# Research Papers — 2025-10 · bundle page 192 of 217

> Full-text markdown of papers #9551–9600 of 10843 published in 2025-10, newest first. AI-readable mirrors of the full 10843-paper 2025-10 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2025-10/page/192
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/191.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/193.md)

### From Moments to Models: Graphon-Mixture Learning for Mixup and Contrastive Learning

Authors: Ali Azizpour, Reza Ramezanpour, Santiago Segarra
Published: 2025-10-04
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.03690v4

Real-world graph datasets often arise from mixtures of populations, where graphs are generated by multiple distinct underlying distributions. In this work, we propose a unified framework that explicitly models graph data as a mixture of probabilistic graph generative models represented by graphons. To characterize and estimate these graphons, we leverage graph moments (motif densities) to cluster graphs generated from the same underlying model. We establish a novel theoretical guarantee, deriving a tighter bound showing that graphs sampled from structurally similar graphons exhibit similar motif densities with high probability. This result enables principled estimation of graphon mixture components. We show how incorporating estimated graphon mixture components enhances two widely used downstream paradigms: graph data augmentation via mixup and graph contrastive learning. By conditioning these methods on the underlying generative models, we develop graphon-mixture-aware mixup (GMAM) and model-aware graph contrastive learning (MGCL). Extensive experiments on both simulated and real-world datasets demonstrate strong empirical performance. In supervised learning, GMAM outperforms existing augmentation strategies, achieving new state-of-the-art accuracy on 6 out of 7 datasets. In unsupervised learning, MGCL performs competitively across seven benchmark datasets and achieves the lowest average rank overall.

---

### SAMSOD: Rethinking SAM Optimization for RGB-T Salient Object Detection

Authors: Zhengyi Liu, Xinrui Wang, Xianyong Fang, Zhengzheng Tu, Linbo Wang
Published: 2025-10-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.03689v1

RGB-T salient object detection (SOD) aims to segment attractive objects by combining RGB and thermal infrared images. To enhance performance, the Segment Anything Model has been fine-tuned for this task. However, the imbalance convergence of two modalities and significant gradient difference between high- and low- activations are ignored, thereby leaving room for further performance enhancement. In this paper, we propose a model called \textit{SAMSOD}, which utilizes unimodal supervision to enhance the learning of non-dominant modality and employs gradient deconfliction to reduce the impact of conflicting gradients on model convergence. The method also leverages two decoupled adapters to separately mask high- and low-activation neurons, emphasizing foreground objects by enhancing background learning. Fundamental experiments on RGB-T SOD benchmark datasets and generalizability experiments on scribble supervised RGB-T SOD, fully supervised RGB-D SOD datasets and full-supervised RGB-D rail surface defect detection all demonstrate the effectiveness of our proposed method.

---

### MedReflect: Teaching Medical LLMs to Self-Improve via Reflective Correction

Authors: Yue Huang, Yanyuan Chen, Dexuan Xu, Chenzhuo Zhao, Weihua Yue, Yu Huang
Published: 2025-10-04
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.03687v2

Medical problem-solving demands expert knowledge and intricate reasoning. Recent studies of large language models (LLMs) attempt to ease this complexity by introducing external knowledge verification through retrieval-augmented generation or by training on reasoning datasets. However, these approaches suffer from drawbacks such as retrieval overhead and high annotation costs, and they heavily rely on substituted external assistants to reach limited performance in medical field. In this paper, we introduce MedReflect, a generalizable framework designed to inspire LLMs with a physician-like reflective thinking mode. MedReflect generates a single-pass reflection chain that includes initial hypothesis generation, self-questioning, self-answering and decision refinement. This self-verified and self-reflective nature releases large language model's latent capability in medical problem-solving without external retrieval or heavy annotation. We demonstrate that MedReflect enables cost-efficient medical dataset construction. With only a minimal subset of randomly sampled training examples and lightweight fine-tuning, this approach achieves notable absolute accuracy improvements across a series of medical benchmarks while significantly cutting annotation requirements. Our results provide evidence that LLMs can learn to solve specialized medical problems via self-reflection and self-improvement, reducing reliance on external supervision and extensive task-specific fine-tuning data.

---

### The analogy theorem in Hoare logic

Authors: Nikitin Nikita
Published: 2025-10-04
Categories: stat.ML, cs.LG, math.LO, stat.CO, stat.ME
arXiv: https://arxiv.org/abs/2510.03685v1

The introduction of machine learning methods has led to significant advances in automation, optimization, and discoveries in various fields of science and technology. However, their widespread application faces a fundamental limitation: the transfer of models between data domains generally lacks a rigorous mathematical justification. The key problem is the lack of formal criteria to guarantee that a model trained on one type of data will retain its properties on another.This paper proposes a solution to this problem by formalizing the concept of analogy between data sets and models using first-order logic and Hoare logic.We formulate and rigorously prove a theorem that sets out the necessary and sufficient conditions for analogy in the task of knowledge transfer between machine learning models. Practical verification of the analogy theorem on model data obtained using the Monte Carlo method, as well as on MNIST and USPS data, allows us to achieving F1 scores of 0.84 and 0.88 for convolutional neural networks and random forests, respectively.The proposed approach not only allows us to justify the correctness of transfer between domains but also provides tools for comparing the applicability of models to different types of data.The main contribution of the work is a rigorous formalization of analogy at the level of program logic, providing verifiable guarantees of the correctness of knowledge transfer, which opens new opportunities for both theoretical research and the practical use of machine learning models in previously inaccessible areas.

---

### Model-Guided Microstimulation Steers Primate Visual Behavior

Authors: Johannes Mehrer, Ben Lonnqvist, Anna Mitola, Abdulkadir Gokce, Paolo Papale, Martin Schrimpf
Published: 2025-10-04
Categories: q-bio.NC, cs.CV
arXiv: https://arxiv.org/abs/2510.03684v1

Brain stimulation is a powerful tool for understanding cortical function and holds promise for therapeutic interventions in neuropsychiatric disorders. Initial visual prosthetics apply electric microstimulation to early visual cortex which can evoke percepts of simple symbols such as letters. However, these approaches are fundamentally limited by hardware constraints and the low-level representational properties of this cortical region. In contrast, higher-level visual areas encode more complex object representations and therefore constitute a promising target for stimulation - but determining representational targets that reliably evoke object-level percepts constitutes a major challenge. We here introduce a computational framework to causally model and guide stimulation of high-level cortex, comprising three key components: (1) a perturbation module that translates microstimulation parameters into spatial changes to neural activity, (2) topographic models that capture the spatial organization of cortical neurons and thus enable prototyping of stimulation experiments, and (3) a mapping procedure that links model-optimized stimulation sites back to primate cortex. Applying this framework in two macaque monkeys performing a visual recognition task, model-predicted stimulation experiments produced significant in-vivo changes in perceptual choices. Per-site model predictions and monkey behavior were strongly correlated, underscoring the promise of model-guided stimulation. Image generation further revealed a qualitative similarity between in-silico stimulation of face-selective sites and a patient's report of facephenes. This proof-of-principle establishes a foundation for model-guided microstimulation and points toward next-generation visual prosthetics capable of inducing more complex visual experiences.

---

### Fine-Tuning Large Language Models with QLoRA for Offensive Language Detection in Roman Urdu-English Code-Mixed Text

Authors: Nisar Hussain, Amna Qasim, Gull Mehak, Muhammad Zain, Momina Hafeez, Grigori Sidorov
Published: 2025-10-04
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.03683v2

The use of derogatory terms in languages that employ code mixing, such as Roman Urdu, presents challenges for Natural Language Processing systems due to unstated grammar, inconsistent spelling, and a scarcity of labeled data. In this work, we propose a QLoRA based fine tuning framework to improve offensive language detection in Roman Urdu-English text. We translated the Roman Urdu-English code mixed dataset into English using Google Translate to leverage English LLMs, while acknowledging that this translation reduces direct engagement with code mixing features. Our focus is on classification performance using English translated low resource inputs. We fine tuned several transformers and large language models, including Meta LLaMA 3 8B, Mistral 7B v0.1, LLaMA 2 7B, ModernBERT, and RoBERTa, with QLoRA for memory efficient adaptation. Models were trained and evaluated on a manually annotated Roman Urdu dataset for offensive vs non offensive content. Of all tested models, the highest F1 score of 91.45 was attained by Meta LLaMA 3 8B, followed by Mistral 7B at 89.66, surpassing traditional transformer baselines. These results demonstrate the efficacy of QLoRA in fine tuning high performing models for low resource environments such as code mixed offensive language detection, and confirm the potential of LLMs for this task. This work advances a scalable approach to Roman Urdu moderation and paves the way for future multilingual offensive detection systems based on LLMs.

---

### Rainbow Padding: Mitigating Early Termination in Instruction-Tuned Diffusion LLMs

Authors: Bumjun Kim, Dongjae Jeon, Dueun Kim, Wonje Jeung, Albert No
Published: 2025-10-04
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.03680v1

Diffusion large language models (dLLMs) have emerged as a promising alternative to autoregressive models, offering flexible generation orders and strong performance on complex reasoning tasks. However, instruction-tuned dLLMs exhibit a critical vulnerability we term \texttt{<eos>} overflow: as allocated sequence length increases, responses paradoxically become shorter, collapsing into early termination or degenerating into streams of \texttt{<eos>} tokens. Although noticed in practice, this issue has not been systematically analyzed. We trace its root cause to the dual role of \texttt{<eos>} as both termination and padding, which concentrates probability mass on \texttt{<eos>} at later positions and propagates backward to trigger early termination. To address this, we introduce Rainbow Padding, a simple remedy that replaces repeated \texttt{<eos>} placeholders with a repeating cycle of distinct padding tokens, distributing probability mass and breaking \texttt{<eos>} dominance. Experiments show that Rainbow Padding substantially improves length robustness and output quality, with as few as seven padding tokens sufficient to prevent early termination. Moreover, the method integrates efficiently into existing instruction-tuned models: LoRA fine-tuning for a single epoch on minimal data yields significant improvements, making this solution highly practical. The code is publicly available at https://github.com/quasar529/rainbow-padding.

---

### Group Policy Gradient

Authors: Junhua Chen, Zixi Zhang, Hantao Zhong, Rika Antonova
Published: 2025-10-04
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.03679v1

We introduce Group Policy Gradient (GPG), a family of critic-free policy-gradient estimators for general MDPs. Inspired by the success of GRPO's approach in Reinforcement Learning from Human Feedback (RLHF), GPG replaces a learned value function with a group-based Monte Carlo advantage estimator, removing the memory, compute, and hyperparameter costs of training a critic while preserving PPO's clipped-objective structure. We prove the consistency of the GPG estimator, analyze the bias-variance tradeoffs, and demonstrate empirically that GPG matches or outperforms PPO on standard benchmarks. GPG makes better use of parallel simulations, which, together with its critic-free design, results in more efficient use of computational resources than PPO.

---

### Towards Sampling Data Structures for Tensor Products in Turnstile Streams

Authors: Zhao Song, Shenghao Xie, Samson Zhou
Published: 2025-10-04
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.03678v1

This paper studies the computational challenges of large-scale attention-based models in artificial intelligence by utilizing importance sampling methods in the streaming setting. Inspired by the classical definition of the $\ell_2$ sampler and the recent progress of the attention scheme in Large Language Models (LLMs), we propose the definition of the attention sampler. Our approach significantly reduces the computational burden of traditional attention mechanisms. We analyze the effectiveness of the attention sampler from a theoretical perspective, including space and update time. Additionally, our framework exhibits scalability and broad applicability across various model architectures and domains.

---

### A Novel Cloud-Based Diffusion-Guided Hybrid Model for High-Accuracy Accident Detection in Intelligent Transportation Systems

Authors: Siva Sai, Saksham Gupta, Vinay Chamola, Rajkumar Buyya
Published: 2025-10-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.03675v1

The integration of Diffusion Models into Intelligent Transportation Systems (ITS) is a substantial improvement in the detection of accidents. We present a novel hybrid model integrating guidance classification with diffusion techniques. By leveraging fine-tuned ExceptionNet architecture outputs as input for our proposed diffusion model and processing image tensors as our conditioning, our approach creates a robust classification framework. Our model consists of multiple conditional modules, which aim to modulate the linear projection of inputs using time embeddings and image covariate embeddings, allowing the network to adapt its behavior dynamically throughout the diffusion process. To address the computationally intensive nature of diffusion models, our implementation is cloud-based, enabling scalable and efficient processing. Our strategy overcomes the shortcomings of conventional classification approaches by leveraging diffusion models inherent capacity to effectively understand complicated data distributions. We investigate important diffusion characteristics, such as timestep schedulers, timestep encoding techniques, timestep count, and architectural design changes, using a thorough ablation study, and have conducted a comprehensive evaluation of the proposed model against the baseline models on a publicly available dataset. The proposed diffusion model performs best in image-based accident detection with an accuracy of 97.32%.

---

### Token Hidden Reward: Steering Exploration-Exploitation in Group Relative Deep Reinforcement Learning

Authors: Wenlong Deng, Yi Ren, Yushu Li, Boying Gong, Danica J. Sutherland, Xiaoxiao Li, Christos Thrampoulidis
Published: 2025-10-04
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2510.03669v4

Reinforcement learning with verifiable rewards has significantly advanced the reasoning capabilities of large language models, yet how to explicitly steer training toward exploration or exploitation remains an open problem. We introduce Token Hidden Reward (THR), a token-level metric that quantifies each token's influence on the likelihood of correct responses under Group Relative Policy Optimization (GRPO). We find that training dynamics are dominated by a small subset of tokens with high absolute THR values. Most interestingly, tokens with positive THR strengthen confidence in correct outputs, thus favoring exploitation, while tokens with negative THR preserve probability mass for alternative outputs, enabling exploration. This insight suggests a natural intervention: a THR-guided reweighting algorithm that modulates GRPO's learning signals to explicitly bias training toward exploitation or exploration. We validate the efficacy of this algorithm on diverse math reasoning benchmarks. By amplifying tokens with positive THR value and weakening negative ones, our algorithm improves greedy-decoding accuracy, favoring exploitation. The reverse strategy yields consistent gains in Pass@K accuracy, favoring exploration. We further demonstrate that our algorithm integrates seamlessly with other RL objectives such as GSPO and generalizes across architectures including Llama. These findings establish THR as a principled and fine-grained mechanism for dynamically controlling exploration and exploitation in RL-tuned LLMs, providing new tools for targeted fine-tuning in reasoning-intensive applications.

---

### MonitorVLM:A Vision Language Framework for Safety Violation Detection in Mining Operations

Authors: Jiang Wu, Sichao Wu, Yinsong Ma, Guangyuan Yu, Haoyuan Xu, Lifang Zheng, Jingliang Duan
Published: 2025-10-04
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.03666v2

Industrial accidents, particularly in high-risk domains such as surface and underground mining, are frequently caused by unsafe worker behaviors. Traditional manual inspection remains labor-intensive, error-prone, and insufficient for large-scale, dynamic environments, highlighting the urgent need for intelligent and automated safety monitoring. In this paper, we present MonitorVLM, a novel vision--language framework designed to detect safety violations directly from surveillance video streams. MonitorVLM introduces three key innovations: (1) a domain-specific violation dataset comprising 9,000 vision--question--answer (VQA) samples across 40 high-frequency mining regulations, enriched with augmentation and auxiliary detection cues; (2) a clause filter (CF) module that dynamically selects the Top-$K$ most relevant clauses, reducing inference latency by 13.56\% while maintaining accuracy; and (3) a behavior magnifier (BM) module that enhances worker regions to improve fine-grained action recognition, yielding additional gains of 3.45% in precision and 8.62% in recall. Experimental results demonstrate that MonitorVLM significantly outperforms baseline vision--language models, achieving improvements of 22.01% in precision, 34.22\% in recall, and 28.37% in F1 score over the 72B unfine-tuned baseline. A lightweight web-based interface further integrates MonitorVLM into practical workflows, enabling automatic violation reporting with video timestamping. This study highlights the potential of multimodal large models to enhance occupational safety monitoring in mining and beyond.

---

### UNIDOC-BENCH: A Unified Benchmark for Document-Centric Multimodal RAG

Authors: Xiangyu Peng, Can Qin, Zeyuan Chen, Ran Xu, Caiming Xiong, Chien-Sheng Wu
Published: 2025-10-04
Categories: cs.CL, cs.CV
arXiv: https://arxiv.org/abs/2510.03663v3

Multimodal retrieval-augmented Generation (MM-RAG) is a key approach for applying large language models (LLMs) and agents to real-world knowledge bases, yet current evaluations are fragmented -- focusing on either text or images in isolation, or simplified multimodal setup, failing to capture document-centric multimodal use cases. In this paper, we introduce UniDoc-Bench, the first large-scale, realistic benchmark for MM-RAG built from $k$ real-world PDF pages across domains. Our pipeline extracts and links evidence from text, tables, and figures, then generates multimodal QA pairs spanning factual retrieval, comparison, summarization, and logical reasoning queries. To ensure reliability, all of QA pairs are validated by multiple human annotators and expert adjudication. UniDoc-Bench supports apples-to-apples comparison across four paradigms: 1) text-only, 2) image-only, 3) \emph{multimodal} text-image fusion and 4) multimodal joint retrieval -- under a unified protocol with standardized candidate pools, prompts, and evaluation metrics. UniDoc-Bench can also be used to evaluate Visual Question Answering (VQA) tasks. Our experiments show that multimodal text-image fusion RAG systems consistently outperform both unimodal and jointly multimodal embedding-based retrieval, indicating that neither text nor images alone are sufficient and that current multimodal embeddings remain inadequate. Beyond benchmarking, our analysis reveals when and how visual context complements textual evidence, uncovers systematic failure modes, and offers actionable guidance for developing more robust MM-RAG pipelines.

---

### Operationalizing Data Minimization for Privacy-Preserving LLM Prompting

Authors: Jijie Zhou, Niloofar Mireshghallah, Tianshi Li
Published: 2025-10-04
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.03662v1

The rapid deployment of large language models (LLMs) in consumer applications has led to frequent exchanges of personal information. To obtain useful responses, users often share more than necessary, increasing privacy risks via memorization, context-based personalization, or security breaches. We present a framework to formally define and operationalize data minimization: for a given user prompt and response model, quantifying the least privacy-revealing disclosure that maintains utility, and we propose a priority-queue tree search to locate this optimal point within a privacy-ordered transformation space. We evaluated the framework on four datasets spanning open-ended conversations (ShareGPT, WildChat) and knowledge-intensive tasks with single-ground-truth answers (CaseHold, MedQA), quantifying achievable data minimization with nine LLMs as the response model. Our results demonstrate that larger frontier LLMs can tolerate stronger data minimization while maintaining task quality than smaller open-source models (85.7% redaction for GPT-5 vs. 19.3% for Qwen2.5-0.5B). By comparing with our search-derived benchmarks, we find that LLMs struggle to predict optimal data minimization directly, showing a bias toward abstraction that leads to oversharing. This suggests not just a privacy gap, but a capability gap: models may lack awareness of what information they actually need to solve a task.

---

### Does higher interpretability imply better utility? A Pairwise Analysis on Sparse Autoencoders

Authors: Xu Wang, Yan Hu, Benyou Wang, Difan Zou
Published: 2025-10-04
Categories: cs.LG, cs.AI, cs.CL, stat.ML
arXiv: https://arxiv.org/abs/2510.03659v1

Sparse Autoencoders (SAEs) are widely used to steer large language models (LLMs), based on the assumption that their interpretable features naturally enable effective model behavior steering. Yet, a fundamental question remains unanswered: does higher interpretability indeed imply better steering utility? To answer this question, we train 90 SAEs across three LLMs (Gemma-2-2B, Qwen-2.5-3B, Gemma-2-9B), spanning five architectures and six sparsity levels, and evaluate their interpretability and steering utility based on SAEBench (arXiv:2501.12345) and AxBench (arXiv:2502.23456) respectively, and perform a rank-agreement analysis via Kendall's rank coefficients (tau b). Our analysis reveals only a relatively weak positive association (tau b approx 0.298), indicating that interpretability is an insufficient proxy for steering performance. We conjecture the interpretability utility gap may stem from the selection of SAE features, as not all of them are equally effective for steering. To further find features that truly steer the behavior of LLMs, we propose a novel selection criterion called Delta Token Confidence, which measures how much amplifying a feature changes the next token distribution. We show that our method improves the steering performance of three LLMs by 52.52 percent compared to the current best output score based criterion (arXiv:2503.34567). Strikingly, after selecting features with high Delta Token Confidence, the correlation between interpretability and utility vanishes (tau b approx 0), and can even become negative. This further highlights the divergence between interpretability and utility for the most effective steering features.

---

### Optimising Battery Energy Storage System Trading via Energy Market Operator Price Forecast

Authors: Aymeric Fabre
Published: 2025-10-04
Categories: cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2510.03657v1

In electricity markets around the world, the ability to anticipate price movements with precision can be the difference between profit and loss, especially for fast-acting assets like battery energy storage systems (BESS). As grid volatility increases due to renewables and market decentralisation, operators and forecasters alike face growing pressure to transform prediction into strategy. Yet while forecast data is abundant, especially in advanced markets like Australia's National Electricity Market (NEM), its practical value in driving real-world BESS trading decisions remains largely unexplored. This thesis dives into that gap. This work addresses a key research question: Can the accuracy of the Australian Energy Market Operator (AEMO) energy price forecasts be systematically leveraged to develop a reliable and profitable battery energy storage system trading algorithm? Despite the availability of AEMO price forecasts, no existing framework evaluates their reliability or incorporates them into practical BESS trading strategies. By analysing patterns in forecast accuracy based on time of day, forecast horizon, and regional variations, this project creates a novel, forecast-informed BESS trading model to optimise arbitrage financial returns. The performance of this forecast-driven algorithm is benchmarked against a basic trading algorithm with no knowledge of forecast data. The study further explores the potential of machine learning techniques to predict future energy prices by enhancing AEMO forecasts to govern a more advanced trading strategy. The research outcomes will inform future improvements in energy market trading models and promote more efficient BESS integration into market operations.

---

### LLM-Guided Evolutionary Program Synthesis for Quasi-Monte Carlo Design

Authors: Amir Sadikov
Published: 2025-10-04
Categories: cs.LG, cs.AI, cs.CE, cs.NE, math.NA
arXiv: https://arxiv.org/abs/2510.03650v1

Low-discrepancy point sets and digital sequences underpin quasi-Monte Carlo (QMC) methods for high-dimensional integration. We cast two long-standing QMC design problems as program synthesis and solve them with an LLM-guided evolutionary loop that mutates and selects code under task-specific fitness: (i) constructing finite 2D/3D point sets with low star discrepancy, and (ii) choosing Sobol' direction numbers that minimize randomized QMC error on downstream integrands. Our two-phase procedure combines constructive code proposals with iterative numerical refinement. On finite sets, we rediscover known optima in small 2D cases and set new best-known 2D benchmarks for N >= 40, while matching most known 3D optima up to the proven frontier (N <= 8) and reporting improved 3D benchmarks beyond. On digital sequences, evolving Sobol' parameters yields consistent reductions in randomized quasi-Monte Carlo (rQMC) mean-squared error for several 32-dimensional option-pricing tasks relative to widely used Joe--Kuo parameters, while preserving extensibility to any sample size and compatibility with standard randomizations. Taken together, the results demonstrate that LLM-driven evolutionary program synthesis can automate the discovery of high-quality QMC constructions, recovering classical designs where they are optimal and improving them where finite-N structure matters. Data and code are available at https://github.com/hockeyguy123/openevolve-star-discrepancy.git.

---

### SAFA-SNN: Sparsity-Aware On-Device Few-Shot Class-Incremental Learning with Fast-Adaptive Structure of Spiking Neural Network

Authors: Huijing Zhang, Muyang Cao, Linshan Jiang, Xin Du, Di Yu, Changze Lv, Shuiguang Deng
Published: 2025-10-04
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.03648v2

Continuous learning of novel classes is crucial for edge devices to preserve data privacy and maintain reliable performance in dynamic environments. However, the scenario becomes particularly challenging when data samples are insufficient, requiring on-device few-shot class-incremental learning (FSCIL). Although existing work has explored parameter-efficient FSCIL frameworks based on artificial neural networks (ANNs), their deployment is still fundamentally constrained by limited device resources. Spiking neural networks (SNNs) process spatiotemporal information efficiently, offering lower energy consumption, greater biological plausibility, and compatibility with neuromorphic hardware than ANNs. In this work, we propose an SNN-based method containing Sparsity-Aware neuronal dynamics and Fast Adaptive structure (SAFA-SNN) for on-device FSCIL. By threshold regulation, most neurons exhibit stable spikes and others exhibit adaptive spikes. As a result, synaptic traces that encode base-class knowledge are naturally preserved, thereby alleviating catastrophic forgetting. To cope with spike non-differentiability in backpropagation, we employ a gradient-free technique, i.e., zeroth-order optimization. Moreover, class prototypes can limit overfitting on few-shot data but introduce bias. We enhance prototype discriminability by orthogonal subspace projection. Extensive experiments conducted on two standard benchmark datasets (CIFAR-100 and Mini-ImageNet) and three neuromorphic datasets (CIFAR10-DVS, DVS128 Gesture, and N-Caltech101) demonstrate that SAFA-SNN outperforms baselines, specifically achieving at least 4.01% improvement at the last incremental session on Mini-ImageNet and 20% lower energy cost on CIFAR-100 over baselines with practical implementation.

---

### In-Vivo Training for Deep Brain Stimulation

Authors: Nicholas Carter, Arkaprava Gupta, Prateek Ganguli, Benedikt Dietrich, Vibhor Krishna, Samarjit Chakraborty
Published: 2025-10-04
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.03643v1

Deep Brain Stimulation (DBS) is a highly effective treatment for Parkinson's Disease (PD). Recent research uses reinforcement learning (RL) for DBS, with RL agents modulating the stimulation frequency and amplitude. But, these models rely on biomarkers that are not measurable in patients and are only present in brain-on-chip (BoC) simulations. In this work, we present an RL-based DBS approach that adapts these stimulation parameters according to brain activity measurable in vivo. Using a TD3 based RL agent trained on a model of the basal ganglia region of the brain, we see a greater suppression of biomarkers correlated with PD severity compared to modern clinical DBS implementations. Our agent outperforms the standard clinical approaches in suppressing PD biomarkers while relying on information that can be measured in a real world environment, thereby opening up the possibility of training personalized RL agents specific to individual patient needs.

---

### Towards Unsupervised Speech Recognition at the Syllable-Level

Authors: Liming Wang, Junrui Ni, Kai-Wei Chang, Saurabhchand Bhati, David Harwath, Mark Hasegawa-Johnson, James R. Glass
Published: 2025-10-04
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.03639v1

Training speech recognizers with unpaired speech and text -- known as unsupervised speech recognition (UASR) -- is a crucial step toward extending ASR to low-resource languages in the long-tail distribution and enabling multimodal learning from non-parallel data. However, existing approaches based on phones often rely on costly resources such as grapheme-to-phoneme converters (G2Ps) and struggle to generalize to languages with ambiguous phoneme boundaries due to training instability. In this paper, we address both challenges by introducing a syllable-level UASR framework based on masked language modeling, which avoids the need for G2P and the instability of GAN-based methods. Our approach achieves up to a 40\% relative reduction in character error rate (CER) on LibriSpeech and generalizes effectively to Mandarin, a language that has remained particularly difficult for prior methods. Code will be released upon acceptance.

---

### Expressive Power of Implicit Models: Rich Equilibria and Test-Time Scaling

Authors: Jialin Liu, Lisang Ding, Stanley Osher, Wotao Yin
Published: 2025-10-04
Categories: cs.LG, cs.AI, math.RT, stat.ML
arXiv: https://arxiv.org/abs/2510.03638v4

Implicit models, an emerging model class, compute outputs by iterating a single parameter block to a fixed point. This architecture realizes an infinite-depth, weight-tied network that trains with constant memory, significantly reducing memory needs for the same level of performance compared to explicit models. While it is empirically known that these compact models can often match or even exceed the accuracy of larger explicit networks by allocating more test-time compute, the underlying mechanism remains poorly understood. We study this gap through a nonparametric analysis of expressive power. We provide a strict mathematical characterization, showing that a simple and regular implicit operator can, through iteration, progressively express more complex mappings. We prove that for a broad class of implicit models, this process lets the model's expressive power scale with test-time compute, ultimately matching a much richer function class. The theory is validated across four domains: image reconstruction, scientific computing, operations research, and LLM reasoning, demonstrating that as test-time iterations increase, the complexity of the learned mapping rises, while the solution quality simultaneously improves and stabilizes.

---

### From Theory to Practice: Evaluating Data Poisoning Attacks and Defenses in In-Context Learning on Social Media Health Discourse

Authors: Rabeya Amin Jhuma, Mostafa Mohaimen Akand Faisal
Published: 2025-10-04
Categories: cs.LG, cs.CL, cs.CR
arXiv: https://arxiv.org/abs/2510.03636v1

This study explored how in-context learning (ICL) in large language models can be disrupted by data poisoning attacks in the setting of public health sentiment analysis. Using tweets of Human Metapneumovirus (HMPV), small adversarial perturbations such as synonym replacement, negation insertion, and randomized perturbation were introduced into the support examples. Even these minor manipulations caused major disruptions, with sentiment labels flipping in up to 67% of cases. To address this, a Spectral Signature Defense was applied, which filtered out poisoned examples while keeping the data's meaning and sentiment intact. After defense, ICL accuracy remained steady at around 46.7%, and logistic regression validation reached 100% accuracy, showing that the defense successfully preserved the dataset's integrity. Overall, the findings extend prior theoretical studies of ICL poisoning to a practical, high-stakes setting in public health discourse analysis, highlighting both the risks and potential defenses for robust LLM deployment. This study also highlights the fragility of ICL under attack and the value of spectral defenses in making AI systems more reliable for health-related social media monitoring.

---

### PRTree: An R Package for Probabilistic Regression Trees with Built-in Missing Data Handling

Authors: Taiane Schaedler Prass, Alisson Silva Neimaier, Guilherme Pumi
Published: 2025-10-04
Categories: stat.ME, stat.ML
arXiv: https://arxiv.org/abs/2510.03634v2

PRTree is an R package for fitting Probabilistic Regression Trees (PRTrees), a class of regression trees that replaces deterministic splits with probabilistic associations to produce smooth prediction functions. The package implements both the original methodology and its recent extension for handling missing predictor values, allowing model fitting and prediction directly from incomplete datasets without prior imputation. It provides a unified framework for model fitting, prediction, visualization, smoothing-parameter selection, cross-validation, and model diagnostics through a standard R interface. Computationally intensive routines are implemented in FORTRAN, while the high-level interface follows the usual R workflow based on S3 classes and generic methods. This paper reviews the underlying methodology, describes the software architecture and main package components, and illustrates their use through reproducible examples.

---

### Predicting Stock Price Movement with LLM-Enhanced Tweet Emotion Analysis

Authors: An Vuong, Susan Gauch
Published: 2025-10-04
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.03633v1

Accurately predicting short-term stock price movement remains a challenging task due to the market's inherent volatility and sensitivity to investor sentiment. This paper discusses a deep learning framework that integrates emotion features extracted from tweet data with historical stock price information to forecast significant price changes on the following day. We utilize Meta's Llama 3.1-8B-Instruct model to preprocess tweet data, thereby enhancing the quality of emotion features derived from three emotion analysis approaches: a transformer-based DistilRoBERTa classifier from the Hugging Face library and two lexicon-based methods using National Research Council Canada (NRC) resources. These features are combined with previous-day stock price data to train a Long Short-Term Memory (LSTM) model. Experimental results on TSLA, AAPL, and AMZN stocks show that all three emotion analysis methods improve the average accuracy for predicting significant price movements, compared to the baseline model using only historical stock prices, which yields an accuracy of 13.5%. The DistilRoBERTa-based stock prediction model achieves the best performance, with accuracy rising from 23.6% to 38.5% when using LLaMA-enhanced emotion analysis. These results demonstrate that using large language models to preprocess tweet content enhances the effectiveness of emotion analysis which in turn improves the accuracy of predicting significant stock price movements.

---

### MITS: Enhanced Tree Search Reasoning for LLMs via Pointwise Mutual Information

Authors: Jiaxi Li, Yucheng Shi, Xiao Huang, Jin Lu, Ninghao Liu
Published: 2025-10-04
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.03632v2

Tree search has become as a representative framework for test-time reasoning with large language models (LLMs), exemplified by methods such as Tree-of-Thought and Monte Carlo Tree Search. However, it remains difficult to provide instant and reliable quantitative assessments of intermediate reasoning step quality, and extensive path exploration is computationally costly. To address this, we propose Mutual Information Tree Search (MITS), a novel framework that guides reasoning with information-theoretic principles. MITS introduces an effective scoring function based on pointwise mutual information (PMI), which enables step-wise evaluation of reasoning paths and search tree expansion via beam search without expensive look-ahead simulations, achieving superior reasoning performances while maintaining computational efficiency. The framework is complemented by an entropy-based dynamic sampling strategy that adaptively allocates computational resources to uncertain reasoning steps where exploration is most beneficial. For final prediction, MITS employs a weighted voting scheme that combines PMI scores with prediction consensus. Through comprehensive experiments on diverse reasoning benchmarks, MITS consistently surpasses baseline methods, establishing a principled and efficient framework for LLM reasoning. The code is available at https://github.com/plusnli/MITS.

---

### Transformed $\ell_1$ Regularizations for Robust Principal Component Analysis: Toward a Fine-Grained Understanding

Authors: Kun Zhao, Haoke Zhang, Jiayi Wang, Yifei Lou
Published: 2025-10-04
Categories: stat.ML, math.ST
arXiv: https://arxiv.org/abs/2510.03624v1

Robust Principal Component Analysis (RPCA) aims to recover a low-rank structure from noisy, partially observed data that is also corrupted by sparse, potentially large-magnitude outliers. Traditional RPCA models rely on convex relaxations, such as nuclear norm and $\ell_1$ norm, to approximate the rank of a matrix and the $\ell_0$ functional (the number of non-zero elements) of another. In this work, we advocate a nonconvex regularization method, referred to as transformed $\ell_1$ (TL1), to improve both approximations. The rationale is that by varying the internal parameter of TL1, its behavior asymptotically approaches either $\ell_0$ or $\ell_1$. Since the rank is equal to the number of non-zero singular values and the nuclear norm is defined as their sum, applying TL1 to the singular values can approximate either the rank or the nuclear norm, depending on its internal parameter. We conduct a fine-grained theoretical analysis of statistical convergence rates, measured in the Frobenius norm, for both the low-rank and sparse components under general sampling schemes. These rates are comparable to those of the classical RPCA model based on the nuclear norm and $\ell_1$ norm. Moreover, we establish constant-order upper bounds on the estimated rank of the low-rank component and the cardinality of the sparse component in the regime where TL1 behaves like $\ell_0$, assuming that the respective matrices are exactly low-rank and exactly sparse. Extensive numerical experiments on synthetic data and real-world applications demonstrate that the proposed approach achieves higher accuracy than the classic convex model, especially under non-uniform sampling schemes.

---

### Explainable but Vulnerable: Adversarial Attacks on XAI Explanation in Cybersecurity Applications

Authors: Maraz Mia, Mir Mehedi A. Pritom
Published: 2025-10-04
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2510.03623v1

Explainable Artificial Intelligence (XAI) has aided machine learning (ML) researchers with the power of scrutinizing the decisions of the black-box models. XAI methods enable looking deep inside the models' behavior, eventually generating explanations along with a perceived trust and transparency. However, depending on any specific XAI method, the level of trust can vary. It is evident that XAI methods can themselves be a victim of post-adversarial attacks that manipulate the expected outcome from the explanation module. Among such attack tactics, fairwashing explanation (FE), manipulation explanation (ME), and backdoor-enabled manipulation attacks (BD) are the notable ones. In this paper, we try to understand these adversarial attack techniques, tactics, and procedures (TTPs) on explanation alteration and thus the effect on the model's decisions. We have explored a total of six different individual attack procedures on post-hoc explanation methods such as SHAP (SHapley Additive exPlanations), LIME (Local Interpretable Model-agnostic Explanation), and IG (Integrated Gradients), and investigated those adversarial attacks in cybersecurity applications scenarios such as phishing, malware, intrusion, and fraudulent website detection. Our experimental study reveals the actual effectiveness of these attacks, thus providing an urgency for immediate attention to enhance the resiliency of XAI methods and their applications.

---

### Neural Bayesian Filtering

Authors: Christopher Solinas, Radovan Haluska, David Sychrovsky, Finbarr Timbers, Nolan Bard, Michael Buro, Martin Schmid, Nathan R. Sturtevant, Michael Bowling
Published: 2025-10-04
Categories: cs.LG, cs.AI, stat.ML
arXiv: https://arxiv.org/abs/2510.03614v2

Sequential estimation under partial observability requires tracking beliefs that may be high-dimensional, multimodal, and non-Gaussian. Classical Bayesian filters generalize zero-shot to any system whose dynamics can be evaluated, but their representations scale poorly: parametric filters struggle to capture multimodality, and particle filters require exponentially many particles in the state dimension. Generative Distribution Embeddings (GDEs) learn compact representations of complex distributions but have no sequential update. We present Neural Bayesian Filtering (NBF), which represents beliefs as embeddings and approximates their Bayesian update. At each step, NBF samples particles from a learned conditional generator, propagates them through the dynamics, and embeds the propagated set, weighted by the likelihood of the new observation. Regenerating the set from the embedding at each step, rather than resampling a surviving pool, mitigates the risk of impoverishment that degrades particle filters. The system dynamics and likelihood enter only through propagation and weighting, so NBF retains zero-shot adaptability to new dynamics as long as the beliefs they produce fall within the family the embedding was trained on. Training the GDE to represent that family requires only the states realized at training time. We validate NBF on Lorenz-96 and a pursuit--evasion domain, showing graceful scaling with state dimension, accurate tracking of multimodal posteriors, and zero-shot generalization to dynamics and likelihoods held out from training.

---

### Explore the Loss space with Hill-ADAM

Authors: Meenakshi Manikandan, Leilani Gilpin
Published: 2025-10-04
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.03613v1

This paper introduces Hill-ADAM. Hill-ADAM is an optimizer with its focus towards escaping local minima in prescribed loss landscapes to find the global minimum. Hill-ADAM escapes minima by deterministically exploring the state space. This eliminates uncertainty from random gradient updates in stochastic algorithms while seldom converging at the first minimum that visits. In the paper we first derive an analytical approximation of the ADAM Optimizer step size at a particular model state. From there define the primary condition determining ADAM limitations in escaping local minima. The proposed optimizer algorithm Hill-ADAM alternates between error minimization and maximization. It maximizes to escape the local minimum and minimizes again afterward. This alternation provides an overall exploration throughout the loss space. This allows the deduction of the global minimum's state. Hill-ADAM was tested with 5 loss functions and 12 amber-saturated to cooler-shade image color correction instances.

---

### Cross-Modal Content Optimization for Steering Web Agent Preferences

Authors: Tanqiu Jiang, Min Bai, Nikolaos Pappas, Yanjun Qi, Sandesh Swamy
Published: 2025-10-04
Categories: cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2510.03612v1

Vision-language model (VLM)-based web agents increasingly power high-stakes selection tasks like content recommendation or product ranking by combining multimodal perception with preference reasoning. Recent studies reveal that these agents are vulnerable against attackers who can bias selection outcomes through preference manipulations using adversarial pop-ups, image perturbations, or content tweaks. Existing work, however, either assumes strong white-box access, with limited single-modal perturbations, or uses impractical settings. In this paper, we demonstrate, for the first time, that joint exploitation of visual and textual channels yields significantly more powerful preference manipulations under realistic attacker capabilities. We introduce Cross-Modal Preference Steering (CPS) that jointly optimizes imperceptible modifications to an item's visual and natural language descriptions, exploiting CLIP-transferable image perturbations and RLHF-induced linguistic biases to steer agent decisions. In contrast to prior studies that assume gradient access, or control over webpages, or agent memory, we adopt a realistic black-box threat setup: a non-privileged adversary can edit only their own listing's images and textual metadata, with no insight into the agent's model internals. We evaluate CPS on agents powered by state-of-the-art proprietary and open source VLMs including GPT-4.1, Qwen-2.5VL and Pixtral-Large on both movie selection and e-commerce tasks. Our results show that CPS is significantly more effective than leading baseline methods. For instance, our results show that CPS consistently outperforms baselines across all models while maintaining 70% lower detection rates, demonstrating both effectiveness and stealth. These findings highlight an urgent need for robust defenses as agentic systems play an increasingly consequential role in society.

---

### Can an LLM Induce a Graph? Investigating Memory Drift and Context Length

Authors: Raquib Bin Yousuf, Aadyant Khatri, Shengzhe Xu, Mandar Sharma, Naren Ramakrishnan
Published: 2025-10-04
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.03611v1

Recently proposed evaluation benchmarks aim to characterize the effective context length and the forgetting tendencies of large language models (LLMs). However, these benchmarks often rely on simplistic 'needle in a haystack' retrieval or continuation tasks that may not accurately reflect the performance of these models in information-dense scenarios. Thus, rather than simple next token prediction, we argue for evaluating these models on more complex reasoning tasks that requires them to induce structured relational knowledge from the text - such as graphs from potentially noisy natural language content. While the input text can be viewed as generated in terms of a graph, its structure is not made explicit and connections must be induced from distributed textual cues, separated by long contexts and interspersed with irrelevant information. Our findings reveal that LLMs begin to exhibit memory drift and contextual forgetting at much shorter effective lengths when tasked with this form of relational reasoning, compared to what existing benchmarks suggest. With these findings, we offer recommendations for the optimal use of popular LLMs for complex reasoning tasks. We further show that even models specialized for reasoning, such as OpenAI o1, remain vulnerable to early memory drift in these settings. These results point to significant limitations in the models' ability to abstract structured knowledge from unstructured input and highlight the need for architectural adaptations to improve long-range reasoning.

---

### PentestMCP: A Toolkit for Agentic Penetration Testing

Authors: Zachary Ezetta, Wu-chang Feng
Published: 2025-10-04
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2510.03610v1

Agentic AI is transforming security by automating many tasks being performed manually. While initial agentic approaches employed a monolithic architecture, the Model-Context-Protocol has now enabled a remote-procedure call (RPC) paradigm to agentic applications, allowing for the flexible construction and composition of multi-function agents. This paper describes PentestMCP, a library of MCP server implementations that support agentic penetration testing. By supporting common penetration testing tasks such as network scanning, resource enumeration, service fingerprinting, vulnerability scanning, exploitation, and post-exploitation, PentestMCP allows a developer to customize multi-agent workflows for performing penetration tests.

---

### Diffusion-Classifier Synergy: Reward-Aligned Learning via Mutual Boosting Loop for FSCIL

Authors: Ruitao Wu, Yifan Zhao, Guangyao Chen, Jia Li
Published: 2025-10-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.03608v3

Few-Shot Class-Incremental Learning (FSCIL) challenges models to sequentially learn new classes from minimal examples without forgetting prior knowledge, a task complicated by the stability-plasticity dilemma and data scarcity. Current FSCIL methods often struggle with generalization due to their reliance on limited datasets. While diffusion models offer a path for data augmentation, their direct application can lead to semantic misalignment or ineffective guidance. This paper introduces Diffusion-Classifier Synergy (DCS), a novel framework that establishes a mutual boosting loop between diffusion model and FSCIL classifier. DCS utilizes a reward-aligned learning strategy, where a dynamic, multi-faceted reward function derived from the classifier's state directs the diffusion model. This reward system operates at two levels: the feature level ensures semantic coherence and diversity using prototype-anchored maximum mean discrepancy and dimension-wise variance matching, while the logits level promotes exploratory image generation and enhances inter-class discriminability through confidence recalibration and cross-session confusion-aware mechanisms. This co-evolutionary process, where generated images refine the classifier and an improved classifier state yields better reward signals, demonstrably achieves state-of-the-art performance on FSCIL benchmarks, significantly enhancing both knowledge retention and new class learning.

---

### Unsupervised Transformer Pre-Training for Images: Self-Distillation, Mean Teachers, and Random Crops

Authors: Mattia Scardecchia
Published: 2025-10-04
Categories: cs.CV, cs.LG, eess.IV
arXiv: https://arxiv.org/abs/2510.03606v1

Recent advances in self-supervised learning (SSL) have made it possible to learn general-purpose visual features that capture both the high-level semantics and the fine-grained spatial structure of images. Most notably, the recent DINOv2 has established a new state of the art by surpassing weakly supervised methods (WSL) like OpenCLIP on most benchmarks. In this survey, we examine the core ideas behind its approach, multi-crop view augmentation and self-distillation with a mean teacher, and trace their development in previous work. We then compare the performance of DINO and DINOv2 with other SSL and WSL methods across various downstream tasks, and highlight some remarkable emergent properties of their learned features with transformer backbones. We conclude by briefly discussing DINOv2's limitations, its impact, and future research directions.

---

### Understanding the Role of Training Data in Test-Time Scaling

Authors: Adel Javanmard, Baharan Mirzasoleiman, Vahab Mirrokni
Published: 2025-10-04
Categories: cs.AI, cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.03605v2

Test-time scaling improves the reasoning capabilities of large language models (LLMs) by allocating extra compute to generate longer Chains-of-Thoughts (CoTs). This enables models to tackle more complex problem by breaking them down into additional steps, backtracking, and correcting mistakes. Despite its strong performance--demonstrated by OpenAI's o1 and DeepSeek R1, the conditions in the training data under which long CoTs emerge, and when such long CoTs improve the performance, remain unclear. In this paper, we study the performance of test-time scaling for transformers trained on an in-context weight prediction task for linear regression. Our analysis provides a theoretical explanation for several intriguing observations: First, at any fixed test error, increasing test-time compute allows us to reduce the number of in-context examples (context length) in training prompts. Second, if the skills required to solve a downstream task are not sufficiently present in the training data, increasing test-time compute can harm performance. Finally, we characterize task hardness via the smallest eigenvalue of its feature covariance matrix and show that training on a diverse, relevant, and hard set of tasks results in best performance for test-time scaling. We confirm our findings with experiments on large, nonlinear transformer architectures.

---

### Deep Domain Adaptation for Turbofan Engine Remaining Useful Life Prediction: Methodologies, Evaluation and Future Trends

Authors: Yucheng Wang, Mohamed Ragab, Yubo Hou, Zhenghua Chen, Min Wu, Xiaoli Li
Published: 2025-10-04
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.03604v1

Remaining Useful Life (RUL) prediction for turbofan engines plays a vital role in predictive maintenance, ensuring operational safety and efficiency in aviation. Although data-driven approaches using machine learning and deep learning have shown potential, they face challenges such as limited data and distribution shifts caused by varying operating conditions. Domain Adaptation (DA) has emerged as a promising solution, enabling knowledge transfer from source domains with abundant data to target domains with scarce data while mitigating distributional shifts. Given the unique properties of turbofan engines, such as complex operating conditions, high-dimensional sensor data, and slower-changing signals, it is essential to conduct a focused review of DA techniques specifically tailored to turbofan engines. To address this need, this paper provides a comprehensive review of DA solutions for turbofan engine RUL prediction, analyzing key methodologies, challenges, and recent advancements. A novel taxonomy tailored to turbofan engines is introduced, organizing approaches into methodology-based (how DA is applied), alignment-based (where distributional shifts occur due to operational variations), and problem-based (why certain adaptations are needed to address specific challenges). This taxonomy offers a multidimensional view that goes beyond traditional classifications by accounting for the distinctive characteristics of turbofan engine data and the standard process of applying DA techniques to this area. Additionally, we evaluate selected DA techniques on turbofan engine datasets, providing practical insights for practitioners and identifying key challenges. Future research directions are identified to guide the development of more effective DA techniques, advancing the state of RUL prediction for turbofan engines.

---

### MECKD: Deep Learning-Based Fall Detection in Multilayer Mobile Edge Computing With Knowledge Distillation

Authors: Wei-Lung Mao, Chun-Chi Wang, Po-Heng Chou, Kai-Chun Liu, Yu Tsao
Published: 2025-10-04
Categories: cs.LG, cs.DC, cs.NI, eess.SP
arXiv: https://arxiv.org/abs/2510.03601v1

The rising aging population has increased the importance of fall detection (FD) systems as an assistive technology, where deep learning techniques are widely applied to enhance accuracy. FD systems typically use edge devices (EDs) worn by individuals to collect real-time data, which are transmitted to a cloud center (CC) or processed locally. However, this architecture faces challenges such as a limited ED model size and data transmission latency to the CC. Mobile edge computing (MEC), which allows computations at MEC servers deployed between EDs and CC, has been explored to address these challenges. We propose a multilayer MEC (MLMEC) framework to balance accuracy and latency. The MLMEC splits the architecture into stations, each with a neural network model. If front-end equipment cannot detect falls reliably, data are transmitted to a station with more robust back-end computing. The knowledge distillation (KD) approach was employed to improve front-end detection accuracy by allowing high-power back-end stations to provide additional learning experiences, enhancing precision while reducing latency and processing loads. Simulation results demonstrate that the KD approach improved accuracy by 11.65% on the SisFall dataset and 2.78% on the FallAllD dataset. The MLMEC with KD also reduced the data latency rate by 54.15% on the FallAllD dataset and 46.67% on the SisFall dataset compared to the MLMEC without KD. In summary, the MLMEC FD system exhibits improved accuracy and reduced latency.

---

### Exploring the Hierarchical Reasoning Model for Small Natural-Image Classification Without Augmentation

Authors: Alexander V. Mantzaris
Published: 2025-10-04
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.03598v1

This paper asks whether the Hierarchical Reasoning Model (HRM) with the two Transformer-style modules $(f_L,f_H)$, one step (DEQ-style) training, deep supervision, Rotary Position Embeddings, and RMSNorm can serve as a practical image classifier. It is evaluated on MNIST, CIFAR-10, and CIFAR-100 under a deliberately raw regime: no data augmentation, identical optimizer family with one-epoch warmup then cosine-floor decay, and label smoothing. HRM optimizes stably and performs well on MNIST ($\approx 98\%$ test accuracy), but on small natural images it overfits and generalizes poorly: on CIFAR-10, HRM reaches 65.0\% after 25 epochs, whereas a two-stage Conv--BN--ReLU baseline attains 77.2\% while training $\sim 30\times$ faster per epoch; on CIFAR-100, HRM achieves only 29.7\% test accuracy despite 91.5\% train accuracy, while the same CNN reaches 45.3\% test with 50.5\% train accuracy. Loss traces and error analyses indicate healthy optimization but insufficient image-specific inductive bias for HRM in this regime. It is concluded that, for small-resolution image classification without augmentation, HRM is not competitive with even simple convolutional architectures as the HRM currently exist but this does not exclude possibilities that modifications to the model may allow it to improve greatly.

---

### Neon: Negative Extrapolation From Self-Training Improves Image Generation

Authors: Sina Alemohammad, Zhangyang Wang, Richard G. Baraniuk
Published: 2025-10-04
Categories: cs.GR, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.03597v3

Scaling generative AI models is bottlenecked by the scarcity of high-quality training data. The ease of synthesizing from a generative model suggests using (unverified) synthetic data to augment a limited corpus of real data for the purpose of fine-tuning in the hope of improving performance. Unfortunately, however, the resulting positive feedback loop leads to model autophagy disorder (MAD, aka model collapse) that results in a rapid degradation in sample quality and/or diversity. In this paper, we introduce Neon (for Negative Extrapolation frOm self-traiNing), a new learning method that turns the degradation from self-training into a powerful signal for self-improvement. Given a base model, Neon first fine-tunes it on its own self-synthesized data but then, counterintuitively, reverses its gradient updates to extrapolate away from the degraded weights. We prove that Neon works because typical inference samplers that favor high-probability regions create a predictable anti-alignment between the synthetic and real data population gradients, which negative extrapolation corrects to better align the model with the true data distribution. Neon is remarkably easy to implement via a simple post-hoc merge that requires no new real data, works effectively with as few as 1k synthetic samples, and typically uses less than 1% additional training compute. We demonstrate Neon's universality across a range of architectures (diffusion, flow matching, autoregressive, and inductive moment matching models) and datasets (ImageNet, CIFAR-10, and FFHQ). In particular, on ImageNet 256x256, Neon elevates the xAR-L model to a new state-of-the-art FID of 1.02 with only 0.36% additional training compute. Code is available at https://github.com/VITA-Group/Neon

---

### Decoupling Task-Solving and Output Formatting in LLM Generation

Authors: Haikang Deng, Po-Nien Kung, Nanyun Peng
Published: 2025-10-04
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.03595v2

Large language models (LLMs) are increasingly adept at solving complex problems, such as mathematical reasoning and automatic evaluation. However, performance often degrades when prompts intertwine task instructions with rigid formatting requirements. This entanglement creates competing goals for the model, hindering its reasoning capabilities. To address this, we introduce Deco-G, a decoding framework that explicitly decouples format adherence from problem solving. Deco-G delegates format adherence to a separate Format Estimation Module (FEM), which performs probabilistic lookahead to estimate future format compliance rate and reweighs token probabilities, allowing the LLM to focus solely on task resolution. To make this approach both practical and efficient, we introduce three key innovations: instruction-aware distillation, a flexible trie-building algorithm, and HMM state pruning. Experiments across mathematical reasoning, event argument extraction, and LLM-as-a-judge demonstrate that Deco-G constantly gains over prompting or structured generation baselines, with guaranteed format compliance. We release our code at https://github.com/haikangdeng/deco-g.

---

### Deep Reinforcement Learning for Multi-Agent Coordination

Authors: Kehinde O. Aina, Sehoon Ha
Published: 2025-10-04
Categories: cs.LG, cs.AI, cs.MA, cs.RO
arXiv: https://arxiv.org/abs/2510.03592v1

We address the challenge of coordinating multiple robots in narrow and confined environments, where congestion and interference often hinder collective task performance. Drawing inspiration from insect colonies, which achieve robust coordination through stigmergy -- modifying and interpreting environmental traces -- we propose a Stigmergic Multi-Agent Deep Reinforcement Learning (S-MADRL) framework that leverages virtual pheromones to model local and social interactions, enabling decentralized emergent coordination without explicit communication. To overcome the convergence and scalability limitations of existing algorithms such as MADQN, MADDPG, and MAPPO, we leverage curriculum learning, which decomposes complex tasks into progressively harder sub-problems. Simulation results show that our framework achieves the most effective coordination of up to eight agents, where robots self-organize into asymmetric workload distributions that reduce congestion and modulate group performance. This emergent behavior, analogous to strategies observed in nature, demonstrates a scalable solution for decentralized multi-agent coordination in crowded environments with communication constraints.

---

### A Hybrid Co-Finetuning Approach for Visual Bug Detection in Video Games

Authors: Faliu Yi, Sherif Abdelfattah, Wei Huang, Adrian Brown
Published: 2025-10-04
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.03591v1

Manual identification of visual bugs in video games is a resource-intensive and costly process, often demanding specialized domain knowledge. While supervised visual bug detection models offer a promising solution, their reliance on extensive labeled datasets presents a significant challenge due to the infrequent occurrence of such bugs. To overcome this limitation, we propose a hybrid Co-FineTuning (CFT) method that effectively integrates both labeled and unlabeled data. Our approach leverages labeled samples from the target game and diverse co-domain games, additionally incorporating unlabeled data to enhance feature representation learning. This strategy maximizes the utility of all available data, substantially reducing the dependency on labeled examples from the specific target game. The developed framework demonstrates enhanced scalability and adaptability, facilitating efficient visual bug detection across various game titles. Our experimental results show the robustness of the proposed method for game visual bug detection, exhibiting superior performance compared to conventional baselines across multiple gaming environments. Furthermore, CFT maintains competitive performance even when trained with only 50% of the labeled data from the target game.

---

### FieldFormer: Locality-Aware Transformers for Spatio-Temporal Modeling on Sparse Sensor Networks

Authors: Ankit Bhardwaj, Ananth Balashankar, Lakshminarayanan Subramanian
Published: 2025-10-04
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.03589v2

Spatio-temporal sensor data in real-world systems is often sparse, noisy, and irregular, making latent field reconstruction fundamentally underconstrained. Under extreme sparsity, multiple physically plausible fields may remain consistent with the same observations, requiring models to rely on inductive biases about locality, transport, and spatial regularity. In such regimes, reliable reconstruction is concentrated around the observational support induced by the sensor network, making sensor-space modeling a more identifiable objective than unconstrained global field recovery. We introduce FieldFormer, a mesh-free transformer architecture for locality-aware sensor-space modeling in persistent sensor networks. For each query, FieldFormer aggregates local evidence using learnable velocity-scaled offsets that adapt neighborhood geometry to spatio-temporal dependencies. Neighborhoods are constructed as fixed maximal sparse contexts over nearby sensors and bounded temporal windows, enabling stable and scalable inference under extreme sparsity. A local transformer encoder integrates neighborhood information, while a coordinate-based neural field formulation supports mesh-free prediction. We evaluate FieldFormer on five synthetic and real-world benchmarks, including anisotropic heat diffusion, shallow-water dynamics, atmospheric transport, and pollution monitoring datasets. Results show that locality-aware reconstruction provides strong advantages when local domains of dependence remain observed, enabling FieldFormer to consistently outperform state-of-the-art baselines on sparse sensor-space prediction tasks.

---

### Exact and Approximate MCMC for Doubly-intractable Probabilistic Graphical Models Leveraging the Underlying Independence Model

Authors: Yujie Chen, Antik Chakraborty, Anindya Bhadra
Published: 2025-10-04
Categories: stat.CO, stat.ME, stat.ML
arXiv: https://arxiv.org/abs/2510.03587v2

Bayesian inference for doubly-intractable pairwise exponential graphical models typically involves variations of the exchange algorithm or approximate Markov chain Monte Carlo (MCMC) samplers. However, existing methods for both classes of algorithms require either perfect samplers or sequential samplers for complex models, which are often either not available, or suffer from poor mixing, especially in high dimensions. We develop a method that does not require perfect or sequential sampling, and can be applied to both classes of methods: exact and approximate MCMC. The key to our approach is to utilize the tractable independence model underlying the intractable probabilistic graphical model for the purpose of constructing a finite sample unbiased Monte Carlo (and not MCMC) estimate of the Metropolis--Hastings ratio. This innovation turns out to be crucial for scalability in high dimensions. The method is demonstrated on the Ising model. Gradient-based alternatives to construct a proposal, such as Langevin and Hamiltonian Monte Carlo approaches, also arise as a natural corollary to our general procedure, and are demonstrated as well.

---

### FrameOracle: Learning What to See and How Much to See in Videos

Authors: Chaoyu Li, Tianzhi Li, Fei Tao, Zhenyu Zhao, Ziqian Wu, Maozheng Zhao, Juntong Song, Cheng Niu, Pooyan Fazli
Published: 2025-10-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.03584v3

Vision-language models (VLMs) advance video understanding but operate under tight computational budgets, making performance dependent on selecting a small, high-quality subset of frames. Existing frame sampling strategies, such as uniform or fixed-budget selection, fail to adapt to variations in content density or task complexity. To address this, we present FrameOracle, a lightweight, plug-and-play module that predicts both (1) which frames are most relevant to a given query and (2) how many frames are needed. FrameOracle is trained via a curriculum that progresses from weak proxy signals, such as cross-modal similarity, to stronger supervision with FrameOracle-41K, the first large-scale VideoQA dataset with validated keyframe annotations specifying minimal sufficient frames per question. Extensive experiments across five VLMs and six benchmarks show that FrameOracle reduces 16-frame inputs to an average of 10.4 frames without accuracy loss. When starting from 64-frame candidates, it reduces inputs to 13.9 frames on average while improving accuracy by 1.5%, achieving state-of-the-art efficiency-accuracy trade-offs for scalable video understanding.

---

### Deep learning the sources of MJO predictability: a spectral view of learned features

Authors: Lin Yao, Da Yang, James P. C. Duncan, Ashesh Chattopadhyay, Pedram Hassanzadeh, Wahid Bhimji, Bin Yu
Published: 2025-10-04
Categories: physics.ao-ph, cs.AI
arXiv: https://arxiv.org/abs/2510.03582v1

The Madden-Julian oscillation (MJO) is a planetary-scale, intraseasonal tropical rainfall phenomenon crucial for global weather and climate; however, its dynamics and predictability remain poorly understood. Here, we leverage deep learning (DL) to investigate the sources of MJO predictability, motivated by a central difference in MJO theories: which spatial scales are essential for driving the MJO? We first develop a deep convolutional neural network (DCNN) to forecast the MJO indices (RMM and ROMI). Our model predicts RMM and ROMI up to 21 and 33 days, respectively, achieving skills comparable to leading subseasonal-to-seasonal models such as NCEP. To identify the spatial scales most relevant for MJO forecasting, we conduct spectral analysis of the latent feature space and find that large-scale patterns dominate the learned signals. Additional experiments show that models using only large-scale signals as the input have the same skills as those using all the scales, supporting the large-scale view of the MJO. Meanwhile, we find that small-scale signals remain informative: surprisingly, models using only small-scale input can still produce skillful forecasts up to 1-2 weeks ahead. We show that this is achieved by reconstructing the large-scale envelope of the small-scale activities, which aligns with the multi-scale view of the MJO. Altogether, our findings support that large-scale patterns--whether directly included or reconstructed--may be the primary source of MJO predictability.

---

### Latent Mixture of Symmetries for Sample-Efficient Dynamic Learning

Authors: Haoran Li, Chenhan Xiao, Muhao Guo, Yang Weng
Published: 2025-10-04
Categories: cs.LG, cs.AI, stat.ML
arXiv: https://arxiv.org/abs/2510.03578v1

Learning dynamics is essential for model-based control and Reinforcement Learning in engineering systems, such as robotics and power systems. However, limited system measurements, such as those from low-resolution sensors, demand sample-efficient learning. Symmetry provides a powerful inductive bias by characterizing equivariant relations in system states to improve sample efficiency. While recent methods attempt to discover symmetries from data, they typically assume a single global symmetry group and treat symmetry discovery and dynamic learning as separate tasks, leading to limited expressiveness and error accumulation. In this paper, we propose the Latent Mixture of Symmetries (Latent MoS), an expressive model that captures a mixture of symmetry-governed latent factors from complex dynamical measurements. Latent MoS focuses on dynamic learning while locally and provably preserving the underlying symmetric transformations. To further capture long-term equivariance, we introduce a hierarchical architecture that stacks MoS blocks. Numerical experiments in diverse physical systems demonstrate that Latent MoS outperforms state-of-the-art baselines in interpolation and extrapolation tasks while offering interpretable latent representations suitable for future geometric and safety-critical analyses.

---

### The use of artificial intelligence in music creation: between interface and appropriation

Authors: Arnaud Zeller, Emmanuelle Chevry Pebayle
Published: 2025-10-03
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2511.17507v1

By observing the activities and relationships of musicians and sound designers to the activities of creation, performance, publishing and dissemination with artificial intelligence (AI), from two specialized forums between 2022 and 2024, this article proposes a lexicometric analysis of the representations linked to their use. Indeed, the machine, now equipped with artificial intelligences requiring new appropriations and enabling new mediations, constitutes new challenges for artists. To study these confrontations and new mediations, our approach mobilizes the theoretical framework of the Human-AI Musicking Framework, based on a lexicometric analysis of content. The aim is to clarify the present and future uses of AI from the interfaces, in the creation of sound and musical content, and to identify the obstacles, obstacles, brakes and limits to appropriation ``in the fact of making the content one's own and integrating it as a part of oneself'' (Bachimont and Crozat, 2004) in the context of a collaboration between musician and machine.

---

### ExplainRec: Towards Explainable Multi-Modal Zero-Shot Recommendation with Preference Attribution and Large Language Models

Authors: Bo Ma, LuYao Liu, ZeHua Hu, Simon Lau
Published: 2025-10-03
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2511.14770v1

Recent advances in Large Language Models (LLMs) have opened new possibilities for recommendation systems, though current approaches such as TALLRec face challenges in explainability and cold-start scenarios. We present ExplainRec, a framework that extends LLM-based recommendation capabilities through preference attribution, multi-modal fusion, and zero-shot transfer learning. The framework incorporates four technical contributions: preference attribution tuning for explainable recommendations, zero-shot preference transfer for cold-start users and items, multi-modal enhancement leveraging visual and textual content, and multi-task collaborative optimization. Experimental evaluation on MovieLens-25M and Amazon datasets shows that ExplainRec outperforms existing methods, achieving AUC improvements of 0.7\% on movie recommendation and 0.9\% on cross-domain tasks, while generating interpretable explanations and handling cold-start scenarios effectively.

---

### Decoupling Positional and Symbolic Attention Behavior in Transformers

Authors: Felipe Urrutia, Jorge Salas, Alexander Kozachinskiy, Cristian Buc Calderon, Hector Pasten, Cristobal Rojas
Published: 2025-10-03
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2511.11579v1

An important aspect subtending language understanding and production is the ability to independently encode positional and symbolic information of the words within a sentence. In Transformers, positional information is typically encoded using Positional Encodings (PEs). One such popular PE, namely Rotary PE (RoPE), has been widely used due to its empirical success. Recently, it has been argued that part of RoPE's success emerges from its ability to encode robust positional and semantic information using large and small frequencies, respectively. In this work, we perform a deeper dive into the positional versus symbolic dichotomy of attention heads behavior, both at the theoretical and empirical level. We provide general definitions of what it means for a head to behave positionally or symbolically, prove that these are two mutually exclusive behaviors and develop a metric to quantify them. We apply our framework to analyze Transformer-based LLMs using RoPE and find that all heads exhibit a strong correspondence between behavior and frequency use. Finally, we introduce canonical tasks designed to be either purely positional or symbolic, and demonstrate that the Transformer performance causally relates to the ability of attention heads to leverage the appropriate frequencies. In particular, we show that we can control the Transformer performance by controlling which frequencies the attention heads can access. Altogether, our work provides a detailed understanding of RoPE, and how its properties relate to model behavior.

---