# Research Papers — 2025-10 · bundle page 93 of 217

> Full-text markdown of papers #4601–4650 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/93
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/92.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/94.md)

### Evaluating Prompting Strategies and Large Language Models in Systematic Literature Review Screening: Relevance and Task-Stage Classification

Authors: Binglan Han, Anuradha Mathrani, Teo Susnjak
Published: 2025-10-17
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.16091v1

This study quantifies how prompting strategies interact with large language models (LLMs) to automate the screening stage of systematic literature reviews (SLRs). We evaluate six LLMs (GPT-4o, GPT-4o-mini, DeepSeek-Chat-V3, Gemini-2.5-Flash, Claude-3.5-Haiku, Llama-4-Maverick) under five prompt types (zero-shot, few-shot, chain-of-thought (CoT), CoT-few-shot, self-reflection) across relevance classification and six Level-2 tasks, using accuracy, precision, recall, and F1. Results show pronounced model-prompt interaction effects: CoT-few-shot yields the most reliable precision-recall balance; zero-shot maximizes recall for high-sensitivity passes; and self-reflection underperforms due to over-inclusivity and instability across models. GPT-4o and DeepSeek provide robust overall performance, while GPT-4o-mini performs competitively at a substantially lower dollar cost. A cost-performance analysis for relevance classification (per 1,000 abstracts) reveals large absolute differences among model-prompt pairings; GPT-4o-mini remains low-cost across prompts, and structured prompts (CoT/CoT-few-shot) on GPT-4o-mini offer attractive F1 at a small incremental cost. We recommend a staged workflow that (1) deploys low-cost models with structured prompts for first-pass screening and (2) escalates only borderline cases to higher-capacity models. These findings highlight LLMs' uneven but promising potential to automate literature screening. By systematically analyzing prompt-model interactions, we provide a comparative benchmark and practical guidance for task-adaptive LLM deployment.

---

### STABLE: Gated Continual Learning for Large Language Models

Authors: William Hoy, Nurcin Celik
Published: 2025-10-17
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.16089v1

Large language models (LLMs) increasingly require mechanisms for continual adaptation without full retraining. However, sequential updates can lead to catastrophic forgetting, where new edits degrade previously acquired knowledge. This work presents STABLE, a gated continual self editing framework that constrains forgetting during sequential updates using parameter efficient fine tuning via Low Rank Adaptation (LoRA; see arXiv:2106.09685). Each candidate edit is evaluated against a stability budget using one of three metrics: (i) Exact Match (EM) drop, capturing factual accuracy loss; (ii) bits increase, reflecting reduced model confidence; and (iii) KL divergence, quantifying distributional drift between the base and adapted models. If a threshold is exceeded, the LoRA update is rescaled through a clipping procedure or rejected. Experiments on the Qwen-2.5-7B model show that gating effectively mitigates forgetting while preserving adaptability. EM based gating achieved the highest cumulative performance in short continual learning sequences. Our results show that different gating strategies can achieve comparable distribution shift (measured by KL divergence) while producing different accuracy outcomes, highlighting the importance of gating design in continual adaptation. This approach offers a principled method for continual model editing, enabling LLMs to integrate new knowledge while maintaining reliability. Code: https://github.com/Bhoy1/STABLE

---

### FSRF: Factorization-guided Semantic Recovery for Incomplete Multimodal Sentiment Analysis

Authors: Ziyang Liu, Pengjunfei Chu, Shuming Dong, Chen Zhang, Mingcheng Li, Jin Wang
Published: 2025-10-17
Categories: cs.LG, stat.AP
arXiv: https://arxiv.org/abs/2510.16086v1

In recent years, Multimodal Sentiment Analysis (MSA) has become a research hotspot that aims to utilize multimodal data for human sentiment understanding. Previous MSA studies have mainly focused on performing interaction and fusion on complete multimodal data, ignoring the problem of missing modalities in real-world applications due to occlusion, personal privacy constraints, and device malfunctions, resulting in low generalizability. To this end, we propose a Factorization-guided Semantic Recovery Framework (FSRF) to mitigate the modality missing problem in the MSA task. Specifically, we propose a de-redundant homo-heterogeneous factorization module that factorizes modality into modality-homogeneous, modality-heterogeneous, and noisy representations and design elaborate constraint paradigms for representation learning. Furthermore, we design a distribution-aligned self-distillation module that fully recovers the missing semantics by utilizing bidirectional knowledge transfer. Comprehensive experiments on two datasets indicate that FSRF has a significant performance advantage over previous methods with uncertain missing modalities.

---

### MoPHES:Leveraging on-device LLMs as Agent for Mobile Psychological Health Evaluation and Support

Authors: Xun Wei, Pukai Zhou, Zeyu Wang
Published: 2025-10-17
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2510.16085v1

The 2022 World Mental Health Report calls for global mental health care reform, amid rising prevalence of issues like anxiety and depression that affect nearly one billion people worldwide. Traditional in-person therapy fails to meet this demand, and the situation is worsened by stigma. While general-purpose large language models (LLMs) offer efficiency for AI-driven mental health solutions, they underperform because they lack specialized fine-tuning. Existing LLM-based mental health chatbots can engage in empathetic conversations, but they overlook real-time user mental state assessment which is critical for professional counseling. This paper proposes MoPHES, a framework that integrates mental state evaluation, conversational support, and professional treatment recommendations. The agent developed under this framework uses two fine-tuned MiniCPM4-0.5B LLMs: one is fine-tuned on mental health conditions datasets to assess users' mental states and predict the severity of anxiety and depression; the other is fine-tuned on multi-turn dialogues to handle conversations with users. By leveraging insights into users' mental states, our agent provides more tailored support and professional treatment recommendations. Both models are also deployed directly on mobile devices to enhance user convenience and protect user privacy. Additionally, to evaluate the performance of MoPHES with other LLMs, we develop a benchmark for the automatic evaluation of mental state prediction and multi-turn counseling dialogues, which includes comprehensive evaluation metrics, datasets, and methods.

---

### Near-Equilibrium Propagation training in nonlinear wave systems

Authors: Karol Sajnok, Michał Matuszewski
Published: 2025-10-17
Categories: cs.LG, cond-mat.quant-gas, math-ph, physics.optics, quant-ph
arXiv: https://arxiv.org/abs/2510.16084v3

Backpropagation learning algorithm, the workhorse of modern artificial intelligence, is notoriously difficult to implement in physical neural networks. Equilibrium Propagation (EP) is an alternative with comparable efficiency and strong potential for in-situ training. We extend EP learning to both discrete and continuous complex-valued wave systems. In contrast to previous EP implementations, our scheme is valid in the weakly dissipative regime, and readily applicable to a wide range of physical settings, even without well defined nodes, where trainable inter-node connections can be replaced by trainable local potential. We test the method in driven-dissipative exciton-polariton condensates governed by generalized Gross-Pitaevskii dynamics. Numerical studies on standard benchmarks, including a simple logical task and handwritten-digit recognition, demonstrate stable convergence, establishing a practical route to in-situ learning in physical systems in which system control is restricted to local parameters.

---

### PassREfinder-FL: Privacy-Preserving Credential Stuffing Risk Prediction via Graph-Based Federated Learning for Representing Password Reuse between Websites

Authors: Jaehan Kim, Minkyoo Song, Minjae Seo, Youngjin Jin, Seungwon Shin, Jinwoo Kim
Published: 2025-10-17
Categories: cs.LG, cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2510.16083v1

Credential stuffing attacks have caused significant harm to online users who frequently reuse passwords across multiple websites. While prior research has attempted to detect users with reused passwords or identify malicious login attempts, existing methods often compromise usability by restricting password creation or website access, and their reliance on complex account-sharing mechanisms hinders real-world deployment. To address these limitations, we propose PassREfinder-FL, a novel framework that predicts credential stuffing risks across websites. We introduce the concept of password reuse relations -- defined as the likelihood of users reusing passwords between websites -- and represent them as edges in a website graph. Using graph neural networks (GNNs), we perform a link prediction task to assess credential reuse risk between sites. Our approach scales to a large number of arbitrary websites by incorporating public website information and linking newly observed websites as nodes in the graph. To preserve user privacy, we extend PassREfinder-FL with a federated learning (FL) approach that eliminates the need to share user sensitive information across administrators. Evaluation on a real-world dataset of 360 million breached accounts from 22,378 websites shows that PassREfinder-FL achieves an F1-score of 0.9153 in the FL setting. We further validate that our FL-based GNN achieves a 4-11% performance improvement over other state-of-the-art GNN models through an ablation study. Finally, we demonstrate that the predicted results can be used to quantify password reuse likelihood as actionable risk scores.

---

### BIOGEN: Evidence-Grounded Multi-Agent Reasoning Framework for Transcriptomic Interpretation in Antimicrobial Resistance

Authors: Elias Hossain, Mehrdad Shoeibi, Ivan Garibay, Niloofar Yousefi
Published: 2025-10-17
Categories: q-bio.QM, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.16082v5

Interpreting gene clusters from RNA sequencing (RNA-seq) remains challenging, especially in antimicrobial resistance studies where mechanistic insight is important for hypothesis generation. Existing pathway enrichment methods can summarize co-expressed modules, but they often provide limited cluster-specific explanations and weak connections to supporting literature. We present BIOGEN, an evidence-grounded multi-agent framework for post hoc interpretation of RNA-seq transcriptional modules. BIOGEN combines biomedical retrieval, structured reasoning, and multi-critic verification to generate traceable cluster-level explanations with explicit evidence and confidence labels. On a primary Salmonella enterica dataset, BIOGEN achieved strong biological grounding, including BERTScore 0.689, Semantic Alignment Score 0.715, KEGG Functional Similarity 0.342, and a hallucination rate of 0.000, compared with 0.100 for an LLM-only baseline. Across four additional bacterial RNA-seq datasets, BIOGEN also maintained zero hallucination under the same fixed pipeline. In comparisons with representative open-source agentic AI baselines, BIOGEN was the only framework that consistently preserved zero hallucination across all five datasets. These findings suggest that retrieval alone is not enough for reliable biological interpretation, and that evidence-grounded orchestration is important for transparent and source-traceable transcriptomic reasoning.

---

### SARHAchat: An LLM-Based Chatbot for Sexual and Reproductive Health Counseling

Authors: Jiaye Yang, Xinyu Zhao, Tianlong Chen, Kandyce Brennan
Published: 2025-10-17
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2510.16081v1

While Artificial Intelligence (AI) shows promise in healthcare applications, existing conversational systems often falter in complex and sensitive medical domains such as Sexual and Reproductive Health (SRH). These systems frequently struggle with hallucination and lack the specialized knowledge required, particularly for sensitive SRH topics. Furthermore, current AI approaches in healthcare tend to prioritize diagnostic capabilities over comprehensive patient care and education. Addressing these gaps, this work at the UNC School of Nursing introduces SARHAchat, a proof-of-concept Large Language Model (LLM)-based chatbot. SARHAchat is designed as a reliable, user-centered system integrating medical expertise with empathetic communication to enhance SRH care delivery. Our evaluation demonstrates SARHAchat's ability to provide accurate and contextually appropriate contraceptive counseling while maintaining a natural conversational flow. The demo is available at https://sarhachat.com/}{https://sarhachat.com/.

---

### TriAgent: Automated Biomarker Discovery with Deep Research Grounding for Triage in Acute Care by LLM-Based Multi-Agent Collaboration

Authors: Kerem Delikoyun, Qianyu Chen, Win Sen Kuan, John Tshon Yit Soong, Matthew Edward Cove, Oliver Hayden
Published: 2025-10-17
Categories: q-bio.QM, cs.AI
arXiv: https://arxiv.org/abs/2510.16080v1

Emergency departments worldwide face rising patient volumes, workforce shortages, and variability in triage decisions that threaten the delivery of timely and accurate care. Current triage methods rely primarily on vital signs, routine laboratory values, and clinicians' judgment, which, while effective, often miss emerging biological signals that could improve risk prediction for infection typing or antibiotic administration in acute conditions. To address this challenge, we introduce TriAgent, a large language model (LLM)-based multi-agent framework that couples automated biomarker discovery with deep research for literature-grounded validation and novelty assessment. TriAgent employs a supervisor research agent to generate research topics and delegate targeted queries to specialized sub-agents for evidence retrieval from various data sources. Findings are synthesized to classify biomarkers as either grounded in existing knowledge or flagged as novel candidates, offering transparent justification and highlighting unexplored pathways in acute care risk stratification. Unlike prior frameworks limited to existing routine clinical biomarkers, TriAgent aims to deliver an end-to-end framework from data analysis to literature grounding to improve transparency, explainability and expand the frontier of potentially actionable clinical biomarkers. Given a user's clinical query and quantitative triage data, TriAgent achieved a topic adherence F1 score of 55.7 +/- 5.0%, surpassing the CoT-ReAct agent by over 10%, and a faithfulness score of 0.42 +/- 0.39, exceeding all baselines by more than 50%. Across experiments, TriAgent consistently outperformed state-of-the-art LLM-based agentic frameworks in biomarker justification and literature-grounded novelty assessment. We share our repo: https://github.com/CellFace/TriAgent.

---

### EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecycle

Authors: Rong Wu, Xiaoman Wang, Jianbiao Mei, Pinlong Cai, Daocheng Fu, Cheng Yang, Licheng Wen, Xuemeng Yang, Yufan Shen, Yuxin Wang, Botian Shi
Published: 2025-10-17
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.16079v3

Current Large Language Model (LLM) agents show strong performance in tool use, but lack the crucial capability to systematically learn from their own experiences. While existing frameworks mainly focus on mitigating external knowledge gaps, they fail to address a more fundamental limitation: the inability to iteratively refine problem-solving strategies. In this work, we introduce EvolveR, a framework designed to enable agent to self-improve through a complete, closed-loop experience lifecycle. This lifecycle comprises two key stages: (1) Offline Self-Distillation, where the agent's interaction trajectories are synthesized into a structured repository of abstract, reusable strategic principles; (2) Online Interaction, where the agent interacts with tasks and actively retrieves distilled principles to guide its decision-making, accumulating a diverse set of behavioral trajectories. This loop employs a policy reinforcement mechanism to iteratively update the agent based on its performance. We demonstrate the effectiveness of EvolveR on complex multi-hop question-answering benchmarks, where it achieves superior performance over strong agentic baselines. Our work presents a comprehensive blueprint for agents that learn not only from external data but also from the consequences of their own actions, paving the way for more autonomous and continuously improving systems. Code is available at https://github.com/Edaizi/EvolveR.

---

### ISO/IEC-Compliant Match-on-Card Face Verification with Short Binary Templates

Authors: Abdelilah Ganmati, Karim Afdel, Lahcen Koutti
Published: 2025-10-17
Categories: cs.CR, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2510.16078v1

We present a practical match-on-card design for face verification in which compact 64/128-bit templates are produced off-card by PCA-ITQ and compared on-card via constant-time Hamming distance. We specify ISO/IEC 7816-4 and 14443-4 command APDUs with fixed-length payloads and decision-only status words (no score leakage), together with a minimal per-identity EEPROM map. Using real binary codes from a CelebA working set (55 identities, 412 images), we (i) derive operating thresholds from ROC/DET, (ii) replay enroll->verify transactions at those thresholds, and (iii) bound end-to-end time by pure link latency plus a small constant on-card budget. Even at the slowest contact rate (9.6 kbps), total verification time is 43.9 ms (64 b) and 52.3 ms (128 b); at 38.4 kbps both are <14 ms. At FAR = 1%, both code lengths reach TPR = 0.836, while 128 b lowers EER relative to 64 b. An optional +6 B helper (targeted symbol-level parity over empirically unstable bits) is latency-negligible. Overall, short binary templates, fixed-payload decision-only APDUs, and constant-time matching satisfy ISO/IEC transport constraints with wide timing margin and align with ISO/IEC 24745 privacy goals. Limitations: single-dataset evaluation and design-level (pre-hardware) timing; we outline AgeDB/CFP-FP and on-card microbenchmarks as next steps.

---

### Continual Knowledge Consolidation LORA for Domain Incremental Learning

Authors: Naeem Paeedeh, Mahardhika Pratama, Weiping Ding, Jimmy Cao, Wolfgang Mayer, Ryszard Kowalczyk, Ary Shiddiqi
Published: 2025-10-17
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.16077v2

Domain Incremental Learning (DIL) is a sub-branch of continual learning that aims to address the never-ending arrival of new domains without catastrophic forgetting. Despite the advent of parameter-efficient fine-tuning (PEFT) approaches, prior works create task-specific LoRAs that overlook shared knowledge across tasks. Inaccurate selection of task-specific LoRAs during inference leads to significant drops in accuracy, while existing works rely on linear or prototype-based classifiers, which have suboptimal generalization powers. Our paper proposes continual knowledge consolidation low-rank adaptation (CONEC-LoRA) addressing the DIL problems. CONEC-LoRA is developed from consolidations between task-shared LORA to extract common knowledge and task-specific LORA to incorporate domain-specific knowledge. Unlike existing approaches, CONEC-LoRA integrates the concept of a stochastic classifier whose parameters are sampled from a distribution, thus enhancing the likelihood of correct classifications. Last but not least, an auxiliary network is deployed to optimally predict the task-specific LoRAs for inference and implements the concept of a different-depth network structure in which every layer is connected with a local classifier to leverage intermediate representations. This module integrates the ball-generator loss and transformation module to address the synthetic sample bias problem. Our rigorous experiments demonstrate the advantage of CONEC-LoRA over prior art on 4 popular benchmark problems with over 5% margins.

---

### BPL: Bias-adaptive Preference Distillation Learning for Recommender System

Authors: SeongKu Kang, Jianxun Lian, Dongha Lee, Wonbin Kweon, Sanghwan Jang, Jaehyun Lee, Jindong Wang, Xing Xie, Hwanjo Yu
Published: 2025-10-17
Categories: cs.LG, cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2510.16076v1

Recommender systems suffer from biases that cause the collected feedback to incompletely reveal user preference. While debiasing learning has been extensively studied, they mostly focused on the specialized (called counterfactual) test environment simulated by random exposure of items, significantly degrading accuracy in the typical (called factual) test environment based on actual user-item interactions. In fact, each test environment highlights the benefit of a different aspect: the counterfactual test emphasizes user satisfaction in the long-terms, while the factual test focuses on predicting subsequent user behaviors on platforms. Therefore, it is desirable to have a model that performs well on both tests rather than only one. In this work, we introduce a new learning framework, called Bias-adaptive Preference distillation Learning (BPL), to gradually uncover user preferences with dual distillation strategies. These distillation strategies are designed to drive high performance in both factual and counterfactual test environments. Employing a specialized form of teacher-student distillation from a biased model, BPL retains accurate preference knowledge aligned with the collected feedback, leading to high performance in the factual test. Furthermore, through self-distillation with reliability filtering, BPL iteratively refines its knowledge throughout the training process. This enables the model to produce more accurate predictions across a broader range of user-item combinations, thereby improving performance in the counterfactual test. Comprehensive experiments validate the effectiveness of BPL in both factual and counterfactual tests. Our implementation is accessible via: https://github.com/SeongKu-Kang/BPL.

---

### Optimization of the quantization of dense neural networks from an exact QUBO formulation

Authors: Sergio Muñiz Subiñas, Manuel L. González, Jorge Ruiz Gómez, Alejandro Mata Ali, Jorge Martínez Martín, Miguel Franco Hernando, Ángel Miguel García-Vico
Published: 2025-10-17
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.16075v1

This work introduces a post-training quantization (PTQ) method for dense neural networks via a novel ADAROUND-based QUBO formulation. Using the Frobenius distance between the theoretical output and the dequantized output (before the activation function) as the objective, an explicit QUBO whose binary variables represent the rounding choice for each weight and bias is obtained. Additionally, by exploiting the structure of the coefficient QUBO matrix, the global problem can be exactly decomposed into $n$ independent subproblems of size $f+1$, which can be efficiently solved using some heuristics such as simulated annealing. The approach is evaluated on MNIST, Fashion-MNIST, EMNIST, and CIFAR-10 across integer precisions from int8 to int1 and compared with a round-to-nearest traditional quantization methodology.

---

### Early-stopping for Transformer model training

Authors: Jing He, Hua Jiang, Cheng Li, Siqian Xin, Shuzhen Yang
Published: 2025-10-17
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.16074v2

This work, based on Random Matrix Theory (RMT), introduces a novel early-stopping strategy for Transformer training dynamics. Utilizing the Power Law (PL) fit to tansformer attention matrices as a probe, we demarcate training into three stages: structural exploration, heavy-tailed structure stabilization, and convergence saturation. Empirically, we observe that the spectral density of the shallow self-attention matrix $V$ consistently evolves into a heavy-tailed distribution. Crucially, we propose two consistent and validation-set-free criteria: a quantitative metric for heavy-tailed dynamics and a novel spectral signature indicative of convergence. The strong alignment between these criteria highlights the utility of RMT for monitoring and diagnosing the progression of Transformer model training.

---

### Data-Driven Analysis of Intersectional Bias in Image Classification: A Framework with Bias-Weighted Augmentation

Authors: Farjana Yesmin
Published: 2025-10-17
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.16072v1

Machine learning models trained on imbalanced datasets often exhibit intersectional biases-systematic errors arising from the interaction of multiple attributes such as object class and environmental conditions. This paper presents a data-driven framework for analyzing and mitigating such biases in image classification. We introduce the Intersectional Fairness Evaluation Framework (IFEF), which combines quantitative fairness metrics with interpretability tools to systematically identify bias patterns in model predictions. Building on this analysis, we propose Bias-Weighted Augmentation (BWA), a novel data augmentation strategy that adapts transformation intensities based on subgroup distribution statistics. Experiments on the Open Images V7 dataset with five object classes demonstrate that BWA improves accuracy for underrepresented class-environment intersections by up to 24 percentage points while reducing fairness metric disparities by 35%. Statistical analysis across multiple independent runs confirms the significance of improvements (p < 0.05). Our methodology provides a replicable approach for analyzing and addressing intersectional biases in image classification systems.

---

### MNO: Multiscale Neural Operator for 3D Computational Fluid Dynamics

Authors: Qinxuan Wang, Chuang Wang, Mingyu Zhang, Jingwei Sun, Peipei Yang, Shuo Tang, Shiming Xiang
Published: 2025-10-17
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.16071v2

Neural operators have emerged as a powerful data-driven paradigm for solving partial differential equations (PDEs), while their accuracy and scalability are still limited, particularly on irregular domains where fluid flows exhibit rich multiscale structures. In this work, we introduce the Multiscale Neural Operator (MNO), a new architecture for computational fluid dynamics (CFD) on 3D unstructured point clouds. MNO explicitly decomposes information across three scales: a global dimension-shrinkage attention module for long-range dependencies, a local graph attention module for neighborhood-level interactions, and a micro point-wise attention module for fine-grained details. This design preserves multiscale inductive biases while remaining computationally efficient. We evaluate MNO on diverse benchmarks, covering steady-state and unsteady flow scenarios with up to 300k points. Across all tasks, MNO consistently outperforms state-of-the-art baselines, reducing prediction errors by 5% to 50%. The results highlight the importance of explicit multiscale design for neural operators and establish MNO as a scalable framework for learning complex fluid dynamics on irregular domains.

---

### Effect of Reporting Mode and Clinical Experience on Radiologists' Gaze and Image Analysis Behavior in Chest Radiography

Authors: Mahta Khoobi, Marc Sebastian von der Stueck, Felix Barajas Ordonez, Anca-Maria Iancu, Eric Corban, Julia Nowak, Aleksandar Kargaliev, Valeria Perelygina, Anna-Sophie Schott, Daniel Pinto dos Santos, Christiane Kuhl, Daniel Truhn et al.
Published: 2025-10-17
Categories: cs.CV, cs.AI, cs.HC, eess.IV
arXiv: https://arxiv.org/abs/2510.16070v1

Structured reporting (SR) and artificial intelligence (AI) may transform how radiologists interact with imaging studies. This prospective study (July to December 2024) evaluated the impact of three reporting modes: free-text (FT), structured reporting (SR), and AI-assisted structured reporting (AI-SR), on image analysis behavior, diagnostic accuracy, efficiency, and user experience. Four novice and four non-novice readers (radiologists and medical students) each analyzed 35 bedside chest radiographs per session using a customized viewer and an eye-tracking system. Outcomes included diagnostic accuracy (compared with expert consensus using Cohen's $κ$), reporting time per radiograph, eye-tracking metrics, and questionnaire-based user experience. Statistical analysis used generalized linear mixed models with Bonferroni post-hoc tests with a significance level of ($P \le .01$). Diagnostic accuracy was similar in FT ($κ= 0.58$) and SR ($κ= 0.60$) but higher in AI-SR ($κ= 0.71$, $P < .001$). Reporting times decreased from $88 \pm 38$ s (FT) to $37 \pm 18$ s (SR) and $25 \pm 9$ s (AI-SR) ($P < .001$). Saccade counts for the radiograph field ($205 \pm 135$ (FT), $123 \pm 88$ (SR), $97 \pm 58$ (AI-SR)) and total fixation duration for the report field ($11 \pm 5$ s (FT), $5 \pm 3$ s (SR), $4 \pm 1$ s (AI-SR)) were lower with SR and AI-SR ($P < .001$ each). Novice readers shifted gaze towards the radiograph in SR, while non-novice readers maintained their focus on the radiograph. AI-SR was the preferred mode. In conclusion, SR improves efficiency by guiding visual attention toward the image, and AI-prefilled SR further enhances diagnostic accuracy and user satisfaction.

---

### Human or AI? Comparing Design Thinking Assessments by Teaching Assistants and Bots

Authors: Sumbul Khan, Wei Ting Liow, Lay Kee Ang
Published: 2025-10-17
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2510.16069v2

As design thinking education grows in secondary and tertiary contexts, educators face the challenge of evaluating creative artefacts that combine visual and textual elements. Traditional rubric-based assessment is laborious, time-consuming, and inconsistent due to reliance on Teaching Assistants (TA) in large, multi-section cohorts. This paper presents an exploratory study investigating the reliability and perceived accuracy of AI-assisted assessment compared to TA-assisted assessment in evaluating student posters in design thinking education. Two activities were conducted with 33 Ministry of Education (MOE) Singapore school teachers to (1) compare AI-generated scores with TA grading across three key dimensions: empathy and user understanding, identification of pain points and opportunities, and visual communication, and (2) examine teacher preferences for AI-assigned, TA-assigned, and hybrid scores. Results showed low statistical agreement between instructor and AI scores for empathy and pain points, with slightly higher alignment for visual communication. Teachers preferred TA-assigned scores in six of ten samples. Qualitative feedback highlighted the potential of AI for formative feedback, consistency, and student self-reflection, but raised concerns about its limitations in capturing contextual nuance and creative insight. The study underscores the need for hybrid assessment models that integrate computational efficiency with human insights. This research contributes to the evolving conversation on responsible AI adoption in creative disciplines, emphasizing the balance between automation and human judgment for scalable and pedagogically sound assessment.

---

### Co-Designing Interdisciplinary Design Projects with AI

Authors: Wei Ting Liow, Sumbul Khan, Lay Kee Ang
Published: 2025-10-17
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2510.16068v1

Creating interdisciplinary design projects is time-consuming and cognitively demanding for teachers, requiring curriculum alignment, cross-subject integration, and careful sequencing. International research reports increasing teacher use of AI alongside persistent workload pressures, underscoring the need for planning support. This paper presents the Interdisciplinary Design Project Planner (IDPplanner), a GPT-based planning assistant grounded in Design Innovation principles, alignment with Singapore secondary school syllabuses, and 21st-century competencies. In a within-subject, counterbalanced workshop with 33 in-service teachers, participants produced two versions of the same project: manual and AI-assisted, followed by self- and peer-evaluations using a six-dimensional rubric. The AI-assisted version received higher scores for Curriculum Alignment, Design Thinking Application, and Coherence and Flow, with a marginal advantage for Assessment Strategies. Teacher reflections indicated that AI-assisted planning improved structure, sequencing, and idea generation, while contextualization to local syllabuses, class profiles, and student needs remained teacher-led. Contributions include a purpose-built planning tool that organizes ideas into a ten-component flow with ready-to-adapt prompts, templates, and assessment suggestions; an empirical, rubric-based comparison of planning quality; and evidence that AI can function as a pedagogical planning partner. Recommendations emphasize hybrid teacher-AI workflows to enhance curriculum alignment and reduce planning complexity, and design suggestions for developers to strengthen contextual customization, iterative design support, and localized rubrics. Although instantiated with a Singapore-based curriculum, the planning flow and rubric are framework-agnostic and can be parameterized for other systems.

---

### AI-BAAM: AI-Driven Bank Statement Analytics as Alternative Data for Malaysian MSME Credit Scoring

Authors: Chun Chet Ng, Zhen Hao Chu, Jia Yu Lim, Yin Yin Boon, Wei Zeng Low, Jin Khye Tan
Published: 2025-10-17
Categories: q-fin.ST, cs.AI, cs.CE, cs.CY, cs.LG, q-fin.RM
arXiv: https://arxiv.org/abs/2510.16066v4

Despite accounting for 96.1% of all businesses in Malaysia, access to financing remains one of the most persistent challenges faced by Micro, Small, and Medium Enterprises (MSMEs). Newly established businesses are often excluded from formal credit markets as traditional underwriting approaches rely heavily on credit bureau data. This study investigates the potential of bank statement data as an alternative data source for credit assessment to promote financial inclusion in emerging markets. First, we propose a cash flow-based underwriting pipeline where we utilize bank statement data for end-to-end data extraction and machine learning credit scoring. Second, we introduce a novel dataset of 611 loan applicants from a Malaysian consulting firm. Third, we develop and evaluate credit scoring models based on application information and bank transaction-derived features. Empirical results demonstrate that incorporating bank statement features yields substantial improvements, with our best model achieving an AUROC of 0.806 on validation set, representing a 24.6% improvement over models using application information only. Finally, we will release the anonymized bank transaction dataset to facilitate further research on MSME financial inclusion within Malaysia's emerging economy.

---

### FedPURIN: Programmed Update and Reduced INformation for Sparse Personalized Federated Learning

Authors: Lunchen Xie, Zehua He, Qingjiang Shi
Published: 2025-10-17
Categories: cs.LG, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2510.16065v1

Personalized Federated Learning (PFL) has emerged as a critical research frontier addressing data heterogeneity issue across distributed clients. Novel model architectures and collaboration mechanisms are engineered to accommodate statistical disparities while producing client-specific models. Parameter decoupling represents a promising paradigm for maintaining model performance in PFL frameworks. However, the communication efficiency of many existing methods remains suboptimal, sustaining substantial communication burdens that impede practical deployment. To bridge this gap, we propose Federated Learning with Programmed Update and Reduced INformation (FedPURIN), a novel framework that strategically identifies critical parameters for transmission through an integer programming formulation. This mathematically grounded strategy is seamlessly integrated into a sparse aggregation scheme, achieving a significant communication reduction while preserving the efficacy. Comprehensive evaluations on standard image classification benchmarks under varied non-IID conditions demonstrate competitive performance relative to state-of-the-art methods, coupled with quantifiable communication reduction through sparse aggregation. The framework establishes a new paradigm for communication-efficient PFL, particularly advantageous for edge intelligence systems operating with heterogeneous data sources.

---

### Residual Correction Models for AC Optimal Power Flow Using DC Optimal Power Flow Solutions

Authors: Muhy Eddin Za'ter, Bri-Mathias Hodge, Kyri Baker
Published: 2025-10-17
Categories: cs.LG, cs.AI, eess.SY
arXiv: https://arxiv.org/abs/2510.16064v1

Solving the nonlinear AC optimal power flow (AC OPF) problem remains a major computational bottleneck for real-time grid operations. In this paper, we propose a residual learning paradigm that uses fast DC optimal power flow (DC OPF) solutions as a baseline, and learns only the nonlinear corrections required to provide the full AC-OPF solution. The method utilizes a topology-aware Graph Neural Network with local attention and two-level DC feature integration, trained using a physics-informed loss that enforces AC power-flow feasibility and operational limits. Evaluations on OPFData for 57-, 118-, and 2000-bus systems show around 25% lower MSE, up to 3X reduction in feasibility error, and up to 13X runtime speedup compared to conventional AC OPF solvers. The model maintains accuracy under N-1 contingencies and scales efficiently to large networks. These results demonstrate that residual learning is a practical and scalable bridge between linear approximations and AC-feasible OPF, enabling near real-time operational decision making.

---

### Learning a Generalized Model for Substation Level Voltage Estimation in Distribution Networks

Authors: Muhy Eddin Za'ter, Bri-Mathias Hodge
Published: 2025-10-17
Categories: cs.LG, cs.AI, eess.SY
arXiv: https://arxiv.org/abs/2510.16063v1

Accurate voltage estimation in distribution networks is critical for real-time monitoring and increasing the reliability of the grid. As DER penetration and distribution level voltage variability increase, robust distribution system state estimation (DSSE) has become more essential to maintain safe and efficient operations. Traditional DSSE techniques, however, struggle with sparse measurements and the scale of modern feeders, limiting their scalability to large networks. This paper presents a hierarchical graph neural network for substation-level voltage estimation that exploits both electrical topology and physical features, while remaining robust to the low observability levels common to real-world distribution networks. Leveraging the public SMART-DS datasets, the model is trained and evaluated on thousands of buses across multiple substations and DER penetration scenarios. Comprehensive experiments demonstrate that the proposed method achieves up to 2 times lower RMSE than alternative data-driven models, and maintains high accuracy with as little as 1\% measurement coverage. The results highlight the potential of GNNs to enable scalable, reproducible, and data-driven voltage monitoring for distribution systems.

---

### Can LLMs Correct Themselves? A Benchmark of Self-Correction in LLMs

Authors: Guiyao Tie, Zenghui Yuan, Zeli Zhao, Chaoran Hu, Tianhe Gu, Ruihang Zhang, Sizhe Zhang, Junran Wu, Xiaoyue Tu, Ming Jin, Qingsong Wen, Lixing Chen et al.
Published: 2025-10-17
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.16062v2

Self-correction of large language models (LLMs) emerges as a critical component for enhancing their reasoning performance. Although various self-correction methods have been proposed, a comprehensive evaluation of these methods remains largely unexplored, and the question of whether LLMs can truly correct themselves is a matter of significant interest and concern. In this study, we introduce CorrectBench, a benchmark developed to evaluate the effectiveness of self-correction strategies, including intrinsic, external, and fine-tuned approaches, across three tasks: commonsense reasoning, mathematical reasoning, and code generation. Our findings reveal that: 1) Self-correction methods can improve accuracy, especially for complex reasoning tasks; 2) Mixing different self-correction strategies yields further improvements, though it reduces efficiency; 3) Reasoning LLMs (e.g., DeepSeek-R1) have limited optimization under additional self-correction methods and have high time costs. Interestingly, a comparatively simple chain-of-thought (CoT) baseline demonstrates competitive accuracy and efficiency. These results underscore the potential of self-correction to enhance LLM's reasoning performance while highlighting the ongoing challenge of improving their efficiency. Consequently, we advocate for further research focused on optimizing the balance between reasoning capabilities and operational efficiency. Project Page: https://correctbench.github.io/

---

### Beyond Accuracy: Are Time Series Foundation Models Well-Calibrated?

Authors: Coen Adler, Yuxin Chang, Felix Draxler, Samar Abdi, Padhraic Smyth
Published: 2025-10-17
Categories: cs.LG, cs.AI, stat.ME, stat.ML
arXiv: https://arxiv.org/abs/2510.16060v2

The recent development of foundation models for time series data has generated considerable interest in using such models across a variety of applications. Although foundation models achieve state-of-the-art predictive performance, their calibration properties remain relatively underexplored, despite the fact that calibration can be critical for many practical applications. In this paper, we investigate the calibration-related properties of five recent time series foundation models and two competitive baselines. We perform a series of systematic evaluations assessing model calibration (i.e., over- or under-confidence), effects of varying prediction heads, and calibration under long-term autoregressive forecasting. We find that time series foundation models are consistently better calibrated than baseline models and tend not to be either systematically over- or under-confident, in contrast to the overconfidence often seen in other deep learning models.

---

### SIADAFIX: issue description response for adaptive program repair

Authors: Xin Cao, Nan Yu
Published: 2025-10-17
Categories: cs.SE, cs.CL
arXiv: https://arxiv.org/abs/2510.16059v1

We propose utilizing fast and slow thinking to enhance the capabilities of large language model-based agents on complex tasks such as program repair. In particular, we design an adaptive program repair method based on issue description response, called SIADAFIX. The proposed method utilizes slow thinking bug fix agent to complete complex program repair tasks, and employs fast thinking workflow decision components to optimize and classify issue descriptions, using issue description response results to guide the orchestration of bug fix agent workflows. SIADAFIX adaptively selects three repair modes, i.e., easy, middle and hard mode, based on problem complexity. It employs fast generalization for simple problems and test-time scaling techniques for complex problems. Experimental results on the SWE-bench Lite show that the proposed method achieves 60.67% pass@1 performance using the Claude-4 Sonnet model, reaching state-of-the-art levels among all open-source methods. SIADAFIX effectively balances repair efficiency and accuracy, providing new insights for automated program repair. Our code is available at https://github.com/liauto-siada/siada-cli.

---

### OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM

Authors: Hanrong Ye, Chao-Han Huck Yang, Arushi Goel, Wei Huang, Ligeng Zhu, Yuanhang Su, Sean Lin, An-Chieh Cheng, Zhen Wan, Jinchuan Tian, Yuming Lou, Dong Yang et al.
Published: 2025-10-17
Categories: cs.CV, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.15870v2

Advancing machine intelligence requires developing the ability to perceive across multiple modalities, much as humans sense the world. We introduce OmniVinci, an initiative to build a strong, open-source, omni-modal LLM. We carefully study the design choices across model architecture and data curation. For model architecture, we present three key innovations: (i) OmniAlignNet for strengthening alignment between vision and audio embeddings in a shared omni-modal latent space; (ii) Temporal Embedding Grouping for capturing relative temporal alignment between vision and audio signals; and (iii) Constrained Rotary Time Embedding for encoding absolute temporal information in omni-modal embeddings. We introduce a curation and synthesis pipeline that generates 24M single-modal and omni-modal conversations. We find that modalities reinforce one another in both perception and reasoning. Our model, OmniVinci, outperforms Qwen2.5-Omni with +19.05 on DailyOmni (cross-modal understanding), +1.7 on MMAR (audio), and +3.9 on Video-MME (vision), while using just 0.2T training tokens - a 6 times reduction compared to Qwen2.5-Omni's 1.2T. We finally demonstrate omni-modal advantages in downstream applications spanning robotics, medical AI, and smart factory.

---

### Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery

Authors: Jie-Ying Lee, Yi-Ruei Liu, Shr-Ruei Tsai, Wei-Cheng Chang, Chung-Ho Wu, Jiewen Chan, Zhenjun Zhao, Chieh Hubert Lin, Yu-Lun Liu
Published: 2025-10-17
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.15869v4

Synthesizing large-scale, explorable, and geometrically accurate 3D urban scenes is a challenging yet valuable task for immersive and embodied applications. The challenge lies in the lack of large-scale and high-quality real-world 3D scans for training generalizable generative models. In this paper, we take an alternative route to create large-scale 3D scenes by leveraging readily available satellite imagery for realistic coarse geometry and open-domain diffusion models for high-quality close-up appearance synthesis. We propose Skyfall-GS, a novel hybrid framework that synthesizes immersive city-block scale 3D urban scenes by combining satellite reconstruction with diffusion refinement, eliminating the need for costly 3D annotations, and also featuring real-time, immersive 3D exploration. We tailor a curriculum-driven iterative refinement strategy to progressively enhance geometric completeness and photorealistic texture. Extensive experiments demonstrate that Skyfall-GS provides improved cross-view consistent geometry and more realistic textures compared to state-of-the-art approaches. Project page: https://skyfall-gs.jayinnn.dev/

---

### LightsOut: Diffusion-based Outpainting for Enhanced Lens Flare Removal

Authors: Shr-Ruei Tsai, Wei-Cheng Chang, Jie-Ying Lee, Chih-Hai Su, Yu-Lun Liu
Published: 2025-10-17
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.15868v1

Lens flare significantly degrades image quality, impacting critical computer vision tasks like object detection and autonomous driving. Recent Single Image Flare Removal (SIFR) methods perform poorly when off-frame light sources are incomplete or absent. We propose LightsOut, a diffusion-based outpainting framework tailored to enhance SIFR by reconstructing off-frame light sources. Our method leverages a multitask regression module and LoRA fine-tuned diffusion model to ensure realistic and physically consistent outpainting results. Comprehensive experiments demonstrate LightsOut consistently boosts the performance of existing SIFR methods across challenging scenarios without additional retraining, serving as a universally applicable plug-and-play preprocessing solution. Project page: https://ray-1026.github.io/lightsout/

---

### BiomedXPro: Prompt Optimization for Explainable Diagnosis with Biomedical Vision Language Models

Authors: Kaushitha Silva, Mansitha Eashwara, Sanduni Ubayasiri, Ruwan Tennakoon, Damayanthi Herath
Published: 2025-10-17
Categories: cs.CV, cs.NE
arXiv: https://arxiv.org/abs/2510.15866v2

The clinical adoption of biomedical vision-language models is hindered by prompt optimization techniques that produce either uninterpretable latent vectors or single textual prompts. This lack of transparency and failure to capture the multi-faceted nature of clinical diagnosis, which relies on integrating diverse observations, limits their trustworthiness in high-stakes settings. To address this, we introduce BiomedXPro, an evolutionary framework that leverages a large language model as both a biomedical knowledge extractor and an adaptive optimizer to automatically generate a diverse ensemble of interpretable, natural-language prompt pairs for disease diagnosis. Experiments on multiple biomedical benchmarks show that BiomedXPro consistently outperforms state-of-the-art prompt-tuning methods, particularly in data-scarce few-shot settings. Furthermore, our analysis demonstrates a strong semantic alignment between the discovered prompts and statistically significant clinical features, grounding the model's performance in verifiable concepts. By producing a diverse ensemble of interpretable prompts, BiomedXPro provides a verifiable basis for model predictions, representing a critical step toward the development of more trustworthy and clinically-aligned AI systems.

---

### PolySkill: Learning Generalizable Skills Through Polymorphic Abstraction

Authors: Simon Yu, Gang Li, Weiyan Shi, Peng Qi
Published: 2025-10-17
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.15863v2

Large language models (LLMs) are moving beyond static uses and are now powering agents that learn continually during their interaction with external environments. For example, agents can learn reusable skills while navigating web pages or toggling new tools. However, existing methods for skill learning often create skills that are over-specialized to a single website and fail to generalize. We introduce PolySkill, a new framework that enables agents to learn generalizable and compositional skills. The core idea, inspired by polymorphism in software engineering, is to decouple a skill's abstract goal (what it accomplishes) and its concrete implementation (how it is executed). Experiments show that our method (1) improves skill reuse by 1.7x on seen websites and (2) boosts success rates by up to 9.4% on Mind2Web and 13.9% on unseen websites, while reducing steps by over 20%. (3) In self-exploration settings without specified tasks, our framework improves the quality of proposed tasks and enables agents to learn generalizable skills that work across different sites. By enabling the agent to identify and refine its own goals, the PolySkill enhances the agent's ability to learn a better curriculum, leading to the acquisition of more generalizable skills compared to baseline methods. This work provides a practical path toward building agents capable of continual learning in adaptive environments. Our findings show that separating a skill's goal from its execution is a crucial step toward developing autonomous agents that can learn and generalize across the open web continuously. Our code can be found in https://github.com/simonucl/PolySkill.

---

### Rethinking the Design of Reinforcement Learning-Based Deep Research Agents

Authors: Yi Wan, Jiuqi Wang, Liam Li, Jinsong Liu, Ruihao Zhu, Zheqing Zhu
Published: 2025-10-17
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.15862v4

Large language models (LLMs) augmented with external tools are increasingly deployed as deep research agents that gather, reason over, and synthesize web information to answer complex queries. Although recent open-source systems achieve strong empirical performance via reinforcement learning from web interactions, the impact of key design choices remains under-explored. We formalize deep research as reinforcement learning in an episodic finite Markov decision process and construct a competitive baseline agent grounded in this formulation. Building on this foundation, we systematically examine critical design decisions at both training and inference time and identify four factors that substantially improve performance: replacing rule-based rewards with AI feedback from an LLM judge, fine-tuning with the on-policy RLOO algorithm instead of the off-policy GRPO algorithm, filtering low-quality training samples, and employing an error-tolerant test-time rollout strategy. Together, these design choices yield a deep research agent that establishes state-of-the-art performance among 7B-scale agents when evaluated across ten widely used benchmarks.

---

### InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training

Authors: Pengkai Wang, Pengwei Liu, Qi Zuo, Zhijie Sang, Congkai Xie, Hongxia Yang
Published: 2025-10-17
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.15859v5

Reinforcement learning (RL) has powered many recent breakthroughs in large language models (LLMs), especially for tasks where rewards can be computed automatically, such as code generation. However, it is less effective in open-ended medical dialogue, where feedback is ambiguous, context-dependent, and difficult to simply summarize into a single scalar signal-often requiring heavily supervised reward models and creating risks of reward hacking. Thus, we introduce ORBIT, an open-ended rubric-based incremental training framework tailored for critical medical dialogues. ORBIT integrates medical dialogue construction with dynamically generated case-conditioned rubrics that serve as adaptive guides for incremental RL. Unlike approaches that rely on external medical knowledge bases or handcrafted rules, ORBIT uses rubric-guided evaluation and can be implemented with general-purpose instruction-following LLMs, avoiding task-specific judge fine-tuning. With only 2k training samples, ORBIT raises Qwen3-4B-Instruct's HealthBench-Hard score from 7.0 to 27.5, achieving state-of-the-art performance among similarly sized open-source models while maintaining strong consultation quality as rubric coverage broadens.

---

### BLIP3o-NEXT: Next Frontier of Native Image Generation

Authors: Jiuhai Chen, Le Xue, Zhiyang Xu, Xichen Pan, Shusheng Yang, Can Qin, An Yan, Honglu Zhou, Zeyuan Chen, Lifu Huang, Tianyi Zhou, Junnan Li et al.
Published: 2025-10-17
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.15857v1

We present BLIP3o-NEXT, a fully open-source foundation model in the BLIP3 series that advances the next frontier of native image generation. BLIP3o-NEXT unifies text-to-image generation and image editing within a single architecture, demonstrating strong image generation and image editing capabilities. In developing the state-of-the-art native image generation model, we identify four key insights: (1) Most architectural choices yield comparable performance; an architecture can be deemed effective provided it scales efficiently and supports fast inference; (2) The successful application of reinforcement learning can further push the frontier of native image generation; (3) Image editing still remains a challenging task, yet instruction following and the consistency between generated and reference images can be significantly enhanced through post-training and data engine; (4) Data quality and scale continue to be decisive factors that determine the upper bound of model performance. Building upon these insights, BLIP3o-NEXT leverages an Autoregressive + Diffusion architecture in which an autoregressive model first generates discrete image tokens conditioned on multimodal inputs, whose hidden states are then used as conditioning signals for a diffusion model to generate high-fidelity images. This architecture integrates the reasoning strength and instruction following of autoregressive models with the fine-detail rendering ability of diffusion models, achieving a new level of coherence and realism. Extensive evaluations of various text-to-image and image-editing benchmarks show that BLIP3o-NEXT achieves superior performance over existing models.

---

### SpeechLLMs for Large-scale Contextualized Zero-shot Slot Filling

Authors: Kadri Hacioglu, Manjunath K E, Andreas Stolcke
Published: 2025-10-17
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2510.15851v1

Slot filling is a crucial subtask in spoken language understanding (SLU), traditionally implemented as a cascade of speech recognition followed by one or more natural language understanding (NLU) components. The recent advent of speech-based large language models (speechLLMs), which integrate speech and textual foundation models, has opened new avenues for achieving speech understanding tasks in a more unified, generative, and instruction-following manner while promising data and compute efficiency with zero-shot abilities, generalizing to unseen slot labels. We address the slot-filling task by creating an empirical upper bound for the task, identifying performance, robustness, and generalization gaps, and proposing improvements to the training data, architecture, and training strategies to narrow the gap with the upper bound result. We show that each of these measures improve performance substantially, while highlighting practical challenges and providing empirical guidance and insights for harnessing these emerging models.

---

### Self-Certifying Primal-Dual Optimization Proxies for Large-Scale Batch Economic Dispatch

Authors: Michael Klamkin, Mathieu Tanneau, Pascal Van Hentenryck
Published: 2025-10-17
Categories: cs.LG, cs.AI, math.OC
arXiv: https://arxiv.org/abs/2510.15850v2

Recent research has shown that optimization proxies can be trained to high fidelity, achieving average optimality gaps under 1% for large-scale problems. However, worst-case analyses show that there exist in-distribution queries that result in orders of magnitude higher optimality gap, making it difficult to trust the predictions in practice. This paper aims at striking a balance between classical solvers and optimization proxies in order to enable trustworthy deployments with interpretable speed-optimality tradeoffs based on a user-defined optimality threshold. To this end, the paper proposes a hybrid solver that leverages duality theory to efficiently bound the optimality gap of predictions, falling back to a classical solver for queries where optimality cannot be certified. To improve the achieved speedup of the hybrid solver, the paper proposes an alternative training procedure that combines the primal and dual proxy training. Experiments on large-scale transmission systems show that the hybrid solver is highly scalable. The proposed hybrid solver achieves speedups of over 1000x compared to a parallelized simplex-based solver while guaranteeing a maximum optimality gap of 2%.

---

### Memory-SAM: Human-Prompt-Free Tongue Segmentation via Retrieval-to-Prompt

Authors: Joongwon Chae, Lihui Luo, Xi Yuan, Dongmei Yu, Zhenglin Chen, Lian Zhang, Peiwu Qin
Published: 2025-10-17
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.15849v3

Accurate tongue segmentation is crucial for reliable TCM analysis. Supervised models require large annotated datasets, while SAM-family models remain prompt-driven. We present Memory-SAM, a training-free, human-prompt-free pipeline that automatically generates effective prompts from a small memory of prior cases via dense DINOv3 features and FAISS retrieval. Given a query image, mask-constrained correspondences to the retrieved exemplar are distilled into foreground/background point prompts that guide SAM2 without manual clicks or model fine-tuning. We evaluate on 600 expert-annotated images (300 controlled, 300 in-the-wild). On the mixed test split, Memory-SAM achieves mIoU 0.9863, surpassing FCN (0.8188) and a detector-to-box SAM baseline (0.1839). On controlled data, ceiling effects above 0.98 make small differences less meaningful given annotation variability, while our method shows clear gains under real-world conditions. Results indicate that retrieval-to-prompt enables data-efficient, robust segmentation of irregular boundaries in tongue imaging. The code is publicly available at https://github.com/jw-chae/memory-sam.

---

### 3DPR: Single Image 3D Portrait Relight using Generative Priors

Authors: Pramod Rao, Abhimitra Meka, Xilong Zhou, Gereon Fox, Mallikarjun B R, Fangneng Zhan, Tim Weyrich, Bernd Bickel, Hanspeter Pfister, Wojciech Matusik, Thabo Beeler, Mohamed Elgharib et al.
Published: 2025-10-17
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.15846v1

Rendering novel, relit views of a human head, given a monocular portrait image as input, is an inherently underconstrained problem. The traditional graphics solution is to explicitly decompose the input image into geometry, material and lighting via differentiable rendering; but this is constrained by the multiple assumptions and approximations of the underlying models and parameterizations of these scene components. We propose 3DPR, an image-based relighting model that leverages generative priors learnt from multi-view One-Light-at-A-Time (OLAT) images captured in a light stage. We introduce a new diverse and large-scale multi-view 4K OLAT dataset of 139 subjects to learn a high-quality prior over the distribution of high-frequency face reflectance. We leverage the latent space of a pre-trained generative head model that provides a rich prior over face geometry learnt from in-the-wild image datasets. The input portrait is first embedded in the latent manifold of such a model through an encoder-based inversion process. Then a novel triplane-based reflectance network trained on our lightstage data is used to synthesize high-fidelity OLAT images to enable image-based relighting. Our reflectance network operates in the latent space of the generative head model, crucially enabling a relatively small number of lightstage images to train the reflectance model. Combining the generated OLATs according to a given HDRI environment maps yields physically accurate environmental relighting results. Through quantitative and qualitative evaluations, we demonstrate that 3DPR outperforms previous methods, particularly in preserving identity and in capturing lighting effects such as specularities, self-shadows, and subsurface scattering. Project Page: https://vcai.mpi-inf.mpg.de/projects/3dpr/

---

### Enhanced Sentiment Interpretation via a Lexicon-Fuzzy-Transformer Framework

Authors: Shayan Rokhva, Mousa Alizadeh, Maryam Abdollahi Shamami
Published: 2025-10-17
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.15843v2

Accurately detecting sentiment polarity and intensity in product reviews and social media posts remains challenging due to informal and domain-specific language. To address this, we propose a novel hybrid lexicon-fuzzy-transformer framework that combines rule-based heuristics, contextual deep learning, and fuzzy logic to generate continuous sentiment scores reflecting both polarity and strength. The pipeline begins with VADER-based initial sentiment estimations, which are refined through a two-stage adjustment process. This involves leveraging confidence scores from DistilBERT, a lightweight transformer and applying fuzzy logic principles to mitigate excessive neutrality bias and enhance granularity. A custom fuzzy inference system then maps the refined scores onto a 0 to 1 continuum, producing expert)like judgments. The framework is rigorously evaluated on four domain-specific datasets. food delivery, e-commerce, tourism, and fashion. Results show improved alignment with user ratings, better identification of sentiment extremes, and reduced misclassifications. Both quantitative metrics (distributional alignment, confusion matrices) and qualitative insights (case studies, runtime analysis) affirm the models robustness and efficiency. This work demonstrates the value of integrating symbolic reasoning with neural models for interpretable, finegrained sentiment analysis in linguistically dynamic domains.

---

### Paper2Web: Let's Make Your Paper Alive!

Authors: Yuhang Chen, Tianpeng Lv, Siyi Zhang, Yixiang Yin, Yao Wan, Philip S. Yu, Dongping Chen
Published: 2025-10-17
Categories: cs.CL, cs.CV
arXiv: https://arxiv.org/abs/2510.15842v1

Academic project websites can more effectively disseminate research when they clearly present core content and enable intuitive navigation and interaction. However, current approaches such as direct Large Language Model (LLM) generation, templates, or direct HTML conversion struggle to produce layout-aware, interactive sites, and a comprehensive evaluation suite for this task has been lacking. In this paper, we introduce Paper2Web, a benchmark dataset and multi-dimensional evaluation framework for assessing academic webpage generation. It incorporates rule-based metrics like Connectivity, Completeness and human-verified LLM-as-a-Judge (covering interactivity, aesthetics, and informativeness), and PaperQuiz, which measures paper-level knowledge retention. We further present PWAgent, an autonomous pipeline that converts scientific papers into interactive and multimedia-rich academic homepages. The agent iteratively refines both content and layout through MCP tools that enhance emphasis, balance, and presentation quality. Our experiments show that PWAgent consistently outperforms end-to-end baselines like template-based webpages and arXiv/alphaXiv versions by a large margin while maintaining low cost, achieving the Pareto-front in academic webpage generation.

---

### Neuro-Symbolic Spatial Reasoning in Segmentation

Authors: Jiayi Lin, Jiabo Huang, Shaogang Gong
Published: 2025-10-17
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.15841v1

Open-Vocabulary Semantic Segmentation (OVSS) assigns pixel-level labels from an open set of categories, requiring generalization to unseen and unlabelled objects. Using vision-language models (VLMs) to correlate local image patches with potential unseen object categories suffers from a lack of understanding of spatial relations of objects in a scene. To solve this problem, we introduce neuro-symbolic (NeSy) spatial reasoning in OVSS. In contrast to contemporary VLM correlation-based approaches, we propose Relational Segmentor (RelateSeg) to impose explicit spatial relational constraints by first order logic (FOL) formulated in a neural network architecture. This is the first attempt to explore NeSy spatial reasoning in OVSS. Specifically, RelateSeg automatically extracts spatial relations, e.g., <cat, to-right-of, person>, and encodes them as first-order logic formulas using our proposed pseudo categories. Each pixel learns to predict both a semantic category (e.g., "cat") and a spatial pseudo category (e.g., "right of person") simultaneously, enforcing relational constraints (e.g., a "cat" pixel must lie to the right of a "person"). Finally, these logic constraints are formulated in a deep network architecture by fuzzy logic relaxation, enabling end-to-end learning of spatial-relationally consistent segmentation. RelateSeg achieves state-of-the-art performance in terms of average mIoU across four benchmark datasets and particularly shows clear advantages on images containing multiple categories, with the cost of only introducing a single auxiliary loss function and no additional parameters, validating the effectiveness of NeSy spatial reasoning in OVSS.

---

### Learning Correlated Reward Models: Statistical Barriers and Opportunities

Authors: Yeshwanth Cherapanamjeri, Constantinos Daskalakis, Gabriele Farina, Sobhan Mohammadpour
Published: 2025-10-17
Categories: cs.LG, econ.EM, stat.ML
arXiv: https://arxiv.org/abs/2510.15839v2

Random Utility Models (RUMs) are a classical framework for modeling user preferences and play a key role in reward modeling for Reinforcement Learning from Human Feedback (RLHF). However, a crucial shortcoming of many of these techniques is the Independence of Irrelevant Alternatives (IIA) assumption, which collapses \emph{all} human preferences to a universal underlying utility function, yielding a coarse approximation of the range of human preferences. On the other hand, statistical and computational guarantees for models avoiding this assumption are scarce. In this paper, we investigate the statistical and computational challenges of learning a \emph{correlated} probit model, a fundamental RUM that avoids the IIA assumption. First, we establish that the classical data collection paradigm of pairwise preference data is \emph{fundamentally insufficient} to learn correlational information, explaining the lack of statistical and computational guarantees in this setting. Next, we demonstrate that \emph{best-of-three} preference data provably overcomes these shortcomings, and devise a statistically and computationally efficient estimator with near-optimal performance. These results highlight the benefits of higher-order preference data in learning correlated utilities, allowing for more fine-grained modeling of human preferences. Finally, we validate these theoretical guarantees on several real-world datasets, demonstrating improved personalization of human preferences.

---

### Transfer Orthology Networks

Authors: Vikash Singh
Published: 2025-10-17
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.15837v1

We present Transfer Orthology Networks (TRON), a novel neural network architecture designed for cross-species transfer learning. TRON leverages orthologous relationships, represented as a bipartite graph between species, to guide knowledge transfer. Specifically, we prepend a learned species conversion layer, whose weights are masked by the biadjacency matrix of this bipartite graph, to a pre-trained feedforward neural network that predicts a phenotype from gene expression data in a source species. This allows for efficient transfer of knowledge to a target species by learning a linear transformation that maps gene expression from the source to the target species' gene space. The learned weights of this conversion layer offer a potential avenue for interpreting functional orthology, providing insights into how genes across species contribute to the phenotype of interest. TRON offers a biologically grounded and interpretable approach to cross-species transfer learning, paving the way for more effective utilization of available transcriptomic data. We are in the process of collecting cross-species transcriptomic/phenotypic data to gain experimental validation of the TRON architecture.

---

### FIDDLE: Reinforcement Learning for Quantum Fidelity Enhancement

Authors: Hoang M. Ngo, Tamer Kahveci, My T. Thai
Published: 2025-10-17
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.15833v1

Quantum computing has the potential to revolutionize fields like quantum optimization and quantum machine learning. However, current quantum devices are hindered by noise, reducing their reliability. A key challenge in gate-based quantum computing is improving the reliability of quantum circuits, measured by process fidelity, during the transpilation process, particularly in the routing stage. In this paper, we address the Fidelity Maximization in Routing Stage (FMRS) problem by introducing FIDDLE, a novel learning framework comprising two modules: a Gaussian Process-based surrogate model to estimate process fidelity with limited training samples and a reinforcement learning module to optimize routing. Our approach is the first to directly maximize process fidelity, outperforming traditional methods that rely on indirect metrics such as circuit depth or gate count. We rigorously evaluate FIDDLE by comparing it with state-of-the-art fidelity estimation techniques and routing optimization methods. The results demonstrate that our proposed surrogate model is able to provide a better estimation on the process fidelity compared to existing learning techniques, and our end-to-end framework significantly improves the process fidelity of quantum circuits across various noise models.

---

### VISTA: A Test-Time Self-Improving Video Generation Agent

Authors: Do Xuan Long, Xingchen Wan, Hootan Nakhost, Chen-Yu Lee, Tomas Pfister, Sercan Ö. Arık
Published: 2025-10-17
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.15831v1

Despite rapid advances in text-to-video synthesis, generated video quality remains critically dependent on precise user prompts. Existing test-time optimization methods, successful in other domains, struggle with the multi-faceted nature of video. In this work, we introduce VISTA (Video Iterative Self-improvemenT Agent), a novel multi-agent system that autonomously improves video generation through refining prompts in an iterative loop. VISTA first decomposes a user idea into a structured temporal plan. After generation, the best video is identified through a robust pairwise tournament. This winning video is then critiqued by a trio of specialized agents focusing on visual, audio, and contextual fidelity. Finally, a reasoning agent synthesizes this feedback to introspectively rewrite and enhance the prompt for the next generation cycle. Experiments on single- and multi-scene video generation scenarios show that while prior methods yield inconsistent gains, VISTA consistently improves video quality and alignment with user intent, achieving up to 60% pairwise win rate against state-of-the-art baselines. Human evaluators concur, preferring VISTA outputs in 66.4% of comparisons.

---

### SNOO: Step-K Nesterov Outer Optimizer - The Surprising Effectiveness of Nesterov Momentum Applied to Pseudo-Gradients

Authors: Dominik Kallusky, Vinay Rao, Vishal Nandavanam, Hao-Jun Michael Shi
Published: 2025-10-17
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.15830v1

The rapid development of large language models (LLMs) has driven the demand for more efficient optimization techniques. Among these, the Lookahead family of optimizers employs a two-loop framework, maintaining fast and slow sets of model weights. Multiple inner optimizer steps on the fast weights produce a trajectory - the pseudo-gradient - that is used to update the slow weights. DiLoCo, a notable example originally designed for distributed training, applies Nesterov momentum to the averaged pseudo-gradient from multiple workers, claiming to even outperform AdamW in a non-distributed setup. In this paper, we empirically show that DiLoCo's surprising effectiveness stems primarily from applying Nesterov momentum to the pseudo-gradient, which improves training in a non-distributed setting. We call this Lookahead variant the Step-$K$ Nesterov Outer Optimizer (SNOO). We demonstrate that SNOO achieves compute factor gains of 1.5 - 2.5$\times$ in a non-distributed setting up to a scale of 1e23 training FLOPs, with improvements that increase with model size. Because of its minimal compute and memory overhead and compatibility with model sharding, SNOO is a practical enhancement for a variety of inner optimizers, including AdamW and Muon.

---

### GENESIS: A Generative Model of Episodic-Semantic Interaction

Authors: Marco D'Alessandro, Leo D'Amato, Mikel Elkano, Mikel Uriz, Giovanni Pezzulo
Published: 2025-10-17
Categories: q-bio.NC, cs.AI
arXiv: https://arxiv.org/abs/2510.15828v2

A central challenge in cognitive neuroscience is to explain how semantic and episodic memory, two major forms of declarative memory, typically associated with cortical and hippocampal processing, interact to support learning, recall, and imagination. Despite significant advances, we still lack a unified computational framework that jointly accounts for core empirical phenomena across both semantic and episodic processing domains. Here, we introduce the Generative Episodic-Semantic Integration System (GENESIS), a computational model that formalizes memory as the interaction between two limited-capacity generative systems: a Cortical-VAE, supporting semantic learning and generalization, and a Hippocampal-VAE, supporting episodic encoding and retrieval within a retrieval-augmented generation (RAG) architecture. GENESIS reproduces hallmark behavioral findings, including generalization in semantic memory, recognition, serial recall effects and gist-based distortions in episodic memory, and constructive episodic simulation, while capturing their dynamic interactions. The model elucidates how capacity constraints shape the fidelity and memorability of experiences, how semantic processing introduces systematic distortions in episodic recall, and how episodic replay can recombine previous experiences. Together, these results provide a principled account of memory as an active, constructive, and resource-bounded process. GENESIS thus advances a unified theoretical framework that bridges semantic and episodic memory, offering new insights into the generative foundations of human cognition.

---

### Adaptive Conformal Inference through the Lens of Blackwell Approachability

Authors: Guillaume Principato, Gilles Stoltz
Published: 2025-10-17
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2510.15824v2

This article considers an online version of conformal inference, called adaptive conformal inference (ACI) and introduced by Gibbs and Candès (2021): prediction sets are issued sequentially, after observing features and before the outcomes are revealed. These sets are evaluated both in terms of validity (the fraction of rounds where the outcome was lying in the prediction set) and efficiency (the average lengths of the prediction sets). The two criteria point to different directions (validity favors larger sets). We also target a wide range of scenarios, with exchangeable data and arbitrary data (lack of any stochastic guarantees) as two extremes. A series of existing strategies for ACI typically guarantee that empirical coverage converges to the desired level for arbitrary sequences, but they generally lack simultaneous efficiency guarantees. To provide a unified study, we first formulate ACI as a repeated two-player game with finite action sets and vector-valued payoffs encoding validity and efficiency. Building on this reformulation, we introduce a strategy based on Blackwell approachability and on its opportunistic extension by Bernstein et al. (2014) that ensures validity while adapting the efficiency of the prediction intervals to the underlying degree of stochasticity of the opponent player. The resulting guarantee is "best of many worlds": it recovers the relevant efficiency guarantees in exchangeable and adversarial settings, and provides guarantees in intermediate settings that arise in typical applications such as the forecasting of time series.

---

### Chronos-2: From Univariate to Universal Forecasting

Authors: Abdul Fatir Ansari, Oleksandr Shchur, Jaris Küken, Andreas Auer, Boran Han, Pedro Mercado, Syama Sundar Rangapuram, Huibin Shen, Lorenzo Stella, Xiyuan Zhang, Mononito Goswami, Shubham Kapoor et al.
Published: 2025-10-17
Categories: cs.LG, cs.AI, stat.ML
arXiv: https://arxiv.org/abs/2510.15821v1

Pretrained time series models have enabled inference-only forecasting systems that produce accurate predictions without task-specific training. However, existing approaches largely focus on univariate forecasting, limiting their applicability in real-world scenarios where multivariate data and covariates play a crucial role. We present Chronos-2, a pretrained model capable of handling univariate, multivariate, and covariate-informed forecasting tasks in a zero-shot manner. Chronos-2 employs a group attention mechanism that facilitates in-context learning (ICL) through efficient information sharing across multiple time series within a group, which may represent sets of related series, variates of a multivariate series, or targets and covariates in a forecasting task. These general capabilities are achieved through training on synthetic datasets that impose diverse multivariate structures on univariate series. Chronos-2 delivers state-of-the-art performance across three comprehensive benchmarks: fev-bench, GIFT-Eval, and Chronos Benchmark II. On fev-bench, which emphasizes multivariate and covariate-informed forecasting, Chronos-2's universal ICL capabilities lead to substantial improvements over existing models. On tasks involving covariates, it consistently outperforms baselines by a wide margin. Case studies in the energy and retail domains further highlight its practical advantages. The in-context learning capabilities of Chronos-2 establish it as a general-purpose forecasting model that can be used "as is" in real-world forecasting pipelines.

---