# Research Papers — 2025-10 · bundle page 23 of 217

> Full-text markdown of papers #1101–1150 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/23
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/22.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/24.md)

### FaRAccel: FPGA-Accelerated Defense Architecture for Efficient Bit-Flip Attack Resilience in Transformer Models

Authors: Najmeh Nazari, Banafsheh Saber Latibari, Elahe Hosseini, Fatemeh Movafagh, Chongzhou Fang, Hosein Mohammadi Makrani, Kevin Immanuel Gubbi, Abhijit Mahalanobis, Setareh Rafatirad, Hossein Sayadi, Houman Homayoun
Published: 2025-10-28
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2510.24985v1

Forget and Rewire (FaR) methodology has demonstrated strong resilience against Bit-Flip Attacks (BFAs) on Transformer-based models by obfuscating critical parameters through dynamic rewiring of linear layers. However, the application of FaR introduces non-negligible performance and memory overheads, primarily due to the runtime modification of activation pathways and the lack of hardware-level optimization. To overcome these limitations, we propose FaRAccel, a novel hardware accelerator architecture implemented on FPGA, specifically designed to offload and optimize FaR operations. FaRAccel integrates reconfigurable logic for dynamic activation rerouting, and lightweight storage of rewiring configurations, enabling low-latency inference with minimal energy overhead. We evaluate FaRAccel across a suite of Transformer models and demonstrate substantial reductions in FaR inference latency and improvement in energy efficiency, while maintaining the robustness gains of the original FaR methodology. To the best of our knowledge, this is the first hardware-accelerated defense against BFAs in Transformers, effectively bridging the gap between algorithmic resilience and efficient deployment on real-world AI platforms.

---

### LRT-Diffusion: Calibrated Risk-Aware Guidance for Diffusion Policies

Authors: Ximan Sun, Xiang Cheng
Published: 2025-10-28
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.24983v2

Diffusion policies are competitive for offline reinforcement learning (RL) but are typically guided at sampling time by heuristics that lack a statistical notion of risk. We introduce LRT-Diffusion, a risk-aware sampling rule that treats each denoising step as a sequential hypothesis test between the unconditional prior and the state-conditional policy head. Concretely, we accumulate a log-likelihood ratio and gate the conditional mean with a logistic controller whose threshold tau is calibrated once under H0 to meet a user-specified Type-I level alpha. This turns guidance from a fixed push into an evidence-driven adjustment with a user-interpretable risk budget. Importantly, we deliberately leave training vanilla (two heads with standard epsilon-prediction) under the structure of DDPM. LRT guidance composes naturally with Q-gradients: critic-gradient updates can be taken at the unconditional mean, at the LRT-gated mean, or a blend, exposing a continuum from exploitation to conservatism. We standardize states and actions consistently at train and test time and report a state-conditional out-of-distribution (OOD) metric alongside return. On D4RL MuJoCo tasks, LRT-Diffusion improves the return-OOD trade-off over strong Q-guided baselines in our implementation while honoring the desired alpha. Theoretically, we establish level-alpha calibration, concise stability bounds, and a return comparison showing when LRT surpasses Q-guidance-especially when off-support errors dominate. Overall, LRT-Diffusion is a drop-in, inference-time method that adds principled, calibrated risk control to diffusion policies for offline RL.

---

### Strategic inputs: feature selection from game-theoretic perspective

Authors: Chi Zhao, Jing Liu, Elena Parilina
Published: 2025-10-28
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.24982v2

The exponential growth of data volumes has led to escalating computational costs in machine learning model training. However, many features fail to contribute positively to model performance while consuming substantial computational resources. This paper presents an end-to-end feature selection framework for tabular data based on game theory. We formulate feature selection procedure based on a cooperative game where features are modeled as players, and their importance is determined through the evaluation of synergistic interactions and marginal contributions. The proposed framework comprises four core components: sample selection, game-theoretic feature importance evaluation, redundant feature elimination, and optimized model training. Experimental results demonstrate that the proposed method achieves substantial computation reduction while preserving predictive performance, thereby offering an efficient solution of the computational challenges of large-scale machine learning. The source code is available at https://github.com/vectorsss/strategy_inputs.

---

### FT-ARM: Fine-Tuned Agentic Reflection Multimodal Language Model for Pressure Ulcer Severity Classification with Reasoning

Authors: Reza Saadati Fard, Emmanuel Agu, Palawat Busaranuvong, Deepak Kumar, Shefalika Gautam, Bengisu Tulu, Diane Strong, Lorraine Loretz
Published: 2025-10-28
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.24980v1

Pressure ulcers (PUs) are a serious and prevalent healthcare concern. Accurate classification of PU severity (Stages I-IV) is essential for proper treatment but remains challenging due to subtle visual distinctions and subjective interpretation, leading to variability among clinicians. Prior AI-based approaches using Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) achieved promising accuracy but offered limited interpretability. We present FT-ARM (Fine-Tuned Agentic Reflection Multimodal model), a fine-tuned multimodal large language model (MLLM) with an agentic self-reflection mechanism for pressure ulcer severity classification. Inspired by clinician-style diagnostic reassessment, FT-ARM iteratively refines its predictions by reasoning over visual features and encoded clinical knowledge from text, enhancing both accuracy and consistency. On the publicly available Pressure Injury Image Dataset (PIID), FT-ARM, fine-tuned from LLaMA 3.2 90B, achieved 85% accuracy in classifying PU stages I-IV, surpassing prior CNN-based models by +4%. Unlike earlier CNN/ViT studies that relied solely on offline evaluations, FT-ARM is designed and tested for live inference, reflecting real-time deployment conditions. Furthermore, it produces clinically grounded natural-language explanations, improving interpretability and trust. By integrating fine-tuning and reflective reasoning across multimodal inputs, FT-ARM advances the reliability, transparency, and clinical applicability of automated wound assessment systems, addressing the critical need for consistent and explainable PU staging to support improved patient care.

---

### Hammering the Diagnosis: Rowhammer-Induced Stealthy Trojan Attacks on ViT-Based Medical Imaging

Authors: Banafsheh Saber Latibari, Najmeh Nazari, Hossein Sayadi, Houman Homayoun, Abhijit Mahalanobis
Published: 2025-10-28
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2510.24976v1

Vision Transformers (ViTs) have emerged as powerful architectures in medical image analysis, excelling in tasks such as disease detection, segmentation, and classification. However, their reliance on large, attention-driven models makes them vulnerable to hardware-level attacks. In this paper, we propose a novel threat model referred to as Med-Hammer that combines the Rowhammer hardware fault injection with neural Trojan attacks to compromise the integrity of ViT-based medical imaging systems. Specifically, we demonstrate how malicious bit flips induced via Rowhammer can trigger implanted neural Trojans, leading to targeted misclassification or suppression of critical diagnoses (e.g., tumors or lesions) in medical scans. Through extensive experiments on benchmark medical imaging datasets such as ISIC, Brain Tumor, and MedMNIST, we show that such attacks can remain stealthy while achieving high attack success rates about 82.51% and 92.56% in MobileViT and SwinTransformer, respectively. We further investigate how architectural properties, such as model sparsity, attention weight distribution, and the number of features of the layer, impact attack effectiveness. Our findings highlight a critical and underexplored intersection between hardware-level faults and deep learning security in healthcare applications, underscoring the urgent need for robust defenses spanning both model architectures and underlying hardware platforms.

---

### Maximum-Entropy Analog Computing Approaching ExaOPS-per-Watt Energy-efficiency at the RF-Edge

Authors: Aswin Undavalli, Kareem Rashed, Zhili Xiao, Arun Natarajan, Shantanu Chakrabartty, Aravind Nagulu
Published: 2025-10-28
Categories: cs.NE, cond-mat.stat-mech, cs.ET
arXiv: https://arxiv.org/abs/2510.24975v1

In this paper, we demonstrate how the physics of entropy production, when combined with symmetry constraints, can be used for implementing high-performance and energy-efficient analog computing systems. At the core of the proposed framework is a generalized maximum-entropy principle that can describe the evolution of a mesoscopic physical system formed by an interconnected ensemble of analog elements, including devices that can be readily fabricated on standard integrated circuit technology. We show that the maximum-entropy state of this ensemble corresponds to a margin-propagation (MP) distribution and can be used for computing correlations and inner products as the ensemble's macroscopic properties. Furthermore, the limits of computational throughput and energy efficiency can be pushed by extending the framework to non-equilibrium or transient operating conditions, which we demonstrate using a proof-of-concept radio-frequency (RF) correlator integrated circuit fabricated in a 22 nm SOI CMOS process. The measured results show a compute efficiency greater than 2 Peta ($10^{15}$) Bit Operations per second per Watt (PetaOPS/W) at 8-bit precision and greater than 0.8 Exa ($10^{18}$) Bit Operations per second per Watt (ExaOPS/W) at 3-bit precision for RF data sampled at rates greater than 4 GS/s. Using the fabricated prototypes, we also showcase several real-world RF applications at the edge, including spectrum sensing, and code-domain communications.

---

### Conformational Rank Conditioned Committees for Machine Learning-Assisted Directed Evolution

Authors: Mia Adler, Carrie Liang, Brian Peng, Oleg Presnyakov, Justin M. Baker, Jannelle Lauffer, Himani Sharma, Barry Merriman
Published: 2025-10-28
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.24974v2

Machine Learning-assisted directed evolution (MLDE) is a powerful tool for efficiently navigating antibody fitness landscapes. Many structure-aware MLDE pipelines rely on a single conformation or a single committee across all conformations, limiting their ability to separate conformational uncertainty from epistemic uncertainty. Here, we introduce a rank -conditioned committee (RCC) framework that leverages ranked conformations to assign a deep neural network committee per rank. This design enables a principled separation between epistemic uncertainty and conformational uncertainty. We validate our RCC-MLDE approach on SARS-CoV-2 antibody docking, demonstrating significant improvements over baseline strategies. Our results offer a scalable route for therapeutic antibody discovery while directly addressing the challenge of modeling conformational uncertainty.

---

### Sequences of Logits Reveal the Low Rank Structure of Language Models

Authors: Noah Golowich, Allen Liu, Abhishek Shetty
Published: 2025-10-28
Categories: cs.LG, cs.AI, cs.CL, stat.ML
arXiv: https://arxiv.org/abs/2510.24966v1

A major problem in the study of large language models is to understand their inherent low-dimensional structure. We introduce an approach to study the low-dimensional structure of language models at a model-agnostic level: as sequential probabilistic models. We first empirically demonstrate that a wide range of modern language models exhibit low-rank structure: in particular, matrices built from the model's logits for varying sets of prompts and responses have low approximate rank. We then show that this low-rank structure can be leveraged for generation -- in particular, we can generate a response to a target prompt using a linear combination of the model's outputs on unrelated, or even nonsensical prompts. On the theoretical front, we observe that studying the approximate rank of language models in the sense discussed above yields a simple universal abstraction whose theoretical predictions parallel our experiments. We then analyze the representation power of the abstraction and give provable learning guarantees.

---

### Exponential Dynamic Energy Network for High Capacity Sequence Memory

Authors: Arjun Karuvally, Pichsinee Lertsaroj, Terrence J. Sejnowski, Hava T. Siegelmann
Published: 2025-10-28
Categories: cs.NE
arXiv: https://arxiv.org/abs/2510.24965v1

The energy paradigm, exemplified by Hopfield networks, offers a principled framework for memory in neural systems by interpreting dynamics as descent on an energy surface. While powerful for static associative memories, it falls short in modeling sequential memory, where transitions between memories are essential. We introduce the Exponential Dynamic Energy Network (EDEN), a novel architecture that extends the energy paradigm to temporal domains by evolving the energy function over multiple timescales. EDEN combines a static high-capacity energy network with a slow, asymmetrically interacting modulatory population, enabling robust and controlled memory transitions. We formally derive short-timescale energy functions that govern local dynamics and use them to analytically compute memory escape times, revealing a phase transition between static and dynamic regimes. The analysis of capacity, defined as the number of memories that can be stored with minimal error rate as a function of the dimensions of the state space (number of feature neurons), for EDEN shows that it achieves exponential sequence memory capacity $O(γ^N)$, outperforming the linear capacity $O(N)$ of conventional models. Furthermore, EDEN's dynamics resemble the activity of time and ramping cells observed in the human brain during episodic memory tasks, grounding its biological relevance. By unifying static and sequential memory within a dynamic energy framework, EDEN offers a scalable and interpretable model for high-capacity temporal memory in both artificial and biological systems.

---

### Language Model Behavioral Phases are Consistent Across Architecture, Training Data, and Scale

Authors: James A. Michaelov, Roger P. Levy, Benjamin K. Bergen
Published: 2025-10-28
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.24963v1

We show that across architecture (Transformer vs. Mamba vs. RWKV), training dataset (OpenWebText vs. The Pile), and scale (14 million parameters to 12 billion parameters), autoregressive language models exhibit highly consistent patterns of change in their behavior over the course of pretraining. Based on our analysis of over 1,400 language model checkpoints on over 110,000 tokens of English, we find that up to 98% of the variance in language model behavior at the word level can be explained by three simple heuristics: the unigram probability (frequency) of a given word, the $n$-gram probability of the word, and the semantic similarity between the word and its context. Furthermore, we see consistent behavioral phases in all language models, with their predicted probabilities for words overfitting to those words' $n$-gram probabilities for increasing $n$ over the course of training. Taken together, these results suggest that learning in neural language models may follow a similar trajectory irrespective of model details.

---

### Resource-Efficient and Robust Inference of Deep and Bayesian Neural Networks on Embedded and Analog Computing Platforms

Authors: Bernhard Klein
Published: 2025-10-28
Categories: cs.LG, cs.AR, cs.NE
arXiv: https://arxiv.org/abs/2510.24951v1

While modern machine learning has transformed numerous application domains, its growing computational demands increasingly constrain scalability and efficiency, particularly on embedded and resource-limited platforms. In practice, neural networks must not only operate efficiently but also provide reliable predictions under distributional shifts or unseen data. Bayesian neural networks offer a principled framework for quantifying uncertainty, yet their computational overhead further compounds these challenges. This work advances resource-efficient and robust inference for both conventional and Bayesian neural networks through the joint pursuit of algorithmic and hardware efficiency. The former reduces computation through model compression and approximate Bayesian inference, while the latter optimizes deployment on digital accelerators and explores analog hardware, bridging algorithmic design and physical realization. The first contribution, Galen, performs automatic layer-specific compression guided by sensitivity analysis and hardware-in-the-loop feedback. Analog accelerators offer efficiency gains at the cost of noise; this work models device imperfections and extends noisy training to nonstationary conditions, improving robustness and stability. A second line of work advances probabilistic inference, developing analytic and ensemble approximations that replace costly sampling, integrate into a compiler stack, and optimize embedded inference. Finally, probabilistic photonic computing introduces a paradigm where controlled analog noise acts as an intrinsic entropy source, enabling fast, energy-efficient probabilistic inference directly in hardware. Together, these studies demonstrate how efficiency and reliability can be advanced jointly through algorithm-hardware co-design, laying the foundation for the next generation of trustworthy, energy-efficient machine-learning systems.

---

### SCOUT: A Lightweight Framework for Scenario Coverage Assessment in Autonomous Driving

Authors: Anil Yildiz, Sarah M. Thornton, Carl Hildebrandt, Sreeja Roy-Singh, Mykel J. Kochenderfer
Published: 2025-10-28
Categories: cs.RO, cs.AI, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.24949v1

Assessing scenario coverage is crucial for evaluating the robustness of autonomous agents, yet existing methods rely on expensive human annotations or computationally intensive Large Vision-Language Models (LVLMs). These approaches are impractical for large-scale deployment due to cost and efficiency constraints. To address these shortcomings, we propose SCOUT (Scenario Coverage Oversight and Understanding Tool), a lightweight surrogate model designed to predict scenario coverage labels directly from an agent's latent sensor representations. SCOUT is trained through a distillation process, learning to approximate LVLM-generated coverage labels while eliminating the need for continuous LVLM inference or human annotation. By leveraging precomputed perception features, SCOUT avoids redundant computations and enables fast, scalable scenario coverage estimation. We evaluate our method across a large dataset of real-life autonomous navigation scenarios, demonstrating that it maintains high accuracy while significantly reducing computational cost. Our results show that SCOUT provides an effective and practical alternative for large-scale coverage analysis. While its performance depends on the quality of LVLM-generated training labels, SCOUT represents a major step toward efficient scenario coverage oversight in autonomous systems.

---

### Finding Culture-Sensitive Neurons in Vision-Language Models

Authors: Xiutian Zhao, Rochelle Choenni, Rohit Saxena, Ivan Titov
Published: 2025-10-28
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.24942v2

Despite their impressive performance, vision-language models (VLMs) still struggle on culturally situated inputs. To understand how VLMs process culturally grounded information, we study the presence of culture-sensitive neurons, i.e., neurons whose activations show preferential sensitivity to inputs associated with particular cultural contexts. We examine whether such neurons are important for culturally diverse visual question answering and where they are located. Using the CVQA benchmark, we identify neurons of culture selectivity and perform diagnostic tests by deactivating the neurons flagged by various identification methods. Experiments on three VLMs across 25 cultural groups demonstrate the existence of neurons whose ablation disproportionately harms performance on questions about the corresponding cultures, while having limited effects on others. Moreover, we introduce a new margin-based selector Contrastive Activation Margin (ConAct) and show that it outperforms probability- and entropy-based methods in identifying neurons associated with cultural selectivity. Finally, our layer-wise analyses reveal that such neurons are not uniformly distributed: they cluster in specific decoder layers in a model-dependent way.

---

### Can Aha Moments Be Fake? Towards Quantifying Decorative and True Thinking in Chain-of-Thought

Authors: Jiachen Zhao, Yiyou Sun, Weiyan Shi, Dawn Song
Published: 2025-10-28
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.24941v4

Large language models can generate long chain-of-thought (CoT) reasoning, yet prior work suggests that CoT can be post-hoc rationalization rather than a faithful reflection of the computation through explicitly designed settings. In this work, we go further and propose a True Thinking Score (TTS) to quantify the causal contribution of each step in CoT to the model's final prediction in realistic reasoning problems. Across eleven models ranging from 1.5B to 1.1T parameters on common reasoning benchmarks, we find that CoTs often interleave true-thinking steps, which causally affect the final answer, with decorative-thinking steps, which appear useful but have little causal influence; Such decorative steps remain prevalent even for frontier models: Over 30% of steps in Kimi-K2.6 are decorative on MATH with TTS <= 0.005. Furthermore, TTS enables effective CoT pruning: removing 50% of CoT steps with the lowest TTS can largely maintain the performance. Self-training on these pruned CoTs reduces reasoning length by 66% while preserving performance on Nemotron3-Nano-30B. Finally, we provide a mechanistic analysis showing that LLMs can be steered in the latent space to engage or disengage with reasoning steps. Overall, our results reveal that frontier LLMs often verbalize reasoning steps that are not causally used, challenging both the efficiency and the trustworthiness of CoT.

---

### SemCoT: Accelerating Chain-of-Thought Reasoning through Semantically-Aligned Implicit Tokens

Authors: Yinhan He, Wendy Zheng, Yaochen Zhu, Zaiyi Zheng, Lin Su, Sriram Vasudevan, Qi Guo, Liangjie Hong, Jundong Li
Published: 2025-10-28
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.24940v3

The verbosity of Chain-of-Thought (CoT) reasoning hinders its mass deployment in efficiency-critical applications. Recently, implicit CoT approaches have emerged, which encode reasoning steps within LLM's hidden embeddings (termed ``implicit reasoning'') rather than explicit tokens. This approach accelerates CoT by reducing the reasoning length and bypassing some LLM components. However, existing implicit CoT methods face two significant challenges: (1) they fail to preserve the semantic alignment between the implicit reasoning (when transformed to natural language) and the ground-truth reasoning, resulting in a significant CoT performance degradation, and (2) they focus on reducing the length of the implicit reasoning; however, they neglect the considerable time cost for an LLM to generate one individual implicit reasoning token. To tackle these challenges, we propose a novel semantically-aligned implicit CoT framework termed SemCoT. In particular, for the first challenge, we design a contrastively trained sentence transformer that evaluates semantic alignment between implicit and explicit reasoning, which is used to enforce semantic preservation during implicit reasoning optimization. To address the second challenge, we introduce an efficient implicit reasoning generator by finetuning a lightweight language model using knowledge distillation. This generator is guided by our sentence transformer to distill ground-truth reasoning into semantically aligned implicit reasoning, while also optimizing for accuracy. SemCoT is the first approach that enhances CoT efficiency by jointly optimizing token-level generation speed and preserving semantic alignment with ground-truth reasoning. Extensive experiments demonstrate the superior performance of SemCoT compared to state-of-the-art methods in both efficiency and effectiveness. Our code can be found at https://github.com/YinhanHe123/SemCoT/.

---

### IBIS: A Hybrid Inception-BiLSTM and SVM Ensemble for Robust Doppler-based Human Activity Recognition

Authors: Alison M. Fernandes, Hermes I. Del Monego, Bruno S. Chang, Anelise Munaretto, Hélder M. Fontes, Rui L. Campos
Published: 2025-10-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.24936v3

Wi-Fi sensing is a leading technology for Human Activity Recognition (HAR), offering a non-intrusive and cost-effective solution for healthcare and smart environments. Despite its potential, existing methods struggle with domain shift issues, often failing to generalize to unseen environments due to overfitting. This paper proposes IBIS, a robust ensemble framework combining Inception-Bidirectional Long Short-Term Memory (BiLSTM) for feature extraction and Support Vector Machine (SVM) for classification of Doppler signatures. The proposed architecture specifically targets generalization capabilities. Experimental results on multiple datasets show that IBIS achieves 95.40% accuracy, delivering a 7.58% performance gain compared to standard architectures in cross-scenario evaluations on external datasets. The analysis confirms that IBIS effectively mitigates environmental dependency in Wi-Fi-based HAR.

---

### Disaggregation Reveals Hidden Training Dynamics: The Case of Agreement Attraction

Authors: James A. Michaelov, Catherine Arnett
Published: 2025-10-28
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.24934v1

Language models generally produce grammatical text, but they are more likely to make errors in certain contexts. Drawing on paradigms from psycholinguistics, we carry out a fine-grained analysis of those errors in different syntactic contexts. We demonstrate that by disaggregating over the conditions of carefully constructed datasets and comparing model performance on each over the course of training, it is possible to better understand the intermediate stages of grammatical learning in language models. Specifically, we identify distinct phases of training where language model behavior aligns with specific heuristics such as word frequency and local context rather than generalized grammatical rules. We argue that taking this approach to analyzing language model behavior more generally can serve as a powerful tool for understanding the intermediate learning phases, overall training dynamics, and the specific generalizations learned by language models.

---

### RiddleBench: A New Generative Reasoning Benchmark for LLMs

Authors: Deepon Halder, Alan Saji, Thanmay Jayakumar, Ratish Puduppully, Anoop Kunchukuttan, Raj Dabre
Published: 2025-10-28
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.24932v1

Large Language Models have demonstrated strong performance on many established reasoning benchmarks. However, these benchmarks primarily evaluate structured skills like quantitative problem-solving, leaving a gap in assessing flexible, multifaceted reasoning abilities that are central to human intelligence. These abilities require integrating logical deduction with spatial awareness and constraint satisfaction, which current evaluations do not measure well. To address this, we introduce RiddleBench, a benchmark of 1,737 challenging puzzles in English designed to probe these core reasoning capabilities. Evaluation of state-of-the-art models on RiddleBench shows fundamental weaknesses. Even top proprietary models like Gemini 2.5 Pro, o3, and Claude 4 Sonnet achieve accuracy just above 60% (60.30%, 63.37%, and 63.16%). Analysis further reveals deep failures, including hallucination cascades (accepting flawed reasoning from other models) and poor self-correction due to a strong self-confirmation bias. Their reasoning is also fragile, with performance degrading significantly when constraints are reordered or irrelevant information is introduced. RiddleBench functions as a diagnostic tool for these issues and as a resource for guiding the development of more robust and reliable language models.

---

### WBT-BGRL: A Non-Contrastive Weighted Bipartite Link Prediction Model for Inductive Learning

Authors: Joel Frank Huarayo Quispe, Lilian Berton, Didier Vega-Oliveros
Published: 2025-10-28
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.24927v1

Link prediction in bipartite graphs is crucial for applications like recommendation systems and failure detection, yet it is less studied than in monopartite graphs. Contrastive methods struggle with inefficient and biased negative sampling, while non-contrastive approaches rely solely on positive samples. Existing models perform well in transductive settings, but their effectiveness in inductive, weighted, and bipartite scenarios remains untested. To address this, we propose Weighted Bipartite Triplet-Bootstrapped Graph Latents (WBT-BGRL), a non-contrastive framework that enhances bootstrapped learning with a novel weighting mechanism in the triplet loss. Using a bipartite architecture with dual GCN encoders, WBT-BGRL is evaluated against adapted state-of-the-art models (T-BGRL, BGRL, GBT, CCA-SSG). Results on real-world datasets (Industry and E-commerce) show competitive performance, especially when weighting is applied during pretraining-highlighting the value of weighted, non-contrastive learning for inductive link prediction in bipartite graphs.

---

### KAN-GCN: Combining Kolmogorov-Arnold Network with Graph Convolution Network for an Accurate Ice Sheet Emulator

Authors: Zesheng Liu, YoungHyun Koo, Maryam Rahnemoonfar
Published: 2025-10-28
Categories: cs.LG, cs.AI, math.NA
arXiv: https://arxiv.org/abs/2510.24926v1

We introduce KAN-GCN, a fast and accurate emulator for ice sheet modeling that places a Kolmogorov-Arnold Network (KAN) as a feature-wise calibrator before graph convolution networks (GCNs). The KAN front end applies learnable one-dimensional warps and a linear mixing step, improving feature conditioning and nonlinear encoding without increasing message-passing depth. We employ this architecture to improve the performance of emulators for numerical ice sheet models. Our emulator is trained and tested using 36 melting-rate simulations with 3 mesh-size settings for Pine Island Glacier, Antarctica. Across 2- to 5-layer architectures, KAN-GCN matches or exceeds the accuracy of pure GCN and MLP-GCN baselines. Despite a small parameter overhead, KAN-GCN improves inference throughput on coarser meshes by replacing one edge-wise message-passing layer with a node-wise transform; only the finest mesh shows a modest cost. Overall, KAN-first designs offer a favorable accuracy vs. efficiency trade-off for large transient scenario sweeps.

---

### Modality-Aware SAM: Sharpness-Aware-Minimization Driven Gradient Modulation for Harmonized Multimodal Learning

Authors: Hossein R. Nowdeh, Jie Ji, Xiaolong Ma, Fatemeh Afghah
Published: 2025-10-28
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.24919v1

In multimodal learning, dominant modalities often overshadow others, limiting generalization. We propose Modality-Aware Sharpness-Aware Minimization (M-SAM), a model-agnostic framework that applies to many modalities and supports early and late fusion scenarios. In every iteration, M-SAM in three steps optimizes learning. \textbf{First, it identifies the dominant modality} based on modalities' contribution in the accuracy using Shapley. \textbf{Second, it decomposes the loss landscape}, or in another language, it modulates the loss to prioritize the robustness of the model in favor of the dominant modality, and \textbf{third, M-SAM updates the weights} by backpropagation of modulated gradients. This ensures robust learning for the dominant modality while enhancing contributions from others, allowing the model to explore and exploit complementary features that strengthen overall performance. Extensive experiments on four diverse datasets show that M-SAM outperforms the latest state-of-the-art optimization and gradient manipulation methods and significantly balances and improves multimodal learning.

---

### Topic Analysis with Side Information: A Neural-Augmented LDA Approach

Authors: Biyi Fang, Truong Vo, Kripa Rajshekhar, Diego Klabjan
Published: 2025-10-28
Categories: cs.LG, stat.ME, stat.ML
arXiv: https://arxiv.org/abs/2510.24918v2

Traditional topic models such as Latent Dirichlet Allocation (LDA) have been widely used to uncover latent structures in text corpora, but they often struggle to integrate auxiliary information such as metadata, user attributes, or document labels. These limitations restrict their expressiveness, personalization, and interpretability. To address this, we propose nnLDA, a neural-augmented probabilistic topic model that dynamically incorporates side information through a neural prior mechanism. nnLDA models each document as a mixture of latent topics, where the prior over topic proportions is generated by a neural network conditioned on auxiliary features. This design allows the model to capture complex nonlinear interactions between side information and topic distributions that static Dirichlet priors cannot represent. We develop a stochastic variational Expectation-Maximization algorithm to jointly optimize the neural and probabilistic components. Across multiple benchmark datasets, nnLDA consistently outperforms LDA and Dirichlet-Multinomial Regression in topic coherence, perplexity, and downstream classification. These results highlight the benefits of combining neural representation learning with probabilistic topic modeling in settings where side information is available.

---

### Computational Foundations for Strategic Coopetition: Formalizing Trust and Reputation Dynamics

Authors: Vik Pant, Eric Yu
Published: 2025-10-28
Categories: cs.MA, cs.AI, cs.CY, cs.SE
arXiv: https://arxiv.org/abs/2510.24909v2

Modern socio-technical systems increasingly involve multi-stakeholder environments where actors simultaneously cooperate and compete. These coopetitive relationships exhibit dynamic trust evolution based on observed behavior over repeated interactions. While conceptual modeling languages like i* represent trust relationships qualitatively, they lack computational mechanisms for analyzing how trust changes with behavioral evidence. Conversely, computational trust models from multi-agent systems provide algorithmic updating but lack grounding in conceptual models that capture strategic dependencies covering mixed motives of actors. This technical report bridges this gap by developing a computational trust model that extends game-theoretic foundations for strategic coopetition with dynamic trust evolution. Building on companion work that achieved 58/60 validation (96.7%) for logarithmic specifications, we introduce trust as a two-layer system with immediate trust responding to current behavior and reputation tracking violation history. Trust evolves through asymmetric updating where cooperation builds trust gradually while violations erode it sharply, creating hysteresis effects and trust ceilings that constrain relationship recovery. We develop a structured translation framework enabling practitioners to instantiate computational trust models from i* dependency networks encompassing mixed motives of actors. Comprehensive experimental validation across 78,125 parameter configurations establishes robust emergence of negativity bias, hysteresis effects, and cumulative damage amplification. Empirical validation using the Renault-Nissan Alliance case study (1999-2025) achieves 49/60 validation points (81.7%), successfully reproducing documented trust evolution across five distinct relationship phases including crisis and recovery periods.

---

### Understanding Multi-View Transformers

Authors: Michal Stary, Julien Gaubil, Ayush Tewari, Vincent Sitzmann
Published: 2025-10-28
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.24907v1

Multi-view transformers such as DUSt3R are revolutionizing 3D vision by solving 3D tasks in a feed-forward manner. However, contrary to previous optimization-based pipelines, the inner mechanisms of multi-view transformers are unclear. Their black-box nature makes further improvements beyond data scaling challenging and complicates usage in safety- and reliability-critical applications. Here, we present an approach for probing and visualizing 3D representations from the residual connections of the multi-view transformers' layers. In this manner, we investigate a variant of the DUSt3R model, shedding light on the development of its latent state across blocks, the role of the individual layers, and suggest how it differs from methods with stronger inductive biases of explicit global pose. Finally, we show that the investigated variant of DUSt3R estimates correspondences that are refined with reconstructed geometry. The code used for the analysis is available at https://github.com/JulienGaubil/und3rstand .

---

### Fair Indivisible Payoffs through Shapley Value

Authors: Mikołaj Czarnecki, Michał Korniak, Oskar Skibski, Piotr Skowron
Published: 2025-10-28
Categories: cs.GT, cs.AI
arXiv: https://arxiv.org/abs/2510.24906v2

We consider the problem of payoff division in indivisible coalitional games, where the value of the grand coalition is a natural number. This number represents a certain quantity of indivisible objects, such as parliamentary seats, kidney exchanges, or top features contributing to the outcome of a machine learning model. The goal of this paper is to propose a fair method for dividing these objects among players. To achieve this, we define the indivisible Shapley value and study its properties. We demonstrate our proposed technique using three case studies, in particular, we use it to identify key regions of an image in the context of an image classification task.

---

### VividCam: Learning Unconventional Camera Motions from Virtual Synthetic Videos

Authors: Qiucheng Wu, Handong Zhao, Zhixin Shu, Jing Shi, Yang Zhang, Shiyu Chang
Published: 2025-10-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.24904v2

Although recent video generative models are getting more capable of following external camera controls, imposed by either text descriptions or camera trajectories, they still struggle to generalize to unconventional camera motions, which is crucial in creating truly original and artistic videos. The challenge lies in finding sufficient training videos with the intended uncommon camera motions. To this end, we propose VividCam, a training paradigm that enables diffusion models to learn complex camera motions from synthetic videos, releasing the reliance on collecting realistic training videos. VividCam incorporates multiple disentanglement strategies that isolate camera motion learning from synthetic appearance artifacts, ensuring more robust motion representation and mitigating domain shift. We show that our design synthesizes a wide range of precisely controlled camera motions using surprisingly simple synthetic data. Notably, this synthetic data often consists of basic geometries within a low-poly 3D scene and can be efficiently rendered by engines like Unity. Our video results can be found in https://wuqiuche.github.io/VividCamDemoPage/ .

---

### Pixels to Signals: A Real-Time Framework for Traffic Demand Estimation

Authors: H Mhatre, M Vyas, A Mittal
Published: 2025-10-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.24902v1

Traffic congestion is becoming a challenge in the rapidly growing urban cities, resulting in increasing delays and inefficiencies within urban transportation systems. To address this issue a comprehensive methodology is designed to optimize traffic flow and minimize delays. The framework is structured with three primary components: (a) vehicle detection, (b) traffic prediction, and (c) traffic signal optimization. This paper presents the first component, vehicle detection. The methodology involves analyzing multiple sequential frames from a camera feed to compute the background, i.e. the underlying roadway, by averaging pixel values over time. The computed background is then utilized to extract the foreground, where the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm is applied to detect vehicles. With its computational efficiency and minimal infrastructure modification requirements, the proposed methodology offers a practical and scalable solution for real-world deployment.

---

### Efficiency Without Cognitive Change: Evidence from Human Interaction with Narrow AI Systems

Authors: María Angélica Benítez, Rocío Candela Ceballos, Karina Del Valle Molina, Sofía Mundo Araujo, Sofía Evangelina Victorio Villaroel, Nadia Justel
Published: 2025-10-28
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2510.24893v2

The growing integration of artificial intelligence (AI) into human cognition raises a fundamental question: does AI merely improve efficiency, or does it alter how we think? This study experimentally tested whether short-term exposure to narrow AI tools enhances core cognitive abilities or simply optimizes task performance. Thirty young adults completed standardized neuropsychological assessments embedded in a seven-week protocol with a four-week online intervention involving problem-solving and verbal comprehension tasks, either with or without AI support (ChatGPT). While AI-assisted participants completed several tasks faster and more accurately, no significant pre-post differences emerged in standardized measures of problem solving or verbal comprehension. These results demonstrate efficiency gains without cognitive change, suggesting that current narrow AI systems serve as cognitive scaffolds extending performance without transforming underlying mental capacities. The findings highlight the need for ethical and educational frameworks that promote critical and autonomous thinking in an increasingly AI-augmented cognitive ecology.

---

### Idea2Plan: Exploring AI-Powered Research Planning

Authors: Jin Huang, Silviu Cucerzan, Sujay Kumar Jauhar, Ryen W. White
Published: 2025-10-28
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2510.24891v2

Large language models (LLMs) have demonstrated significant potential to accelerate scientific discovery as valuable tools for analyzing data, generating hypotheses, and supporting innovative approaches in various scientific fields. In this work, we investigate how LLMs can handle the transition from conceptual research ideas to well-structured research plans. Effective research planning not only supports scientists in advancing their research but also represents a crucial capability for the development of autonomous research agents. Despite its importance, the field lacks a systematic understanding of LLMs' research planning capability. To rigorously measure this capability, we introduce the Idea2Plan task and Idea2Plan Bench, a set of benchmarks built from ICML 2025 and Nature Mental Health papers released after major LLM training cutoffs. Each benchmark instance includes a research idea and a grading rubric capturing the key components of valid plans. We further propose Idea2Plan JudgeEval, a complementary benchmark to assess the reliability of LLM-based judges against expert annotations. Experimental results show that GPT-5 achieves the strongest performance on the benchmark, though substantial headroom remains for improvement. Our study provides new insights into LLMs' capability for research planning and lays the groundwork for future progress.

---

### Adaptive EEG-based stroke diagnosis with a GRU-TCN classifier and deep Q-learning thresholding

Authors: Shakeel Abdulkareem, Bora Yimenicioglu, Khartik Uppalapati, Aneesh Gudipati, Adan Eftekhari, Saleh Yassin
Published: 2025-10-28
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.24889v3

Rapid triage of suspected stroke needs accurate, bedside-deployable tools; EEG is promising but underused at first contact. We present an adaptive multitask EEG classifier that converts 32-channel signals to power spectral density features (Welch), uses a recurrent-convolutional network (GRU-TCN) to predict stroke type (healthy, ischemic, hemorrhagic), hemispheric lateralization, and severity, and applies a deep Q-network (DQN) to tune decision thresholds in real time. Using a patient-wise split of the UCLH Stroke EIT/EEG data set (44 recordings; about 26 acute stroke, 10 controls), the primary outcome was stroke-type performance; secondary outcomes were severity and lateralization. The baseline GRU-TCN reached 89.3% accuracy (F1 92.8%) for stroke type, about 96.9% (F1 95.9%) for severity, and about 96.7% (F1 97.4%) for lateralization. With DQN threshold adaptation, stroke-type accuracy increased to about 98.0% (F1 97.7%). We also tested robustness on an independent, low-density EEG cohort (ZJU4H) and report paired patient-level statistics. Analyses follow STARD 2015 guidance for diagnostic accuracy studies (index test: GRU-TCN+DQN; reference standard: radiology/clinical diagnosis; patient-wise evaluation). Adaptive thresholding shifts the operating point to clinically preferred sensitivity-specificity trade-offs, while integrated scalp-map and spectral visualizations support interpretability.

---

### Proper Body Landmark Subset Enables More Accurate and 5X Faster Recognition of Isolated Signs in LIBRAS

Authors: Daniele L. V. dos Santos, Thiago B. Pereira, Carlos Eduardo G. R. Alves, Richard J. M. G. Tello, Francisco de A. Boldt, Thiago M. Paixão
Published: 2025-10-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.24887v4

This paper examines the feasibility of utilizing lightweight body landmark detection for recognizing isolated signs in Brazilian Sign Language (LIBRAS). Although the use of skeleton-image representation has enabled substantial improvements in recognition performance, the use of OpenPose for landmark extraction hindered time performance. In a preliminary investigation, we observed that simply replacing OpenPose with lightweight MediaPipe, while improving processing speed, significantly reduced accuracy. To overcome this limitation, we explored landmark subset selection strategies to optimize recognition performance. Experimental results show that a proper landmark subset achieves comparable or superior performance to state-of-the-art methods while reducing processing time by more than 5X. As an additional contribution, we demonstrate that spline-based imputation effectively mitigates missing landmark issues, leading to substantial accuracy gains.

---

### FruitProm: Probabilistic Maturity Estimation and Detection of Fruits and Vegetables

Authors: Sidharth Rai, Rahul Harsha Cheppally, Benjamin Vail, Keziban Yalçın Dokumacı, Ajay Sharda
Published: 2025-10-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.24885v1

Maturity estimation of fruits and vegetables is a critical task for agricultural automation, directly impacting yield prediction and robotic harvesting. Current deep learning approaches predominantly treat maturity as a discrete classification problem (e.g., unripe, ripe, overripe). This rigid formulation, however, fundamentally conflicts with the continuous nature of the biological ripening process, leading to information loss and ambiguous class boundaries. In this paper, we challenge this paradigm by reframing maturity estimation as a continuous, probabilistic learning task. We propose a novel architectural modification to the state-of-the-art, real-time object detector, RT-DETRv2, by introducing a dedicated probabilistic head. This head enables the model to predict a continuous distribution over the maturity spectrum for each detected object, simultaneously learning the mean maturity state and its associated uncertainty. This uncertainty measure is crucial for downstream decision-making in robotics, providing a confidence score for tasks like selective harvesting. Our model not only provides a far richer and more biologically plausible representation of plant maturity but also maintains exceptional detection performance, achieving a mean Average Precision (mAP) of 85.6\% on a challenging, large-scale fruit dataset. We demonstrate through extensive experiments that our probabilistic approach offers more granular and accurate maturity assessments than its classification-based counterparts, paving the way for more intelligent, uncertainty-aware automated systems in modern agriculture

---

### Aggregation Hides Out-of-Distribution Generalization Failures from Spurious Correlations

Authors: Olawale Salaudeen, Haoran Zhang, Kumail Alhamoud, Sara Beery, Marzyeh Ghassemi
Published: 2025-10-28
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.24884v1

Benchmarks for out-of-distribution (OOD) generalization frequently show a strong positive correlation between in-distribution (ID) and OOD accuracy across models, termed "accuracy-on-the-line." This pattern is often taken to imply that spurious correlations - correlations that improve ID but reduce OOD performance - are rare in practice. We find that this positive correlation is often an artifact of aggregating heterogeneous OOD examples. Using a simple gradient-based method, OODSelect, we identify semantically coherent OOD subsets where accuracy on the line does not hold. Across widely used distribution shift benchmarks, the OODSelect uncovers subsets, sometimes over half of the standard OOD set, where higher ID accuracy predicts lower OOD accuracy. Our findings indicate that aggregate metrics can obscure important failure modes of OOD robustness. We release code and the identified subsets to facilitate further research.

---

### Seeing Through the MiRAGE: Evaluating Multimodal Retrieval Augmented Generation

Authors: Alexander Martin, William Walden, Reno Kriz, Dengjia Zhang, Kate Sanders, Eugene Yang, Chihsheng Jin, Benjamin Van Durme
Published: 2025-10-28
Categories: cs.CL, cs.CV, cs.IR
arXiv: https://arxiv.org/abs/2510.24870v3

We introduce MiRAGE, an evaluation framework for retrieval-augmented generation (RAG) from multimodal sources. As audiovisual media becomes a more prevalent source of information online, RAG systems must integrate such media into generation. Yet, existing evaluation methods for RAG are largely text-centric and do not readily transfer to multimodal settings. MiRAGE is a claim-centric approach to multimodal RAG evaluation, consisting of InfoF1, which assesses factuality and information coverage, and CiteF1, which assesses citation support and completeness. We show that, when applied by humans, MiRAGE strongly aligns with extrinsic judgments of output quality. We additionally introduce an automatic implementation of MiRAGE and compare it to multimodal variants of three prominent text-centric RAG metrics---ALCE, ARGUE, and RAGAS---finding that MiRAGE outperforms all three on text while being the only one to generalize to multimodal sources. We release open-source implementations and outline evaluation methods for multimodal RAG.

---

### Do Large Language Models Grasp The Grammar? Evidence from Grammar-Book-Guided Probing in Luxembourgish

Authors: Lujun Li, Yewei Song, Lama Sleem, Yiqun Wang, Yangjie Xu, Cedric Lothritz, Niccolo Gentile, Radu State, Tegawende F. Bissyande, Jacques Klein
Published: 2025-10-28
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.24856v2

Grammar refers to the system of rules that governs the structural organization and the semantic relations among linguistic units such as sentences, phrases, and words within a given language. In natural language processing, there remains a notable scarcity of grammar focused evaluation protocols, a gap that is even more pronounced for low-resource languages. Moreover, the extent to which large language models genuinely comprehend grammatical structure, especially the mapping between syntactic structures and meanings, remains under debate. To investigate this issue, we propose a Grammar Book Guided evaluation pipeline intended to provide a systematic and generalizable framework for grammar evaluation consisting of four key stages, and in this work we take Luxembourgish as a case study. The results show a weak positive correlation between translation performance and grammatical understanding, indicating that strong translations do not necessarily imply deep grammatical competence. Larger models perform well overall due to their semantic strength but remain weak in morphology and syntax, struggling particularly with Minimal Pair tasks, while strong reasoning ability offers a promising way to enhance their grammatical understanding.

---

### Scheduling Your LLM Reinforcement Learning with Reasoning Trees

Authors: Hong Wang, Zhezheng Hao, Jian Luo, Chenxing Wei, Yao Shu, Lei Liu, Qiang Lin, Hande Dong, Jiawei Chen
Published: 2025-10-28
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.24832v2

Using Reinforcement Learning with Verifiable Rewards (RLVR) to optimize Large Language Models (LLMs) can be conceptualized as progressively editing a query's `Reasoning Tree'. This process involves exploring nodes (tokens) and dynamically modifying the model's policy at each node. When combined with data scheduling, this process yields further gains in data efficiency and accuracy. However, existing RLVR data scheduling methods typically rely on path-based metrics to rank queries, overlooking the reasoning tree structures of these queries. In this paper, we introduce a novel metric, namely Reasoning Score (r-score), which measures the query's learning difficulty based on the structure of its reasoning tree. Based on the r-score, we propose the Reasoning Tree Schedule (Re-Schedule), a scheduling algorithm that constructs a curriculum progressing from structurally simple (high r-score) to complex (low r-score) queries. Experiments on six math-reasoning benchmarks show that Re-Schedule significantly improves average accuracy, achieving gains of up to 3.2%. These strong results validate our approach and demonstrate that a structural understanding of the reasoning tree provides a more powerful and principled foundation for RLVR data scheduling.

---

### The Narrative Continuity Test: A Conceptual Framework for Evaluating Identity Persistence in AI Systems

Authors: Stefano Natangelo
Published: 2025-10-28
Categories: cs.CY, cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2510.24831v2

Artificial intelligence systems based on large language models (LLMs) can now generate coherent text, music, and images, yet they operate without a persistent state: each inference reconstructs context from scratch. This paper introduces the Narrative Continuity Test (NCT) -- a conceptual framework for evaluating identity persistence and diachronic coherence in AI systems. Unlike capability benchmarks that assess task performance, the NCT examines whether an LLM remains the same interlocutor across time and interaction gaps. The framework defines five necessary axes -- Situated Memory, Goal Persistence, Autonomous Self-Correction, Stylistic & Semantic Stability, and Persona/Role Continuity -- and explains why current architectures systematically fail to support them. Case analyses (Character.\,AI, Grok, Replit, Air Canada) show predictable continuity failures under stateless inference. The NCT reframes AI evaluation from performance to persistence, outlining conceptual requirements for future benchmarks and architectural designs that could sustain long-term identity and goal coherence in generative models.

---

### The Generation Phases of Flow Matching: a Denoising Perspective

Authors: Anne Gagneux, Ségolène Martin, Rémi Gribonval, Mathurin Massias
Published: 2025-10-28
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.24830v2

Flow matching has achieved remarkable success, yet the factors influencing the quality of its generation process remain poorly understood. In this work, we adopt a denoising perspective and design a framework to empirically probe the generation process. Laying down the formal connections between flow matching models and denoisers, we provide a common ground to compare their performances on generation and denoising. This enables the design of principled and controlled perturbations to influence sample generation: noise and drift. This leads to new insights on the distinct dynamical phases of the generative process, enabling us to precisely characterize at which stage of the generative process denoisers succeed or fail and why this matters.

---

### Send Less, Save More: Energy-Efficiency Benchmark of Embedded CNN Inference vs. Data Transmission in IoT

Authors: Benjamin Karic, Nina Herrmann, Jan Stenkamp, Paula Scharf, Fabian Gieseke, Angela Schwering
Published: 2025-10-28
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.24829v2

The integration of the Internet of Things (IoT) and Artificial Intelligence offers significant opportunities to enhance our ability to monitor and address ecological changes. As environmental challenges become increasingly pressing, the need for effective remote monitoring solutions is more critical than ever. A major challenge in designing IoT applications for environmental monitoring - particularly those involving image data - is to create energy-efficient IoT devices capable of long-term operation in remote areas with limited power availability. Advancements in the field of Tiny Machine Learning allow the use of Convolutional Neural Networks (CNNs) on resource-constrained, battery-operated microcontrollers. Since data transfer is energy-intensive, performing inference directly on microcontrollers to reduce the message size can extend the operational lifespan of IoT nodes. This work evaluates the use of common Low Power Wide Area Networks and compressed CNNs trained on domain specific datasets on an ESP32-S3. Our experiments demonstrate, among other things, that executing CNN inference on-device and transmitting only the results reduces the overall energy consumption by a factor of up to five compared to sending raw image data. These findings advocate the development of IoT applications with reduced carbon footprint and capable of operating autonomously in environmental monitoring scenarios by incorporating EmbeddedML.

---

### MCIHN: A Hybrid Network Model Based on Multi-path Cross-modal Interaction for Multimodal Emotion Recognition

Authors: Haoyang Zhang, Zhou Yang, Ke Sun, Yucai Pang, Guoliang Xu
Published: 2025-10-28
Categories: cs.CV, cs.MM
arXiv: https://arxiv.org/abs/2510.24827v1

Multimodal emotion recognition is crucial for future human-computer interaction. However, accurate emotion recognition still faces significant challenges due to differences between different modalities and the difficulty of characterizing unimodal emotional information. To solve these problems, a hybrid network model based on multipath cross-modal interaction (MCIHN) is proposed. First, adversarial autoencoders (AAE) are constructed separately for each modality. The AAE learns discriminative emotion features and reconstructs the features through a decoder to obtain more discriminative information about the emotion classes. Then, the latent codes from the AAE of different modalities are fed into a predefined Cross-modal Gate Mechanism model (CGMM) to reduce the discrepancy between modalities, establish the emotional relationship between interacting modalities, and generate the interaction features between different modalities. Multimodal fusion using the Feature Fusion module (FFM) for better emotion recognition. Experiments were conducted on publicly available SIMS and MOSI datasets, demonstrating that MCIHN achieves superior performance.

---

### Augmenting Biological Fitness Prediction Benchmarks with Landscapes Features from GraphFLA

Authors: Mingyu Huang, Shasha Zhou, Ke Li
Published: 2025-10-28
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.24826v1

Machine learning models increasingly map biological sequence-fitness landscapes to predict mutational effects. Effective evaluation of these models requires benchmarks curated from empirical data. Despite their impressive scales, existing benchmarks lack topographical information regarding the underlying fitness landscapes, which hampers interpretation and comparison of model performance beyond averaged scores. Here, we introduce GraphFLA, a Python framework that constructs and analyzes fitness landscapes from mutagensis data in diverse modalities (e.g., DNA, RNA, protein, and beyond) with up to millions of mutants. GraphFLA calculates 20 biologically relevant features that characterize 4 fundamental aspects of landscape topography. By applying GraphFLA to over 5,300 landscapes from ProteinGym, RNAGym, and CIS-BP, we demonstrate its utility in interpreting and comparing the performance of dozens of fitness prediction models, highlighting factors influencing model accuracy and respective advantages of different models. In addition, we release 155 combinatorially complete empirical fitness landscapes, encompassing over 2.2 million sequences across various modalities. All the codes and datasets are available at https://github.com/COLA-Laboratory/GraphFLA.

---

### Parallel Loop Transformer for Efficient Test-Time Computation Scaling

Authors: Bohong Wu, Mengzhao Chen, Xiang Luo, Shen Yan, Qifan Yu, Fan Xia, Tianqi Zhang, Hongrui Zhan, Zheng Zhong, Xun Zhou, Siyuan Qiao, Xingyan Bin
Published: 2025-10-28
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.24824v1

Large Language Models (LLMs) are powerful but often too slow and costly for real-world use during inference. Looped transformers save on parameters by reusing the same weights for multiple computational steps, or "loops." However, this approach has a major flaw: the loops run one after another, causing inference latency and memory requirements to increase with each added loop. This makes them impractical for fast applications. To solve this problem, we introduce the Parallel Loop Transformer (PLT). PLT is a new architecture that delivers the performance benefits of a deep, looped model but with the low latency of a standard, non-looped model. PLT works using two key techniques. First, Cross-Loop Parallelism (CLP) breaks the sequential dependency by computing different loops for different tokens at the same time, all within a single pass. Second, to prevent memory costs from growing, we use an Efficient Representation Enhancement strategy. This method shares the memory (KV cache) from the first loop with all other loops. It then uses a Gated Sliding-Window Attention (G-SWA) to combine this shared global information with local information, maintaining high accuracy. Our experiments show that PLT achieves the high accuracy of a traditional looped model but with almost no extra latency or memory cost compared to a standard transformer.

---

### Do Chatbots Walk the Talk of Responsible AI?

Authors: Susan Ariel Aaronson, Michael Moreno
Published: 2025-10-28
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2510.24823v1

This study examines whether leading AI chatbot companies implement the responsible AI principles they publicly advocate. The authors used a mixed-methods approach analyzing four major chatbots (ChatGPT, Gemini, DeepSeek, and Grok) across company websites, technical documentation, and direct chatbot evaluations. We found significant gaps between corporate rhetoric and practice.

---

### Ming-Flash-Omni: A Sparse, Unified Architecture for Multimodal Perception and Generation

Authors: Inclusion AI, :, Bowen Ma, Cheng Zou, ChengKun Du, Canxiang Yan, Chunxiang Jin, Chunjie Shen, Chenyu Lian, Chengxiang Fan, Dandan Zheng, Fudong Wang et al.
Published: 2025-10-28
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.24821v3

We propose Ming-Flash-Omni, an upgraded version of Ming-Omni, built upon a sparser Mixture-of-Experts (MoE) variant of Ling-Flash-2.0 with 100 billion total parameters, of which only 6.1 billion are active per token. This architecture enables highly efficient scaling (dramatically improving computational efficiency while significantly expanding model capacity) and empowers stronger unified multimodal intelligence across vision, speech, and language, representing a key step toward Artificial General Intelligence (AGI). Compared to its predecessor, the upgraded version exhibits substantial improvements across multimodal understanding and generation. Notably, it achieves strong performance on vision-language understanding benchmarks, with overall scores on par with Gemini 2.5 Pro, and enables seamless switching among multimodal tasks in multi-turn interactions. In speech, it achieves strong performance in contextual and dialect-aware ASR while enabling joint, continuous-generation of speech, sound, and music. In vision, it introduces generative semantic segmentation that achieves competitive standalone performance and enhances spatial control and editing consistency, alongside marked improvements in identity preservation, and high-fidelity in-image text rendering. Together, these capabilities demonstrate that a single unified model can serve as a practical foundation for general-purpose multimodal intelligence.

---

### SafeEditor: Unified MLLM for Efficient Post-hoc T2I Safety Editing

Authors: Ruiyang Zhang, Jiahao Luo, Xiaoru Feng, Qiufan Pang, Yaodong Yang, Juntao Dai
Published: 2025-10-28
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.24820v1

With the rapid advancement of text-to-image (T2I) models, ensuring their safety has become increasingly critical. Existing safety approaches can be categorized into training-time and inference-time methods. While inference-time methods are widely adopted due to their cost-effectiveness, they often suffer from limitations such as over-refusal and imbalance between safety and utility. To address these challenges, we propose a multi-round safety editing framework that functions as a model-agnostic, plug-and-play module, enabling efficient safety alignment for any text-to-image model. Central to this framework is MR-SafeEdit, a multi-round image-text interleaved dataset specifically constructed for safety editing in text-to-image generation. We introduce a post-hoc safety editing paradigm that mirrors the human cognitive process of identifying and refining unsafe content. To instantiate this paradigm, we develop SafeEditor, a unified MLLM capable of multi-round safety editing on generated images. Experimental results show that SafeEditor surpasses prior safety approaches by reducing over-refusal while achieving a more favorable safety-utility balance.

---

### Towards a Method for Synthetic Generation of Persons with Aphasia Transcripts

Authors: Jason M. Pittman, Anton Phillips, Yesenia Medina-Santos, Brielle C. Stark
Published: 2025-10-28
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.24817v2

In aphasia research, Speech-Language Pathologists (SLPs) devote extensive time to manually coding speech samples using Correct Information Units (CIUs), a measure of how informative an individual sample of speech is. Developing automated systems to recognize aphasic language is limited by data scarcity. For example, only about 600 transcripts are available in AphasiaBank yet billions of tokens are used to train large language models (LLMs). In the broader field of machine learning (ML), researchers increasingly turn to synthetic data when such are sparse. Therefore, this study constructs and validates two methods to generate synthetic transcripts of the AphasiaBank Cat Rescue picture description task. One method leverages a procedural programming approach while the second uses Mistral 7b Instruct and Llama 3.1 8b Instruct LLMs. The methods generate transcripts across four severity levels (Mild, Moderate, Severe, Very Severe) through word dropping, filler insertion, and paraphasia substitution. Overall, we found, compared to human-elicited transcripts, Mistral 7b Instruct best captures key aspects of linguistic degradation observed in aphasia, showing realistic directional changes in NDW, word count, and word length amongst the synthetic generation methods. Based on the results, future work should plan to create a larger dataset, fine-tune models for better aphasic representation, and have SLPs assess the realism and usefulness of the synthetic transcripts.

---

### Perception, Understanding and Reasoning, A Multimodal Benchmark for Video Fake News Detection

Authors: Cui Yakun, Peng Qi, Fushuo Huo, Hang Du, Weijie Shi, Juntao Dai, Zhenghao Zhu, Sirui Han, Yike Guo
Published: 2025-10-28
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.24816v2

The advent of multi-modal large language models (MLLMs) has greatly advanced research on video fake news detection (VFND) tasks. Existing benchmarks typically focus on the detection accuracy, while failing to provide fine-grained assessments for the entire detection process. To address these limitations, we introduce {POVFNDB (Process-oriented Video Fake News Detection Benchmark)}, a process-oriented benchmark comprising 10 tasks designed to systematically evaluate MLLMs' perception, understanding, and reasoning capabilities in VFND. This benchmark contains \textit{36,240} human-annotated question-answer (QA) in structured or open-ended formats, spanning 15 distinct evaluation dimensions that characterize different aspects of the video fake news detection process. Using POVFNDB, we conduct comprehensive evaluations on both proprietary and open-source MLLMs. Moreover, we establish a strong benchmark baseline by fine-tuning Qwen2.5VL-7B-Instruct on process-oriented chain-of-thought data constructed with our proposed POVFND-CoT framework, achieving state-of-the-art performance on VFND.

---

### Tree Ensemble Explainability through the Hoeffding Functional Decomposition and TreeHFD Algorithm

Authors: Clément Bénard
Published: 2025-10-28
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2510.24815v1

Tree ensembles have demonstrated state-of-the-art predictive performance across a wide range of problems involving tabular data. Nevertheless, the black-box nature of tree ensembles is a strong limitation, especially for applications with critical decisions at stake. The Hoeffding or ANOVA functional decomposition is a powerful explainability method, as it breaks down black-box models into a unique sum of lower-dimensional functions, provided that input variables are independent. In standard learning settings, input variables are often dependent, and the Hoeffding decomposition is generalized through hierarchical orthogonality constraints. Such generalization leads to unique and sparse decompositions with well-defined main effects and interactions. However, the practical estimation of this decomposition from a data sample is still an open problem. Therefore, we introduce the TreeHFD algorithm to estimate the Hoeffding decomposition of a tree ensemble from a data sample. We show the convergence of TreeHFD, along with the main properties of orthogonality, sparsity, and causal variable selection. The high performance of TreeHFD is demonstrated through experiments on both simulated and real data, using our treehfd Python package (https://github.com/ThalesGroup/treehfd). Besides, we empirically show that the widely used TreeSHAP method, based on Shapley values, is strongly connected to the Hoeffding decomposition.

---

### Deep Feature Optimization for Enhanced Fish Freshness Assessment

Authors: Phi-Hung Hoang, Nam-Thuan Trinh, Van-Manh Tran, Thi-Thu-Hong Phan
Published: 2025-10-28
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.24814v1

Assessing fish freshness is vital for ensuring food safety and minimizing economic losses in the seafood industry. However, traditional sensory evaluation remains subjective, time-consuming, and inconsistent. Although recent advances in deep learning have automated visual freshness prediction, challenges related to accuracy and feature transparency persist. This study introduces a unified three-stage framework that refines and leverages deep visual representations for reliable fish freshness assessment. First, five state-of-the-art vision architectures - ResNet-50, DenseNet-121, EfficientNet-B0, ConvNeXt-Base, and Swin-Tiny - are fine-tuned to establish a strong baseline. Next, multi-level deep features extracted from these backbones are used to train seven classical machine learning classifiers, integrating deep and traditional decision mechanisms. Finally, feature selection methods based on Light Gradient Boosting Machine (LGBM), Random Forest, and Lasso identify a compact and informative subset of features. Experiments on the Freshness of the Fish Eyes (FFE) dataset demonstrate that the best configuration combining Swin-Tiny features, an Extra Trees classifier, and LGBM-based feature selection achieves an accuracy of 85.99%, outperforming recent studies on the same dataset by 8.69-22.78%. These findings confirm the effectiveness and generalizability of the proposed framework for visual quality evaluation tasks.

---

### DualCap: Enhancing Lightweight Image Captioning via Dual Retrieval with Similar Scenes Visual Prompts

Authors: Binbin Li, Guimiao Yang, Zisen Qi, Haiping Wang, Yu Ding
Published: 2025-10-28
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.24813v1

Recent lightweight retrieval-augmented image caption models often utilize retrieved data solely as text prompts, thereby creating a semantic gap by leaving the original visual features unenhanced, particularly for object details or complex scenes. To address this limitation, we propose $DualCap$, a novel approach that enriches the visual representation by generating a visual prompt from retrieved similar images. Our model employs a dual retrieval mechanism, using standard image-to-text retrieval for text prompts and a novel image-to-image retrieval to source visually analogous scenes. Specifically, salient keywords and phrases are derived from the captions of visually similar scenes to capture key objects and similar details. These textual features are then encoded and integrated with the original image features through a lightweight, trainable feature fusion network. Extensive experiments demonstrate that our method achieves competitive performance while requiring fewer trainable parameters compared to previous visual-prompting captioning approaches.

---