# Research Papers — 2025-10 · bundle page 19 of 217 > Full-text markdown of papers #901–950 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/19 [← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/18.md) [Next bundle →](https://aipod.dev/papers/archive/2025-10/page/20.md) ### Alibaba International E-commerce Product Search Competition DcuRAGONs Team Technical Report Authors: Thang-Long Nguyen-Ho, Minh-Khoi Pham, Hoang-Bao Le Published: 2025-10-29 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2510.25428v1 This report details our methodology and results developed for the Multilingual E-commerce Search Competition. The problem aims to recognize relevance between user queries versus product items in a multilingual context and improve recommendation performance on e-commerce platforms. Utilizing Large Language Models (LLMs) and their capabilities in other tasks, our data-centric method achieved the highest score compared to other solutions during the competition. Final leaderboard is publised at https://alibaba-international-cikm2025.github.io. The source code for our project is published at https://github.com/nhtlongcs/e-commerce-product-search. --- ### RLMEval: Evaluating Research-Level Neural Theorem Proving Authors: Auguste Poiroux, Antoine Bosselut, Viktor Kunčak Published: 2025-10-29 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2510.25427v1 Despite impressive results on curated benchmarks, the practical impact of large language models (LLMs) on research-level neural theorem proving and proof autoformalization is still limited. We introduce RLMEval, an evaluation suite for these tasks, focusing on research-level mathematics from real-world Lean formalization projects. RLMEval targets the evaluation of neural theorem proving and proof autoformalization on challenging research-level theorems by leveraging real Lean Blueprint formalization projects. Our evaluation of state-of-the-art models on RLMEval, comprising 613 theorems from 6 Lean projects, reveals a significant gap: progress on existing benchmarks does not readily translate to these more realistic settings, with the best model achieving only a 10.3 % pass rate. RLMEval provides a new, challenging benchmark designed to guide and accelerate progress in automated reasoning for formal mathematics. --- ### Implicature in Interaction: Understanding Implicature Improves Alignment in Human-LLM Interaction Authors: Asutosh Hota, Jussi P. P. Jokinen Published: 2025-10-29 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2510.25426v2 The rapid advancement of Large Language Models (LLMs) is positioning language at the core of human-computer interaction (HCI). We argue that advancing HCI requires attention to the linguistic foundations of interaction, particularly implicature (meaning conveyed beyond explicit statements through shared context) which is essential for human-AI (HAI) alignment. This study examines LLMs' ability to infer user intent embedded in context-driven prompts and whether understanding implicature improves response generation. Results show that larger models approximate human interpretations more closely, while smaller models struggle with implicature inference. Furthermore, implicature-based prompts significantly enhance the perceived relevance and quality of responses across models, with notable gains in smaller models. Overall, 67.6% of participants preferred responses with implicature-embedded prompts to literal ones, highlighting a clear preference for contextually nuanced communication. Our work contributes to understanding how linguistic theory can be used to address the alignment problem by making HAI interaction more natural and contextually grounded. --- ### Improving Temporal Consistency and Fidelity at Inference-time in Perceptual Video Restoration by Zero-shot Image-based Diffusion Models Authors: Nasrin Rahimi, A. Murat Tekalp Published: 2025-10-29 Categories: eess.IV, cs.AI arXiv: https://arxiv.org/abs/2510.25420v1 Diffusion models have emerged as powerful priors for single-image restoration, but their application to zero-shot video restoration suffers from temporal inconsistencies due to the stochastic nature of sampling and complexity of incorporating explicit temporal modeling. In this work, we address the challenge of improving temporal coherence in video restoration using zero-shot image-based diffusion models without retraining or modifying their architecture. We propose two complementary inference-time strategies: (1) Perceptual Straightening Guidance (PSG) based on the neuroscience-inspired perceptual straightening hypothesis, which steers the diffusion denoising process towards smoother temporal evolution by incorporating a curvature penalty in a perceptual space to improve temporal perceptual scores, such as Fréchet Video Distance (FVD) and perceptual straightness; and (2) Multi-Path Ensemble Sampling (MPES), which aims at reducing stochastic variation by ensembling multiple diffusion trajectories to improve fidelity (distortion) scores, such as PSNR and SSIM, without sacrificing sharpness. Together, these training-free techniques provide a practical path toward temporally stable high-fidelity perceptual video restoration using large pretrained diffusion models. We performed extensive experiments over multiple datasets and degradation types, systematically evaluating each strategy to understand their strengths and limitations. Our results show that while PSG enhances temporal naturalness, particularly in case of temporal blur, MPES consistently improves fidelity and spatio-temporal perception--distortion trade-off across all tasks. --- ### Adaptive End-to-End Transceiver Design for NextG Pilot-Free and CP-Free Wireless Systems Authors: Jiaming Cheng, Wei Chen, Bo Ai Published: 2025-10-29 Categories: eess.SP, cs.AI arXiv: https://arxiv.org/abs/2510.25416v1 The advent of artificial intelligence (AI)-native wireless communication is fundamentally reshaping the design paradigm of next-generation (NextG) systems, where intelligent air interfaces are expected to operate adaptively and efficiently in highly dynamic environments. Conventional orthogonal frequency division multiplexing (OFDM) systems rely heavily on pilots and the cyclic prefix (CP), resulting in significant overhead and reduced spectral efficiency. To address these limitations, we propose an adaptive end-to-end (E2E) transceiver architecture tailored for pilot-free and CP-free wireless systems. The architecture combines AI-driven constellation shaping and a neural receiver through joint training. To enhance robustness against mismatched or time-varying channel conditions, we introduce a lightweight channel adapter (CA) module, which enables rapid adaptation with minimal computational overhead by updating only the CA parameters. Additionally, we present a framework that is scalable to multiple modulation orders within a unified model, significantly reducing model storage requirements. Moreover, to tackle the high peak-to-average power ratio (PAPR) inherent to OFDM, we incorporate constrained E2E training, achieving compliance with PAPR targets without additional transmission overhead. Extensive simulations demonstrate that the proposed framework delivers superior bit error rate (BER), throughput, and resilience across diverse channel scenarios, highlighting its potential for AI-native NextG. --- ### Seeing, Signing, and Saying: A Vision-Language Model-Assisted Pipeline for Sign Language Data Acquisition and Curation from Social Media Authors: Shakib Yazdani, Yasser Hamidullah, Cristina España-Bonet, Josef van Genabith Published: 2025-10-29 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.25413v1 Most existing sign language translation (SLT) datasets are limited in scale, lack multilingual coverage, and are costly to curate due to their reliance on expert annotation and controlled recording setup. Recently, Vision Language Models (VLMs) have demonstrated strong capabilities as evaluators and real-time assistants. Despite these advancements, their potential remains untapped in the context of sign language dataset acquisition. To bridge this gap, we introduce the first automated annotation and filtering framework that utilizes VLMs to reduce reliance on manual effort while preserving data quality. Our method is applied to TikTok videos across eight sign languages and to the already curated YouTube-SL-25 dataset in German Sign Language for the purpose of additional evaluation. Our VLM-based pipeline includes a face visibility detection, a sign activity recognition, a text extraction from video content, and a judgment step to validate alignment between video and text, implementing generic filtering, annotation and validation steps. Using the resulting corpus, TikTok-SL-8, we assess the performance of two off-the-shelf SLT models on our filtered dataset for German and American Sign Languages, with the goal of establishing baselines and evaluating the robustness of recent models on automatically extracted, slightly noisy data. Our work enables scalable, weakly supervised pretraining for SLT and facilitates data acquisition from social media. --- ### Serve Programs, Not Prompts Authors: In Gim, Lin Zhong Published: 2025-10-29 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.25412v1 Current large language model (LLM) serving systems, primarily designed for text completion, are neither efficient nor adaptable for increasingly complex LLM applications due to their inflexible design. We propose a new LLM serving system architecture that serves programs instead of prompts to address this problem. These programs, called LLM Inference Programs (LIPs), allow users to customize token prediction and KV cache management at runtime and to offload parts of their application logic, such as tool execution, to the server. We describe an example of this architecture through a system named Symphony, which functions as an operating system for LIPs. Symphony exposes LLM model computations via system calls and virtualizes KV cache with a dedicated file system, while ensuring GPU efficiency with a two-level process scheduling scheme. Symphony has the potential to open the door to a more efficient and extensible ecosystem for LLM applications. --- ### BhashaBench V1: A Comprehensive Benchmark for the Quadrant of Indic Domains Authors: Vijay Devane, Mohd Nauman, Bhargav Patel, Aniket Mahendra Wakchoure, Yogeshkumar Sant, Shyam Pawar, Viraj Thakur, Ananya Godse, Sunil Patra, Neha Maurya, Suraj Racha, Nitish Kamal Singh et al. Published: 2025-10-29 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2510.25409v2 The rapid advancement of large language models(LLMs) has intensified the need for domain and culture specific evaluation. Existing benchmarks are largely Anglocentric and domain-agnostic, limiting their applicability to India-centric contexts. To address this gap, we introduce BhashaBench V1, the first domain-specific, multi-task, bilingual benchmark focusing on critical Indic knowledge systems. BhashaBench V1 contains 74,166 meticulously curated question-answer pairs, with 52,494 in English and 21,672 in Hindi, sourced from authentic government and domain-specific exams. It spans four major domains: Agriculture, Legal, Finance, and Ayurveda, comprising 90+ subdomains and covering 500+ topics, enabling fine-grained evaluation. Evaluation of 29+ LLMs reveals significant domain and language specific performance gaps, with especially large disparities in low-resource domains. For instance, GPT-4o achieves 76.49% overall accuracy in Legal but only 59.74% in Ayurveda. Models consistently perform better on English content compared to Hindi across all domains. Subdomain-level analysis shows that areas such as Cyber Law, International Finance perform relatively well, while Panchakarma, Seed Science, and Human Rights remain notably weak. BhashaBench V1 provides a comprehensive dataset for evaluating large language models across India's diverse knowledge domains. It enables assessment of models' ability to integrate domain-specific knowledge with bilingual understanding. All code, benchmarks, and resources are publicly available to support open research. --- ### SemanticOpt: Towards LLM-Based Semantic Black-Box Optimization Authors: Jamison Meindl, Yunsheng Tian, Tony Cui, Veronika Thost, Zhang-Wei Hong, Jie Chen, Wojciech Matusik, Mina Konaković Luković Published: 2025-10-29 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2510.25404v3 Optimizing an experimental system can be extremely challenging when each experiment is expensive, time-consuming, or difficult to perform. Existing optimizers for expensive black-box problems, such as Bayesian optimization, are typically limited to numerical or categorical observations. They do not make use of broader domain knowledge, such as expert heuristics, relevant scientific papers, or similar previous experiments. Large language models (LLMs) can interpret this semantic information; however, even state-of-the-art LLMs struggle to reliably solve black-box optimization problems. We introduce SemanticOpt, a framework for semantic black-box optimization that equips LLMs with optimization capabilities by fine-tuning them on structured Bayesian optimization trajectories augmented with natural-language context. SemanticOpt jointly uses numerical and semantic evidence when proposing new experiments, while producing interpretable predictions aligned with Bayesian surrogate models. We construct a range of real-world optimization problems paired with semantic information to create a diverse benchmark for evaluating semantic black-box optimization. Across these domains, SemanticOpt outperforms both classical optimizers and existing LLM-based approaches on average when given relevant semantic information. --- ### Estimation of discrete distributions with high probability under $χ^2$-divergence Authors: Sirine Louati Published: 2025-10-29 Categories: math.ST, stat.ML arXiv: https://arxiv.org/abs/2510.25400v1 We investigate the high-probability estimation of discrete distributions from an \iid sample under $χ^2$-divergence loss. Although the minimax risk in expectation is well understood, its high-probability counterpart remains largely unexplored. We provide sharp upper and lower bounds for the classical Laplace estimator, showing that it achieves optimal performance among estimators that do not rely on the confidence level. We further characterize the minimax high-probability risk for any estimator and demonstrate that it can be attained through a simple smoothing strategy. Our analysis highlights an intrinsic separation between asymptotic and non-asymptotic guarantees, with the latter suffering from an unavoidable overhead. This work sharpens existing guarantees and advances the theoretical understanding of divergence-based estimation. --- ### Grouping Nodes With Known Value Differences: A Lossless UCT-based Abstraction Algorithm Authors: Robin Schmöcker, Alexander Dockhorn, Bodo Rosenhahn Published: 2025-10-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2510.25388v1 A core challenge of Monte Carlo Tree Search (MCTS) is its sample efficiency, which can be improved by grouping state-action pairs and using their aggregate statistics instead of single-node statistics. On the Go Abstractions in Upper Confidence bounds applied to Trees (OGA-UCT) is the state-of-the-art MCTS abstraction algorithm for deterministic environments that builds its abstraction using the Abstractions of State-Action Pairs (ASAP) framework, which aims to detect states and state-action pairs with the same value under optimal play by analysing the search graph. ASAP, however, requires two state-action pairs to have the same immediate reward, which is a rigid condition that limits the number of abstractions that can be found and thereby the sample efficiency. In this paper, we break with the paradigm of grouping value-equivalent states or state-action pairs and instead group states and state-action pairs with possibly different values as long as the difference between their values can be inferred. We call this abstraction framework Known Value Difference Abstractions (KVDA), which infers the value differences by analysis of the immediate rewards and modifies OGA-UCT to use this framework instead. The modification is called KVDA-UCT, which detects significantly more abstractions than OGA-UCT, introduces no additional parameter, and outperforms OGA-UCT on a variety of deterministic environments and parameter settings. --- ### Instance-Level Composed Image Retrieval Authors: Bill Psomas, George Retsinas, Nikos Efthymiadis, Panagiotis Filntisis, Yannis Avrithis, Petros Maragos, Ondrej Chum, Giorgos Tolias Published: 2025-10-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.25387v2 The progress of composed image retrieval (CIR), a popular research direction in image retrieval, where a combined visual and textual query is used, is held back by the absence of high-quality training and evaluation data. We introduce a new evaluation dataset, i-CIR, which, unlike existing datasets, focuses on an instance-level class definition. The goal is to retrieve images that contain the same particular object as the visual query, presented under a variety of modifications defined by textual queries. Its design and curation process keep the dataset compact to facilitate future research, while maintaining its challenge-comparable to retrieval among more than 40M random distractors-through a semi-automated selection of hard negatives. To overcome the challenge of obtaining clean, diverse, and suitable training data, we leverage pre-trained vision-and-language models (VLMs) in a training-free approach called BASIC. The method separately estimates query-image-to-image and query-text-to-image similarities, performing late fusion to upweight images that satisfy both queries, while down-weighting those that exhibit high similarity with only one of the two. Each individual similarity is further improved by a set of components that are simple and intuitive. BASIC sets a new state of the art on i-CIR but also on existing CIR datasets that follow a semantic-level class definition. Project page: https://vrg.fel.cvut.cz/icir/. --- ### Integrating Legal and Logical Specifications in Perception, Prediction, and Planning for Automated Driving: A Survey of Methods Authors: Kumar Manas, Mert Keser, Alois Knoll Published: 2025-10-29 Categories: cs.RO, cs.AI, eess.SY arXiv: https://arxiv.org/abs/2510.25386v1 This survey provides an analysis of current methodologies integrating legal and logical specifications into the perception, prediction, and planning modules of automated driving systems. We systematically explore techniques ranging from logic-based frameworks to computational legal reasoning approaches, emphasizing their capability to ensure regulatory compliance and interpretability in dynamic and uncertain driving environments. A central finding is that significant challenges arise at the intersection of perceptual reliability, legal compliance, and decision-making justifiability. To systematically analyze these challenges, we introduce a taxonomy categorizing existing approaches by their theoretical foundations, architectural implementations, and validation strategies. We particularly focus on methods that address perceptual uncertainty and incorporate explicit legal norms, facilitating decisions that are both technically robust and legally defensible. The review covers neural-symbolic integration methods for perception, logic-driven rule representation, and norm-aware prediction strategies, all contributing toward transparent and accountable autonomous vehicle operation. We highlight critical open questions and practical trade-offs that must be addressed, offering multidisciplinary insights from engineering, logic, and law to guide future developments in legally compliant autonomous driving systems. --- ### Roleplaying with Structure: Synthetic Therapist-Client Conversation Generation from Questionnaires Authors: Doan Nam Long Vu, Rui Tan, Lena Moench, Svenja Jule Francke, Daniel Woiwod, Florian Thomas-Odenthal, Sanna Stroth, Tilo Kircher, Christiane Hermann, Udo Dannlowski, Hamidreza Jamalabadi, Simone Balloccu et al. Published: 2025-10-29 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.25384v2 Large Language Models (LLMs) are promising tools for synthetic data generation in mental health. However, privacy policies and restrictions forced previous work to rely mainly on generic information. We present a comprehensive corpus of synthetic therapist-client conversations generated through LLMs. We construct our generation pipeline, SQPsych (Structured Questionnaire-based Psychotherapy), which uses real structured client profiles and psychological questionnaires without leaking any sensitive data. We fine-tune various open-weight LLMs on our generated corpus, SQPsychConv , and test them through both automatic benchmarks and human evaluation with trained psychotherapists. We find that standard benchmarks do not adequately capture the strengths of our dataset, but expert judgment shows that SQPsych makes LLMs significantly better at therapist roleplaying. Experts also consistently prefer therapy sessions generated by our models compared to other mental-health-oriented LLMs. We release our code, fine-tuned models SQPsychLLM, and corpora at https://ai-mh.github.io/SQPsych.html. --- ### A Deep Learning Framework for Multi-Operator Learning: Architectures and Approximation Theory Authors: Adrien Weihs, Jingmin Sun, Zecheng Zhang, Hayden Schaeffer Published: 2025-10-29 Categories: cs.LG, math.NA arXiv: https://arxiv.org/abs/2510.25379v1 While many problems in machine learning focus on learning mappings between finite-dimensional spaces, scientific applications require approximating mappings between function spaces, i.e., operators. We study the problem of learning collections of operators and provide both theoretical and empirical advances. We distinguish between two regimes: (i) multiple operator learning, where a single network represents a continuum of operators parameterized by a parametric function, and (ii) learning several distinct single operators, where each operator is learned independently. For the multiple operator case, we introduce two new architectures, $\mathrm{MNO}$ and $\mathrm{MONet}$, and establish universal approximation results in three settings: continuous, integrable, or Lipschitz operators. For the latter, we further derive explicit scaling laws that quantify how the network size must grow to achieve a target approximation accuracy. For learning several single operators, we develop a framework for balancing architectural complexity across subnetworks and show how approximation order determines computational efficiency. Empirical experiments on parametric PDE benchmarks confirm the strong expressive power and efficiency of the proposed architectures. Overall, this work establishes a unified theoretical and practical foundation for scalable neural operator learning across multiple operators. --- ### Hallucinations in Bibliographic Recommendation: Citation Frequency as a Proxy for Training Data Redundancy Authors: Junichiro Niimi Published: 2025-10-29 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2510.25378v1 Large language models (LLMs) have been increasingly applied to a wide range of tasks, from natural language understanding to code generation. While they have also been used to assist in bibliographic recommendation, the hallucination of non-existent papers remains a major issue. Building on prior studies, this study hypothesizes that an LLM's ability to correctly produce bibliographic information depends on whether the underlying knowledge is generated or memorized, with highly cited papers (i.e., more frequently appear in the training corpus) showing lower hallucination rates. We therefore assume citation count as a proxy for training data redundancy (i.e., the frequency with which a given bibliographic record is repeatedly represented in the pretraining corpus) and investigate how citation frequency affects hallucinated references in LLM outputs. Using GPT-4.1, we generated and manually verified 100 bibliographic records across twenty computer-science domains, and measured factual consistency via cosine similarity between generated and authentic metadata. The results revealed that (i) hallucination rates vary across research domains, (ii) citation count is strongly correlated with factual accuracy, and (iii) bibliographic information becomes almost verbatimly memorized beyond approximately 1,000 citations. These findings suggest that highly cited papers are nearly verbatimly retained in the model, indicating a threshold where generalization shifts into memorization. --- ### Prompt Estimation from Prototypes for Federated Prompt Tuning of Vision Transformers Authors: M Yashwanth, Sharannya Ghosh, Aditay Tripathi, Anirban Chakraborty Published: 2025-10-29 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2510.25372v2 Visual Prompt Tuning (VPT) of pre-trained Vision Transformers (ViTs) has proven highly effective as a parameter-efficient fine-tuning technique for adapting large models to downstream tasks with limited data. Its parameter efficiency makes it particularly suitable for Federated Learning (FL), where both communication and computation budgets are often constrained. However, global prompt tuning struggles to generalize across heterogeneous clients, while personalized tuning overfits to local data and lacks generalization. We propose PEP-FedPT (Prompt Estimation from Prototypes for Federated Prompt Tuning), a unified framework designed to achieve both generalization and personalization in federated prompt tuning of ViTs. Within this framework, we introduce the novel Class-Contextualized Mixed Prompt (CCMP) - based on class-specific prompts maintained alongside a globally shared prompt. For each input, CCMP adaptively combines class-specific prompts using weights derived from global class prototypes and client class priors. This approach enables per-sample prompt personalization without storing client-dependent trainable parameters. The prompts are collaboratively optimized via traditional federated averaging technique on the same. Comprehensive evaluations on CIFAR-100, TinyImageNet, DomainNet, and iNaturalist datasets demonstrate that PEP-FedPT consistently surpasses the state-of-the-art baselines under diverse data heterogeneity scenarios, establishing a strong foundation for efficient and generalizable federated prompt tuning of Vision Transformers. --- ### Monitoring Transformative Technological Convergence Through LLM-Extracted Semantic Entity Triple Graphs Authors: Alexander Sternfeld, Andrei Kucharavy, Dimitri Percia David, Alain Mermoud, Julian Jang-Jaccard, Nathan Monnet Published: 2025-10-29 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.25370v2 Forecasting transformative technologies remains a critical but challenging task, particularly in fast-evolving domains such as Information and Communication Technologies (ICTs). Traditional expert-based methods struggle to keep pace with short innovation cycles and ambiguous early-stage terminology. In this work, we propose a novel, data-driven pipeline to monitor the emergence of transformative technologies by identifying patterns of technological convergence. Our approach leverages advances in Large Language Models (LLMs) to extract semantic triples from unstructured text and construct a large-scale graph of technology-related entities and relations. We introduce a new method for grouping semantically similar technology terms (noun stapling) and develop graph-based metrics to detect convergence signals. The pipeline includes multi-stage filtering, domain-specific keyword clustering, and a temporal trend analysis of topic co-occurence. We validate our methodology on two complementary datasets: 278,625 arXiv preprints (2017--2024) to capture early scientific signals, and 9,793 USPTO patent applications (2018-2024) to track downstream commercial developments. Our results demonstrate that the proposed pipeline can identify both established and emerging convergence patterns, offering a scalable and generalizable framework for technology forecasting grounded in full-text analysis. --- ### Position: Biology is the Challenge Physics-Informed ML Needs to Evolve Authors: Julien Martinelli Published: 2025-10-29 Categories: cs.LG, cs.AI, cs.NE arXiv: https://arxiv.org/abs/2510.25368v1 Physics-Informed Machine Learning (PIML) has successfully integrated mechanistic understanding into machine learning, particularly in domains governed by well-known physical laws. This success has motivated efforts to apply PIML to biology, a field rich in dynamical systems but shaped by different constraints. Biological modeling, however, presents unique challenges: multi-faceted and uncertain prior knowledge, heterogeneous and noisy data, partial observability, and complex, high-dimensional networks. In this position paper, we argue that these challenges should not be seen as obstacles to PIML, but as catalysts for its evolution. We propose Biology-Informed Machine Learning (BIML): a principled extension of PIML that retains its structural grounding while adapting to the practical realities of biology. Rather than replacing PIML, BIML retools its methods to operate under softer, probabilistic forms of prior knowledge. We outline four foundational pillars as a roadmap for this transition: uncertainty quantification, contextualization, constrained latent structure inference, and scalability. Foundation Models and Large Language Models will be key enablers, bridging human expertise with computational modeling. We conclude with concrete recommendations to build the BIML ecosystem and channel PIML-inspired innovation toward challenges of high scientific and societal relevance. --- ### A Convexity-dependent Two-Phase Training Algorithm for Deep Neural Networks Authors: Tomas Hrycej, Bernhard Bermeitinger, Massimo Pavone, Götz-Henrik Wiegand, Siegfried Handschuh Published: 2025-10-29 Categories: cs.LG, cs.AI, math.OC arXiv: https://arxiv.org/abs/2510.25366v2 The key task of machine learning is to minimize the loss function that measures the model fit to the training data. The numerical methods to do this efficiently depend on the properties of the loss function. The most decisive among these properties is the convexity or non-convexity of the loss function. The fact that the loss function can have, and frequently has, non-convex regions has led to a widespread commitment to non-convex methods such as Adam. However, a local minimum implies that, in some environment around it, the function is convex. In this environment, second-order minimizing methods such as the Conjugate Gradient (CG) give a guaranteed superlinear convergence. We propose a novel framework grounded in the hypothesis that loss functions in real-world tasks swap from initial non-convexity to convexity towards the optimum. This is a property we leverage to design an innovative two-phase optimization algorithm. The presented algorithm detects the swap point by observing the gradient norm dependence on the loss. In these regions, non-convex (Adam) and convex (CG) algorithms are used, respectively. Computing experiments confirm the hypothesis that this simple convexity structure is frequent enough to be practically exploited to substantially improve convergence and accuracy. --- ### CLASS-IT: Conversational and Lecture-Aligned Small-Scale Instruction Tuning for BabyLMs Authors: Luca Capone, Alessandro Bondielli, Alessandro Lenci Published: 2025-10-29 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.25364v1 This work investigates whether small-scale LMs can benefit from instruction tuning. We compare conversational and question-answering instruction tuning datasets, applied either in a merged or sequential curriculum, using decoder-only models with 100M and 140M parameters. Evaluation spans both fine-tuning (SuperGLUE) and zero-shot (BLiMP, EWoK, WUGs, entity tracking, and psycholinguistic correlation) settings. Results show that instruction tuning yields small but consistent gains in fine-tuning scenarios, with sequential curricula outperforming merged data; however, improvements do not consistently transfer to zero-shot tasks, suggesting a trade-off between interaction-focused adaptation and broad linguistic generalization. These results highlight both the potential and the constraints of adapting human-inspired learning strategies to low-resource LMs, and point toward hybrid, curriculum-based approaches for enhancing generalization under ecological training limits. --- ### Parameter Averaging in Link Prediction Authors: Rupesh Sapkota, Caglar Demir, Arnab Sharma, Axel-Cyrille Ngonga Ngomo Published: 2025-10-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.25361v1 Ensemble methods are widely employed to improve generalization in machine learning. This has also prompted the adoption of ensemble learning for the knowledge graph embedding (KGE) models in performing link prediction. Typical approaches to this end train multiple models as part of the ensemble, and the diverse predictions are then averaged. However, this approach has some significant drawbacks. For instance, the computational overhead of training multiple models increases latency and memory overhead. In contrast, model merging approaches offer a promising alternative that does not require training multiple models. In this work, we introduce model merging, specifically weighted averaging, in KGE models. Herein, a running average of model parameters from a training epoch onward is maintained and used for predictions. To address this, we additionally propose an approach that selectively updates the running average of the ensemble model parameters only when the generalization performance improves on a validation dataset. We evaluate these two different weighted averaging approaches on link prediction tasks, comparing the state-of-the-art benchmark ensemble approach. Additionally, we evaluate the weighted averaging approach considering literal-augmented KGE models and multi-hop query answering tasks as well. The results demonstrate that the proposed weighted averaging approach consistently improves performance across diverse evaluation settings. --- ### Prompting from the bench: Large-scale pretraining is not sufficient to prepare LLMs for ordinary meaning analysis Authors: Abhishek Purushothama, Junghyun Min, Brandon Waldon, Nathan Schneider Published: 2025-10-29 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.25356v3 In the U.S. judicial system, a widespread approach to legal interpretation entails assessing how a legal text would be understood by an `ordinary' speaker of the language. Recent scholarship has proposed that legal practitioners leverage large language models (LLMs) to ascertain a text's ordinary meaning. But are LLMs up to the task? As textual interpretation questions arise in spheres ranging from criminal law to civil rights, we argue it is crucial that models not be taken as authoritative without rigorous evaluation. This work offers an empirical argument against LLM-assisted interpretation as recently practiced by legal scholars and federal judges, who reasoned the large amount of data that models see in training would enable models to illuminate how people ordinarily use certain words or phrases. In controlled experiments, we find failures in robustness which cast doubt on this assumption and raise serious questions about the utility of these models in practice. For the models in our evaluation, slight changes to the format of a question can lead to wildly different conclusions -- a vulnerability that parties with an interest in the outcome could exploit. Comparing with a dataset where people were asked similar legal interpretation questions, we see that these models are at best moderately correlated to human judgments -- not strong enough given the stakes in this domain. --- ### Analysis of Semi-Supervised Learning on Hypergraphs Authors: Adrien Weihs, Andrea L. Bertozzi, Matthew Thorpe Published: 2025-10-29 Categories: cs.LG, math.ST arXiv: https://arxiv.org/abs/2510.25354v3 Hypergraphs provide a natural framework for modeling multiway interactions. We analyze a class of variational semi-supervised learning problems posed on random geometric hypergraphs and establish asymptotic consistency in the large-data limit. In particular, we identify scaling regimes that ensure well-posedness--yielding nontrivial label propagation rather than collapse to a constant labeling--and show that discrete minimizers converge, in the continuum, to solutions of a density-weighted p-Laplacian equation. We also propose Higher-Order Hypergraph Learning (HOHL), a multiscale regularization scheme based on powers of Laplacians associated with hypergraph-induced subgraphs. For geometric point clouds, we analyze an efficient multiscale Laplacian surrogate for HOHL and prove convergence to a higher-order Sobolev-type seminorm. Numerical experiments on standard benchmarks support the practical utility of the resulting higher-order regularization. --- ### From Leakage to Fidelity: Reliable Benchmarking for Temporal Cascade Prediction Authors: Jie Peng, Rui Wang, Qiang Wang, Zhewei Wei, Bin Tong, Guan Wang, Bo Zheng Published: 2025-10-29 Categories: cs.LG, cs.SI arXiv: https://arxiv.org/abs/2510.25348v3 Temporal cascade prediction is widely studied, yet its empirical foundations remain fragile. Most existing works report results under random cascade splits that mix past and future signals, rely on datasets with limited features and no downstream conversion labels, and compare increasingly complex models without systematically examining whether benchmark conclusions are protocol-dependent. This paper argues that the field should move from leakage-prone evaluation toward fidelity-aware benchmarking. We introduce a protocol suite and renewed evaluation standard for temporal cascade prediction, centered on the Full Temporal protocol, overlap-based leakage diagnostics, and analyses of performance inflation and temporal drift. To broaden the scope of benchmark tasks, we also present Taoke, a real-world e-commerce cascade dataset with rich promoter/product features and observed purchase conversions, enabling both first-stage popularity forecasting and second-stage conversion forecasting under a shared benchmark asset. Finally, we include CasTemp as a lightweight reference method and additionally probe a larger same-task internal extension to verify that this pipeline remains operational at substantially greater scale. Together, these components turn cascade prediction from a protocol-sensitive leaderboard exercise into a more reliable analysis and benchmarking problem, while still providing a practical reference pipeline for large-scale evaluation and conversion-aware modeling. --- ### 3D CT-Based Coronary Calcium Assessment: A Feature-Driven Machine Learning Framework Authors: Ayman Abaid, Gianpiero Guidone, Sara Alsubai, Foziyah Alquahtani, Talha Iqbal, Ruth Sharif, Hesham Elzomor, Emiliano Bianchini, Naeif Almagal, Michael G. Madden, Faisal Sharif, Ihsan Ullah Published: 2025-10-29 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2510.25347v1 Coronary artery calcium (CAC) scoring plays a crucial role in the early detection and risk stratification of coronary artery disease (CAD). In this study, we focus on non-contrast coronary computed tomography angiography (CCTA) scans, which are commonly used for early calcification detection in clinical settings. To address the challenge of limited annotated data, we propose a radiomics-based pipeline that leverages pseudo-labeling to generate training labels, thereby eliminating the need for expert-defined segmentations. Additionally, we explore the use of pretrained foundation models, specifically CT-FM and RadImageNet, to extract image features, which are then used with traditional classifiers. We compare the performance of these deep learning features with that of radiomics features. Evaluation is conducted on a clinical CCTA dataset comprising 182 patients, where individuals are classified into two groups: zero versus non-zero calcium scores. We further investigate the impact of training on non-contrast datasets versus combined contrast and non-contrast datasets, with testing performed only on non contrast scans. Results show that radiomics-based models significantly outperform CNN-derived embeddings from foundation models (achieving 84% accuracy and p<0.05), despite the unavailability of expert annotations. --- ### Informative Sample Selection Model for Skeleton-based Action Recognition with Limited Training Samples Authors: Zhigang Tu, Zhengbo Zhang, Jia Gong, Junsong Yuan, Bo Du Published: 2025-10-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.25345v1 Skeleton-based human action recognition aims to classify human skeletal sequences, which are spatiotemporal representations of actions, into predefined categories. To reduce the reliance on costly annotations of skeletal sequences while maintaining competitive recognition accuracy, the task of 3D Action Recognition with Limited Training Samples, also known as semi-supervised 3D Action Recognition, has been proposed. In addition, active learning, which aims to proactively select the most informative unlabeled samples for annotation, has been explored in semi-supervised 3D Action Recognition for training sample selection. Specifically, researchers adopt an encoder-decoder framework to embed skeleton sequences into a latent space, where clustering information, combined with a margin-based selection strategy using a multi-head mechanism, is utilized to identify the most informative sequences in the unlabeled set for annotation. However, the most representative skeleton sequences may not necessarily be the most informative for the action recognizer, as the model may have already acquired similar knowledge from previously seen skeleton samples. To solve it, we reformulate Semi-supervised 3D action recognition via active learning from a novel perspective by casting it as a Markov Decision Process (MDP). Built upon the MDP framework and its training paradigm, we train an informative sample selection model to intelligently guide the selection of skeleton sequences for annotation. To enhance the representational capacity of the factors in the state-action pairs within our method, we project them from Euclidean space to hyperbolic space. Furthermore, we introduce a meta tuning strategy to accelerate the deployment of our method in real-world scenarios. Extensive experiments on three 3D action recognition benchmarks demonstrate the effectiveness of our method. --- ### PACT: Phenotype-Aware Contrastive Team Representation for Multi-Phenotype Grouped Ad Hoc Teamwork Authors: Beiwen Zhang, Yongheng Liang, Guowei Zou, Haitao Wang, Liu Cong, Hejun Wu Published: 2025-10-29 Categories: cs.MA, cs.AI arXiv: https://arxiv.org/abs/2510.25340v2 Learning to collaborate with various unfamiliar teammates poses a great challenge in the domain of multi-agent systems. Existing ad hoc teamwork methods typically drive controlled agents to collaborate with a group of teammates exhibiting a single coordination phenotype shaped by the same reward function. However, in real-world applications, controlled agents should collaborate with unfamiliar teammates of diverse coordination phenotypes among groups that have never worked together. We formalize this as the Multi-Phenotype Grouped Ad Hoc Teamwork (MPG-AHT) problem, and propose Phenotype-Aware Contrastive Team Representation (PACT) to solve this problem. PACT is empowered with phenotype-aware contrastive learning and relational reasoning to accurately distinguish coordination phenotypes and capture inter-agent interactions. Extensive experiments on multi-phenotype collaboration tasks show that PACT outperforms state-of-the-art baselines on average, achieving a mean 21.0% gain in out-of-distribution evaluation and a mean 36.5% gain in sample efficiency. --- ### CRMWeaver: Building Powerful Business Agent via Agentic RL and Shared Memories Authors: Yilong Lai, Yipin Yang, Ting Liang, Jialong Wu, Zhenglin Wang, Jianguo Lin, Keping Yang Published: 2025-10-29 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.25333v2 Recent years have witnessed the rapid development of LLM-based agents, which shed light on using language agents to solve complex real-world problems. A prominent application lies in business agents, which interact with databases and internal knowledge bases via tool calls to fulfill diverse user requirements. However, this domain is characterized by intricate data relationships and a wide range of heterogeneous tasks, from statistical data queries to knowledge-based question-answering. To address these challenges, we propose CRMWeaver, a novel approach that enhances business agents in such complex settings. To acclimate the agentic model to intricate business environments, we employ a synthesis data generation and RL-based paradigm during training, which significantly improves the model's ability to handle complex data and varied tasks. During inference, a shared memories mechanism is introduced, prompting the agent to learn from task guidelines in similar problems, thereby further boosting its effectiveness and generalization, especially in unseen scenarios. We validate the efficacy of our approach on the CRMArena-Pro dataset, where our lightweight model achieves competitive results in both B2B and B2C business scenarios, underscoring its practical value for real-world applications. --- ### StreamingCoT: A Dataset for Temporal Dynamics and Multimodal Chain-of-Thought Reasoning in Streaming VideoQA Authors: Yuhang Hu, Zhenyu Yang, Shihan Wang, Shengsheng Qian, Bin Wen, Fan Yang, Tingting Gao, Changsheng Xu Published: 2025-10-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.25332v1 The rapid growth of streaming video applications demands multimodal models with enhanced capabilities for temporal dynamics understanding and complex reasoning. However, current Video Question Answering (VideoQA) datasets suffer from two critical limitations: 1) Static annotation mechanisms fail to capture the evolving nature of answers in temporal video streams, and 2) The absence of explicit reasoning process annotations restricts model interpretability and logical deduction capabilities. To address these challenges, We introduce StreamingCoT, the first dataset explicitly designed for temporally evolving reasoning in streaming VideoQA and multimodal Chain-of-Thought (CoT) tasks. Our framework first establishes a dynamic hierarchical annotation architecture that generates per-second dense descriptions and constructs temporally-dependent semantic segments through similarity fusion, paired with question-answer sets constrained by temporal evolution patterns. We further propose an explicit reasoning chain generation paradigm that extracts spatiotemporal objects via keyframe semantic alignment, derives object state transition-based reasoning paths using large language models, and ensures logical coherence through human-verified validation. This dataset establishes a foundation for advancing research in streaming video understanding, complex temporal reasoning, and multimodal inference. Our StreamingCoT and its construction toolkit can be accessed at https://github.com/Fleeting-hyh/StreamingCoT. --- ### MMEdge: Accelerating On-device Multimodal Inference via Pipelined Sensing and Encoding Authors: Runxi Huang, Mingxuan Yu, Mingyu Tsoi, Xiaomin Ouyang Published: 2025-10-29 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.25327v6 Real-time multimodal inference on resource-constrained edge devices is essential for applications such as autonomous driving, human-computer interaction, and mobile health. However, prior work often overlooks the tight coupling between sensing dynamics and model execution, as well as the complex inter-modality dependencies. In this paper, we propose MMEdge, a new on-device multimodal inference framework based on pipelined sensing and encoding. Instead of waiting for complete sensor inputs, MMEdge decomposes the entire inference process into a sequence of fine-grained sensing and encoding units, allowing computation to proceed incrementally as data arrive. MMEdge also introduces a lightweight but effective temporal aggregation module that captures rich temporal dynamics across different pipelined units to maintain accuracy performance. Such pipelined design also opens up opportunities for fine-grained cross-modal optimization and early decision-making during inference. To further enhance system performance under resource variability and input data complexity, MMEdge incorporates an adaptive multimodal configuration optimizer that dynamically selects optimal sensing and model configurations for each modality under latency constraints, and a cross-modal speculative skipping mechanism that bypasses future units of slower modalities when early predictions reach sufficient confidence. We evaluate MMEdge using two public multimodal datasets and deploy it on a real-world unmanned aerial vehicle (UAV)-based multimodal testbed. The results show that MMEdge significantly reduces end-to-end latency while maintaining high task accuracy across various system and data dynamics. A video demonstration of MMEdge's performance in real world is available at https://youtu.be/qRew7sT-iWw. --- ### CDFlow: Building Invertible Layers with Circulant and Diagonal Matrices Authors: Xuchen Feng, Siyu Liao Published: 2025-10-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.25323v4 Normalizing flows are deep generative models that enable efficient likelihood estimation and sampling through invertible transformations. A key challenge is to design linear layers that enhance expressiveness while maintaining efficient computation of the Jacobian determinant and inverse. We introduce a novel invertible linear layer based on the product of circulant and diagonal matrices. This decomposition reduces parameter complexity from $\mathcal{O}(n^2)$ to $\mathcal{O}(mn)$ using $m$ diagonal matrices and $m-1$ circulant matrices while still approximating general linear transformations. By leveraging the Fast Fourier Transform, our approach reduces the time complexity of matrix inversion from $\mathcal{O}(n^3)$ to $\mathcal{O}(mn\log n)$ and that of computing the log-determinant from $\mathcal{O}(n^3)$ to $\mathcal{O}(mn)$, where $n$ is the input dimension. We build upon this layer to develop Circulant-Diagonal Flow (CDFlow), which achieves strong density estimation on natural image datasets and effectively models data with inherent periodic structure. Furthermore, CDFlow significantly accelerates key operations in normalizing flows, providing practical benefits for scalable generative modeling. --- ### GAP: Graph-Based Agent Planning with Parallel Tool Use and Reinforcement Learning Authors: Jiaqi Wu, Qinlao Zhao, Zefeng Chen, Kai Qin, Yifei Zhao, Xueqian Wang, Yuhang Yao Published: 2025-10-29 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2510.25320v1 Autonomous agents powered by large language models (LLMs) have shown impressive capabilities in tool manipulation for complex task-solving. However, existing paradigms such as ReAct rely on sequential reasoning and execution, failing to exploit the inherent parallelism among independent sub-tasks. This sequential bottleneck leads to inefficient tool utilization and suboptimal performance in multi-step reasoning scenarios. We introduce Graph-based Agent Planning (GAP), a novel framework that explicitly models inter-task dependencies through graph-based planning to enable adaptive parallel and serial tool execution. Our approach trains agent foundation models to decompose complex tasks into dependency-aware sub-task graphs, autonomously determining which tools can be executed in parallel and which must follow sequential dependencies. This dependency-aware orchestration achieves substantial improvements in both execution efficiency and task accuracy. To train GAP, we construct a high-quality dataset of graph-based planning traces derived from the Multi-Hop Question Answering (MHQA) benchmark. We employ a two-stage training strategy: supervised fine-tuning (SFT) on the curated dataset, followed by reinforcement learning (RL) with a correctness-based reward function on strategically sampled queries where tool-based reasoning provides maximum value. Experimental results on MHQA datasets demonstrate that GAP significantly outperforms traditional ReAct baselines, particularly on multi-step retrieval tasks, while achieving dramatic improvements in tool invocation efficiency through intelligent parallelization. The project page is available at: https://github.com/WJQ7777/Graph-Agent-Planning. --- ### 4-Doodle: Text to 3D Sketches that Move! Authors: Hao Chen, Jiaqi Wang, Yonggang Qi, Ke Li, Kaiyue Pang, Yi-Zhe Song Published: 2025-10-29 Categories: cs.GR, cs.AI arXiv: https://arxiv.org/abs/2510.25319v1 We present a novel task: text-to-3D sketch animation, which aims to bring freeform sketches to life in dynamic 3D space. Unlike prior works focused on photorealistic content generation, we target sparse, stylized, and view-consistent 3D vector sketches, a lightweight and interpretable medium well-suited for visual communication and prototyping. However, this task is very challenging: (i) no paired dataset exists for text and 3D (or 4D) sketches; (ii) sketches require structural abstraction that is difficult to model with conventional 3D representations like NeRFs or point clouds; and (iii) animating such sketches demands temporal coherence and multi-view consistency, which current pipelines do not address. Therefore, we propose 4-Doodle, the first training-free framework for generating dynamic 3D sketches from text. It leverages pretrained image and video diffusion models through a dual-space distillation scheme: one space captures multi-view-consistent geometry using differentiable Bézier curves, while the other encodes motion dynamics via temporally-aware priors. Unlike prior work (e.g., DreamFusion), which optimizes from a single view per step, our multi-view optimization ensures structural alignment and avoids view ambiguity, critical for sparse sketches. Furthermore, we introduce a structure-aware motion module that separates shape-preserving trajectories from deformation-aware changes, enabling expressive motion such as flipping, rotation, and articulated movement. Extensive experiments show that our method produces temporally realistic and structurally stable 3D sketch animations, outperforming existing baselines in both fidelity and controllability. We hope this work serves as a step toward more intuitive and accessible 4D content creation. --- ### Prototype-Driven Adaptation for Few-Shot Object Detection Authors: Yushen Huang, Zhiming Wang Published: 2025-10-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.25318v1 Few-shot object detection (FSOD) often suffers from base-class bias and unstable calibration when only a few novel samples are available. We propose Prototype-Driven Alignment (PDA), a lightweight, plug-in metric head for DeFRCN that provides a prototype-based "second opinion" complementary to the linear classifier. PDA maintains support-only prototypes in a learnable identity-initialized projection space and optionally applies prototype-conditioned RoI alignment to reduce geometric mismatch. During fine-tuning, prototypes can be adapted via exponential moving average(EMA) updates on labeled foreground RoIs-without introducing class-specific parameters-and are frozen at inference to ensure strict protocol compliance. PDA employs a best-of-K matching scheme to capture intra-class multi-modality and temperature-scaled fusion to combine metric similarities with detector logits. Experiments on VOC FSOD and GFSOD benchmarks show that PDA consistently improves novel-class performance with minimal impact on base classes and negligible computational overhead. --- ### Tuning-Free Sampling via Optimization on the Space of Probability Measures Authors: Louis Sharrock, Christopher Nemeth Published: 2025-10-29 Categories: stat.ME, stat.ML arXiv: https://arxiv.org/abs/2510.25315v1 We introduce adaptive, tuning-free step size schedules for gradient-based sampling algorithms obtained as time-discretizations of Wasserstein gradient flows. The result is a suite of tuning-free sampling algorithms, including tuning-free variants of the unadjusted Langevin algorithm (ULA), stochastic gradient Langevin dynamics (SGLD), mean-field Langevin dynamics (MFLD), Stein variational gradient descent (SVGD), and variational gradient descent (VGD). More widely, our approach yields tuning-free algorithms for solving a broad class of stochastic optimization problems over the space of probability measures. Under mild assumptions (e.g., geodesic convexity and locally bounded stochastic gradients), we establish strong theoretical guarantees for our approach. In particular, we recover the convergence rate of optimally tuned versions of these algorithms up to logarithmic factors, in both nonsmooth and smooth settings. We then benchmark the performance of our methods against comparable existing approaches. Across a variety of tasks, our algorithms achieve similar performance to the optimal performance of existing algorithms, with no need to tune a step size parameter. --- ### Large-FOV RGBD Imaging via Structured PSF Coding in a Bio-inspired Monocentric System Authors: Zongxi Yu, Xiaolong Qian, Shaohua Gao, Qi Jiang, Yao Gao, Kailun Yang, Kaiwei Wang Published: 2025-10-29 Categories: cs.CV, cs.RO, eess.IV, physics.optics arXiv: https://arxiv.org/abs/2510.25314v2 High-fidelity large-field-of-view (LFOV) 3D sensing, essential for autonomous platforms, is hindered by the coupling of anisotropic off-axis aberrations and the ill-posed nature of monocular depth estimation. To address this fundamental physical bottleneck, we propose the Bio-inspired Monocentric Imaging (BMI) framework, a holistic co-design integrating a monocentric optical topology with a physics-aware reconstruction network. By pairing a concentric spherical lens with a hemispherical sensor, our system structurally eliminates coma, astigmatism, and field curvature. Instead of relying on external modulators or hardware redundancy, we exploit the intrinsic aberration as a deterministic, radially symmetric carrier for depth encoding. Theoretical analysis via the Cramér-Rao Lower Bound confirms that this topology maintains superior depth sensitivity across the entire FOV. To decode these optical cues, our framework utilizes a dual-head network to jointly recover high-fidelity All-in-Focus images and dense metric depth maps from single-shot captures. The efficacy of this co-design is evaluated through physically-based simulations of field-dependent PSFs across the full optical FOV. On NYU Depth V2, our system achieves a superior balance of image fidelity (31.15dB PSNR) and depth precision (0.161m RMSE). It further maintains consistent reconstruction under spatially varying PSFs sampled across a 120° optical FOV, mitigating the peripheral degradation observed in conventional wide-field designs. The source code is publicly available at https://github.com/ZongxiYu-ZJU/BMI. --- ### Dense and Diverse Goal Coverage in Multi Goal Reinforcement Learning Authors: Sagalpreet Singh, Rishi Saket, Aravindan Raghuveer Published: 2025-10-29 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2510.25311v2 Reinforcement Learning algorithms are primarily focused on learning a policy that maximizes expected return. As a result, the learned policy can exploit one or few reward sources. However, in many natural situations, it is desirable to learn a policy that induces a dispersed marginal state distribution over rewarding states, while maximizing the expected return which is typically tied to reaching a goal state. This aspect remains relatively unexplored. Existing techniques based on entropy regularization and intrinsic rewards use stochasticity for encouraging exploration to find an optimal policy which may not necessarily lead to dispersed marginal state distribution over rewarding states. Other RL algorithms which match a target distribution assume the latter to be available apriori. This may be infeasible in large scale systems where enumeration of all states is not possible and a state is determined to be a goal state only upon reaching it. We formalize the problem of maximizing the expected return while uniformly visiting the goal states as Multi Goal RL in which an oracle classifier over the state space determines the goal states. We propose a novel algorithm that learns a high-return policy mixture with marginal state distribution dispersed over the set of goal states. Our algorithm is based on optimizing a custom RL reward which is computed - based on the current policy mixture - at each iteration for a set of sampled trajectories. The latter are used via an offline RL algorithm to update the policy mixture. We prove performance guarantees for our algorithm, showing efficient convergence bounds for optimizing a natural objective which captures the expected return as well as the dispersion of the marginal state distribution over the goal states. We design and perform experiments on synthetic MDPs and standard RL environments to evaluate the effectiveness of our algorithm. --- ### Parrot: A Training Pipeline Enhances Both Program CoT and Natural Language CoT for Reasoning Authors: Senjie Jin, Lu Chen, Zhiheng Xi, Yuhui Wang, Sirui Song, Yuhao Zhou, Xinbo Zhang, Peng Sun, Hong Lu, Tao Gui, Qi Zhang, Xuanjing Huang Published: 2025-10-29 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.25310v1 Natural language chain-of-thought (N-CoT) and Program chain-of-thought (P-CoT) have emerged as two primary paradigms for large language models (LLMs) to solve mathematical reasoning problems. Current research typically endeavors to achieve unidirectional enhancement: P-CoT enhanced N-CoT or N-CoT enhanced P-CoT. In this paper, we seek to fully unleash the two paradigms' strengths for mutual enhancement and ultimately achieve simultaneous improvements. We conduct a detailed analysis of the error types across two paradigms, based on which we propose Parrot, a novel training pipeline for mathematical problems: 1) Three target-designed subtasks integrate sequential P-CoT and N-CoT generation. 2) A subtask hybrid training strategy to facilitate natural language semantic transferability. 3) The converted N-CoT auxiliary reward is designed to alleviate the sparse rewards in P-CoT optimization. Extensive experiments demonstrate that Parrot significantly enhances both the performance of N-CoT and P-CoT, especially on N-CoT. Using Parrot SFT, the N-CoT performance of LLaMA2 and CodeLLaMA achieve gains of +21.87 and +21.48 on MathQA over the RL baseline, which is resource-intensive. --- ### Hierarchical Physics-Embedded Learning for Partially Known Spatiotemporal Dynamics Authors: Xizhe Wang, Xiaobin Song, Hongbo Zhao, Qingshan Jia, Qianchuan Zhao, Hao Sun, Benben Jiang Published: 2025-10-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.25306v3 Partial physical knowledge--governing structures known, constitutive relations or their combinations not--pervades spatiotemporal systems. Existing scientific machine learning paradigms learn evolution largely from data, impose equations as soft constraints, or hard-code physical terms into network updates; none exploits knowledge of this form. Here we introduce the hierarchical physics-embedded adaptive Fourier neural operator, encoding such knowledge as computational architecture rather than penalizing or appending it: a first level learns or embeds fundamental physical expressions as intermediate representations, and a second level learns or embeds their governing combination, with adaptive Fourier layers capturing nonlocal, high-order couplings at each level. We prove a hierarchical error decomposition--embedding known components removes or shrinks their terms, and a parameter-complexity advantage: when the hierarchy aligns with the compositional structure of the dynamics, the number of learnable Fourier parameters sufficient for a prescribed accuracy grows strictly more slowly than for a single-level operator. Across canonical phase-field systems and experimental hydrofoil wake data, our method reduces long horizon extrapolation errors by up to ~70% relative to state-of-the-art physics encoded and neural operator baselines, while preserving physically meaningful morphology, energetic consistency, and spectral structure, and maintaining robust performance under sparse and noisy observations. The separated intermediate representations further enable symbolic recovery of unknown constitutive relations in partially specified PDEs. These results establish hierarchical physics embedding as a theoretically grounded route to prediction and discovery when governing laws are neither fully known nor absent, but partially known and compositionally organized. --- ### Teaching Sarcasm: Few-Shot Multimodal Sarcasm Detection via Distillation to a Parameter-Efficient Student Authors: Soumyadeep Jana, Sanasam Ranbir Singh Published: 2025-10-29 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.25303v1 Multimodal sarcasm detection is challenging, especially in low-resource settings where subtle image-text contradictions are hard to learn due to scarce annotated data, which hinders the model's performance. Parameter-efficient fine-tuning (PEFT) methods like adapters, LoRA, and prompt tuning reduce overfitting but struggle to reach optimal performance due to limited supervision from few-shot data. We propose PEKD, a unified framework that enhances PEFT methods via distillation from an expert model trained on large-scale sarcasm data, which acts as the teacher. To mitigate unreliable signals from the teacher, we introduce an entropy-aware gating mechanism that dynamically adjusts the distillation strength based on teacher confidence. Experiments on two public datasets demonstrate that our PEKD framework enables PEFT methods to outperform both prior parameter-efficient approaches and large multimodal models, achieving strong results in the few-shot scenario. The framework is modular and adaptable to a wide range of multimodal models and tasks. --- ### GaTector+: A Unified Head-free Framework for Gaze Object and Gaze Following Prediction Authors: Yang Jin, Guangyu Guo, Binglu Wang Published: 2025-10-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.25301v1 Gaze object detection and gaze following are fundamental tasks for interpreting human gaze behavior or intent. However, most previous methods usually solve these two tasks separately, and their prediction of gaze objects and gaze following typically depend on head-related prior knowledge during both the training phase and real-world deployment. This dependency necessitates an auxiliary network to extract head location, thus precluding joint optimization across the entire system and constraining the practical applicability. To this end, we propose GaTector+, a unified framework for gaze object detection and gaze following, which eliminates the dependence on the head-related priors during inference. Specifically, GaTector+ uses an expanded specific-general-specific feature extractor that leverages a shared backbone, which extracts general features for gaze following and object detection using the shared backbone while using specific blocks before and after the shared backbone to better consider the specificity of each sub-task. To obtain head-related knowledge without prior information, we first embed a head detection branch to predict the head of each person. Then, before regressing the gaze point, a head-based attention mechanism is proposed to fuse the sense feature and gaze feature with the help of head location. Since the suboptimization of the gaze point heatmap leads to the performance bottleneck, we propose an attention supervision mechanism to accelerate the learning of the gaze heatmap. Finally, we propose a novel evaluation metric, mean Similarity over Candidates (mSoC), for gaze object detection, which is more sensitive to variations between bounding boxes. The experimental results on multiple benchmark datasets demonstrate the effectiveness of our model in both gaze object detection and gaze following tasks. --- ### Stochastic Optimization in Semi-Discrete Optimal Transport: Convergence Analysis and Minimax Rate Authors: Ferdinand Genans, Antoine Godichon-Baggioni, François-Xavier Vialard, Olivier Wintenberger Published: 2025-10-29 Categories: math.ST, stat.ML arXiv: https://arxiv.org/abs/2510.25287v1 We investigate the semi-discrete Optimal Transport (OT) problem, where a continuous source measure $μ$ is transported to a discrete target measure $ν$, with particular attention to the OT map approximation. In this setting, Stochastic Gradient Descent (SGD) based solvers have demonstrated strong empirical performance in recent machine learning applications, yet their theoretical guarantee to approximate the OT map is an open question. In this work, we answer it positively by providing both computational and statistical convergence guarantees of SGD. Specifically, we show that SGD methods can estimate the OT map with a minimax convergence rate of $\mathcal{O}(1/\sqrt{n})$, where $n$ is the number of samples drawn from $μ$. To establish this result, we study the averaged projected SGD algorithm, and identify a suitable projection set that contains a minimizer of the objective, even when the source measure is not compactly supported. Our analysis holds under mild assumptions on the source measure and applies to MTW cost functions,whic include $\|\cdot\|^p$ for $p \in (1, \infty)$. We finally provide numerical evidence for our theoretical results. --- ### On the Stability of Neural Networks in Deep Learning Authors: Blaise Delattre Published: 2025-10-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.25282v1 Deep learning has achieved remarkable success across a wide range of tasks, but its models often suffer from instability and vulnerability: small changes to the input may drastically affect predictions, while optimization can be hindered by sharp loss landscapes. This thesis addresses these issues through the unifying perspective of sensitivity analysis, which examines how neural networks respond to perturbations at both the input and parameter levels. We study Lipschitz networks as a principled way to constrain sensitivity to input perturbations, thereby improving generalization, adversarial robustness, and training stability. To complement this architectural approach, we introduce regularization techniques based on the curvature of the loss function, promoting smoother optimization landscapes and reducing sensitivity to parameter variations. Randomized smoothing is also explored as a probabilistic method for enhancing robustness at decision boundaries. By combining these perspectives, we develop a unified framework where Lipschitz continuity, randomized smoothing, and curvature regularization interact to address fundamental challenges in stability. The thesis contributes both theoretical analysis and practical methodologies, including efficient spectral norm computation, novel Lipschitz-constrained layers, and improved certification procedures. --- ### Diffusion-Driven Progressive Target Manipulation for Source-Free Domain Adaptation Authors: Yuyang Huang, Yabo Chen, Junyu Zhou, Wenrui Dai, Xiaopeng Zhang, Junni Zou, Hongkai Xiong, Qi Tian Published: 2025-10-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.25279v1 Source-free domain adaptation (SFDA) is a challenging task that tackles domain shifts using only a pre-trained source model and unlabeled target data. Existing SFDA methods are restricted by the fundamental limitation of source-target domain discrepancy. Non-generation SFDA methods suffer from unreliable pseudo-labels in challenging scenarios with large domain discrepancies, while generation-based SFDA methods are evidently degraded due to enlarged domain discrepancies in creating pseudo-source data. To address this limitation, we propose a novel generation-based framework named Diffusion-Driven Progressive Target Manipulation (DPTM) that leverages unlabeled target data as references to reliably generate and progressively refine a pseudo-target domain for SFDA. Specifically, we divide the target samples into a trust set and a non-trust set based on the reliability of pseudo-labels to sufficiently and reliably exploit their information. For samples from the non-trust set, we develop a manipulation strategy to semantically transform them into the newly assigned categories, while simultaneously maintaining them in the target distribution via a latent diffusion model. Furthermore, we design a progressive refinement mechanism that progressively reduces the domain discrepancy between the pseudo-target domain and the real target domain via iterative refinement. Experimental results demonstrate that DPTM outperforms existing methods by a large margin and achieves state-of-the-art performance on four prevailing SFDA benchmark datasets with different scales. Remarkably, DPTM can significantly enhance the performance by up to 18.6% in scenarios with large source-target gaps. --- ### Adapting Small Language Models to Low-Resource Domains: A Case Study in Hindi Tourism QA Authors: Sandipan Majhi, Paheli Bhattacharya Published: 2025-10-29 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.25273v1 Domain-specific question answering in low-resource languages faces two key challenges: scarcity of annotated datasets and limited domain knowledge in general-purpose language models. In this work, we present a multi-stage finetuning strategy to adapt lightweight language models to the Hindi tourism domain by leveraging both original and synthetic training data. Synthetic question-answer pairs are generated using large LLMs (LLaMA-70B, Phi-14B) and used to augment the limited original dataset. We explore several training methodologies and analyse their impact on domain generalisation. Our results demonstrate that large models can efficiently generate synthetic data, while small models can effectively adapt to it, offering a scalable pathway for low-resource, domain-specific QA. --- ### SynHLMA:Synthesizing Hand Language Manipulation for Articulated Object with Discrete Human Object Interaction Representation Authors: Wang zhi, Yuyan Liu, Liu Liu, Li Zhang, Ruixuan Lu, Dan Guo Published: 2025-10-29 Categories: cs.RO, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2510.25268v2 Generating hand grasps with language instructions is a widely studied topic that benefits from embodied AI and VR/AR applications. While transferring into hand articulatied object interaction (HAOI), the hand grasps synthesis requires not only object functionality but also long-term manipulation sequence along the object deformation. This paper proposes a novel HAOI sequence generation framework SynHLMA, to synthesize hand language manipulation for articulated objects. Given a complete point cloud of an articulated object, we utilize a discrete HAOI representation to model each hand object interaction frame. Along with the natural language embeddings, the representations are trained by an HAOI manipulation language model to align the grasping process with its language description in a shared representation space. A joint-aware loss is employed to ensure hand grasps follow the dynamic variations of articulated object joints. In this way, our SynHLMA achieves three typical hand manipulation tasks for articulated objects of HAOI generation, HAOI prediction and HAOI interpolation. We evaluate SynHLMA on our built HAOI-lang dataset and experimental results demonstrate the superior hand grasp sequence generation performance comparing with state-of-the-art. We also show a robotics grasp application that enables dexterous grasps execution from imitation learning using the manipulation sequence provided by our SynHLMA. Our codes and datasets will be made publicly available. --- ### LangHOPS: Language Grounded Hierarchical Open-Vocabulary Part Segmentation Authors: Yang Miao, Jan-Nico Zaech, Xi Wang, Fabien Despinoy, Danda Pani Paudel, Luc Van Gool Published: 2025-10-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.25263v3 We propose LangHOPS, the first Multimodal Large Language Model (MLLM) based framework for open-vocabulary object-part instance segmentation. Given an image, LangHOPS can jointly detect and segment hierarchical object and part instances from open-vocabulary candidate categories. Unlike prior approaches that rely on heuristic or learnable visual grouping, our approach grounds object-part hierarchies in language space. It integrates the MLLM into the object-part parsing pipeline to leverage its rich knowledge and reasoning capabilities, and link multi-granularity concepts within the hierarchies. We evaluate LangHOPS across multiple challenging scenarios, including in-domain and cross-dataset object-part instance segmentation, and zero-shot semantic segmentation. LangHOPS achieves state-of-the-art results, surpassing previous methods by 5.5% Average Precision (AP) (in-domain) and 4.8% (cross-dataset) on the PartImageNet dataset and by 2.5% mIOU on unseen object parts in ADE20K (zero-shot). Ablation studies further validate the effectiveness of the language-grounded hierarchy and MLLM driven part query refinement strategy. The code will be released here. --- ### IBNorm: Information-Bottleneck Inspired Normalization for Representation Learning Authors: Xiandong Zou, Jia Li, Xiaotong Yuan, Pan Zhou Published: 2025-10-29 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2510.25262v2 Normalization is fundamental to deep learning, but existing approaches such as BatchNorm, LayerNorm, and RMSNorm are variance-centric by enforcing zero mean and unit variance, stabilizing training without controlling how representations capture task-relevant information. We propose IB-Inspired Normalization (IBNorm), a simple yet powerful family of methods grounded in the Information Bottleneck principle. IBNorm introduces bounded compression operations that encourage embeddings to preserve predictive information while suppressing nuisance variability, yielding more informative representations while retaining the stability and compatibility of standard normalization. Theoretically, we prove that IBNorm achieves a higher IB value and tighter generalization bounds than variance-centric methods. Empirically, IBNorm consistently outperforms BatchNorm, LayerNorm, and RMSNorm across large-scale language models (LLaMA, GPT-2) and vision models (ResNet, ViT), with mutual information analysis confirming superior information bottleneck behavior. Code will be released publicly. --- ### TV-Rec: Time-Variant Convolutional Filter for Sequential Recommendation Authors: Yehjin Shin, Jeongwhan Choi, Seojin Kim, Noseong Park Published: 2025-10-29 Categories: cs.IR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.25259v1 Recently, convolutional filters have been increasingly adopted in sequential recommendation for their ability to capture local sequential patterns. However, most of these models complement convolutional filters with self-attention. This is because convolutional filters alone, generally fixed filters, struggle to capture global interactions necessary for accurate recommendation. We propose Time-Variant Convolutional Filters for Sequential Recommendation (TV-Rec), a model inspired by graph signal processing, where time-variant graph filters capture position-dependent temporal variations in user sequences. By replacing both fixed kernels and self-attention with time-variant filters, TV-Rec achieves higher expressive power and better captures complex interaction patterns in user behavior. This design not only eliminates the need for self-attention but also reduces computation while accelerating inference. Extensive experiments on six public benchmarks show that TV-Rec outperforms state-of-the-art baselines by an average of 7.49%. ---