors: Samaresh Kumar Singh, Joyjit Roy, Martin So Published: 2025-12-29 Categories: cs.LG, cs.AI, cs.CR, cs.DC, cs.MA arXiv: https://arxiv.org/abs/2512.23809v1 Recent attacks on critical infrastructure, including the 2021 Oldsmar water treatment breach and 2023 Danish energy sector compromises, highlight urgent security gaps in Industrial IoT (IIoT) deployments. While Federated Learning (FL) enables privacy-preserving collaborative intrusion detection, existing frameworks remain vulnerable to Byzantine poisoning attacks and lack robust agent authentication. We propose Zero-Trust Agentic Federated Learning (ZTA-FL), a defense in depth framework combining: (1) TPM-based cryptographic attestation achieving less than 0.0000001 false acceptance rate, (2) a novel SHAP-weighted aggregation algorithm providing explainable Byzantine detection under non-IID conditions with theoretical guarantees, and (3) privacy-preserving on-device adversarial training. Comprehensive experiments across three IDS benchmarks (Edge-IIoTset, CIC-IDS2017, UNSW-NB15) demonstrate that ZTA-FL achieves 97.8 percent detection accuracy, 93.2 percent accuracy under 30 percent Byzantine attacks (outperforming FLAME by 3.1 percent, p less than 0.01), and 89.3 percent adversarial robustness while reducing communication overhead by 34 percent. We provide theoretical analysis, failure mode characterization, and release code for reproducibility. --- ### MiMo-Audio: Audio Language Models are Few-Shot Learners Authors: Xiaomi LLM-Core Team, :, Dong Zhang, Gang Wang, Jinlong Xue, Kai Fang, Liang Zhao, Rui Ma, Shuhuai Ren, Shuo Liu, Tao Guo, Weiji Zhuang et al. Published: 2025-12-29 Categories: cs.CL, cs.SD, eess.AS arXiv: https://arxiv.org/abs/2512.23808v1 Existing audio language models typically rely on task-specific fine-tuning to accomplish particular audio tasks. In contrast, humans are able to generalize to new audio tasks with only a few examples or simple instructions. GPT-3 has shown that scaling next-token prediction pretraining enables strong generalization capabilities in text, and we believe this paradigm is equally applicable to the audio domain. By scaling MiMo-Audio's pretraining data to over one hundred million of hours, we observe the emergence of few-shot learning capabilities across a diverse set of audio tasks. We develop a systematic evaluation of these capabilities and find that MiMo-Audio-7B-Base achieves SOTA performance on both speech intelligence and audio understanding benchmarks among open-source models. Beyond standard metrics, MiMo-Audio-7B-Base generalizes to tasks absent from its training data, such as voice conversion, style transfer, and speech editing. MiMo-Audio-7B-Base also demonstrates powerful speech continuation capabilities, capable of generating highly realistic talk shows, recitations, livestreaming and debates. At the post-training stage, we curate a diverse instruction-tuning corpus and introduce thinking mechanisms into both audio understanding and generation. MiMo-Audio-7B-Instruct achieves open-source SOTA on audio understanding benchmarks (MMSU, MMAU, MMAR, MMAU-Pro), spoken dialogue benchmarks (Big Bench Audio, MultiChallenge Audio) and instruct-TTS evaluations, approaching or surpassing closed-source models. Model checkpoints and full evaluation suite are available at https://github.com/XiaomiMiMo/MiMo-Audio. --- ### Fitted Q-Evaluation without Bellman Completeness via Occupancy Weighting Authors: Lars van der Laan, Nathan Kallus Published: 2025-12-29 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2512.23805v4 Fitted \(Q\)-evaluation (FQE) is a standard regression-based method for off-policy evaluation, but under distribution shift, value-function realizability alone does not ensure convergence, and existing analyses often require Bellman completeness. We trace this instability to a geometric mismatch: standard FQE projects Bellman targets in the norm induced by the offline distribution, which need not preserve Bellman contraction. We therefore study \emph{occupancy-weighted FQE}, which changes only the regression weights. Weighting by a target-policy discounted occupancy ratio aligns the projection norm with the target-policy dynamics and restores contraction of the population projected Bellman operator. We derive finite-sample guarantees with estimated occupancy ratios and function-class misspecification, separating finite-iteration, statistical, approximation, and ratio-estimation errors. Exact occupancy weighting removes the need for Bellman completeness; with estimated weights, approximate completeness and value-function realizability reduce sensitivity to ratio-estimation error, with exact realizability yielding higher-order dependence. Combining occupancy-weighted FQE with fitted occupancy-ratio evaluation gives an end-to-end guarantee governed by the complexities and direct approximation errors of the value-function and occupancy-ratio classes. Under coverage, joint realizability of these two classes suffices for consistent estimation without Bellman or critic-side completeness. Controlled experiments illustrate the projection-norm mechanism and the finite-sample tradeoff between contraction and coverage. --- ### TabMixNN: A Unified Deep Learning Framework for Structural Mixed Effects Modeling on Tabular Data Authors: Deniz Akdemir Published: 2025-12-29 Categories: cs.LG, stat.CO, stat.ME arXiv: https://arxiv.org/abs/2512.23787v1 We present TabMixNN, a flexible PyTorch-based deep learning framework that synthesizes classical mixed-effects modeling with modern neural network architectures for tabular data analysis. TabMixNN addresses the growing need for methods that can handle hierarchical data structures while supporting diverse outcome types including regression, classification, and multitask learning. The framework implements a modular three-stage architecture: (1) a mixed-effects encoder with variational random effects and flexible covariance structures, (2) backbone architectures including Generalized Structural Equation Models (GSEM) and spatial-temporal manifold networks, and (3) outcome-specific prediction heads supporting multiple outcome families. Key innovations include an R-style formula interface for accessibility, support for directed acyclic graph (DAG) constraints for causal structure learning, Stochastic Partial Differential Equation (SPDE) kernels for spatial modeling, and comprehensive interpretability tools including SHAP values and variance decomposition. We demonstrate the framework's flexibility through applications to longitudinal data analysis, genomic prediction, and spatial-temporal modeling. TabMixNN provides a unified interface for researchers to leverage deep learning while maintaining the interpretability and theoretical grounding of classical mixed-effects models. --- ### Bridging the Ex-Vivo to In-Vivo Gap: Synthetic Priors for Monocular Depth Estimation in Specular Surgical Environments Authors: Ankan Aich, Emma D. Ryan, Kris Moe, Isaac Schmale, Li-Xing Man, Yangming Lee Published: 2025-12-29 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2512.23786v2 Accurate Monocular Depth Estimation (MDE) is critical for autonomous robotic surgery. However, existing self-supervised methods often exhibit a severe "ex-vivo to in-vivo gap": they achieve high accuracy on public datasets but struggle in actual clinical deployments. This disparity arises because the severe specular reflections and fluid-filled deformations inherent to real surgeries. Models trained on noisy real-world pseudo-labels consequently suffer from severe boundary collapse. To address this, we leverage the high-fidelity synthetic priors of the \textit{Depth Anything V2} architecture, which inherently capture precise geometric details, and efficiently adapt them to the medical domain using Dynamic Vector Low-Rank Adaptation (DV-LORA). Our contributions are two-fold. Technically, our approach establishes a new state-of-the-art on the public SCARED dataset; under a novel physically-stratified evaluation protocol, it reduces Squared Relative Error by over 17\% in high-specularity regimes compared to strong baselines. Furthermore, to provide a rigorous reality check for the field, we introduce \textbf{ROCAL-T 90} (Real Operative CT-Aligned Laparoscopic Trajectories 90), the first real-surgery validation dataset featuring 90 clinical endoscopic sequences with sub-millimeter ($< 1$mm) ground-truth trajectories. Evaluations on ROCAL-T 90 demonstrate our model's superior robustness in true clinical settings. --- ### Prompt-Induced Over-Generation as Denial-of-Service: A Black-Box Attack-Side Benchmark Authors: Manu, Yi Guo, Kanchana Thilakarathna, Nirhoshan Sivaroopan, Jo Plested, Tim Lynar, Jack Yang, Wangli Yang Published: 2025-12-29 Categories: cs.CR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.23779v2 Large Language Models (LLMs) can be driven into over-generation, emitting thousands of tokens before producing an end-of-sequence (EOS) token. This degrades answer quality, inflates latency and cost, and can be weaponized as a denial-of-service (DoS) attack. Recent work has begun to study DoS-style prompt attacks, but typically focuses on a single attack algorithm or assumes white-box access, without an attack-side benchmark that compares prompt-based attackers in a black-box, query-only regime with a known tokenizer. We introduce such a benchmark and study two prompt-only attackers. The first is an Evolutionary Over-Generation Prompt Search (EOGen) that searches the token space for prefixes that suppress EOS and induce long continuations. The second is a goal-conditioned reinforcement learning attacker (RL-GOAL) that trains a network to generate prefixes conditioned on a target length. To characterize behavior, we introduce Over-Generation Factor (OGF): the ratio of produced tokens to a model's context window, along with stall and latency summaries. EOGen discovers short-prefix attacks that raise Phi-3 to OGF = 1.39 +/- 1.14 (Success@>=2: 25.2%); RL-GOAL nearly doubles severity to OGF = 2.70 +/- 1.43 (Success@>=2: 64.3%) and drives budget-hit non-termination in 46% of trials. --- ### A Survey on Graph Neural Networks for Fraud Detection in Ride Hailing Platforms Authors: Kanishka Hewageegana, Janani Harischandra, Nipuna Senanayake, Gihan Danansuriya, Kavindu Hapuarachchi, Pooja Illangarathne Published: 2025-12-29 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.23777v1 This study investigates fraud detection in ride hailing platforms through Graph Neural Networks (GNNs),focusing on the effectiveness of various models. By analyzing prevalent fraudulent activities, the research highlights and compares the existing work related to fraud detection which can be useful when addressing fraudulent incidents within the online ride hailing platforms. Also, the paper highlights addressing class imbalance and fraudulent camouflage. It also outlines a structured overview of GNN architectures and methodologies applied to anomaly detection, identifying significant methodological progress and gaps. The paper calls for further exploration into real-world applicability and technical improvements to enhance fraud detection strategies in the rapidly evolving ride-hailing industry. --- ### FineFT: Efficient and Risk-Aware Ensemble Reinforcement Learning for Futures Trading Authors: Molei Qin, Xinyu Cai, Yewen Li, Haochong Xia, Chuqiao Zong, Shuo Sun, Xinrun Wang, Bo An Published: 2025-12-29 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.23773v1 Futures are contracts obligating the exchange of an asset at a predetermined date and price, notable for their high leverage and liquidity and, therefore, thrive in the Crypto market. RL has been widely applied in various quantitative tasks. However, most methods focus on the spot and could not be directly applied to the futures market with high leverage because of 2 challenges. First, high leverage amplifies reward fluctuations, making training stochastic and difficult to converge. Second, prior works lacked self-awareness of capability boundaries, exposing them to the risk of significant loss when encountering new market state (e.g.,a black swan event like COVID-19). To tackle these challenges, we propose the Efficient and Risk-Aware Ensemble Reinforcement Learning for Futures Trading (FineFT), a novel three-stage ensemble RL framework with stable training and proper risk management. In stage I, ensemble Q learners are selectively updated by ensemble TD errors to improve convergence. In stage II, we filter the Q-learners based on their profitabilities and train VAEs on market states to identify the capability boundaries of the learners. In stage III, we choose from the filtered ensemble and a conservative policy, guided by trained VAEs, to maintain profitability and mitigate risk with new market states. Through extensive experiments on crypto futures in a high-frequency trading environment with high fidelity and 5x leverage, we demonstrate that FineFT outperforms 12 SOTA baselines in 6 financial metrics, reducing risk by more than 40% while achieving superior profitability compared to the runner-up. Visualization of the selective update mechanism shows that different agents specialize in distinct market dynamics, and ablation studies certify routing with VAEs reduces maximum drawdown effectively, and selective update improves convergence and performance. --- ### SB-TRPO: Towards Safe Reinforcement Learning with Hard Constraints Authors: Dominik Wagner, Ankit Kanwar, Luke Ong Published: 2025-12-29 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.23770v4 In safety-critical domains, reinforcement learning (RL) systems must satisfy strict, zero-cost safety constraints while achieving meaningful task performance. Existing model-free methods can struggle to achieve high safety without substantially compromising task performance. We introduce \emph{Safety-Biased Trust Region Policy Optimisation (SB-TRPO)}, a principled approach to RL with zero-cost constraints, which requires only a fixed fraction of the maximal cost reduction achievable within the trust region, thus retaining flexibility for reward optimisation. We show that the idealised update nevertheless converges to zero cost and maximal reward amongst zero-cost policies in finite MDPs. A practical gradient-based approximation provides local improvements in both safety and reward under suitable gradient alignment. Experiments on \emph{Safety Gymnasium} demonstrate high safety alongside strong task performance. --- ### Uncovering Discrimination Clusters: Quantifying and Explaining Systematic Fairness Violations Authors: Ranit Debnath Akash, Ashish Kumar, Verya Monjezi, Ashutosh Trivedi, Gang, Tan, Saeid Tizpaz-Niari Published: 2025-12-29 Categories: cs.SE, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.23769v1 Fairness in algorithmic decision-making is often framed in terms of individual fairness, which requires that similar individuals receive similar outcomes. A system violates individual fairness if there exists a pair of inputs differing only in protected attributes (such as race or gender) that lead to significantly different outcomes-for example, one favorable and the other unfavorable. While this notion highlights isolated instances of unfairness, it fails to capture broader patterns of systematic or clustered discrimination that may affect entire subgroups. We introduce and motivate the concept of discrimination clustering, a generalization of individual fairness violations. Rather than detecting single counterfactual disparities, we seek to uncover regions of the input space where small perturbations in protected features lead to k-significantly distinct clusters of outcomes. That is, for a given input, we identify a local neighborhood-differing only in protected attributes-whose members' outputs separate into many distinct clusters. These clusters reveal significant arbitrariness in treatment solely based on protected attributes that help expose patterns of algorithmic bias that elude pairwise fairness checks. We present HyFair, a hybrid technique that combines formal symbolic analysis (via SMT and MILP solvers) to certify individual fairness with randomized search to discover discriminatory clusters. This combination enables both formal guarantees-when no counterexamples exist-and the detection of severe violations that are computationally challenging for symbolic methods alone. Given a set of inputs exhibiting high k-unfairness, we introduce a novel explanation method to generate interpretable, decision-tree-style artifacts. Our experiments demonstrate that HyFair outperforms state-of-the-art fairness verification and local explanation methods. --- ### Enabling Physical AI at the Edge: Hardware-Accelerated Recovery of System Dynamics Authors: Bin Xu, Ayan Banerjee, Sandeep Gupta Published: 2025-12-29 Categories: cs.LG, cs.AI, cs.AR arXiv: https://arxiv.org/abs/2512.23767v1 Physical AI at the edge -- enabling autonomous systems to understand and predict real-world dynamics in real time -- requires hardware-efficient learning and inference. Model recovery (MR), which identifies governing equations from sensor data, is a key primitive for safe and explainable monitoring in mission-critical autonomous systems operating under strict latency, compute, and power constraints. However, state-of-the-art MR methods (e.g., EMILY and PINN+SR) rely on Neural ODE formulations that require iterative solvers and are difficult to accelerate efficiently on edge hardware. We present \textbf{MERINDA} (Model Recovery in Reconfigurable Dynamic Architecture), an FPGA-accelerated MR framework designed to make physical AI practical on resource-constrained devices. MERINDA replaces expensive Neural ODE components with a hardware-friendly formulation that combines (i) GRU-based discretized dynamics, (ii) dense inverse-ODE layers, (iii) sparsity-driven dropout, and (iv) lightweight ODE solvers. The resulting computation is structured for streaming parallelism, enabling critical kernels to be fully parallelized on the FPGA. Across four benchmark nonlinear dynamical systems, MERINDA delivers substantial gains over GPU implementations: \textbf{114$\times$ lower energy} (434~J vs.\ 49{,}375~J), \textbf{28$\times$ smaller memory footprint} (214~MB vs.\ 6{,}118~MB), and \textbf{1.68$\times$ faster training}, while matching state-of-the-art model-recovery accuracy. These results demonstrate that MERINDA can bring accurate, explainable MR to the edge for real-time monitoring of autonomous systems. --- ### A Granular Grassmannian Clustering Framework via the Schubert Variety of Best Fit Authors: Karim Salta, Michael Kirby, Chris Peterson Published: 2025-12-29 Categories: cs.LG, cs.CG, cs.CV, cs.DC arXiv: https://arxiv.org/abs/2512.23766v1 In many classification and clustering tasks, it is useful to compute a geometric representative for a dataset or a cluster, such as a mean or median. When datasets are represented by subspaces, these representatives become points on the Grassmann or flag manifold, with distances induced by their geometry, often via principal angles. We introduce a subspace clustering algorithm that replaces subspace means with a trainable prototype defined as a Schubert Variety of Best Fit (SVBF) - a subspace that comes as close as possible to intersecting each cluster member in at least one fixed direction. Integrated in the Linde-Buzo-Grey (LBG) pipeline, this SVBF-LBG scheme yields improved cluster purity on synthetic, image, spectral, and video action data, while retaining the mathematical structure required for downstream analysis. --- ### Entropy-Aware Token Rejection for Improving Speculative Decoding Authors: Tiancheng Su, Meicong Zhang, Guoxiu He Published: 2025-12-29 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.23765v2 Speculative decoding (SD) accelerates large language model (LLM) inference by using a lightweight draft model to propose tokens and a stronger target model to verify them. However, standard SD is mainly designed for acceleration, and its output quality is typically constrained by the target model. In this work, we propose Entropy-Aware Speculative Decoding (EASD), a lightweight and training-free extension of SD that improves reasoning quality through token-level entropy-guided rejection. EASD detects cases where both draft and target models exhibit high uncertainty while strongly overlapping in their top predictions. In such uncertain-agreement cases, EASD rejects the aligned token and resamples from the target distribution, preventing low-confidence errors from propagating. Experiments on challenging reasoning benchmarks show that EASD consistently improves accuracy over standard SD and reward-guided variants while maintaining comparable inference efficiency. Notably, EASD can surpass the standalone performance of the target model, suggesting that speculative decoding can serve not only as an acceleration method but also as an effective mechanism for improving reasoning quality. The code is available at https://github.com/ECNU-Text-Computing/EASD. --- ### Exploring Cumulative Effects in Survival Data Using Deep Learning Networks Authors: Kang-Chung Yang, Shinsheng Yuan Published: 2025-12-29 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2512.23764v1 In epidemiological research, modeling the cumulative effects of time-dependent exposures on survival outcomes presents a challenge due to their intricate temporal dynamics. Conventional spline-based statistical methods, though effective, require repeated data transformation for each spline parameter tuning, with survival analysis computations relying on the entire dataset, posing difficulties for large datasets. Meanwhile, existing neural network-based survival analysis methods focus on accuracy but often overlook the interpretability of cumulative exposure patterns. To bridge this gap, we introduce CENNSurv, a novel deep learning approach that captures dynamic risk relationships from time-dependent data. Evaluated on two diverse real-world datasets, CENNSurv revealed a multi-year lagged association between chronic environmental exposure and a critical survival outcome, as well as a critical short-term behavioral shift prior to subscription lapse. This demonstrates CENNSurv's ability to model complex temporal patterns with improved scalability. CENNSurv provides researchers studying cumulative effects a practical tool with interpretable insights. ---