# Research Papers — 2025-10 · bundle page 51 of 217

> Full-text markdown of papers #2501–2550 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/51
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/50.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/52.md)

### Relieving the Over-Aggregating Effect in Graph Transformers

Authors: Junshu Sun, Wanxing Chang, Chenxue Yang, Qingming Huang, Shuhui Wang
Published: 2025-10-24
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.21267v1

Graph attention has demonstrated superior performance in graph learning tasks. However, learning from global interactions can be challenging due to the large number of nodes. In this paper, we discover a new phenomenon termed over-aggregating. Over-aggregating arises when a large volume of messages is aggregated into a single node with less discrimination, leading to the dilution of the key messages and potential information loss. To address this, we propose Wideformer, a plug-and-play method for graph attention. Wideformer divides the aggregation of all nodes into parallel processes and guides the model to focus on specific subsets of these processes. The division can limit the input volume per aggregation, avoiding message dilution and reducing information loss. The guiding step sorts and weights the aggregation outputs, prioritizing the informative messages. Evaluations show that Wideformer can effectively mitigate over-aggregating. As a result, the backbone methods can focus on the informative messages, achieving superior performance compared to baseline methods.

---

### Topology Sculptor, Shape Refiner: Discrete Diffusion Model for High-Fidelity 3D Meshes Generation

Authors: Kaiyu Song, Hanjiang Lai, Yaqing Zhang, Chuangjian Cai, Yan Pan Kun Yue, Jian Yin
Published: 2025-10-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.21264v2

In this paper, we introduce Topology Sculptor, Shape Refiner (TSSR), a novel method for generating high-quality, artist-style 3D meshes based on Discrete Diffusion Models (DDMs). Our primary motivation for TSSR is to achieve highly accurate token prediction while enabling parallel generation, a significant advantage over sequential autoregressive methods. By allowing TSSR to "see" all mesh tokens concurrently, we unlock a new level of efficiency and control. We leverage this parallel generation capability through three key innovations: 1) Decoupled Training and Hybrid Inference, which distinctly separates the DDM-based generation into a topology sculpting stage and a subsequent shape refinement stage. This strategic decoupling enables TSSR to effectively capture both intricate local topology and overarching global shape. 2) An Improved Hourglass Architecture, featuring bidirectional attention enriched by face-vertex-sequence level Rotational Positional Embeddings (RoPE), thereby capturing richer contextual information across the mesh structure. 3) A novel Connection Loss, which acts as a topological constraint to further enhance the realism and fidelity of the generated meshes. Extensive experiments on complex datasets demonstrate that TSSR generates high-quality 3D artist-style meshes, capable of achieving up to 10,000 faces at a remarkable spatial resolution of $1024^3$. The code will be released at: https://github.com/psky1111/Tencent-TSSR.

---

### PINN Balls: Scaling Second-Order Methods for PINNs with Domain Decomposition and Adaptive Sampling

Authors: Andrea Bonfanti, Ismael Medina, Roman List, Björn Staeves, Roberto Santana, Marco Ellero
Published: 2025-10-24
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.21262v1

Recent advances in Scientific Machine Learning have shown that second-order methods can enhance the training of Physics-Informed Neural Networks (PINNs), making them a suitable alternative to traditional numerical methods for Partial Differential Equations (PDEs). However, second-order methods induce large memory requirements, making them scale poorly with the model size. In this paper, we define a local Mixture of Experts (MoE) combining the parameter-efficiency of ensemble models and sparse coding to enable the use of second-order training. Our model -- \textsc{PINN Balls} -- also features a fully learnable domain decomposition structure, achieved through the use of Adversarial Adaptive Sampling (AAS), which adapts the DD to the PDE and its domain. \textsc{PINN Balls} achieves better accuracy than the state-of-the-art in scientific machine learning, while maintaining invaluable scalability properties and drawing from a sound theoretical background.

---

### Correlation Dimension of Auto-Regressive Large Language Models

Authors: Xin Du, Kumiko Tanaka-Ishii
Published: 2025-10-24
Categories: cs.CL, cs.AI, nlin.CD
arXiv: https://arxiv.org/abs/2510.21258v1

Large language models (LLMs) have achieved remarkable progress in natural language generation, yet they continue to display puzzling behaviors -- such as repetition and incoherence -- even when exhibiting low perplexity. This highlights a key limitation of conventional evaluation metrics, which emphasize local prediction accuracy while overlooking long-range structural complexity. We introduce correlation dimension, a fractal-geometric measure of self-similarity, to quantify the epistemological complexity of text as perceived by a language model. This measure captures the hierarchical recurrence structure of language, bridging local and global properties in a unified framework. Through extensive experiments, we show that correlation dimension (1) reveals three distinct phases during pretraining, (2) reflects context-dependent complexity, (3) indicates a model's tendency toward hallucination, and (4) reliably detects multiple forms of degeneration in generated text. The method is computationally efficient, robust to model quantization (down to 4-bit precision), broadly applicable across autoregressive architectures (e.g., Transformer and Mamba), and provides fresh insight into the generative dynamics of LLMs.

---

### Out-of-Distribution Detection for Safety Assurance of AI and Autonomous Systems

Authors: Victoria J. Hodge, Colin Paterson, Ibrahim Habli
Published: 2025-10-24
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.21254v1

The operational capabilities and application domains of AI-enabled autonomous systems have expanded significantly in recent years due to advances in robotics and machine learning (ML). Demonstrating the safety of autonomous systems rigorously is critical for their responsible adoption but it is challenging as it requires robust methodologies that can handle novel and uncertain situations throughout the system lifecycle, including detecting out-of-distribution (OoD) data. Thus, OOD detection is receiving increased attention from the research, development and safety engineering communities. This comprehensive review analyses OOD detection techniques within the context of safety assurance for autonomous systems, in particular in safety-critical domains. We begin by defining the relevant concepts, investigating what causes OOD and exploring the factors which make the safety assurance of autonomous systems and OOD detection challenging. Our review identifies a range of techniques which can be used throughout the ML development lifecycle and we suggest areas within the lifecycle in which they may be used to support safety assurance arguments. We discuss a number of caveats that system and safety engineers must be aware of when integrating OOD detection into system lifecycles. We conclude by outlining the challenges and future work necessary for the safe development and operation of autonomous systems across a range of domains and applications.

---

### Unified Implementations of Recurrent Neural Networks in Multiple Deep Learning Frameworks

Authors: Francesco Martinuzzi
Published: 2025-10-24
Categories: cs.LG, cs.SE
arXiv: https://arxiv.org/abs/2510.21252v1

Recurrent neural networks (RNNs) are a cornerstone of sequence modeling across various scientific and industrial applications. Owing to their versatility, numerous RNN variants have been proposed over the past decade, aiming to improve the modeling of long-term dependencies and to address challenges such as vanishing and exploding gradients. However, no central library is available to test these variations, and reimplementing diverse architectures can be time-consuming and error-prone, limiting reproducibility and exploration. Here, we introduce three open-source libraries in Julia and Python that centralize numerous recurrent cell implementations and higher-level recurrent architectures. torchrecurrent, RecurrentLayers.jl, and LuxRecurrentLayers.jl offer a consistent framework for constructing and extending RNN models, providing built-in mechanisms for customization and experimentation. All packages are available under the MIT license and actively maintained on GitHub.

---

### Improved Training Technique for Shortcut Models

Authors: Anh Nguyen, Viet Nguyen, Duc Vu, Trung Dao, Chi Tran, Toan Tran, Anh Tran
Published: 2025-10-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.21250v1

Shortcut models represent a promising, non-adversarial paradigm for generative modeling, uniquely supporting one-step, few-step, and multi-step sampling from a single trained network. However, their widespread adoption has been stymied by critical performance bottlenecks. This paper tackles the five core issues that held shortcut models back: (1) the hidden flaw of compounding guidance, which we are the first to formalize, causing severe image artifacts; (2) inflexible fixed guidance that restricts inference-time control; (3) a pervasive frequency bias driven by a reliance on low-level distances in the direct domain, which biases reconstructions toward low frequencies; (4) divergent self-consistency arising from a conflict with EMA training; and (5) curvy flow trajectories that impede convergence. To address these challenges, we introduce iSM, a unified training framework that systematically resolves each limitation. Our framework is built on four key improvements: Intrinsic Guidance provides explicit, dynamic control over guidance strength, resolving both compounding guidance and inflexibility. A Multi-Level Wavelet Loss mitigates frequency bias to restore high-frequency details. Scaling Optimal Transport (sOT) reduces training variance and learns straighter, more stable generative paths. Finally, a Twin EMA strategy reconciles training stability with self-consistency. Extensive experiments on ImageNet 256 x 256 demonstrate that our approach yields substantial FID improvements over baseline shortcut models across one-step, few-step, and multi-step generation, making shortcut models a viable and competitive class of generative models.

---

### Forecast reconciliation with non-linear constraints

Authors: Daniele Girolimetto, Anastasios Panagiotelis, Tommaso Di Fonzo, Han Li
Published: 2025-10-24
Categories: stat.ME, stat.AP, stat.ML
arXiv: https://arxiv.org/abs/2510.21249v1

Methods for forecasting time series adhering to linear constraints have seen notable development in recent years, especially with the advent of forecast reconciliation. This paper extends forecast reconciliation to the open question of non-linearly constrained time series. Non-linear constraints can emerge with variables that are formed as ratios such as mortality rates and unemployment rates. On the methodological side, Non-linearly Constrained Reconciliation (NLCR) is proposed. This algorithm adjusts forecasts that fail to meet non-linear constraints, in a way that ensures the new forecasts meet the constraints. The NLCR method is a projection onto a non-linear surface, formulated as a constrained optimisation problem. On the theoretical side, optimisation methods are again used, this time to derive sufficient conditions for when the NLCR methodology is guaranteed to improve forecast accuracy. Finally on the empirical side, NLCR is applied to two datasets from demography and economics and shown to significantly improve forecast accuracy relative to relevant benchmarks.

---

### Convergence of Stochastic Gradient Langevin Dynamics in the Lazy Training Regime

Authors: Noah Oberweis, Semih Cayci
Published: 2025-10-24
Categories: cs.LG, math.OC
arXiv: https://arxiv.org/abs/2510.21245v3

Continuous-time models provide important insights into the training dynamics of optimization algorithms in deep learning. In this work, we establish a non-asymptotic convergence analysis of stochastic gradient Langevin dynamics (SGLD), which is an Itô stochastic differential equation (SDE) approximation of stochastic gradient descent in continuous time, in the lazy training regime. We show that, under regularity conditions on the Hessian of the loss function, SGLD with multiplicative and state-dependent noise (i) yields a non-degenerate kernel throughout the training process with high probability, and (ii) achieves exponential convergence to the empirical risk minimizer in expectation, and we establish finite-time and finite-width bounds on the optimality gap. We corroborate our theoretical findings with numerical examples in the regression setting.

---

### VoiceAgentEval: A Dual-Dimensional Benchmark for Expert-Level Intelligent Voice-Agent Evaluation of Xbench's Professional-Aligned Series

Authors: Pengyu Xu, Shijia Li, Ao Sun, Feng Zhang, Yahan Li, Bo Wu, Zhanyu Ma, Jiguo Li, Jun Xu, Jiuchong Gao, Jinghua Hao, Renqing He et al.
Published: 2025-10-24
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.21244v2

We propose OutboundEval, a comprehensive benchmark for evaluating large language models (LLMs) in expert-level intelligent outbound calling scenarios. Unlike existing methods that suffer from three key limitations - insufficient dataset diversity and category coverage, unrealistic user simulation, and inaccurate evaluation metrics - OutboundEval addresses these issues through a structured framework. First, we design a benchmark spanning six major business domains and 30 representative sub-scenarios, each with scenario-specific process decomposition, weighted scoring, and domain-adaptive metrics. Second, we develop a large-model-driven User Simulator that generates diverse, persona-rich virtual users with realistic behaviors, emotional variability, and communication styles, providing a controlled yet authentic testing environment. Third, we introduce a dynamic evaluation method that adapts to task variations, integrating automated and human-in-the-loop assessment to measure task execution accuracy, professional knowledge application, adaptability, and user experience quality. Experiments on 12 state-of-the-art LLMs reveal distinct trade-offs between expert-level task completion and interaction fluency, offering practical insights for building reliable, human-like outbound AI systems. OutboundEval establishes a practical, extensible, and domain-oriented standard for benchmarking LLMs in professional applications.

---

### Physics-Informed Neural Networks for MIMO Beam Map and Environment Reconstruction

Authors: Wangqian Chen, Junting Chen, Shuguang Cui
Published: 2025-10-24
Categories: eess.SY, cs.AI, cs.IT
arXiv: https://arxiv.org/abs/2510.21238v1

As communication networks evolve towards greater complexity (e.g., 6G and beyond), a deep understanding of the wireless environment becomes increasingly crucial. When explicit knowledge of the environment is unavailable, geometry-aware feature extraction from channel state information (CSI) emerges as a pivotal methodology to bridge physical-layer measurements with network intelligence. This paper proposes to explore the received signal strength (RSS) data, without explicit 3D environment knowledge, to jointly construct the radio beam map and environmental geometry for a multiple-input multiple-output (MIMO) system. Unlike existing methods that only learn blockage structures, we propose an oriented virtual obstacle model that captures the geometric features of both blockage and reflection. Reflective zones are formulated to identify relevant reflected paths according to the geometry relation of the environment. We derive an analytical expression for the reflective zone and further analyze its geometric characteristics to develop a reformulation that is more compatible with deep learning representations. A physics-informed deep learning framework that incorporates the reflective-zone-based geometry model is proposed to learn the blockage, reflection, and scattering components, along with the beam pattern, which leverages physics prior knowledge to enhance network transferability. Numerical experiments demonstrate that, in addition to reconstructing the blockage and reflection geometry, the proposed model can construct a more accurate MIMO beam map with a 32%-48% accuracy improvement.

---

### AgentBound: Securing Execution Boundaries of AI Agents

Authors: Christoph Bühler, Matteo Biagiola, Luca Di Grazia, Guido Salvaneschi
Published: 2025-10-24
Categories: cs.CR, cs.AI, cs.SE
arXiv: https://arxiv.org/abs/2510.21236v3

Large Language Models (LLMs) have evolved into AI agents that interact with external tools and environments to perform complex tasks. The Model Context Protocol (MCP) has become the de facto standard for connecting agents with such resources, but security has lagged behind: thousands of MCP servers execute with unrestricted access to host systems, creating a broad attack surface. In this paper, we introduce AgentBound, the first access control framework for MCP servers. AgentBound combines a declarative policy mechanism, inspired by the Android permission model, with a policy enforcement engine that contains malicious behavior without requiring MCP server modifications. We build a dataset containing the 296 most popular MCP servers, and show that access control policies can be generated automatically from source code with 80.9% accuracy. We also show that AgentBound blocks the majority of security threats in several malicious MCP servers, and that the policy enforcement engine introduces negligible overhead. Our contributions provide developers and project managers with a foundation for securing MCP servers while maintaining productivity, enabling researchers and tool builders to explore new directions for declarative access control and MCP security.

---

### How Hard is it to Confuse a World Model?

Authors: Waris Radji, Odalric-Ambrym Maillard
Published: 2025-10-24
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.21232v1

In reinforcement learning (RL) theory, the concept of most confusing instances is central to establishing regret lower bounds, that is, the minimal exploration needed to solve a problem. Given a reference model and its optimal policy, a most confusing instance is the statistically closest alternative model that makes a suboptimal policy optimal. While this concept is well-studied in multi-armed bandits and ergodic tabular Markov decision processes, constructing such instances remains an open question in the general case. In this paper, we formalize this problem for neural network world models as a constrained optimization: finding a modified model that is statistically close to the reference one, while producing divergent performance between optimal and suboptimal policies. We propose an adversarial training procedure to solve this problem and conduct an empirical study across world models of varying quality. Our results suggest that the degree of achievable confusion correlates with uncertainty in the approximate model, which may inform theoretically-grounded exploration strategies for deep model-based RL.

---

### DispatchMAS: Fusing taxonomy and artificial intelligence agents for emergency medical services

Authors: Xiang Li, Huizi Yu, Wenkong Wang, Yiran Wu, Jiayan Zhou, Wenyue Hua, Xinxin Lin, Wenjia Tan, Lexuan Zhu, Bingyi Chen, Guang Chen, Ming-Li Chen et al.
Published: 2025-10-24
Categories: cs.CL, cs.HC
arXiv: https://arxiv.org/abs/2510.21228v1

Objective: Emergency medical dispatch (EMD) is a high-stakes process challenged by caller distress, ambiguity, and cognitive load. Large Language Models (LLMs) and Multi-Agent Systems (MAS) offer opportunities to augment dispatchers. This study aimed to develop and evaluate a taxonomy-grounded, LLM-powered multi-agent system for simulating realistic EMD scenarios. Methods: We constructed a clinical taxonomy (32 chief complaints, 6 caller identities from MIMIC-III) and a six-phase call protocol. Using this framework, we developed an AutoGen-based MAS with Caller and Dispatcher Agents. The system grounds interactions in a fact commons to ensure clinical plausibility and mitigate misinformation. We used a hybrid evaluation framework: four physicians assessed 100 simulated cases for "Guidance Efficacy" and "Dispatch Effectiveness," supplemented by automated linguistic analysis (sentiment, readability, politeness). Results: Human evaluation, with substantial inter-rater agreement (Gwe's AC1 > 0.70), confirmed the system's high performance. It demonstrated excellent Dispatch Effectiveness (e.g., 94 % contacting the correct potential other agents) and Guidance Efficacy (advice provided in 91 % of cases), both rated highly by physicians. Algorithmic metrics corroborated these findings, indicating a predominantly neutral affective profile (73.7 % neutral sentiment; 90.4 % neutral emotion), high readability (Flesch 80.9), and a consistently polite style (60.0 % polite; 0 % impolite). Conclusion: Our taxonomy-grounded MAS simulates diverse, clinically plausible dispatch scenarios with high fidelity. Findings support its use for dispatcher training, protocol evaluation, and as a foundation for real-time decision support. This work outlines a pathway for safely integrating advanced AI agents into emergency response workflows.

---

### Model Merging with Functional Dual Anchors

Authors: Kexuan Shi, Yandong Wen, Weiyang Liu
Published: 2025-10-24
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.21223v1

Model merging is an efficient post-training strategy for integrating knowledge from multiple finetuned checkpoints of a shared foundation model. Existing methods operate in the parameter space, combining task vectors to mitigate conflicts, but remain constrained by parameter inconsistencies. We propose Functional Dual Anchors (FDAs), a framework that instead models the input-representation space. FDAs are synthetic inputs whose induced gradients align with task vectors, capturing task-specific functional shifts relative to the pretrained model. This perspective bridges joint multi-task training and post-hoc merging, offering both robustness and flexibility. We further introduce a principled initialization scheme and show that FDAs are complementary to parameter-space model merging. Comprehensive experiments demonstrate the effectiveness of FDAs in model merging.

---

### The "Right" Discourse on Migration: Analysing Migration-Related Tweets in Right and Far-Right Political Movements

Authors: Nishan Chatterjee, Veronika Bajt, Ana Zwitter Vitez, Senja Pollak
Published: 2025-10-24
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.21220v1

The rise of right-wing populism in Europe has brought to the forefront the significance of analysing social media discourse to understand the dissemination of extremist ideologies and their impact on political outcomes. Twitter, as a platform for interaction and mobilisation, provides a unique window into the everyday communication of far-right supporters. In this paper, we propose a methodology that uses state-of-the-art natural language processing techniques with sociological insights to analyse the MIGR-TWIT corpus of far-right tweets in English and French. We aim to uncover patterns of discourse surrounding migration, hate speech, and persuasion techniques employed by right and far-right actors. By integrating linguistic, sociological, and computational approaches, we seek to offer cross-disciplinary insights into societal dynamics and contribute to a better understanding of contemporary challenges posed by right-wing extremism on social media platforms.

---

### On the flow matching interpretability

Authors: Francesco Pivi, Simone Gazza, Davide Evangelista, Roberto Amadini, Maurizio Gabbrielli
Published: 2025-10-24
Categories: cs.LG, math.ST, physics.app-ph, physics.comp-ph
arXiv: https://arxiv.org/abs/2510.21210v1

Generative models based on flow matching have demonstrated remarkable success in various domains, yet they suffer from a fundamental limitation: the lack of interpretability in their intermediate generation steps. In fact these models learn to transform noise into data through a series of vector field updates, however the meaning of each step remains opaque. We address this problem by proposing a general framework constraining each flow step to be sampled from a known physical distribution. Flow trajectories are mapped to (and constrained to traverse) the equilibrium states of the simulated physical process. We implement this approach through the 2D Ising model in such a way that flow steps become thermal equilibrium points along a parametric cooling schedule. Our proposed architecture includes an encoder that maps discrete Ising configurations into a continuous latent space, a flow-matching network that performs temperature-driven diffusion, and a projector that returns to discrete Ising states while preserving physical constraints. We validate this framework across multiple lattice sizes, showing that it preserves physical fidelity while outperforming Monte Carlo generation in speed as the lattice size increases. In contrast with standard flow matching, each vector field represents a meaningful stepwise transition in the 2D Ising model's latent space. This demonstrates that embedding physical semantics into generative flows transforms opaque neural trajectories into interpretable physical processes.

---

### Adaptive Graph Mixture of Residual Experts: Unsupervised Learning on Diverse Graphs with Heterogeneous Specialization

Authors: Yunlong Chu, Minglai Shao, Zengyi Wo, Bing Hao, Yuhang Liu, Ruijie Wang, Jianxin Li
Published: 2025-10-24
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.21207v1

Graph Neural Networks (GNNs) face a fundamental adaptability challenge: their fixed message-passing architectures struggle with the immense diversity of real-world graphs, where optimal computational strategies vary by local structure and task. While Mixture-of-Experts (MoE) offers a promising pathway to adaptability, existing graph MoE methods remain constrained by their reliance on supervised signals and instability when training heterogeneous experts. We introduce ADaMoRE (Adaptive Mixture of Residual Experts), a principled framework that enables robust, fully unsupervised training of heterogeneous MoE on graphs. ADaMoRE employs a backbone-residual expert architecture where foundational encoders provide stability while specialized residual experts capture diverse computational patterns. A structurally-aware gating network performs fine-grained node routing. The entire architecture is trained end-to-end using a unified unsupervised objective, which integrates a primary reconstruction task with an information-theoretic diversity regularizer to explicitly enforce functional specialization among the experts. Theoretical analysis confirms our design improves data efficiency and training stability. Extensive evaluation across 16 benchmarks validates ADaMoRE's state-of-the-art performance in unsupervised node classification and few-shot learning, alongside superior generalization, training efficiency, and faster convergence on diverse graphs and tasks.

---

### Mitra: Mixed Synthetic Priors for Enhancing Tabular Foundation Models

Authors: Xiyuan Zhang, Danielle C. Maddix, Junming Yin, Nick Erickson, Abdul Fatir Ansari, Boran Han, Shuai Zhang, Leman Akoglu, Christos Faloutsos, Michael W. Mahoney, Cuixiong Hu, Huzefa Rangwala et al.
Published: 2025-10-24
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.21204v1

Since the seminal work of TabPFN, research on tabular foundation models (TFMs) based on in-context learning (ICL) has challenged long-standing paradigms in machine learning. Without seeing any real-world data, models pretrained on purely synthetic datasets generalize remarkably well across diverse datasets, often using only a moderate number of in-context examples. This shifts the focus in tabular machine learning from model architecture design to the design of synthetic datasets, or, more precisely, to the prior distributions that generate them. Yet the guiding principles for prior design remain poorly understood. This work marks the first attempt to address the gap. We systematically investigate and identify key properties of synthetic priors that allow pretrained TFMs to generalize well. Based on these insights, we introduce Mitra, a TFM trained on a curated mixture of synthetic priors selected for their diversity, distinctiveness, and performance on real-world tabular data. Mitra consistently outperforms state-of-the-art TFMs, such as TabPFNv2 and TabICL, across both classification and regression benchmarks, with better sample efficiency.

---

### Online AUC Optimization Based on Second-order Surrogate Loss

Authors: JunRu Luo, Difei Cheng, Bo Zhang
Published: 2025-10-24
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.21202v1

The Area Under the Curve (AUC) is an important performance metric for classification tasks, particularly in class-imbalanced scenarios. However, minimizing the AUC presents significant challenges due to the non-convex and discontinuous nature of pairwise 0/1 losses, which are difficult to optimize, as well as the substantial memory cost of instance-wise storage, which creates bottlenecks in large-scale applications. To overcome these challenges, we propose a novel second-order surrogate loss based on the pairwise hinge loss, and develop an efficient online algorithm. Unlike conventional approaches that approximate each individual pairwise 0/1 loss term with an instance-wise surrogate function, our approach introduces a new paradigm that directly substitutes the entire aggregated pairwise loss with a surrogate loss function constructed from the first- and second-order statistics of the training data. Theoretically, while existing online AUC optimization algorithms typically achieve an $\mathcal{O}(\sqrt{T})$ regret bound, our method attains a tighter $\mathcal{O}(\ln T)$ bound. Furthermore, we extend the proposed framework to nonlinear settings through a kernel-based formulation. Extensive experiments on multiple benchmark datasets demonstrate the superior efficiency and effectiveness of the proposed second-order surrogate loss in optimizing online AUC performance.

---

### 3rd Place Solution to Large-scale Fine-grained Food Recognition

Authors: Yang Zhong, Yifan Yao, Tong Luo, Youcai Zhang, Yaqian Li
Published: 2025-10-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.21199v1

Food analysis is becoming a hot topic in health area, in which fine-grained food recognition task plays an important role. In this paper, we describe the details of our solution to the LargeFineFoodAI-ICCV Workshop-Recognition challenge held on Kaggle. We find a proper combination of Arcface loss(1) and Circle loss(9) can bring improvement to the performance. With Arcface and the combined loss, model was trained with carefully tuned configurations and ensembled to get the final results. Our solution won the 3rd place in the competition.

---

### 3rd Place Solution to ICCV LargeFineFoodAI Retrieval

Authors: Yang Zhong, Zhiming Wang, Zhaoyang Li, Jinyu Ma, Xiang Li
Published: 2025-10-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.21198v1

This paper introduces the 3rd place solution to the ICCV LargeFineFoodAI Retrieval Competition on Kaggle. Four basic models are independently trained with the weighted sum of ArcFace and Circle loss, then TTA and Ensemble are successively applied to improve feature representation ability. In addition, a new reranking method for retrieval is proposed based on diffusion and k-reciprocal reranking. Finally, our method scored 0.81219 and 0.81191 mAP@100 on the public and private leaderboard, respectively.

---

### Estonian Native Large Language Model Benchmark

Authors: Helena Grete Lillepalu, Tanel Alumäe
Published: 2025-10-24
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.21193v2

The availability of LLM benchmarks for the Estonian language is limited, and a comprehensive evaluation comparing the performance of different LLMs on Estonian tasks has yet to be conducted. We introduce a new benchmark for evaluating LLMs in Estonian, based on seven diverse datasets. These datasets assess general and domain-specific knowledge, understanding of Estonian grammar and vocabulary, summarization abilities, contextual comprehension, and more. The datasets are all generated from native Estonian sources without using machine translation. We compare the performance of base models, instruction-tuned open-source models, and commercial models. Our evaluation includes 6 base models and 26 instruction-tuned models. To assess the results, we employ both human evaluation and LLM-as-a-judge methods. Human evaluation scores showed moderate to high correlation with benchmark evaluations, depending on the dataset. Claude 3.7 Sonnet, used as an LLM judge, demonstrated strong alignment with human ratings, indicating that top-performing LLMs can effectively support the evaluation of Estonian-language models.

---

### Gen-Review: A Large-scale Dataset of AI-Generated (and Human-written) Peer Reviews

Authors: Luca Demetrio, Giovanni Apruzzese, Kathrin Grosse, Pavel Laskov, Emil Lupu, Vera Rimmer, Philine Widmer
Published: 2025-10-24
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.21192v1

How does the progressive embracement of Large Language Models (LLMs) affect scientific peer reviewing? This multifaceted question is fundamental to the effectiveness -- as well as to the integrity -- of the scientific process. Recent evidence suggests that LLMs may have already been tacitly used in peer reviewing, e.g., at the 2024 International Conference of Learning Representations (ICLR). Furthermore, some efforts have been undertaken in an attempt to explicitly integrate LLMs in peer reviewing by various editorial boards (including that of ICLR'25). To fully understand the utility and the implications of LLMs' deployment for scientific reviewing, a comprehensive relevant dataset is strongly desirable. Despite some previous research on this topic, such dataset has been lacking so far. We fill in this gap by presenting GenReview, the hitherto largest dataset containing LLM-written reviews. Our dataset includes 81K reviews generated for all submissions to the 2018--2025 editions of the ICLR by providing the LLM with three independent prompts: a negative, a positive, and a neutral one. GenReview is also linked to the respective papers and their original reviews, thereby enabling a broad range of investigations. To illustrate the value of GenReview, we explore a sample of intriguing research questions, namely: if LLMs exhibit bias in reviewing (they do); if LLM-written reviews can be automatically detected (so far, they can); if LLMs can rigorously follow reviewing instructions (not always) and whether LLM-provided ratings align with decisions on paper acceptance or rejection (holds true only for accepted papers). GenReview can be accessed at the following link: https://anonymous.4open.science/r/gen_review.

---

### PLAN: Proactive Low-Rank Allocation for Continual Learning

Authors: Xiequn Wang, Zhan Zhuang, Yu Zhang
Published: 2025-10-24
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.21188v1

Continual learning (CL) requires models to continuously adapt to new tasks without forgetting past knowledge. In this work, we propose \underline{P}roactive \underline{L}ow-rank \underline{A}llocatio\underline{N} (PLAN), a framework that extends Low-Rank Adaptation (LoRA) to enable efficient and interference-aware fine-tuning of large pre-trained models in CL settings. PLAN proactively manages the allocation of task-specific subspaces by introducing orthogonal basis vectors for each task and optimizing them through a perturbation-based strategy that minimizes conflicts with previously learned parameters. Furthermore, PLAN incorporates a novel selection mechanism that identifies and assigns basis vectors with minimal sensitivity to interference, reducing the risk of degrading past knowledge while maintaining efficient adaptation to new tasks. Empirical results on standard CL benchmarks demonstrate that PLAN consistently outperforms existing methods, establishing a new state-of-the-art for continual learning with foundation models.

---

### Reducing the Probability of Undesirable Outputs in Language Models Using Probabilistic Inference

Authors: Stephen Zhao, Aidan Li, Rob Brekelmans, Roger Grosse
Published: 2025-10-24
Categories: cs.LG, cs.AI, cs.CL, stat.ML
arXiv: https://arxiv.org/abs/2510.21184v1

Reinforcement learning (RL) has become a predominant technique to align language models (LMs) with human preferences or promote outputs which are deemed to be desirable by a given reward function. Standard RL approaches optimize average reward, while methods explicitly focused on reducing the probability of undesired outputs typically come at a cost to average-case performance. To improve this tradeoff, we introduce RePULSe, a new training method that augments the standard RL loss with an additional loss that uses learned proposals to guide sampling low-reward outputs, and then reduces those outputs' probability. We run experiments demonstrating that RePULSe produces a better tradeoff of expected reward versus the probability of undesired outputs and is more adversarially robust, compared to standard RL alignment approaches and alternatives.

---

### KBE-DME: Dynamic Multimodal Evaluation via Knowledge Enhanced Benchmark Evolution

Authors: Junzhe Zhang, Huixuan Zhang, Xiaojun Wan
Published: 2025-10-24
Categories: cs.CV, cs.CL
arXiv: https://arxiv.org/abs/2510.21182v2

The rapid progress of multimodal large language models (MLLMs) calls for more reliable evaluation protocols. Existing static benchmarks suffer from the potential risk of data contamination and saturation, leading to inflated or misleading performance evaluations. To address these issues, we first apply Graph formulation to represent a static or dynamic VQA sample. With the formulation, we propose Knowledge-enhanced Benchmark Evolution(KBE), a dynamic multimodal evaluation framework. KBE first analyzes the original static benchmark, then expands it by integrating multimodal knowledge, transforming the static benchmark into a controllable, dynamic evolving version. Crucially, KBE can both reconstruct questions by Re-selecting visual information in the original image and expand existing questions with external textual knowledge. It enables difficulty-controllable evaluation by adjusting the degree of question exploration. Extensive experiments demonstrate that KBE alleviates the risk of data contamination, data saturation, and provides a more comprehensive assessment of MLLM capabilities.

---

### Shylock: Causal Discovery in Multivariate Time Series based on Hybrid Constraints

Authors: Shuo Li, Keqin Xu, Jie Liu, Dan Ye
Published: 2025-10-24
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.21181v1

Causal relationship discovery has been drawing increasing attention due to its prevalent application. Existing methods rely on human experience, statistical methods, or graphical criteria methods which are error-prone, stuck at the idealized assumption, and rely on a huge amount of data. And there is also a serious data gap in accessing Multivariate time series(MTS) in many areas, adding difficulty in finding their causal relationship. Existing methods are easy to be over-fitting on them. To fill the gap we mentioned above, in this paper, we propose Shylock, a novel method that can work well in both few-shot and normal MTS to find the causal relationship. Shylock can reduce the number of parameters exponentially by using group dilated convolution and a sharing kernel, but still learn a better representation of variables with time delay. By combing the global constraint and the local constraint, Shylock achieves information sharing among networks to help improve the accuracy. To evaluate the performance of Shylock, we also design a data generation method to generate MTS with time delay. We evaluate it on commonly used benchmarks and generated datasets. Extensive experiments show that Shylock outperforms two existing state-of-art methods on both few-shot and normal MTS. We also developed Tcausal, a library for easy use and deployed it on the EarthDataMiner platform

---

### Social Simulations with Large Language Model Risk Utopian Illusion

Authors: Ning Bian, Xianpei Han, Hongyu Lin, Baolei Wu, Jun Wang
Published: 2025-10-24
Categories: cs.CL, cs.SI
arXiv: https://arxiv.org/abs/2510.21180v1

Reliable simulation of human behavior is essential for explaining, predicting, and intervening in our society. Recent advances in large language models (LLMs) have shown promise in emulating human behaviors, interactions, and decision-making, offering a powerful new lens for social science studies. However, the extent to which LLMs diverge from authentic human behavior in social contexts remains underexplored, posing risks of misinterpretation in scientific studies and unintended consequences in real-world applications. Here, we introduce a systematic framework for analyzing LLMs' behavior in social simulation. Our approach simulates multi-agent interactions through chatroom-style conversations and analyzes them across five linguistic dimensions, providing a simple yet effective method to examine emergent social cognitive biases. We conduct extensive experiments involving eight representative LLMs across three families. Our findings reveal that LLMs do not faithfully reproduce genuine human behavior but instead reflect overly idealized versions of it, shaped by the social desirability bias. In particular, LLMs show social role bias, primacy effect, and positivity bias, resulting in "Utopian" societies that lack the complexity and variability of real human interactions. These findings call for more socially grounded LLMs that capture the diversity of human social behavior.

---

### Instance-Adaptive Hypothesis Tests with Heterogeneous Agents

Authors: Flora C. Shi, Martin J. Wainwright, Stephen Bates
Published: 2025-10-24
Categories: cs.GT, cs.LG, econ.EM, math.ST, stat.ME
arXiv: https://arxiv.org/abs/2510.21178v1

We study hypothesis testing over a heterogeneous population of strategic agents with private information. Any single test applied uniformly across the population yields statistical error that is sub-optimal relative to the performance of an oracle given access to the private information. We show how it is possible to design menus of statistical contracts that pair type-optimal tests with payoff structures, inducing agents to self-select according to their private information. This separating menu elicits agent types and enables the principal to match the oracle performance even without a priori knowledge of the agent type. Our main result fully characterizes the collection of all separating menus that are instance-adaptive, matching oracle performance for an arbitrary population of heterogeneous agents. We identify designs where information elicitation is essentially costless, requiring negligible additional expense relative to a single-test benchmark, while improving statistical performance. Our work establishes a connection between proper scoring rules and menu design, showing how the structure of the hypothesis test constrains the elicitable information. Numerical examples illustrate the geometry of separating menus and the improvements they deliver in error trade-offs. Overall, our results connect statistical decision theory with mechanism design, demonstrating how heterogeneity and strategic participation can be harnessed to improve efficiency in hypothesis testing.

---

### Scalable Principal-Agent Contract Design via Gradient-Based Optimization

Authors: Tomer Galanti, Aarya Bookseller, Korok Ray
Published: 2025-10-24
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.21177v1

We study a bilevel \emph{max-max} optimization framework for principal-agent contract design, in which a principal chooses incentives to maximize utility while anticipating the agent's best response. This problem, central to moral hazard and contract theory, underlies applications ranging from market design to delegated portfolio management, hedge fund fee structures, and executive compensation. While linear-quadratic models such as Holmstr"om-Milgrom admit closed-form solutions, realistic environments with nonlinear utilities, stochastic dynamics, or high-dimensional actions generally do not. We introduce a generic algorithmic framework that removes this reliance on closed forms. Our method adapts modern machine learning techniques for bilevel optimization -- using implicit differentiation with conjugate gradients (CG) -- to compute hypergradients efficiently through Hessian-vector products, without ever forming or inverting Hessians. In benchmark CARA-Normal (Constant Absolute Risk Aversion with Gaussian distribution of uncertainty) environments, the approach recovers known analytical optima and converges reliably from random initialization. More broadly, because it is matrix-free, variance-reduced, and problem-agnostic, the framework extends naturally to complex nonlinear contracts where closed-form solutions are unavailable, such as sigmoidal wage schedules (logistic pay), relative-performance/tournament compensation with common shocks, multi-task contracts with vector actions and heterogeneous noise, and CARA-Poisson count models with $\mathbb{E}(X\mid a)=e^{a}$. This provides a new computational tool for contract design, enabling systematic study of models that have remained analytically intractable.

---

### A visual big data system for the prediction of weather-related variables: Jordan-Spain case study

Authors: Shadi Aljawarneh, Juan A. Lara, Muneer Bani Yassein
Published: 2025-10-24
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.21176v1

The Meteorology is a field where huge amounts of data are generated, mainly collected by sensors at weather stations, where different variables can be measured. Those data have some particularities such as high volume and dimensionality, the frequent existence of missing values in some stations, and the high correlation between collected variables. In this regard, it is crucial to make use of Big Data and Data Mining techniques to deal with those data and extract useful knowledge from them that can be used, for instance, to predict weather phenomena. In this paper, we propose a visual big data system that is designed to deal with high amounts of weather-related data and lets the user analyze those data to perform predictive tasks over the considered variables (temperature and rainfall). The proposed system collects open data and loads them onto a local NoSQL database fusing them at different levels of temporal and spatial aggregation in order to perform a predictive analysis using univariate and multivariate approaches as well as forecasting based on training data from neighbor stations in cases with high rates of missing values. The system has been assessed in terms of usability and predictive performance, obtaining an overall normalized mean squared error value of 0.00013, and an overall directional symmetry value of nearly 0.84. Our system has been rated positively by a group of experts in the area (all aspects of the system except graphic desing were rated 3 or above in a 1-5 scale). The promising preliminary results obtained demonstrate the validity of our system and invite us to keep working on this area.

---

### Memory-Free Continual Learning with Null Space Adaptation for Zero-Shot Vision-Language Models

Authors: Yujin Jo, Taesup Kim
Published: 2025-10-24
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.21175v2

Pre-trained vision-language models (VLMs), such as CLIP, have demonstrated remarkable zero-shot generalization, enabling deployment in a wide range of real-world tasks without additional task-specific training. However, in real deployment scenarios with evolving environments or emerging classes, these models inevitably face distributional shifts and novel tasks. In such contexts, static zero-shot capabilities are insufficient, and there is a growing need for continual learning methods that allow models to adapt over time while avoiding catastrophic forgetting. We introduce NuSA-CL (Null Space Adaptation for Continual Learning), a lightweight memory-free continual learning framework designed to address this challenge. NuSA-CL employs low-rank adaptation and constrains task-specific weight updates to lie within an approximate null space of the model's current parameters. This strategy minimizes interference with previously acquired knowledge, effectively preserving the zero-shot capabilities of the original model. Unlike methods relying on replay buffers or costly distillation, NuSA-CL imposes minimal computational and memory overhead, making it practical for deployment in resource-constrained, real-world continual learning environments. Experiments show that our framework not only effectively preserves zero-shot transfer capabilities but also achieves highly competitive performance on continual learning benchmarks. These results position NuSA-CL as a practical and scalable solution for continually evolving zero-shot VLMs in real-world applications.

---

### A Unified Matrix Factorization Framework for Classical and Robust Clustering

Authors: Angshul Majumdar
Published: 2025-10-24
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.21172v1

This paper presents a unified matrix factorization framework for classical and robust clustering. We begin by revisiting the well-known equivalence between crisp k-means clustering and matrix factorization, following and rigorously rederiving an unpublished formulation by Bauckhage. Extending this framework, we derive an analogous matrix factorization interpretation for fuzzy c-means clustering, which to the best of our knowledge has not been previously formalized. These reformulations allow both clustering paradigms to be expressed as optimization problems over factor matrices, thereby enabling principled extensions to robust variants. To address sensitivity to outliers, we propose robust formulations for both crisp and fuzzy clustering by replacing the Frobenius norm with the l1,2-norm, which penalizes the sum of Euclidean norms across residual columns. We develop alternating minimization algorithms for the standard formulations and IRLS-based algorithms for the robust counterparts. All algorithms are theoretically proven to converge to a local minimum.

---

### TokenCLIP: Token-wise Prompt Learning for Zero-shot Anomaly Detection

Authors: Qihang Zhou, Binbin Gao, Guansong Pang, Xin Wang, Jiming Chen, Shibo He
Published: 2025-10-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.21171v4

Adapting CLIP for anomaly detection on unseen objects has shown strong potential in a zero-shot manner. However, existing methods typically rely on a single textual space to align with visual semantics across diverse objects and domains. The indiscriminate alignment hinders the model from accurately capturing varied anomaly semantics. We propose TokenCLIP, a token-wise adaptation framework that enables dynamic alignment between visual and learnable textual spaces for fine-grained anomaly learning. Rather than mapping all visual tokens to a single, token-agnostic textual space, TokenCLIP aligns each token with a customized textual subspace that represents its visual characteristics. Explicitly assigning a unique learnable textual space to each token is computationally intractable and prone to insufficient optimization. We instead expand the token-agnostic textual space into a set of orthogonal subspaces, and then dynamically assign each token to a subspace combination guided by semantic affinity, which jointly supports customized and efficient token-wise adaptation. To this end, we formulate dynamic alignment as an optimal transport problem, where all visual tokens in an image are transported to textual subspaces based on semantic similarity. The transport constraints of OT ensure sufficient optimization across subspaces and encourage them to focus on different semantics. Solving the problem yields a transport plan that adaptively assigns each token to semantically relevant subspaces. A top-k masking is then applied to sparsify the plan and specialize subspaces for distinct visual regions. Extensive experiments demonstrate the superiority of TokenCLIP.

---

### Blockwise Flow Matching: Improving Flow Matching Models For Efficient High-Quality Generation

Authors: Dogyun Park, Taehoon Lee, Minseok Joo, Hyunwoo J. Kim
Published: 2025-10-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.21167v1

Recently, Flow Matching models have pushed the boundaries of high-fidelity data generation across a wide range of domains. It typically employs a single large network to learn the entire generative trajectory from noise to data. Despite their effectiveness, this design struggles to capture distinct signal characteristics across timesteps simultaneously and incurs substantial inference costs due to the iterative evaluation of the entire model. To address these limitations, we propose Blockwise Flow Matching (BFM), a novel framework that partitions the generative trajectory into multiple temporal segments, each modeled by smaller but specialized velocity blocks. This blockwise design enables each block to specialize effectively in its designated interval, improving inference efficiency and sample quality. To further enhance generation fidelity, we introduce a Semantic Feature Guidance module that explicitly conditions velocity blocks on semantically rich features aligned with pretrained representations. Additionally, we propose a lightweight Feature Residual Approximation strategy that preserves semantic quality while significantly reducing inference cost. Extensive experiments on ImageNet 256x256 demonstrate that BFM establishes a substantially improved Pareto frontier over existing Flow Matching methods, achieving 2.1x to 4.9x accelerations in inference complexity at comparable generation performance. Code is available at https://github.com/mlvlab/BFM.

---

### Towards Physics-informed Spatial Intelligence with Human Priors: An Autonomous Driving Pilot Study

Authors: Guanlin Wu, Boyan Su, Yang Zhao, Pu Wang, Yichen Lin, Hao Frank Yang
Published: 2025-10-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.21160v1

How to integrate and verify spatial intelligence in foundation models remains an open challenge. Current practice often proxies Visual-Spatial Intelligence (VSI) with purely textual prompts and VQA-style scoring, which obscures geometry, invites linguistic shortcuts, and weakens attribution to genuinely spatial skills. We introduce Spatial Intelligence Grid (SIG): a structured, grid-based schema that explicitly encodes object layouts, inter-object relations, and physically grounded priors. As a complementary channel to text, SIG provides a faithful, compositional representation of scene structure for foundation-model reasoning. Building on SIG, we derive SIG-informed evaluation metrics that quantify a model's intrinsic VSI, which separates spatial capability from language priors. In few-shot in-context learning with state-of-the-art multimodal LLMs (e.g. GPT- and Gemini-family models), SIG yields consistently larger, more stable, and more comprehensive gains across all VSI metrics compared to VQA-only representations, indicating its promise as a data-labeling and training schema for learning VSI. We also release SIGBench, a benchmark of 1.4K driving frames annotated with ground-truth SIG labels and human gaze traces, supporting both grid-based machine VSI tasks and attention-driven, human-like VSI tasks in autonomous-driving scenarios.

---

### Towards Straggler-Resilient Split Federated Learning: An Unbalanced Update Approach

Authors: Dandan Liang, Jianing Zhang, Evan Chen, Zhe Li, Rui Li, Haibo Yang
Published: 2025-10-24
Categories: cs.DC, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.21155v1

Split Federated Learning (SFL) enables scalable training on edge devices by combining the parallelism of Federated Learning (FL) with the computational offloading of Split Learning (SL). Despite its great success, SFL suffers significantly from the well-known straggler issue in distributed learning systems. This problem is exacerbated by the dependency between Split Server and clients: the Split Server side model update relies on receiving activations from clients. Such synchronization requirement introduces significant time latency, making straggler a critical bottleneck to the scalability and efficiency of the system. To mitigate this problem, we propose MU-SplitFed, a straggler-resilient SFL algorithm in zeroth-order optimization that decouples training progress from straggler delays via a simple yet effective unbalanced update mechanism. By enabling the server to perform $τ$ local updates per client round, MU-SplitFed achieves a convergence rate of $O(\sqrt{d/(τT)})$ for non-convex objectives, demonstrating a linear speedup of $τ$ in communication rounds. Experiments demonstrate that MU-SplitFed consistently outperforms baseline methods with the presence of stragglers and effectively mitigates their impact through adaptive tuning of $τ$. The code for this project is available at https://github.com/Johnny-Zip/MU-SplitFed.

---

### Uncertainty-Aware Multi-Objective Reinforcement Learning-Guided Diffusion Models for 3D De Novo Molecular Design

Authors: Lianghong Chen, Dongkyu Eugene Kim, Mike Domaratzki, Pingzhao Hu
Published: 2025-10-24
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.21153v2

Designing de novo 3D molecules with desirable properties remains a fundamental challenge in drug discovery and molecular engineering. While diffusion models have demonstrated remarkable capabilities in generating high-quality 3D molecular structures, they often struggle to effectively control complex multi-objective constraints critical for real-world applications. In this study, we propose an uncertainty-aware Reinforcement Learning (RL) framework to guide the optimization of 3D molecular diffusion models toward multiple property objectives while enhancing the overall quality of the generated molecules. Our method leverages surrogate models with predictive uncertainty estimation to dynamically shape reward functions, facilitating balance across multiple optimization objectives. We comprehensively evaluate our framework across three benchmark datasets and multiple diffusion model architectures, consistently outperforming baselines for molecular quality and property optimization. Additionally, Molecular Dynamics (MD) simulations and ADMET profiling of top generated candidates indicate promising drug-like behavior and binding stability, comparable to known Epidermal Growth Factor Receptor (EGFR) inhibitors. Our results demonstrate the strong potential of RL-guided generative diffusion models for advancing automated molecular design.

---

### String Seed of Thought: Prompting LLMs for Distribution-Faithful and Diverse Generation

Authors: Kou Misaki, Takuya Akiba
Published: 2025-10-24
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.21150v3

We introduce String Seed of Thought (SSoT), a novel prompting method for LLMs that improves Probabilistic Instruction Following (PIF). We define PIF as a task requiring an LLM to select its answer from a predefined set of options, each associated with a specific probability, such that the empirical distribution of the generated answers aligns with the target distribution when prompted multiple times. While LLMs excel at tasks with single, deterministic answers, they often fail at PIF, exhibiting biases problematic for applications requiring non-deterministic behaviors, such as human-behavior simulation, content diversification, and multiplayer games. It also harms the diversity of generated responses, a crucial factor in test-time scaling, by causing the outputs to collapse into a limited set of answers. To address this, we propose SSoT, a simple prompting method that instructs an LLM to first output a random string to generate sufficient entropy. SSoT also instructs the LLM to extract randomness by manipulating this string to derive a final answer, thereby preserving diversity while adhering to specific constraints. We demonstrate that SSoT significantly improves the PIF performance of LLMs, approaching the ideal performance of a pseudo-random number generator. Furthermore, our experiments on NoveltyBench show SSoT's benefits extend beyond closed-set tasks to open-ended tasks by enhancing response diversity.

---

### How to Auto-optimize Prompts for Domain Tasks? Adaptive Prompting and Reasoning through Evolutionary Domain Knowledge Adaptation

Authors: Yang Zhao, Pu Wang, Hao Frank Yang
Published: 2025-10-24
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.21148v1

Designing optimal prompts and reasoning processes for large language models (LLMs) on domain-specific tasks is both necessary and challenging in real-world applications. Determining how to integrate domain knowledge, enhance reasoning efficiency, and even provide domain experts with refined knowledge integration hints are particularly crucial yet unresolved tasks. In this research, we propose Evolutionary Graph Optimization for Prompting (EGO-Prompt), an automated framework to designing better prompts, efficient reasoning processes and providing enhanced causal-informed process. EGO-Prompt begins with a general prompt and fault-tolerant initial Semantic Causal Graph (SCG) descriptions, constructed by human experts, which is then automatically refined and optimized to guide LLM reasoning. Recognizing that expert-defined SCGs may be partial or imperfect and that their optimal integration varies across LLMs, EGO-Prompt integrates a novel causal-guided textual gradient process in two steps: first, generating nearly deterministic reasoning guidance from the SCG for each instance, and second, adapting the LLM to effectively utilize the guidance alongside the original input. The iterative optimization algorithm further refines both the SCG and the reasoning mechanism using textual gradients with ground-truth. We tested the framework on real-world public health, transportation and human behavior tasks. EGO-Prompt achieves 7.32%-12.61% higher F1 than cutting-edge methods, and allows small models to reach the performence of larger models at under 20% of the original cost. It also outputs a refined, domain-specific SCG that improves interpretability.

---

### Hierarchical AI Multi-Agent Fundamental Investing: Evidence from China's A-Share Market

Authors: Chujun He, Zhonghao Huang, Xiangguo Li, Ye Luo, Kewei Ma, Yuxuan Xiong, Xiaowei Zhang, Mingyang Zhao
Published: 2025-10-24
Categories: q-fin.PM, cs.AI
arXiv: https://arxiv.org/abs/2510.21147v1

We present a multi-agent, AI-driven framework for fundamental investing that integrates macro indicators, industry-level and firm-specific information to construct optimized equity portfolios. The architecture comprises: (i) a Macro agent that dynamically screens and weights sectors based on evolving economic indicators and industry performance; (ii) four firm-level agents -- Fundamental, Technical, Report, and News -- that conduct in-depth analyses of individual firms to ensure both breadth and depth of coverage; (iii) a Portfolio agent that uses reinforcement learning to combine the agent outputs into a unified policy to generate the trading strategy; and (iv) a Risk Control agent that adjusts portfolio positions in response to market volatility. We evaluate the system on the constituents by the CSI 300 Index of China's A-share market and find that it consistently outperforms standard benchmarks and a state-of-the-art multi-agent trading system on risk-adjusted returns and drawdown control. Our core contribution is a hierarchical multi-agent design that links top-down macro screening with bottom-up fundamental analysis, offering a robust and extensible approach to factor-based portfolio construction.

---

### NeuroGenPoisoning: Neuron-Guided Attacks on Retrieval-Augmented Generation of LLM via Genetic Optimization of External Knowledge

Authors: Hanyu Zhu, Lance Fiondella, Jiawei Yuan, Kai Zeng, Long Jiao
Published: 2025-10-24
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.21144v2

Retrieval-Augmented Generation (RAG) empowers Large Language Models (LLMs) to dynamically integrate external knowledge during inference, improving their factual accuracy and adaptability. However, adversaries can inject poisoned external knowledge to override the model's internal memory. While existing attacks iteratively manipulate retrieval content or prompt structure of RAG, they largely ignore the model's internal representation dynamics and neuron-level sensitivities. The underlying mechanism of RAG poisoning has not been fully studied and the effect of knowledge conflict with strong parametric knowledge in RAG is not considered. In this work, we propose NeuroGenPoisoning, a novel attack framework that generates adversarial external knowledge in RAG guided by LLM internal neuron attribution and genetic optimization. Our method first identifies a set of Poison-Responsive Neurons whose activation strongly correlates with contextual poisoning knowledge. We then employ a genetic algorithm to evolve adversarial passages that maximally activate these neurons. Crucially, our framework enables massive-scale generation of effective poisoned RAG knowledge by identifying and reusing promising but initially unsuccessful external knowledge variants via observed attribution signals. At the same time, Poison-Responsive Neurons guided poisoning can effectively resolves knowledge conflict. Experimental results across models and datasets demonstrate consistently achieving high Population Overwrite Success Rate (POSR) of over 90% while preserving fluency. Empirical evidence shows that our method effectively resolves knowledge conflict.

---

### PanicToCalm: A Proactive Counseling Agent for Panic Attacks

Authors: Jihyun Lee, Yejin Min, San Kim, Yejin Jeon, SungJun Yang, Hyounghun Kim, Gary Geunbae Lee
Published: 2025-10-24
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.21143v2

Panic attacks are acute episodes of fear and distress, in which timely, appropriate intervention can significantly help individuals regain stability. However, suitable datasets for training such models remain scarce due to ethical and logistical issues. To address this, we introduce PACE, which is a dataset that includes high-distress episodes constructed from first-person narratives, and structured around the principles of Psychological First Aid (PFA). Using this data, we train PACER, a counseling model designed to provide both empathetic and directive support, which is optimized through supervised learning and simulated preference alignment. To assess its effectiveness, we propose PanicEval, a multi-dimensional framework covering general counseling quality and crisis-specific strategies. Experimental results show that PACER outperforms strong baselines in both counselor-side metrics and client affect improvement. Human evaluations further confirm its practical value, with PACER consistently preferred over general, CBT-based, and GPT-4-powered models in panic scenarios (Code is available at https://github.com/JihyunLee1/PanicToCalm ).

---

### TURBOTEST: Learning When Less is Enough through Early Termination of Internet Speed Tests

Authors: Haarika Manda, Manshi Sagar, Yogesh, Kartikay Singh, Cindy Zhao, Tarun Mangla, Phillipa Gill, Elizabeth Belding, Arpit Gupta
Published: 2025-10-24
Categories: cs.NI, cs.LG
arXiv: https://arxiv.org/abs/2510.21141v2

Internet speed tests are indispensable for users, ISPs, and policymakers, but their static flooding-based design imposes growing costs: a single high-speed test can transfer hundreds of MB, and collectively, platforms like Ookla, M-Lab, and Fast.com generate petabytes of traffic each month. Reducing this burden requires deciding when a test can be stopped early without sacrificing accuracy. We frame this as an optimal stopping problem and show that existing heuristics-static thresholds, BBR pipe-full signals, or throughput stability rules from Fast.com and FastBTS-capture only a narrow slice of the achievable accuracy-savings trade-off. This paper introduces TurboTest, a systematic framework for speed test termination that sits atop existing platforms. The key idea is to decouple throughput prediction (Stage 1) from test termination (Stage 2): Stage 1 trains a regressor to estimate final throughput from partial measurements, while Stage 2 trains a classifier to decide when sufficient evidence has accumulated to stop. Leveraging richer transport-level features (RTT, retransmissions, congestion window) alongside throughput, TurboTest exposes a single tunable parameter epsilon for accuracy tolerance and includes a fallback mechanism for high-variability cases. Evaluation on 1 million M-Lab NDT speed tests (2024-2025) shows that TurboTest achieves 1.8-4.4x higher data savings than an approach based on BBR signals while reducing median error. These results demonstrate that adaptive ML-based termination can deliver accurate, efficient, and deployable speed tests at scale.

---

### Digital Contrast CT Pulmonary Angiography Synthesis from Non-contrast CT for Pulmonary Vascular Disease

Authors: Ying Ming, Yue Lin, Longfei Zhao, Gengwan Li, Zuopeng Tan, Bing Li, Sheng Xie, Wei Song, Qiqi Xu
Published: 2025-10-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.21140v1

Computed Tomography Pulmonary Angiography (CTPA) is the reference standard for diagnosing pulmonary vascular diseases such as Pulmonary Embolism (PE) and Chronic Thromboembolic Pulmonary Hypertension (CTEPH). However, its reliance on iodinated contrast agents poses risks including nephrotoxicity and allergic reactions, particularly in high-risk patients. This study proposes a method to generate Digital Contrast CTPA (DCCTPA) from Non-Contrast CT (NCCT) scans using a cascaded synthesizer based on Cycle-Consistent Generative Adversarial Networks (CycleGAN). Totally retrospective 410 paired CTPA and NCCT scans were obtained from three centers. The model was trained and validated internally on 249 paired images. Extra dataset that comprising 161 paired images was as test set for model generalization evaluation and downstream clinical tasks validation. Compared with state-of-the-art (SOTA) methods, the proposed method achieved the best comprehensive performance by evaluating quantitative metrics (For validation, MAE: 156.28, PSNR: 20.71 and SSIM: 0.98; For test, MAE: 165.12, PSNR: 20.27 and SSIM: 0.98) and qualitative visualization, demonstrating valid vessel enhancement, superior image fidelity and structural preservation. The approach was further applied to downstream tasks of pulmonary vessel segmentation and vascular quantification. On the test set, the average Dice, clDice, and clRecall of artery and vein pulmonary segmentation was 0.70, 0.71, 0.73 and 0.70, 0.72, 0.75 respectively, all markedly improved compared with NCCT inputs.\@ Inter-class Correlation Coefficient (ICC) for vessel volume between DCCTPA and CTPA was significantly better than that between NCCT and CTPA (Average ICC : 0.81 vs 0.70), indicating effective vascular enhancement in DCCTPA, especially for small vessels.

---

### Cloud-Fog-Edge Collaborative Computing for Sequential MIoT Workflow: A Two-Tier DDPG-Based Scheduling Framework

Authors: Yuhao Fu, Yinghao Zhang, Yalin Liu, Bishenghui Tao, Junhong Ruan
Published: 2025-10-24
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.21135v1

The Medical Internet of Things (MIoT) demands stringent end-to-end latency guarantees for sequential healthcare workflows deployed over heterogeneous cloud-fog-edge infrastructures. Scheduling these sequential workflows to minimize makespan is an NP-hard problem. To tackle this challenge, we propose a Two-tier DDPG-based scheduling framework that decomposes the scheduling decision into a hierarchical process: a global controller performs layer selection (edge, fog, or cloud), while specialized local controllers handle node assignment within the chosen layer. The primary optimization objective is the minimization of the workflow makespan. Experiments results validate our approach, demonstrating increasingly superior performance over baselines as workflow complexity rises. This trend highlights the frameworks ability to learn effective long-term strategies, which is critical for complex, large-scale MIoT scheduling scenarios.

---

### Quantifying CBRN Risk in Frontier Models

Authors: Divyanshu Kumar, Nitin Aravind Birur, Tanay Baswa, Sahil Agarwal, Prashanth Harshangi
Published: 2025-10-24
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2510.21133v1

Frontier Large Language Models (LLMs) pose unprecedented dual-use risks through the potential proliferation of chemical, biological, radiological, and nuclear (CBRN) weapons knowledge. We present the first comprehensive evaluation of 10 leading commercial LLMs against both a novel 200-prompt CBRN dataset and a 180-prompt subset of the FORTRESS benchmark, using a rigorous three-tier attack methodology. Our findings expose critical safety vulnerabilities: Deep Inception attacks achieve 86.0\% success versus 33.8\% for direct requests, demonstrating superficial filtering mechanisms; Model safety performance varies dramatically from 2\% (claude-opus-4) to 96\% (mistral-small-latest) attack success rates; and eight models exceed 70\% vulnerability when asked to enhance dangerous material properties. We identify fundamental brittleness in current safety alignment, where simple prompt engineering techniques bypass safeguards for dangerous CBRN information. These results challenge industry safety claims and highlight urgent needs for standardized evaluation frameworks, transparent safety metrics, and more robust alignment techniques to mitigate catastrophic misuse risks while preserving beneficial capabilities.

---

### Large Language Models Meet Text-Attributed Graphs: A Survey of Integration Frameworks and Applications

Authors: Guangxin Su, Hanchen Wang, Jianwei Wang, Wenjie Zhang, Ying Zhang, Jian Pei
Published: 2025-10-24
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.21131v1

Large Language Models (LLMs) have achieved remarkable success in natural language processing through strong semantic understanding and generation. However, their black-box nature limits structured and multi-hop reasoning. In contrast, Text-Attributed Graphs (TAGs) provide explicit relational structures enriched with textual context, yet often lack semantic depth. Recent research shows that combining LLMs and TAGs yields complementary benefits: enhancing TAG representation learning and improving the reasoning and interpretability of LLMs. This survey provides the first systematic review of LLM--TAG integration from an orchestration perspective. We introduce a novel taxonomy covering two fundamental directions: LLM for TAG, where LLMs enrich graph-based tasks, and TAG for LLM, where structured graphs improve LLM reasoning. We categorize orchestration strategies into sequential, parallel, and multi-module frameworks, and discuss advances in TAG-specific pretraining, prompting, and parameter-efficient fine-tuning. Beyond methodology, we summarize empirical insights, curate available datasets, and highlight diverse applications across recommendation systems, biomedical analysis, and knowledge-intensive question answering. Finally, we outline open challenges and promising research directions, aiming to guide future work at the intersection of language and graph learning.

---

### SolarBoost: Distributed Photovoltaic Power Forecasting Amid Time-varying Grid Capacity

Authors: Linyuan Geng, Linxiao Yang, Xinyue Gu, Liang Sun
Published: 2025-10-24
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.21129v1

This paper presents SolarBoost, a novel approach for forecasting power output in distributed photovoltaic (DPV) systems. While existing centralized photovoltaic (CPV) methods are able to precisely model output dependencies due to uniformity, it is difficult to apply such techniques to DPV systems, as DPVs face challenges such as missing grid-level data, temporal shifts in installed capacity, geographic variability, and panel diversity. SolarBoost overcomes these challenges by modeling aggregated power output as a composite of output from small grids, where each grid output is modeled using a unit output function multiplied by its capacity. This approach decouples the homogeneous unit output function from dynamic capacity for accurate prediction. Efficient algorithms over an upper-bound approximation are proposed to overcome computational bottlenecks in loss functions. We demonstrate the superiority of grid-level modeling via theoretical analysis and experiments. SolarBoost has been validated through deployment across various cities in China, significantly reducing potential losses and provides valuable insights for the operation of power grids. The code for this work is available at https://github.com/DAMO-DI-ML/SolarBoost.

---