# Research Papers — 2025-10 · bundle page 115 of 217

> Full-text markdown of papers #5701–5750 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/115
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/114.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/116.md)

### Data for Inclusion: The Redistributive Power of Data Economics

Authors: Diego Vallarino
Published: 2025-10-14
Categories: econ.GN, cs.LG
arXiv: https://arxiv.org/abs/2510.16009v1

This paper evaluates the redistributive and efficiency impacts of expanding access to positive credit information in a financially excluded economy. Using microdata from Uruguay's 2021 household survey, we simulate three data regimes negative only, partial positive (Score+), and synthetic full visibility and assess their effects on access to credit, interest burden, and inequality. Our findings reveal that enabling broader data sharing substantially reduces financial costs, compresses interest rate dispersion, and lowers the Gini coefficient of credit burden. While partial visibility benefits a subset of the population, full synthetic access delivers the most equitable and efficient outcomes. The analysis positions credit data as a non-rival public asset with transformative implications for financial inclusion and poverty reduction.

---

### Convolutional Attention in Betting Exchange Markets

Authors: Rui Gonçalves, Vitor Miguel Ribeiro, Roman Chertovskih, António Pedro Aguiar
Published: 2025-10-14
Categories: q-fin.ST, cs.LG
arXiv: https://arxiv.org/abs/2510.16008v1

This study presents the implementation of a short-term forecasting system for price movements in exchange markets, using market depth data and a systematic procedure to enable a fully automated trading system. The case study focuses on the UK to Win Horse Racing market during the pre-live stage on the world's leading betting exchange, Betfair. Innovative convolutional attention mechanisms are introduced and applied to multiple recurrent neural networks and bi-dimensional convolutional recurrent neural network layers. Additionally, a novel padding method for convolutional layers is proposed, specifically designed for multivariate time series processing. These innovations are thoroughly detailed, along with their execution process. The proposed architectures follow a standard supervised learning approach, involving model training and subsequent testing on new data, which requires extensive pre-processing and data analysis. The study also presents a complete end-to-end framework for automated feature engineering and market interactions using the developed models in production. The key finding of this research is that all proposed innovations positively impact the performance metrics of the classification task under examination, thereby advancing the current state-of-the-art in convolutional attention mechanisms and padding methods applied to multivariate time series problems.

---

### Layer-Aware Influence for Online Data Valuation Estimation

Authors: Ziao Yang, Longbo Huang, Hongfu Liu
Published: 2025-10-14
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.16007v1

Data-centric learning emphasizes curating high-quality training samples to boost performance rather than designing new architectures. A central problem is to estimate the influence of training sample efficiently. Prior studies largely focus on static influence measured on a converged model, overlooking how data valuation dynamically changes during optimization. This omission neglects the dynamic nature of sample influence during optimization, especially in deep models. To address the computational burden of frequent influence estimation, we develop a layer-aware online estimator that requires only loss-to-output gradients. This design avoids parameter-level and full-network gradients while preserving ranking fidelity. Extensive experiments across LLM pretraining, fine-tuning, and image classification show our method improves accuracy with substantially lower time and memory cost, making dynamic data curation efficient and scalable in practice.

---

### Breaking Guardrails, Facing Walls: Insights on Adversarial AI for Defenders & Researchers

Authors: Giacomo Bertollo, Naz Bodemir, Jonah Burgess
Published: 2025-10-14
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2510.16005v1

Analyzing 500 CTF participants, this paper shows that while participants readily bypassed simple AI guardrails using common techniques, layered multi-step defenses still posed significant challenges, offering concrete insights for building safer AI systems.

---

### PAINT: Parallel-in-time Neural Twins for Dynamical System Reconstruction

Authors: Andreas Radler, Vincent Seyfried, Johannes Brandstetter, Thomas Lichtenegger
Published: 2025-10-14
Categories: cs.AI, physics.flu-dyn
arXiv: https://arxiv.org/abs/2510.16004v2

Neural surrogates have shown great potential in simulating dynamical systems, while offering real-time capabilities. We envision Neural Twins as a progression of neural surrogates, aiming to create digital replicas of real systems. A neural twin consumes measurements at test time to update its state, thereby enabling context-specific decision-making. We argue, that a critical property of neural twins is their ability to remain on-trajectory, i.e., to stay close to the true system state over time. We introduce Parallel-in-time Neural Twins (PAINT), an architecture-agnostic family of methods for modeling dynamical systems from measurements. PAINT trains a generative neural network to model the distribution of states in parallel over time. At test time, states are predicted from measurements in a sliding window fashion. Our theoretical analysis shows that PAINT is on-trajectory, whereas autoregressive models generally are not. Empirically, we evaluate our method on a challenging two-dimensional turbulent fluid dynamics problem. The results demonstrate that PAINT stays on-trajectory and predicts system states from sparse measurements with high fidelity. These findings underscore PAINT's potential for developing neural twins that stay on-trajectory, enabling more accurate state estimation and decision-making.

---

### An Order-Sensitive Conflict Measure for Random Permutation Sets

Authors: Ruolan Cheng, Yong Deng
Published: 2025-10-14
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.16001v2

Random permutation set (RPS) is a new formalism for reasoning with uncertainty involving order information. Measuring the conflict between two pieces of evidence represented by permutation mass functions remains an open issue in order-dependent uncertain information fusion. This paper analyzes conflicts in RPS from two different perspectives: random finite set (RFS) and Dempster-Shafer theory (DST). From the DST perspective, the order information incorporated into focal sets reflects a qualitative propensity where higher-ranked elements are more significant. Motivated by this view and observations on permutations, we define a non-overlap-based inconsistency measure for permutations and develop an order-sensitive conflict measure for RPSs. The proposed method reformulates the conflict in RPSs as a graded, order-dependent notion rather than a simple dichotomy of conflict versus non-conflict. Numerical examples are presented to validate the behavior and properties of the proposed conflict measure. The proposed method not only exhibits an inherent top-weightedness property and effectively quantifies conflict between RPSs within the DST framework, but also provides decision-makers with flexibility in selecting weights, parameters, and truncation depths.

---

### AMStraMGRAM: Adaptive Multi-cutoff Strategy Modification for ANaGRAM

Authors: Nilo Schwencke, Cyriaque Rousselot, Alena Shilova, Cyril Furtlehner
Published: 2025-10-14
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.15998v1

Recent works have shown that natural gradient methods can significantly outperform standard optimizers when training physics-informed neural networks (PINNs). In this paper, we analyze the training dynamics of PINNs optimized with ANaGRAM, a natural-gradient-inspired approach employing singular value decomposition with cutoff regularization. Building on this analysis, we propose a multi-cutoff adaptation strategy that further enhances ANaGRAM's performance. Experiments on benchmark PDEs validate the effectiveness of our method, which allows to reach machine precision on some experiments. To provide theoretical grounding, we develop a framework based on spectral theory that explains the necessity of regularization and extend previous shown connections with Green's functions theory.

---

### Using Kolmogorov-Smirnov Distance for Measuring Distribution Shift in Machine Learning

Authors: Ozan K. Tonguz, Federico Taschin
Published: 2025-10-14
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.15996v1

One of the major problems in Machine Learning (ML) and Artificial Intelligence (AI) is the fact that the probability distribution of the test data in the real world could deviate substantially from the probability distribution of the training data set. When this happens, the predictions of an ML system or an AI agent could involve large errors which is very troublesome and undesirable. While this is a well-known hard problem plaguing the AI and ML systems' accuracy and reliability, in certain applications such errors could be critical for safety and reliability of AI and ML systems. One approach to deal with this problem is to monitor and measure the deviation in the probability distribution of the test data in real time and to compensate for this deviation. In this paper, we propose and explore the use of Kolmogorov-Smirnov (KS) Test for measuring the distribution shift and we show how the KS distance can be used to quantify the distribution shift and its impact on an AI agent's performance. Our results suggest that KS distance could be used as a valuable statistical tool for monitoring and measuring the distribution shift. More specifically, it is shown that even a distance of KS=0.02 could lead to about 50\% increase in the travel time at a single intersection using a Reinforcement Learning agent which is quite significant. It is hoped that the use of KS Test and KS distance in AI-based smart transportation could be an important step forward for gauging the performance degradation of an AI agent in real time and this, in turn, could help the AI agent to cope with the distribution shift in a more informed manner.

---

### The Invisible Handshake: Persistent Overpricing by Adaptive Market Agents

Authors: Luigi Foscari, Emanuele Guidotti, Nicolò Cesa-Bianchi, Tatjana Chavdarova, Alfio Ferrara
Published: 2025-10-14
Categories: q-fin.TR, cs.GT, cs.LG
arXiv: https://arxiv.org/abs/2510.15995v3

We study overpricing in a repeated game between two representative agents: a market maker, who controls market liquidity, and a market taker, who chooses trade quantities. Market prices evolve through the endogenous price impact of trades and exogenous shocks. We define overpricing relative to a counterfactual price path that holds fixed the same sequence of shocks while shutting down price impact, and characterize the set of feasible strategy profiles that generate persistent overpricing while respecting cash and inventory constraints. We provide a sufficient condition for decentralized learning to reach the overpricing region in finite time, and we show that this condition is satisfied, in particular, by projected stochastic gradient ascent. A key step in the analysis is a decomposition of the game into a competitive component, which favors zero price impact, and a collaborative component, which makes overpricing jointly profitable when aggregate inventory is positive. We further show that the same structural incentives govern both myopic and farsighted objectives. Together, these results show how decentralized learning by adaptive market agents can lead to persistent overpricing in financial markets.

---

### MCP Security Bench (MSB): Benchmarking Attacks Against Model Context Protocol in LLM Agents

Authors: Dongsen Zhang, Zekun Li, Xu Luo, Xuannan Liu, Peipei Li, Wenjun Xu
Published: 2025-10-14
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2510.15994v2

The Model Context Protocol (MCP) standardizes how large language model (LLM) agents discover, describe, and call external tools. While MCP unlocks broad interoperability, it also enlarges the attack surface by making tools first-class, composable objects with natural-language metadata, and standardized I/O. We present MSB (MCP Security Benchmark), the first end-to-end evaluation suite that systematically measures how well LLM agents resist MCP-specific attacks throughout the full tool-use pipeline: task planning, tool invocation, and response handling. MSB contributes: (1) a taxonomy of 12 attacks including name-collision, preference manipulation, prompt injections embedded in tool descriptions, out-of-scope parameter requests, user-impersonating responses, false-error escalation, tool-transfer, retrieval injection, and mixed attacks; (2) an evaluation harness that executes attacks by running real tools (both benign and malicious) via MCP rather than simulation; and (3) a robustness metric that quantifies the trade-off between security and performance: Net Resilient Performance (NRP). We evaluate nine popular LLM agents across 10 domains and 405 tools, producing 2,000 attack instances. Results reveal the effectiveness of attacks against each stage of MCP. Models with stronger performance are more vulnerable to attacks due to their outstanding tool calling and instruction following capabilities. MSB provides a practical baseline for researchers and practitioners to study, compare, and harden MCP agents. Code: https://github.com/dongsenzhang/MSB

---

### Aligning Language Models with Investor and Market Behavior for Financial Recommendations

Authors: Fernando Spadea, Oshani Seneviratne
Published: 2025-10-14
Categories: q-fin.PM, cs.LG, q-fin.ST
arXiv: https://arxiv.org/abs/2510.15993v1

Most financial recommendation systems often fail to account for key behavioral and regulatory factors, leading to advice that is misaligned with user preferences, difficult to interpret, or unlikely to be followed. We present FLARKO (Financial Language-model for Asset Recommendation with Knowledge-graph Optimization), a novel framework that integrates Large Language Models (LLMs), Knowledge Graphs (KGs), and Kahneman-Tversky Optimization (KTO) to generate asset recommendations that are both profitable and behaviorally aligned. FLARKO encodes users' transaction histories and asset trends as structured KGs, providing interpretable and controllable context for the LLM. To demonstrate the adaptability of our approach, we develop and evaluate both a centralized architecture (CenFLARKO) and a federated variant (FedFLARKO). To our knowledge, this is the first demonstration of combining KTO for fine-tuning of LLMs for financial asset recommendation. We also present the first use of structured KGs to ground LLM reasoning over behavioral financial data in a federated learning (FL) setting. Evaluated on the FAR-Trans dataset, FLARKO consistently outperforms state-of-the-art recommendation baselines on behavioral alignment and joint profitability, while remaining interpretable and resource-efficient.

---

### Stratos: An End-to-End Distillation Pipeline for Customized LLMs under Distributed Cloud Environments

Authors: Ziming Dai, Tuo Zhang, Fei Gao, Xingyi Cai, Xiaofei Wang, Cheng Zhang, Wenyu Wang, Chengjie Zang
Published: 2025-10-14
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.15992v1

The growing industrial demand for customized and cost-efficient large language models (LLMs) is fueled by the rise of vertical, domain-specific tasks and the need to optimize performance under constraints such as latency and budget. Knowledge distillation, as an efficient model compression and transfer technique, offers a feasible solution. However, existing distillation frameworks often require manual intervention and struggle to meet such complex user-defined distillation requirements. To bridge this gap, we propose Stratos, an end-to-end LLM distillation pipeline that automates server and model selection, knowledge distillation, and deployment in distributed cloud environments. Given user-defined constraints on model performance and system budget, Stratos automatically selects Pareto-optimal servers, dynamically matches teacher-student pairs, and adapts distillation strategies based on task complexity to optimize cloud hosting. Experiments show that Stratos produces a student model that achieves four times the accuracy of its GPT-4o teacher baseline on a rare, domain-specific Mahjong reasoning task with reverse synthetic data and knowledge injection. Moreover, it achieves reduced latency and cost without compromising accuracy. These results highlight its promise for vertical-domain LLM deployment.

---

### CrossRay3D: Geometry and Distribution Guidance for Efficient Multimodal 3D Detection

Authors: Huiming Yang, Wenzhuo Liu, Yicheng Qiao, Lei Yang, Xianzhu Zeng, Li Wang, Zhiwei Li, Zijian Zeng, Zhiying Jiang, Huaping Liu, Kunfeng Wang
Published: 2025-10-14
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.15991v3

The sparse cross-modality detector offers more advantages than its counterpart, the Bird's-Eye-View (BEV) detector, particularly in terms of adaptability for downstream tasks and computational cost savings. However, existing sparse detectors overlook the quality of token representation, leaving it with a sub-optimal foreground quality and limited performance. In this paper, we identify that the geometric structure preserved and the class distribution are the key to improving the performance of the sparse detector, and propose a Sparse Selector (SS). The core module of SS is Ray-Aware Supervision (RAS), which preserves rich geometric information during the training stage, and Class-Balanced Supervision, which adaptively reweights the salience of class semantics, ensuring that tokens associated with small objects are retained during token sampling. Thereby, outperforming other sparse multi-modal detectors in the representation of tokens. Additionally, we design Ray Positional Encoding (Ray PE) to address the distribution differences between the LiDAR modality and the image. Finally, we integrate the aforementioned module into an end-to-end sparse multi-modality detector, dubbed CrossRay3D. Experiments show that, on the challenging nuScenes benchmark, CrossRay3D achieves state-of-the-art performance with 72.4 mAP and 74.7 NDS, while running 1.84 faster than other leading methods. Moreover, CrossRay3D demonstrates strong robustness even in scenarios where LiDAR or camera data are partially or entirely missing.

---

### Can GRPO Help LLMs Transcend Their Pretraining Origin?

Authors: Kangqi Ni, Zhen Tan, Zijie Liu, Pingzhi Li, Tianlong Chen
Published: 2025-10-14
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.15990v1

Reinforcement Learning with Verifiable Rewards (RLVR), primarily driven by the Group Relative Policy Optimization (GRPO) algorithm, is a leading approach for enhancing the reasoning abilities of Large Language Models (LLMs). Despite its wide adoption, GRPO's gains are often inconsistent; for instance, a model may show significant improvement in one reasoning domain, like mathematics, yet remain stagnant in another, such as medicine. This inconsistency raises a critical question: under what conditions does GRPO improve reasoning and generalize out-of-distribution (OOD)? We investigate this from a data distribution perspective. We first prove theoretically that GRPO is a conservative reweighting scheme, bounded by the base model's distribution and thus unable to discover completely novel solutions. We further validate this in carefully designed controlled studies by training transformers from scratch, evaluating generalization across reasoning depth, input length, token representation, and compositionality. Our results provide a principled explanation for GRPO's boundaries: OOD improvement emerges only when the target task aligns with the model's pretrained biases, while gains on in-distribution (ID) tasks diminish as performance saturates. This reframes GRPO not as a universal reasoning enhancer but as a tool that sharpens pretraining biases. Our findings motivate future development of algorithms that can expand a model's capabilities beyond its pretraining origin.

---

### Interpreting the Latent Structure of Operator Precedence in Language Models

Authors: Dharunish Yugeswardeenoo, Harshil Nukala, Ved Shah, Cole Blondin, Sean O Brien, Vasu Sharma, Kevin Zhu
Published: 2025-10-14
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.13908v2

Large Language Models (LLMs) have demonstrated impressive reasoning capabilities but continue to struggle with arithmetic tasks. Prior works largely focus on outputs or prompting strategies, leaving the open question of the internal structure through which models do arithmetic computation. In this work, we investigate whether LLMs encode operator precedence in their internal representations via the open-source instruction-tuned LLaMA 3.2-3B model. We constructed a dataset of arithmetic expressions with three operands and two operators, varying the order and placement of parentheses. Using this dataset, we trace whether intermediate results appear in the residual stream of the instruction-tuned LLaMA 3.2-3B model. We apply interpretability techniques such as logit lens, linear classification probes, and UMAP geometric visualization. Our results show that intermediate computations are present in the residual stream, particularly after MLP blocks. We also find that the model linearly encodes precedence in each operator's embeddings post attention layer. We introduce partial embedding swap, a technique that modifies operator precedence by exchanging high-impact embedding dimensions between operators.

---

### LLM Prompt Duel Optimizer: Efficient Label-Free Prompt Optimization

Authors: Yuanchen Wu, Saurabh Verma, Justin Lee, Fangzhou Xiong, Poppy Zhang, Amel Awadelkarim, Xu Chen, Yubai Yuan, Shawndra Hill
Published: 2025-10-14
Categories: cs.CL, stat.ML
arXiv: https://arxiv.org/abs/2510.13907v3

Large language models (LLMs) are highly sensitive to prompts, but most automatic prompt optimization (APO) methods assume access to ground-truth references (e.g., labeled validation data) that are costly to obtain. We propose the Prompt Duel Optimizer (PDO), a sample-efficient framework for label-free prompt optimization based on pairwise preference feedback from an LLM judge. PDO casts prompt selection as a dueling-bandit problem and combines (i) Double Thompson Sampling to prioritize informative comparisons under a fixed judge budget, with (ii) top-performer guided mutation to expand the candidate pool while pruning weak prompts. Experiments on BIG-bench Hard (BBH) and MS MARCO show that PDO consistently identifies stronger prompts than label-free baselines, while offering favorable quality--cost trade-offs under constrained comparison budgets.

---

### Switchboard-Affect: Emotion Perception Labels from Conversational Speech

Authors: Amrit Romana, Jaya Narain, Tien Dung Tran, Andrea Davis, Jason Fong, Ramya Rasipuram, Vikramjit Mitra
Published: 2025-10-14
Categories: eess.AS, cs.LG, cs.SD
arXiv: https://arxiv.org/abs/2510.13906v1

Understanding the nuances of speech emotion dataset curation and labeling is essential for assessing speech emotion recognition (SER) model potential in real-world applications. Most training and evaluation datasets contain acted or pseudo-acted speech (e.g., podcast speech) in which emotion expressions may be exaggerated or otherwise intentionally modified. Furthermore, datasets labeled based on crowd perception often lack transparency regarding the guidelines given to annotators. These factors make it difficult to understand model performance and pinpoint necessary areas for improvement. To address this gap, we identified the Switchboard corpus as a promising source of naturalistic conversational speech, and we trained a crowd to label the dataset for categorical emotions (anger, contempt, disgust, fear, sadness, surprise, happiness, tenderness, calmness, and neutral) and dimensional attributes (activation, valence, and dominance). We refer to this label set as Switchboard-Affect (SWB-Affect). In this work, we present our approach in detail, including the definitions provided to annotators and an analysis of the lexical and paralinguistic cues that may have played a role in their perception. In addition, we evaluate state-of-the-art SER models, and we find variable performance across the emotion categories with especially poor generalization for anger. These findings underscore the importance of evaluation with datasets that capture natural affective variations in speech. We release the labels for SWB-Affect to enable further analysis in this domain.

---

### Schema for In-Context Learning

Authors: Pan Chen, Shaohong Chen, Mark Wang, Shi Xuan Leong, Priscilla Fung, Varinia Bernales, Alan Aspuru-Guzik
Published: 2025-10-14
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.13905v3

In-Context Learning (ICL) enables transformer-based language models to adapt to new tasks by conditioning on demonstration examples. However, traditional example-driven in-context learning lacks explicit modules for knowledge retrieval and transfer at the abstraction level. Inspired by cognitive science, specifically schema theory, which holds that humans interpret new information by activating pre-existing mental frameworks (schemas) to structure understanding, we introduce Schema-Activated In-Context Learning (SA-ICL). This framework extracts the representation of the building blocks of cognition for the reasoning process instilled from prior examples, creating an abstracted schema, a lightweight, structured template of key inferential steps and their relationships, which is then used to augment a model's reasoning process when presented with a novel question. We demonstrate that a broad range of large language models (LLMs) lack the capacity to form and utilize internal schema-based learning representations implicitly, but instead benefit significantly from explicit schema-based scaffolding. Across chemistry and physics questions from the GPQA dataset, our experiments show that SA-ICL consistently boosts performance, up to 36.19 percent, when the single demonstration example is of high quality, which simultaneously reduces reliance on the number of demonstrations and enhances interpretability. Schema-Activated In-Context Learning not only bridges disparate ICL strategies ranging from pattern priming to Chain-of-Thought prompting, but also paves a new path for enhancing human-like reasoning in LLMs.

---

### Benefits and Limitations of Communication in Multi-Agent Reasoning

Authors: Michael Rizvi-Martel, Satwik Bhattamishra, Neil Rathi, Guillaume Rabusseau, Michael Hahn
Published: 2025-10-14
Categories: cs.MA, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.13903v2

Chain-of-thought prompting has popularized step-by-step reasoning in large language models, yet model performance still degrades as problem complexity and context length grow. By decomposing difficult tasks with long contexts into shorter, manageable ones, recent multi-agent paradigms offer a promising near-term solution to this problem. However, the fundamental capacities of such systems are poorly understood. In this work, we propose a theoretical framework to analyze the expressivity of multi-agent systems. We apply our framework to three algorithmic families: state tracking, recall, and $k$-hop reasoning. We derive bounds on (i) the number of agents required to solve the task exactly, (ii) the quantity and structure of inter-agent communication, and (iii) the achievable speedups as problem size and context scale. Our results identify regimes where communication is provably beneficial, delineate tradeoffs between agent count and bandwidth, and expose intrinsic limitations when either resource is constrained. We complement our theoretical analysis with a set of experiments on pretrained LLMs using controlled synthetic benchmarks. Empirical outcomes confirm the tradeoffs between key quantities predicted by our theory. Collectively, our analysis offers principled guidance for designing scalable multi-agent reasoning systems.

---

### Investigating Political and Demographic Associations in Large Language Models Through Moral Foundations Theory

Authors: Nicole Smith-Vaniz, Harper Lyon, Lorraine Steigner, Ben Armstrong, Nicholas Mattei
Published: 2025-10-14
Categories: cs.CL, cs.CY
arXiv: https://arxiv.org/abs/2510.13902v1

Large Language Models (LLMs) have become increasingly incorporated into everyday life for many internet users, taking on significant roles as advice givers in the domains of medicine, personal relationships, and even legal matters. The importance of these roles raise questions about how and what responses LLMs make in difficult political and moral domains, especially questions about possible biases. To quantify the nature of potential biases in LLMs, various works have applied Moral Foundations Theory (MFT), a framework that categorizes human moral reasoning into five dimensions: Harm, Fairness, Ingroup Loyalty, Authority, and Purity. Previous research has used the MFT to measure differences in human participants along political, national, and cultural lines. While there has been some analysis of the responses of LLM with respect to political stance in role-playing scenarios, no work so far has directly assessed the moral leanings in the LLM responses, nor have they connected LLM outputs with robust human data. In this paper we analyze the distinctions between LLM MFT responses and existing human research directly, investigating whether commonly available LLM responses demonstrate ideological leanings: either through their inherent responses, straightforward representations of political ideologies, or when responding from the perspectives of constructed human personas. We assess whether LLMs inherently generate responses that align more closely with one political ideology over another, and additionally examine how accurately LLMs can represent ideological perspectives through both explicit prompting and demographic-based role-playing. By systematically analyzing LLM behavior across these conditions and experiments, our study provides insight into the extent of political and demographic dependency in AI-generated responses.

---

### RAID: Refusal-Aware and Integrated Decoding for Jailbreaking LLMs

Authors: Tuan T. Nguyen, John Le, Thai T. Vu, Willy Susilo, Heath Cooper
Published: 2025-10-14
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.13901v2

Large language models (LLMs) achieve impressive performance across diverse tasks yet remain vulnerable to jailbreak attacks that bypass safety mechanisms. We present RAID (Refusal-Aware and Integrated Decoding), a framework that systematically probes these weaknesses by crafting adversarial suffixes that induce restricted content while preserving fluency. RAID relaxes discrete tokens into continuous embeddings and optimizes them with a joint objective that (i) encourages restricted responses, (ii) incorporates a refusal-aware regularizer to steer activations away from refusal directions in embedding space, and (iii) applies a coherence term to maintain semantic plausibility and non-redundancy. After optimization, a critic-guided decoding procedure maps embeddings back to tokens by balancing embedding affinity with language-model likelihood. This integration yields suffixes that are both effective in bypassing defenses and natural in form. Experiments on multiple open-source LLMs show that RAID achieves higher attack success rates with fewer queries and lower computational cost than recent white-box and black-box baselines. These findings highlight the importance of embedding-space regularization for understanding and mitigating LLM jailbreak vulnerabilities.

---

### Narrow Finetuning Leaves Clearly Readable Traces in Activation Differences

Authors: Julian Minder, Clément Dumas, Stewart Slocum, Helena Casademunt, Cameron Holmes, Robert West, Neel Nanda
Published: 2025-10-14
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.13900v3

Finetuning on narrow domains has become an essential tool to adapt Large Language Models (LLMs) to specific tasks and to create models with known unusual properties that are useful for research. We show that narrow finetuning creates strong biases in LLM activations that can be interpreted to understand the finetuning domain. These biases can be discovered using simple tools from model diffing - the study of differences between models before and after finetuning. In particular, analyzing activation differences on the first few tokens of random text and steering by adding this difference to the model activations produces text similar to the format and general content of the finetuning data. We demonstrate that these analyses contain crucial information by creating an LLM-based interpretability agent to understand the finetuning domain. With access to the bias, the agent performs significantly better compared to baseline agents using simple prompting. Our analysis spans synthetic document finetuning for false facts, emergent misalignment, subliminal learning, and taboo word guessing game models across different architectures (Gemma, LLaMA, Qwen) and scales (1B to 32B parameters). We suspect these biases reflect overfitting and find that mixing pretraining data into the finetuning corpus largely removes them, though residual risks may remain. Our work (1) demonstrates that narrowly finetuned models have salient traces of their training objective in their activations and suggests ways to improve how they are trained, (2) warns AI safety and interpretability researchers that the common practice of using such models as a proxy for studying broader finetuning (e.g., chat-tuning) might not be realistic, and (3) highlights the need for deeper investigation into the effects of narrow finetuning and development of truly realistic case studies for model-diffing, safety and interpretability research.

---

### Post-surgical Endometriosis Segmentation in Laparoscopic Videos

Authors: Andreas Leibetseder, Klaus Schoeffmann, Jörg Keckstein, Simon Keckstein
Published: 2025-10-14
Categories: cs.CV, cs.LG, cs.MM
arXiv: https://arxiv.org/abs/2510.13899v1

Endometriosis is a common women's condition exhibiting a manifold visual appearance in various body-internal locations. Having such properties makes its identification very difficult and error-prone, at least for laymen and non-specialized medical practitioners. In an attempt to provide assistance to gynecologic physicians treating endometriosis, this demo paper describes a system that is trained to segment one frequently occurring visual appearance of endometriosis, namely dark endometrial implants. The system is capable of analyzing laparoscopic surgery videos, annotating identified implant regions with multi-colored overlays and displaying a detection summary for improved video browsing.

---

### Attribution Quality in AI-Generated Content:Benchmarking Style Embeddings and LLM Judges

Authors: Misam Abbas
Published: 2025-10-14
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.13898v1

Attributing authorship in the era of large language models (LLMs) is increasingly challenging as machine-generated prose rivals human writing. We benchmark two complementary attribution mechanisms , fixed Style Embeddings and an instruction-tuned LLM judge (GPT-4o) on the Human AI Parallel Corpus, an open dataset of 600 balanced instances spanning six domains (academic, news, fiction, blogs, spoken transcripts, and TV/movie scripts). Each instance contains a human prompt with both a gold continuation and an LLM-generated continuation from either GPT-4o or LLaMA-70B-Instruct. The Style Embedding baseline achieves stronger aggregate accuracy on GPT continuations (82 pct vs. 68 pct). The LLM Judge is slightly better than the Style embeddings on LLaMA continuations (85 pct vs. 81 pct) but the results are not statistically significant. Crucially, the LLM judge significantly outperforms in fiction and academic prose, indicating semantic sensitivity, whereas embeddings dominate in spoken and scripted dialogue, reflecting structural strengths. These complementary patterns highlight attribution as a multidimensional problem requiring hybrid strategies. To support reproducibility we provide code on GitHub and derived data on Hugging Face under the MIT license. This open framework provides a reproducible benchmark for attribution quality assessment in AI-generated content, along with a review of related literature influencing this work.

---

### Dual-attention ResNet outperforms transformers in HER2 prediction on DCE-MRI

Authors: Naomi Fridman, Anat Goldstein
Published: 2025-10-14
Categories: q-bio.QM, cs.AI
arXiv: https://arxiv.org/abs/2510.13897v1

Breast cancer is the most diagnosed cancer in women, with HER2 status critically guiding treatment decisions. Noninvasive prediction of HER2 status from dynamic contrast-enhanced MRI (DCE-MRI) could streamline diagnostics and reduce reliance on biopsy. However, preprocessing high-dynamic-range DCE-MRI into standardized 8-bit RGB format for pretrained neural networks is nontrivial, and normalization strategy significantly affects model performance. We benchmarked intensity normalization strategies using a Triple-Head Dual-Attention ResNet that processes RGB-fused temporal sequences from three DCE phases. Trained on a multicenter cohort (n=1,149) from the I-SPY trials and externally validated on BreastDCEDL_AMBL (n=43 lesions), our model outperformed transformer-based architectures, achieving 0.75 accuracy and 0.74 AUC on I-SPY test data. N4 bias field correction slightly degraded performance. Without fine-tuning, external validation yielded 0.66 AUC, demonstrating cross-institutional generalizability. These findings highlight the effectiveness of dual-attention mechanisms in capturing transferable spatiotemporal features for HER2 stratification, advancing reproducible deep learning biomarkers in breast cancer imaging.

---

### GenCellAgent: Generalizable, Training-Free Cellular Image Segmentation via Large Language Model Agents

Authors: Xi Yu, Yang Yang, Qun Liu, Yonghua Du, Sean McSweeney, Yuewei Lin
Published: 2025-10-14
Categories: q-bio.QM, cs.AI, cs.CV, cs.MA
arXiv: https://arxiv.org/abs/2510.13896v2

Cellular image segmentation is essential for quantitative biology yet remains difficult due to heterogeneous modalities, morphological variability, and limited annotations. We present GenCellAgent, a training-free multi-agent framework that orchestrates specialist segmenters and generalist vision-language models via a planner-executor-evaluator loop (choose tool $\rightarrow$ run $\rightarrow$ quality-check) with long-term memory. The system (i) automatically routes images to the best tool, (ii) adapts on the fly using a few reference images when imaging conditions differ from what a tool expects, (iii) supports text-guided segmentation of organelles not covered by existing models, and (iv) commits expert edits to memory, enabling self-evolution and personalized workflows. Across seven cell-segmentation benchmarks spanning diverse microscopy modalities (4,718 images), this routing consistently matches or exceeds the best individual tool on every dataset and outperforms all baselines in overall accuracy. On out-of-distribution organelle data, GenCellAgent substantially outperforms specialist models that were not trained on the target domain, recovering structures that dedicated tools fail to detect. It also segments novel objects such as the Golgi apparatus via iterative text-guided refinement, with light human correction further boosting performance. Together, these capabilities provide a practical path to robust, adaptable cellular image segmentation without retraining, while reducing annotation burden and matching user preferences.

---

### Bayes or Heisenberg: Who(se) Rules?

Authors: Volker Tresp, Hang Li, Federico Harjes, Yunpu Ma
Published: 2025-10-14
Categories: q-bio.NC, cs.AI, cs.LG, quant-ph
arXiv: https://arxiv.org/abs/2510.13894v2

Although quantum systems are generally described by quantum state vectors, we show that in certain cases their measurement processes can be reformulated as probabilistic equations expressed in terms of probabilistic state vectors. These probabilistic representations can, in turn, be approximated by the neural network dynamics of the Tensor Brain (TB) model. The Tensor Brain is a recently proposed framework for modeling perception and memory in the brain, providing a biologically inspired mechanism for efficiently integrating generated symbolic representations into reasoning processes.

---

### Guarding the Guardrails: A Taxonomy-Driven Approach to Jailbreak Detection

Authors: Francesco Giarrusso, Olga E. Sorokoletova, Vincenzo Suriani, Daniele Nardi
Published: 2025-10-14
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.13893v2

Jailbreaking techniques pose a significant threat to the safety of Large Language Models (LLMs). Existing defenses typically focus on single-turn attacks, lack coverage across languages, and rely on limited taxonomies that either fail to capture the full diversity of attack strategies or emphasize risk categories rather than jailbreaking techniques. To advance the understanding of the effectiveness of jailbreaking techniques, we conducted a structured red-teaming challenge. The outcomes of our experiments are fourfold. First, we developed a comprehensive hierarchical taxonomy of jailbreak strategies that systematically consolidates techniques previously studied in isolation and harmonizes existing, partially overlapping classifications with explicit cross-references to prior categorizations. The taxonomy organizes jailbreak strategies into seven mechanism-oriented families: impersonation, persuasion, privilege escalation, cognitive overload, obfuscation, goal conflict, and data poisoning. Second, we analyzed the data collected from the challenge to examine the prevalence and success rates of different attack types, providing insights into how specific jailbreak strategies exploit model vulnerabilities and induce misalignment. Third, we benchmarked GPT-5 as a judge for jailbreak detection, evaluating the benefits of taxonomy-guided prompting for improving automatic detection. Finally, we compiled a new Italian dataset of 1364 multi-turn adversarial dialogues, annotated with our taxonomy, enabling the study of interactions where adversarial intent emerges gradually and succeeds in bypassing traditional safeguards.

---

### The Harder The Better: Maintaining Supervised Fine-tuning Generalization with Less but Harder Data

Authors: Zhaoyang Shang, Sibo Wei, Jianbin Guo, Rui Zhou, Lifeng Dong, Yin Luo
Published: 2025-10-14
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.13892v1

Large Language Models (LLMs) excel in general tasks, but adapting them to specialized domains relies on high-quality supervised fine-tuning (SFT) data. Although existing methods can identify subsets of high-quality data and reduce training cost to some extent, their selection process still suffers from over-reliance on LLMs' internal knowledge, weak interpretability, and limited generalization. To address these limitations, we propose THTB (The Harder The Better), a cognitive science-inspired framework for instruction data selection and annotation guidance. THTB prioritizes higher-level cognitive instructions by combining quality filtering with intrinsic and extrinsic hardness scoring, offering interpretable and quantifiable criteria for efficient SFT, both in data selection and annotation guidance. Experiments show that THTB enables models trained on only 5% of the data to outperform full-dataset training, while achieving superior generalization compared with LLM-only selection. In addition, THTB provides effective annotation guidance in vertical domains, enabling a model trained on just 2% of the data to surpass models trained on much larger datasets, demonstrating strong potential for domain adaptation. Our code, datasets, and models are available on https://github.com/DYJG-research/THTB.

---

### K-frames: Scene-Driven Any-k Keyframe Selection for long video understanding

Authors: Yifeng Yao, Yike Yun, Jing Wang, Huishuai Zhang, Dongyan Zhao, Ke Tian, Zhihao Wang, Minghui Qiu, Tao Wang
Published: 2025-10-14
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.13891v1

Multimodal Large Language Models (MLLMs) have demonstrated significant capabilities in image understanding, but long-video are constrained by context windows and computational cost. Uniform frame sampling often leads to substantial information loss. Meanwhile existing keyframe selection methods such as text-frame retrieval or RL-based frame optimization typically yield sparse and temporally disjointed frames, overlooking scene continuity and lacking flexibility for multi-scale frame selection. To address these limitations, we introduce K-frames, a novel paradigm for scene-driven keyframe selection that preserves temporal continuity. Instead of selecting individual frames, K-frames predicts semantically coherent, query-relevant clips, which enables any-k keyframes selection to meet diverse user budgets. To achieve this approach, we first introduce PeakClips, a dataset of 200K video highlights conditioned by query. Building on this dataset, K-frames learns clip2frame selection using a three-stage progressive curriculum. It involves two Supervised Fine-Tuning stages for temporal grounding and key-clip perception, followed by a Reinforcement Learning stage that directly optimizes the scene-driven prediction policy for downstream task without further annotations. Extensive experiments on major long-video understanding benchmarks demonstrate that K-frames provides an effective, interpretable, and plug-and-play solution for keyframe selection at various scales. Our dataset and model will be available.

---

### A Survey on Collaborating Small and Large Language Models for Performance, Cost-effectiveness, Cloud-edge Privacy, and Trustworthiness

Authors: Fali Wang, Jihai Chen, Shuhua Yang, Ali Al-Lawati, Linli Tang, Hui Liu, Suhang Wang
Published: 2025-10-14
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.13890v2

Large language models (LLMs) have achieved remarkable progress across domains and applications but face challenges such as high fine-tuning costs, inference latency, limited edge deployability, and reliability concerns. Small language models (SLMs), with compact, efficient, and adaptable features, offer promising solutions. Building on this potential, recent research explores collaborative frameworks that integrate their complementary strengths, leveraging SLMs' specialization and efficiency with LLMs' generalization and reasoning to address diverse objectives across tasks and deployment scenarios. Motivated by these developments, this paper presents a systematic survey of SLM-LLM collaboration from the perspective of collaboration objectives. We propose a taxonomy covering four goals: performance enhancement, cost-effectiveness, cloud-edge privacy, and trustworthiness. Under this framework, we review representative methods, summarize design paradigms, and outline open challenges and future directions toward efficient and secure SLM-LLM collaboration. The collected papers are available at https://github.com/FairyFali/SLMs-Survey.

---

### MultiFoodhat: A potential new paradigm for intelligent food quality inspection

Authors: Yue Hu, Guohang Zhuang
Published: 2025-10-14
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.13889v1

Food image classification plays a vital role in intelligent food quality inspection, dietary assessment, and automated monitoring. However, most existing supervised models rely heavily on large labeled datasets and exhibit limited generalization to unseen food categories. To overcome these challenges, this study introduces MultiFoodChat, a dialogue-driven multi-agent reasoning framework for zero-shot food recognition. The framework integrates vision-language models (VLMs) and large language models (LLMs) to enable collaborative reasoning through multi-round visual-textual dialogues. An Object Perception Token (OPT) captures fine-grained visual attributes, while an Interactive Reasoning Agent (IRA) dynamically interprets contextual cues to refine predictions. This multi-agent design allows flexible and human-like understanding of complex food scenes without additional training or manual annotations. Experiments on multiple public food datasets demonstrate that MultiFoodChat achieves superior recognition accuracy and interpretability compared with existing unsupervised and few-shot methods, highlighting its potential as a new paradigm for intelligent food quality inspection and analysis.

---

### Reliable Fine-Grained Evaluation of Natural Language Math Proofs

Authors: Wenjie Ma, Andrei Cojocaru, Neel Kolhe, Bradley Louie, Robin Said Sharif, Haihan Zhang, Vincent Zhuang, Matei Zaharia, Sewon Min
Published: 2025-10-14
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.13888v2

Recent advances in large language models (LLMs) for mathematical reasoning have largely focused on tasks with easily verifiable final answers while generating and verifying natural language math proofs remains an open challenge. We identify the absence of a reliable, fine-grained evaluator for LLM-generated math proofs as a critical gap. To address this, we propose a systematic methodology for developing and validating evaluators that assign fine-grained scores on a 0-7 scale to model-generated math proofs. To enable this study, we introduce ProofBench, the first expert-annotated dataset of fine-grained proof ratings, spanning 145 problems from six major math competitions (USAMO, IMO, Putnam, etc) and 435 LLM-generated solutions from Gemini-2.5-Pro, o3, and DeepSeek-R1. Using ProofBench as a testbed, we systematically explore the evaluator design space across key axes: the backbone model, input context, instructions and evaluation workflow. Our analysis delivers ProofGrader, an evaluator that combines a strong reasoning backbone LM, rich context from reference solutions and marking schemes, and a simple ensembling method; it achieves a low Mean Absolute Error (MAE) of 0.926 against expert scores, significantly outperforming naive baselines. Finally, we demonstrate its practical utility in a best-of-$n$ selection task: at $n=16$, ProofGrader achieves an average score of 4.14/7, closing 78\% of the gap between a naive binary evaluator (2.48) and the human oracle (4.62), highlighting its potential to advance downstream proof generation.

---

### Incomplete Multi-view Clustering via Hierarchical Semantic Alignment and Cooperative Completion

Authors: Xiaojian Ding, Lin Zhao, Xian Li, Xiaoying Zhu
Published: 2025-10-14
Categories: eess.IV, cs.AI, cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.13887v4

Incomplete multi-view data, where certain views are entirely missing for some samples, poses significant challenges for traditional multi-view clustering methods. Existing deep incomplete multi-view clustering approaches often rely on static fusion strategies or two-stage pipelines, leading to suboptimal fusion results and error propagation issues. To address these limitations, this paper proposes a novel incomplete multi-view clustering framework based on Hierarchical Semantic Alignment and Cooperative Completion (HSACC). HSACC achieves robust cross-view fusion through a dual-level semantic space design. In the low-level semantic space, consistency alignment is ensured by maximizing mutual information across views. In the high-level semantic space, adaptive view weights are dynamically assigned based on the distributional affinity between individual views and an initial fused representation, followed by weighted fusion to generate a unified global representation. Additionally, HSACC implicitly recovers missing views by projecting aligned latent representations into high-dimensional semantic spaces and jointly optimizes reconstruction and clustering objectives, enabling cooperative learning of completion and clustering. Experimental results demonstrate that HSACC significantly outperforms state-of-the-art methods on five benchmark datasets. Ablation studies validate the effectiveness of the hierarchical alignment and dynamic weighting mechanisms, while parameter analysis confirms the model's robustness to hyperparameter variations. The code is available at https://github.com/XiaojianDing/2025-NeurIPS-HSACC.

---

### Physics-Informed autoencoder for DSC-MRI Perfusion post-processing: application to glioma grading

Authors: Pierre Fayolle, Alexandre Bône, Noëlie Debs, Mathieu Naudin, Pascal Bourdon, Remy Guillevin, David Helbert
Published: 2025-10-14
Categories: q-bio.QM, cs.AI, eess.IV, eess.SP
arXiv: https://arxiv.org/abs/2510.13886v1

DSC-MRI perfusion is a medical imaging technique for diagnosing and prognosing brain tumors and strokes. Its analysis relies on mathematical deconvolution, but noise or motion artifacts in a clinical environment can disrupt this process, leading to incorrect estimate of perfusion parameters. Although deep learning approaches have shown promising results, their calibration typically rely on third-party deconvolution algorithms to generate reference outputs and are bound to reproduce their limitations. To adress this problem, we propose a physics-informed autoencoder that leverages an analytical model to decode the perfusion parameters and guide the learning of the encoding network. This autoencoder is trained in a self-supervised fashion without any third-party software and its performance is evaluated on a database with glioma patients. Our method shows reliable results for glioma grading in accordance with other well-known deconvolution algorithms despite a lower computation time. It also achieved competitive performance even in the presence of high noise which is critical in a medical environment.

---

### Order from Chaos: Comparative Study of Ten Leading LLMs on Unstructured Data Categorization

Authors: Ariel Kamen
Published: 2025-10-14
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.13885v1

This study presents a comparative evaluation of ten state-of-the-art large language models (LLMs) applied to unstructured text categorization using the Interactive Advertising Bureau (IAB) 2.2 hierarchical taxonomy. The analysis employed a uniform dataset of 8,660 human-annotated samples and identical zero-shot prompts to ensure methodological consistency across all models. Evaluation metrics included four classic measures - accuracy, precision, recall, and F1-score - and three LLM-specific indicators: hallucination ratio, inflation ratio, and categorization cost. Results show that, despite their rapid advancement, contemporary LLMs achieve only moderate classic performance, with average scores of 34% accuracy, 42% precision, 45% recall, and 41% F1-score. Hallucination and inflation ratios reveal that models frequently overproduce categories relative to human annotators. Among the evaluated systems, Gemini 1.5/2.0 Flash and GPT 20B/120B offered the most favorable cost-to-performance balance, while GPT 120B demonstrated the lowest hallucination ratio. The findings suggest that scaling and architectural improvements alone do not ensure better categorization accuracy, as the task requires compressing rich unstructured text into a limited taxonomy - a process that challenges current model architectures. To address these limitations, a separate ensemble-based approach was developed and tested. The ensemble method, in which multiple LLMs act as independent experts, substantially improved accuracy, reduced inflation, and completely eliminated hallucinations. These results indicate that coordinated orchestration of models - rather than sheer scale - may represent the most effective path toward achieving or surpassing human-expert performance in large-scale text categorization.

---

### Too Open for Opinion? Embracing Open-Endedness in Large Language Models for Social Simulation

Authors: Bolei Ma, Yong Cao, Indira Sen, Anna-Carolina Haensch, Frauke Kreuter, Barbara Plank, Daniel Hershcovich
Published: 2025-10-14
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.13884v2

Large Language Models (LLMs) are increasingly used to simulate public opinion and other social phenomena. Most current studies constrain these simulations to multiple-choice or short-answer formats for ease of scoring and comparison, but such closed designs overlook the inherently generative nature of LLMs. In this position paper, we argue that open-endedness, using free-form text that captures topics, viewpoints, and reasoning processes "in" LLMs, is essential for realistic social simulation. Drawing on decades of survey-methodology research and recent advances in NLP, we argue why this open-endedness is valuable in LLM social simulations, showing how it can improve measurement and design, support exploration of unanticipated views, and reduce researcher-imposed directive bias. It also captures expressiveness and individuality, aids in pretesting, and ultimately enhances methodological utility. We call for novel practices and evaluation frameworks that leverage rather than constrain the open-ended generative diversity of LLMs, creating synergies between NLP and social science.

---

### ECG-Mamba-V2: Architectural Refinements to a Bidirectional State Space Model for Multi-Label 12-Lead ECG Classification

Authors: Huawei Jiang, Husna Mutahira, Shibo Wei, Gan Huang, Vladimir Shin, Dongryeol Ryu, Juneho Yi, Mannan Saeed Muhammad
Published: 2025-10-14
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.13046v3

State space models offer linear-time sequence modeling and are a promising backbone for multi-label 12-lead ECG classification, but the design choices that drive their accuracy remain unclear. This letter presents ECG-Mamba-V2, a set of empirical refinements to a bidirectional Vision Mamba encoder: the class token is appended at the end of the token sequence instead of the midpoint, the forward and backward scan outputs are summed without the conventional 1/2 scaling, and dropout is applied at a uniform rate across blocks. On PhysioNet/CinC Challenge 2021, ECG-Mamba-V2 reaches 0.6494 macro AUPRC and 0.9716 macro AUROC, against 0.6100 and 0.9646 for its predecessor, while using 34\% fewer parameters and delivering 38\% higher throughput; it wins all 15 paired runs.

---

### SceneAdapt: Scene-aware Adaptation of Human Motion Diffusion

Authors: Jungbin Cho, Minsu Kim, Jisoo Kim, Ce Zheng, Laszlo A. Jeni, Ming-Hsuan Yang, Youngjae Yu, Seonjoo Kim
Published: 2025-10-14
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.13044v2

Human motion is inherently diverse and semantically rich, while also shaped by the surrounding scene. However, existing motion generation approaches fail to generate semantically diverse motion while simultaneously respecting geometric scene constraints, since constructing large-scale datasets with both rich text-motion coverage and precise scene interactions is extremely challenging. In this work, we introduce SceneAdapt, a two-stage adaptation framework that enables semantically diverse, scene-aware human motion generation from text without large-scale paired text--scene--motion data. Our key idea is to use motion inbetweening, a learnable proxy task that requires no text, as a bridge between two disjoint resources: a text-motion dataset and a scene-motion dataset. By first adapting a text-to-motion model through inbetweening and then through scene-aware inbetweening, SceneAdapt injects geometric scene constraints into text-conditioned generation while preserving semantic diversity. To enable adaptation for inbetweening, we propose a novel Context-aware Keyframing (CaKey) layer that modulates motion latents for keyframe-conditioned synthesis while preserving the original latent manifold. To further adapt the model for scene-aware inbetweening, we introduce a Scene-conditioning (SceneCo) layer that injects geometric scene information by adaptively querying local context via cross-attention. Experimental results show that SceneAdapt effectively injects scene-awareness into text-to-motion models without sacrificing semantic diversity, and we further analyze the mechanisms through which this awareness emerges. Code and models will be released. Project page: \href{https://sceneadapt.github.io/}{sceneadapt.github.io}

---

### SeqBench: Benchmarking Sequential Narrative Generation in Text-to-Video Models

Authors: Zhengxu Tang, Zizheng Wang, Luning Wang, Zitao Shuai, Chenhao Zhang, Siyu Qian, Yirui Wu, Bohao Wang, Haosong Rao, Zhenyu Yang, Chenwei Wu
Published: 2025-10-14
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.13042v1

Text-to-video (T2V) generation models have made significant progress in creating visually appealing videos. However, they struggle with generating coherent sequential narratives that require logical progression through multiple events. Existing T2V benchmarks primarily focus on visual quality metrics but fail to evaluate narrative coherence over extended sequences. To bridge this gap, we present SeqBench, a comprehensive benchmark for evaluating sequential narrative coherence in T2V generation. SeqBench includes a carefully designed dataset of 320 prompts spanning various narrative complexities, with 2,560 human-annotated videos generated from 8 state-of-the-art T2V models. Additionally, we design a Dynamic Temporal Graphs (DTG)-based automatic evaluation metric, which can efficiently capture long-range dependencies and temporal ordering while maintaining computational efficiency. Our DTG-based metric demonstrates a strong correlation with human annotations. Through systematic evaluation using SeqBench, we reveal critical limitations in current T2V models: failure to maintain consistent object states across multi-action sequences, physically implausible results in multi-object scenarios, and difficulties in preserving realistic timing and ordering relationships between sequential actions. SeqBench provides the first systematic framework for evaluating narrative coherence in T2V generation and offers concrete insights for improving sequential reasoning capabilities in future models. Please refer to https://videobench.github.io/SeqBench.github.io/ for more details.

---

### Randomness and Interpolation Improve Gradient Descent

Authors: Jiawen Li, Pascal Lefevre, Anwar Pp Abdul Majeed
Published: 2025-10-14
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.13040v1

Based on Stochastic Gradient Descent (SGD), the paper introduces two optimizers, named Interpolational Accelerating Gradient Descent (IAGD) as well as Noise-Regularized Stochastic Gradient Descent (NRSGD). IAGD leverages second-order Newton Interpolation to expedite the convergence process during training, assuming relevancy in gradients between iterations. To avoid over-fitting, NRSGD incorporates a noise regularization technique that introduces controlled noise to the gradients during the optimization process. Comparative experiments of this research are conducted on the CIFAR-10, and CIFAR-100 datasets, benchmarking different CNNs(Convolutional Neural Networks) with IAGD and NRSGD against classical optimizers in Keras Package. Results demonstrate the potential of those two viable improvement methods in SGD, implicating the effectiveness of the advancements.

---

### Conformal Inference for Open-Set and Imbalanced Classification

Authors: Tianmin Xie, Yanfei Zhou, Ziyi Liang, Stefano Favaro, Matteo Sesia
Published: 2025-10-14
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2510.13037v1

This paper presents a conformal prediction method for classification in highly imbalanced and open-set settings, where there are many possible classes and not all may be represented in the data. Existing approaches require a finite, known label space and typically involve random sample splitting, which works well when there is a sufficient number of observations from each class. Consequently, they have two limitations: (i) they fail to provide adequate coverage when encountering new labels at test time, and (ii) they may become overly conservative when predicting previously seen labels. To obtain valid prediction sets in the presence of unseen labels, we compute and integrate into our predictions a new family of conformal p-values that can test whether a new data point belongs to a previously unseen class. We study these p-values theoretically, establishing their optimality, and uncover an intriguing connection with the classical Good--Turing estimator for the probability of observing a new species. To make more efficient use of imbalanced data, we also develop a selective sample splitting algorithm that partitions training and calibration data based on label frequency, leading to more informative predictions. Despite breaking exchangeability, this allows maintaining finite-sample guarantees through suitable re-weighting. With both simulated and real data, we demonstrate our method leads to prediction sets with valid coverage even in challenging open-set scenarios with infinite numbers of possible labels, and produces more informative predictions under extreme class imbalance.

---

### Repairing Reward Functions with Feedback to Mitigate Reward Hacking

Authors: Stephane Hatgis-Kessell, Logan Mondal Bhamidipaty, Emma Brunskill
Published: 2025-10-14
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.13036v2

Human-designed reward functions for reinforcement learning (RL) agents are frequently misaligned with the humans' true, unobservable objectives, and thus act only as proxies. Optimizing for a misspecified proxy reward function often induces reward hacking, resulting in a policy misaligned with the human's true objectives. An alternative is to perform RL from human feedback, which involves learning a reward function from scratch by collecting human preferences over pairs of trajectories. However, building such datasets is costly. To address the limitations of both approaches, we propose Preference-Based Reward Repair (PBRR): an automated iterative framework that repairs a human-specified proxy reward function by learning an additive, transition-dependent correction term from preferences. A manually specified reward function can yield policies that are highly suboptimal under the ground-truth objective, yet corrections on only a few transitions may suffice to recover optimal performance. To identify and correct for those transitions, PBRR uses a targeted exploration strategy and a new preference-learning objective. We prove in tabular domains PBRR has a cumulative regret that matches, up to constants, that of prior preference-based RL methods. In addition, on a suite of reward-hacking benchmarks, PBRR consistently outperforms baselines that learn a reward function from scratch from preferences or modify the proxy reward function using other approaches, requiring substantially fewer preferences to learn high performing policies.

---

### Bridging Idealized and Operational Models: An Explainable AI Framework for Earth System Emulators

Authors: Pouria Behnoudfar, Charlotte Moser, Marc Bocquet, Sibo Cheng, Nan Chen
Published: 2025-10-14
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.13030v1

Computer models are indispensable tools for understanding the Earth system. While high-resolution operational models have achieved many successes, they exhibit persistent biases, particularly in simulating extreme events and statistical distributions. In contrast, coarse-grained idealized models isolate fundamental processes and can be precisely calibrated to excel in characterizing specific dynamical and statistical features. However, different models remain siloed by disciplinary boundaries. By leveraging the complementary strengths of models of varying complexity, we develop an explainable AI framework for Earth system emulators. It bridges the model hierarchy through a reconfigured latent data assimilation technique, uniquely suited to exploit the sparse output from the idealized models. The resulting bridging model inherits the high resolution and comprehensive variables of operational models while achieving global accuracy enhancements through targeted improvements from idealized models. Crucially, the mechanism of AI provides a clear rationale for these advancements, moving beyond black-box correction to physically insightful understanding in a computationally efficient framework that enables effective physics-assisted digital twins and uncertainty quantification. We demonstrate its power by significantly correcting biases in CMIP6 simulations of El Niño spatiotemporal patterns, leveraging statistically accurate idealized models. This work also highlights the importance of pushing idealized model development and advancing communication between modeling communities.

---

### Toward Reasoning-Centric Time-Series Analysis

Authors: Xinlei Wang, Mingtian Tan, Jing Qiu, Junhua Zhao, Jinjin Gu
Published: 2025-10-14
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.13029v1

Traditional time series analysis has long relied on pattern recognition, trained on static and well-established benchmarks. However, in real-world settings -- where policies shift, human behavior adapts, and unexpected events unfold -- effective analysis must go beyond surface-level trends to uncover the actual forces driving them. The recent rise of Large Language Models (LLMs) presents new opportunities for rethinking time series analysis by integrating multimodal inputs. However, as the use of LLMs becomes popular, we must remain cautious, asking why we use LLMs and how to exploit them effectively. Most existing LLM-based methods still employ their numerical regression ability and ignore their deeper reasoning potential. This paper argues for rethinking time series with LLMs as a reasoning task that prioritizes causal structure and explainability. This shift brings time series analysis closer to human-aligned understanding, enabling transparent and context-aware insights in complex real-world environments.

---

### Information Shapes Koopman Representation

Authors: Xiaoyuan Cheng, Wenxuan Yuan, Yiming Yang, Yuanzhao Zhang, Sibo Cheng, Yi He, Zhuo Sun
Published: 2025-10-14
Categories: cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2510.13025v2

The Koopman operator provides a powerful framework for modeling dynamical systems and has attracted growing interest from the machine learning community. However, its infinite-dimensional nature makes identifying suitable finite-dimensional subspaces challenging, especially for deep architectures. We argue that these difficulties come from suboptimal representation learning, where latent variables fail to balance expressivity and simplicity. This tension is closely related to the information bottleneck (IB) dilemma: constructing compressed representations that are both compact and predictive. Rethinking Koopman learning through this lens, we demonstrate that latent mutual information promotes simplicity, yet an overemphasis on simplicity may cause latent space to collapse onto a few dominant modes. In contrast, expressiveness is sustained by the von Neumann entropy, which prevents such collapse and encourages mode diversity. This insight leads us to propose an information-theoretic Lagrangian formulation that explicitly balances this tradeoff. Furthermore, we propose a new algorithm based on the Lagrangian formulation that encourages both simplicity and expressiveness, leading to a stable and interpretable Koopman representation. Beyond quantitative evaluations, we further visualize the learned manifolds under our representations, observing empirical results consistent with our theoretical predictions. Finally, we validate our approach across a diverse range of dynamical systems, demonstrating improved performance over existing Koopman learning methods. The implementation is publicly available at https://github.com/Wenxuan52/InformationKoopman.

---

### Machine Learning-Based Ultrasonic Weld Characterization Using Hierarchical Wave Modeling and Diffusion-Driven Distribution Alignment

Authors: Joshua R. Tempelman, Adam J. Wachtor, Eric B. Flynn
Published: 2025-10-14
Categories: cs.LG, physics.comp-ph
arXiv: https://arxiv.org/abs/2510.13023v2

Automated ultrasonic weld inspection remains a significant challenge in the nondestructive evaluation (NDE) community to factors such as limited training data (due to the complexity of curating experimental specimens or high-fidelity simulations) and environmental volatility of many industrial settings (resulting in the corruption of on-the-fly measurements). Thus, an end-to-end machine learning (ML) workflow for acoustic weld inspection in realistic (i.e., industrial) settings has remained an elusive goal. This work addresses the challenges of data curation and signal corruption by proposing workflow consisting of a reduced-order modeling scheme, diffusion based distribution alignment, and U-Net-based segmentation and inversion. A reduced-order Helmholtz model based on Lamb wave theory is used to generate a comprehensive dataset over varying weld heterogeneity and crack defects. The relatively inexpensive low-order solutions provide a robust training dateset for inversion models which are refined through a transfer learning stage using a limited set of full 3D elastodynamic simulations. To handle out-of-distribution (OOD) real-world measurements with varying and unpredictable noise distributions, i.e., Laser Doppler Vibrometry scans, guided diffusion produces in-distribution representations of OOD experimental LDV scans which are subsequently processed by the inversion models. This integrated framework provides an end-to-end solution for automated weld inspection on real data.

---

### On the Role of Preference Variance in Preference Optimization

Authors: Jiacheng Guo, Zihao Li, Jiahao Qiu, Yue Wu, Mengdi Wang
Published: 2025-10-14
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.13022v1

Direct Preference Optimization (DPO) has emerged as an important approach for learning from human preferences in aligning large language models (LLMs). However, collecting human preference data is costly and inefficient, motivating methods to reduce the required annotations. In this work, we investigate the impact of \emph{preference variance} (PVar), which measures the variance in model preferences when comparing pairs of responses, on the effectiveness of DPO training. We provide a theoretical insight by establishing an upper bound on the DPO gradient norm for any given prompt, showing it is controlled by the PVar of that prompt. This implies that prompts with low PVar can only produce small gradient updates, making them less valuable for learning. We validate this finding by fine-tuning LLMs with preferences generated by a reward model, evaluating on two benchmarks (AlpacaEval 2.0 and Arena-Hard). Experimental results demonstrate that prompts with higher PVar outperform randomly selected prompts or those with lower PVar. We also show that our PVar-based selection method is robust, when using smaller reward models (1B, 3B) for selection. Notably, in a separate experiment using the original human annotations from the UltraFeedback dataset, we found that training on only the top 10\% of prompts with the highest PVar yields better evaluation performance than training on the full dataset, highlighting the importance of preference variance in identifying informative examples for efficient LLM alignment.

---

### Escaping Local Optima in the Waddington Landscape: A Two-Stage TRPO-PPO Approach for Single-Cell Perturbation Analysis

Authors: Francis Boabang, Samuel Asante Gyamerah
Published: 2025-10-14
Categories: cs.LG, q-bio.QM
arXiv: https://arxiv.org/abs/2510.13018v2

Modeling cellular responses to genetic and chemical perturbations remains a central challenge in single-cell biology. Existing data-driven frameworks have advanced perturbation prediction through variational autoencoders, chemically conditioned autoencoders, and large-scale transformer pretraining. However, most existing models rely exclusively on either in silico perturbation data or experimental perturbation data but rarely integrate both, limiting their ability to generalize and validate predictions across simulated and real biological contexts in a digital twin system. Moreover, the models are prone to local optima in the nonconvex Waddington landscape of cell fate decisions, where poor initialization can trap trajectories in spurious lineages. In this work, we introduce a two-stage reinforcement learning algorithm for modeling single-cell perturbation. We first compute an explicit natural gradient update using Fisher-vector products and a conjugate gradient solver, scaled by a KL trust-region constraint to provide a safe, curvature-aware first step for the policy. Starting with these preconditioned parameters, we then apply a second phase of proximal policy optimization (PPO) with a KL penalty, exploiting minibatch efficiency to refine the policy. We demonstrate that this initialization strategy substantially improves generalization on Single-cell RNA sequencing (scRNA-seq) perturbation analysis in a digital twin system.

---

### SVAG-Bench: A Large-Scale Benchmark for Multi-Instance Spatio-temporal Video Action Grounding

Authors: Tanveer Hannan, Shuaicong Wu, Mark Weber, Suprosanna Shit, Jindong Gu, Rajat Koner, Aljoša Ošep, Laura Leal-Taixé, Thomas Seidl
Published: 2025-10-14
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.13016v3

A truly capable AI system must do more than detect objects or recognize activities in isolation. It must form unified, grounded representations of who is acting, what they are doing, and when and where these actions unfold. These representations provide the perceptual bedrock for high-level reasoning, planning, and embodied interaction in the real world. Building such agents is central to long-horizon goals in embodied AI and robotics. Current video benchmarks evaluate fragments of these capabilities in isolation. They focus on either spatial grounding, object tracking, or temporal localization. As a result, they cannot rigorously measure progress on their joint, multi-instance integration. We introduce Spatio-temporal Video Action Grounding (SVAG), a task and benchmark that explicitly targets this unified competence by requiring models to simultaneously detect, track, and temporally localize all objects that satisfy a natural language query in complex, multi-actor scenes. To support this task, we construct SVAG-Bench. It comprises 688 videos, 19,590 verified annotations, and 903 unique action verbs drawn from crowded urban environments, wildlife, and traffic surveillance. Each video has on average 28.5 action-centric queries. This yields the densest annotation among comparable video grounding benchmarks and enables fine-grained evaluation of multi-actor disambiguation, temporal overlap, and action compositionality. Annotations are produced by a pipeline that combines expert manual labeling, GPT-3.5 paraphrase augmentation, and human verification to ensure both linguistic diversity and correctness. We further release SVAGEval, a standardized multi-referent evaluation toolkit. We also introduce SVAGFormer, a strong modular baseline architecture for SVAG.

---