# Research Papers — 2025-10 · bundle page 103 of 217

> Full-text markdown of papers #5101–5150 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/103
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/102.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/104.md)

### Response to Discussions of "Causal and Counterfactual Views of Missing Data Models"

Authors: Razieh Nabi, Rohit Bhattacharya, Ilya Shpitser, James M. Robins
Published: 2025-10-16
Categories: stat.ME, cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.14694v1

We are grateful to the discussants, Levis and Kennedy (2025), Luo and Geng (2025), Wang and van der Laan (2025), and Yang and Kim (2025), for their thoughtful comments on our paper (Nabi et al., 2025). In this rejoinder, we summarize our main contributions and respond to each discussion in turn.

---

### Online Reliable Anomaly Detection via Neuromorphic Sensing and Communications

Authors: Junya Shiraishi, Jiechen Chen, Osvaldo Simeone, Petar Popovski
Published: 2025-10-16
Categories: cs.LG, cs.NE
arXiv: https://arxiv.org/abs/2510.14688v1

This paper proposes a low-power online anomaly detection framework based on neuromorphic wireless sensor networks, encompassing possible use cases such as brain-machine interfaces and remote environmental monitoring. In the considered system, a central reader node actively queries a subset of neuromorphic sensor nodes (neuro-SNs) at each time frame. The neuromorphic sensors are event-driven, producing spikes in correspondence to relevant changes in the monitored system. The queried neuro-SNs respond to the reader with impulse radio (IR) transmissions that directly encode the sensed local events. The reader processes these event-driven signals to determine whether the monitored environment is in a normal or anomalous state, while rigorously controlling the false discovery rate (FDR) of detections below a predefined threshold. The proposed approach employs an online hypothesis testing method with e-values to maintain FDR control without requiring knowledge of the anomaly rate, and it dynamically optimizes the sensor querying strategy by casting it as a best-arm identification problem in a multi-armed bandit framework. Extensive performance evaluation demonstrates that the proposed method can reliably detect anomalies under stringent FDR requirements, while efficiently scheduling sensor communications and achieving low detection latency.

---

### xLLM Technical Report

Authors: Tongxuan Liu, Tao Peng, Peijun Yang, Xiaoyang Zhao, Xiusheng Lu, Weizhe Huang, Zirui Liu, Xiaoyu Chen, Zhiwei Liang, Jun Xiong, Donghe Jin, Minchao Zhang et al.
Published: 2025-10-16
Categories: cs.DC, cs.AI
arXiv: https://arxiv.org/abs/2510.14686v2

We introduce xLLM, an intelligent and efficient Large Language Model (LLM) inference framework designed for high-performance, large-scale enterprise-grade serving, with deep optimizations for diverse AI accelerators. To address these challenges, xLLM builds a novel decoupled service-engine architecture. At the service layer, xLLM-Service features an intelligent scheduling module that efficiently processes multimodal requests and co-locates online and offline tasks through unified elastic scheduling to maximize cluster utilization. This module also relies on a workload-adaptive dynamic Prefill-Decode (PD) disaggregation policy and a novel Encode-Prefill-Decode (EPD) disaggregation policy designed for multimodal inputs. Furthermore, it incorporates a distributed architecture to provide global KV Cache management and robust fault-tolerant capabilities for high availability. At the engine layer, xLLM-Engine co-optimizes system and algorithm designs to fully saturate computing resources. This is achieved through comprehensive multi-layer execution pipeline optimizations, an adaptive graph mode and an xTensor memory management. xLLM-Engine also further integrates algorithmic enhancements such as optimized speculative decoding and dynamic EPLB, collectively serving to substantially boost throughput and inference efficiency. Extensive evaluations demonstrate that xLLM delivers significantly superior performance and resource efficiency. Under identical TPOT constraints, xLLM achieves throughput up to 1.7x that of MindIE and 2.2x that of vLLM-Ascend with Qwen-series models, while maintaining an average throughput of 1.7x that of MindIE with Deepseek-series models. xLLM framework is publicly available at https://github.com/jd-opensource/xllm and https://github.com/jd-opensource/xllm-service.

---

### Practical, Utilitarian Algorithm Configuration

Authors: Devon Graham, Eros Rojas Velez, Kevin Leyton-Brown
Published: 2025-10-16
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.14683v2

Utilitarian algorithm configuration identifies a parameter setting for a given algorithm that maximizes a user's utility. Utility functions offer a theoretically well-grounded approach to optimizing decision-making under uncertainty and are flexible enough to capture a user's preferences over algorithm runtimes (e.g., they can describe a sharp cutoff after which a solution is no longer required, a per-hour cost for compute, or diminishing returns from algorithms that take longer to run). COUP is a recently-introduced utilitarian algorithm configuration procedure which was designed mainly to offer strong theoretical guarantees about the quality of the configuration it returns, with less attention paid to its practical performance. This paper closes that gap, bringing theoretically-grounded, utilitarian algorithm configuration to the point where it is competitive with widely used, heuristic configuration procedures that offer no performance guarantees. We present a series of improvements to COUP that improve its empirical performance without degrading its theoretical guarantees and demonstrate their benefit experimentally. Using a case study, we also illustrate ways of exploring the robustness of a given solution to the algorithm selection problem to variations in the utility function.

---

### When Planners Meet Reality: How Learned, Reactive Traffic Agents Shift nuPlan Benchmarks

Authors: Steffen Hagedorn, Luka Donkov, Aron Distelzweig, Alexandru P. Condurache
Published: 2025-10-16
Categories: cs.RO, cs.AI, cs.LG, cs.MA
arXiv: https://arxiv.org/abs/2510.14677v1

Planner evaluation in closed-loop simulation often uses rule-based traffic agents, whose simplistic and passive behavior can hide planner deficiencies and bias rankings. Widely used IDM agents simply follow a lead vehicle and cannot react to vehicles in adjacent lanes, hindering tests of complex interaction capabilities. We address this issue by integrating the state-of-the-art learned traffic agent model SMART into nuPlan. Thus, we are the first to evaluate planners under more realistic conditions and quantify how conclusions shift when narrowing the sim-to-real gap. Our analysis covers 14 recent planners and established baselines and shows that IDM-based simulation overestimates planning performance: nearly all scores deteriorate. In contrast, many planners interact better than previously assumed and even improve in multi-lane, interaction-heavy scenarios like lane changes or turns. Methods trained in closed-loop demonstrate the best and most stable driving performance. However, when reaching their limits in augmented edge-case scenarios, all learned planners degrade abruptly, whereas rule-based planners maintain reasonable basic behavior. Based on our results, we suggest SMART-reactive simulation as a new standard closed-loop benchmark in nuPlan and release the SMART agents as a drop-in alternative to IDM at https://github.com/shgd95/InteractiveClosedLoop.

---

### NAEL: Non-Anthropocentric Ethical Logic

Authors: Bianca Maria Lerma, Rafael Peñaloza
Published: 2025-10-16
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.14676v1

We introduce NAEL (Non-Anthropocentric Ethical Logic), a novel ethical framework for artificial agents grounded in active inference and symbolic reasoning. Departing from conventional, human-centred approaches to AI ethics, NAEL formalizes ethical behaviour as an emergent property of intelligent systems minimizing global expected free energy in dynamic, multi-agent environments. We propose a neuro-symbolic architecture to allow agents to evaluate the ethical consequences of their actions in uncertain settings. The proposed system addresses the limitations of existing ethical models by allowing agents to develop context-sensitive, adaptive, and relational ethical behaviour without presupposing anthropomorphic moral intuitions. A case study involving ethical resource distribution illustrates NAEL's dynamic balancing of self-preservation, epistemic learning, and collective welfare.

---

### VTimeCoT: Thinking by Drawing for Video Temporal Grounding and Reasoning

Authors: Jinglei Zhang, Yuanfan Guo, Rolandos Alexandros Potamias, Jiankang Deng, Hang Xu, Chao Ma
Published: 2025-10-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.14672v1

In recent years, video question answering based on multimodal large language models (MLLM) has garnered considerable attention, due to the benefits from the substantial advancements in LLMs. However, these models have a notable deficiency in the domains of video temporal grounding and reasoning, posing challenges to the development of effective real-world video understanding systems. Inspired by how humans use video players to interact with the progress bar for video comprehension, we introduce VTimeCoT, a simple yet effective training-free framework, designed for high-performance video grounding and reasoning. The proposed framework incorporates two novel visual tools of the progress bar: a plug-and-play progress bar integration tool and a high-efficiency highlighting tool. In addition, to address the limitations of conventional text-based chain-of-thought (CoT) approaches, we introduce a visuotemporal CoT process that integrates cross-modality reasoning across both video and text. Our approach demonstrates significant performance improvements on both Qwen2VL-7B and GPT4o baselines in tasks of video temporal grounding and reasoning-based question answering. Finally, we showcase that the proposed framework achieves a compositional and interpretable reasoning process. Project page: https://vtimecot.github.io

---

### TITAN: Graph-Executable Reasoning for Cyber Threat Intelligence

Authors: Marco Simoni, Aleksandar Fontana, Andrea Saracino, Paolo Mori
Published: 2025-10-16
Categories: cs.AI, cs.CL, cs.CR, cs.IR
arXiv: https://arxiv.org/abs/2510.14670v1

TITAN (Threat Intelligence Through Automated Navigation) is a framework that connects natural-language cyber threat queries with executable reasoning over a structured knowledge graph. It integrates a path planner model, which predicts logical relation chains from text, and a graph executor that traverses the TITAN Ontology to retrieve factual answers and supporting evidence. Unlike traditional retrieval systems, TITAN operates on a typed, bidirectional graph derived from MITRE, allowing reasoning to move clearly and reversibly between threats, behaviors, and defenses. To support training and evaluation, we introduce the TITAN Dataset, a corpus of 88209 examples (Train: 74258; Test: 13951) pairing natural language questions with executable reasoning paths and step by step Chain of Thought explanations. Empirical evaluations show that TITAN enables models to generate syntactically valid and semantically coherent reasoning paths that can be deterministically executed on the underlying graph.

---

### Machine Learning and Public Health: Identifying and Mitigating Algorithmic Bias through a Systematic Review

Authors: Sara Altamirano, Arjan Vreeken, Sennay Ghebreab
Published: 2025-10-16
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.14669v1

Machine learning (ML) promises to revolutionize public health through improved surveillance, risk stratification, and resource allocation. However, without systematic attention to algorithmic bias, ML may inadvertently reinforce existing health disparities. We present a systematic literature review of algorithmic bias identification, discussion, and reporting in Dutch public health ML research from 2021 to 2025. To this end, we developed the Risk of Algorithmic Bias Assessment Tool (RABAT) by integrating elements from established frameworks (Cochrane Risk of Bias, PROBAST, Microsoft Responsible AI checklist) and applied it to 35 peer-reviewed studies. Our analysis reveals pervasive gaps: although data sampling and missing data practices are well documented, most studies omit explicit fairness framing, subgroup analyses, and transparent discussion of potential harms. In response, we introduce a four-stage fairness-oriented framework called ACAR (Awareness, Conceptualization, Application, Reporting), with guiding questions derived from our systematic literature review to help researchers address fairness across the ML lifecycle. We conclude with actionable recommendations for public health ML practitioners to consistently consider algorithmic bias and foster transparency, ensuring that algorithmic innovations advance health equity rather than undermine it.

---

### WeCKD: Weakly-supervised Chained Distillation Network for Efficient Multimodal Medical Imaging

Authors: Md. Abdur Rahman, Mohaimenul Azam Khan Raiaan, Sami Azam, Asif Karim, Jemima Beissbarth, Amanda Leach
Published: 2025-10-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.14668v2

Knowledge distillation (KD) has traditionally relied on a static teacher-student framework, where a large, well-trained teacher transfers knowledge to a single student model. However, these approaches often suffer from knowledge degradation, inefficient supervision, and reliance on either a very strong teacher model or large labeled datasets. To address these, we present the first-ever Weakly-supervised Chain-based KD network (WeCKD) that redefines knowledge transfer through a structured sequence of interconnected models. Unlike conventional KD, it forms a progressive distillation chain, where each model not only learns from its predecessor but also refines the knowledge before passing it forward. This structured knowledge transfer further enhances feature learning and addresses the limitations of one-step KD. Each model in the chain is trained on only a fraction of the dataset and shows that effective learning can be achieved with minimal supervision. Extensive evaluation on six imaging datasets across otoscopic, microscopic, and magnetic resonance imaging modalities shows that it generalizes and outperforms existing methods. Furthermore, the proposed distillation chain resulted in cumulative accuracy gains of up to +23% over a single backbone trained on the same limited data, which highlights its potential for real-world adoption.

---

### Geometric Moment Alignment for Domain Adaptation via Siegel Embeddings

Authors: Shayan Gharib, Marcelo Hartmann, Arto Klami
Published: 2025-10-16
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.14666v1

We address the problem of distribution shift in unsupervised domain adaptation with a moment-matching approach. Existing methods typically align low-order statistical moments of the source and target distributions in an embedding space using ad-hoc similarity measures. We propose a principled alternative that instead leverages the intrinsic geometry of these distributions by adopting a Riemannian distance for this alignment. Our key novelty lies in expressing the first- and second-order moments as a single symmetric positive definite (SPD) matrix through Siegel embeddings. This enables simultaneous adaptation of both moments using the natural geometric distance on the shared manifold of SPD matrices, preserving the mean and covariance structure of the source and target distributions and yielding a more faithful metric for cross-domain comparison. We connect the Riemannian manifold distance to the target-domain error bound, and validate the method on image denoising and image classification benchmarks. Our code is publicly available at https://github.com/shayangharib/GeoAdapt.

---

### Beyond "Hallucinations": A Framework for Stable Human-AI Reasoning

Authors: Rikard Rosenbacke, Carl Rosenbacke, Victor Rosenbacke, Martin McKee
Published: 2025-10-16
Categories: cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2510.14665v2

As large language models (LLMs) become integrated into everyday and high-stakes decision-making, they inherit the ambiguity and biases of human language. While they produce fluent and coherent outputs, they rely on statistical pattern prediction rather than grounded reasoning, creating a risk of outputs that are plausible but incorrect. This paper argues that these failures are not only technical but cognitive. LLMs reproduce associative patterns similar to intuitive human reasoning, amplifying systematic misinterpretations when combined with human users. To analyse this, we introduce the Rose-Frame, a cognitive-epistemological framework for diagnosing breakdowns in human-AI interaction. The framework identifies three recurrent traps: (i) map vs territory, distinguishing representations from reality; (ii) intuition vs reason, separating fast associative judgments from reflective reasoning; and (iii) conflict vs confirmation, examining whether ideas are critically tested or mutually reinforced. These mechanisms can compound into epistemic drift when human and model reasoning interact. We show how these failures emerge in practice and propose human-side interventions, including interpretive cues, reflective prompts, and structured disagreement, to stabilise reasoning. Rather than modifying models, the framework focuses on governing interaction. The central claim is that fluency can create an illusion of understanding. Aligning AI therefore requires not only technical improvements but structures that enable reflective and falsifiable human oversight.

---

### Semantic Prosody in Machine Translation: the English-Chinese Case of Passive Structures

Authors: Xinyue Ma, Pol Pastells, Mireia Farrús, Mariona Taulé
Published: 2025-10-16
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.14662v1

Semantic prosody is a collocational meaning formed through the co-occurrence of a linguistic unit and a consistent series of collocates, which should be treated separately from semantic meaning. Since words that are literal translations of each other may have different semantic prosody, more attention should be paid to this linguistic property to generate accurate translations. However, current machine translation models cannot handle this problem. To bridge the gap, we propose an approach to teach machine translation models about semantic prosody of a specific structure. We focus on Chinese BEI passives and create a dataset of English-Chinese sentence pairs with the purpose of demonstrating the negative semantic prosody of BEI passives. Then we fine-tune OPUS-MT, NLLB-600M and mBART50 models with our dataset for the English-Chinese translation task. Our results show that fine-tuned MT models perform better on using BEI passives for translating unfavourable content and avoid using it for neutral and favourable content. Also, in NLLB-600M, which is a multilingual model, this knowledge of semantic prosody can be transferred from English-Chinese translation to other language pairs, such as Spanish-Chinese.

---

### EuroMineNet: A Multitemporal Sentinel-2 Benchmark for Spatiotemporal Mining Footprint Analysis in the European Union (2015-2024)

Authors: Weikang Yu, Vincent Nwazelibe, Xianping Ma, Xiaokang Zhang, Richard Gloaguen, Xiao Xiang Zhu, Pedram Ghamisi
Published: 2025-10-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.14661v1

Mining activities are essential for industrial and economic development, but remain a leading source of environmental degradation, contributing to deforestation, soil erosion, and water contamination. Sustainable resource management and environmental governance require consistent, long-term monitoring of mining-induced land surface changes, yet existing datasets are often limited in temporal depth or geographic scope. To address this gap, we present EuroMineNet, the first comprehensive multitemporal benchmark for mining footprint mapping and monitoring based on Sentinel-2 multispectral imagery. Spanning 133 mining sites across the European Union, EuroMineNet provides annual observations and expert-verified annotations from 2015 to 2024, enabling GeoAI-based models to analyze environmental dynamics at a continental scale. It supports two sustainability-driven tasks: (1) multitemporal mining footprint mapping for consistent annual land-use delineation, evaluated with a novel Change-Aware Temporal IoU (CA-TIoU) metric, and (2) cross-temporal change detection to capture both gradual and abrupt surface transformations. Benchmarking 20 state-of-the-art deep learning models reveals that while GeoAI methods effectively identify long-term environmental changes, challenges remain in detecting short-term dynamics critical for timely mitigation. By advancing temporally consistent and explainable mining monitoring, EuroMineNet contributes to sustainable land-use management, environmental resilience, and the broader goal of applying GeoAI for social and environmental good. We release the codes and datasets by aligning with FAIR and the open science paradigm at https://github.com/EricYu97/EuroMineNet.

---

### An Efficient Rubric-based Generative Verifier for Search-Augmented LLMs

Authors: Linyue Ma, Yilong Xu, Xiang Long, Zhi Zheng
Published: 2025-10-16
Categories: cs.CL, cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2510.14660v1

Search augmentation empowers Large Language Models with retrieval capabilities to overcome the limitations imposed by static parameters. Recently, Reinforcement Learning leverages tailored reward signals as a viable technique to enhance LLMs performing tasks involving search. However, existing reward modeling for search-augmented LLMs faces several limitations. Rule-based rewards, such as Exact Match, are verifiable but fragile to variations in expression and cannot be applied to long-form workloads. In contrast, generative rewards improve robustness, but designing verifiable and stable rewards for long-form workloads in dynamic corpora remains challenging and also incurs high computational costs. In this paper, we propose a unified and verifiable paradigm, "nugget-as-rubric", which treats atomic information points as structured evaluation criteria for different search-augmentation workloads. Short-form tasks correspond to a single rubric, whereas long-form tasks expand to multiple rubrics aligned with the question's information needs. To support long-form settings, we design an automatic rubric construction pipeline based on query rewriting, which can automatically retrieve passages relevant to each question and extract rubrics from them, both from static corpora and from dynamic online web content. Furthermore, we introduce \textbf{Search-Gen-V}, a 4B-parameter efficient generative verifier under our proposed verifiable paradigm, which is trained via the idea of distillation and a two-stage strategy. Experimental results show that Search-Gen-V achieves strong verification accuracy across different workloads, making it a scalable, robust, and efficient verifiable reward constructor for search-augmented LLMs.

---

### Decorrelation Speeds Up Vision Transformers

Authors: Kieran Carrigg, Rob van Gastel, Melda Yeghaian, Sander Dalm, Faysal Boughorbel, Marcel van Gerven
Published: 2025-10-16
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.14657v3

Masked Autoencoder (MAE) pre-training of vision transformers (ViTs) yields strong performance in low-label data regimes but comes with substantial computational costs, making it impractical in time- and resource-constrained industrial settings. We address this by integrating Decorrelated Backpropagation (DBP) into MAE pre-training, an optimization method that iteratively reduces input correlations at each layer to accelerate convergence. Applied selectively to the encoder, DBP achieves faster pre-training without loss of stability. To mimic constrained-data scenarios, we evaluate our approach on ImageNet-1K pre-training and ADE20K fine-tuning using randomly sampled subsets of each dataset. Under this setting, DBP-MAE reduces wall-clock time to baseline performance by 21.1%, lowers carbon emissions by 21.4%, and improves segmentation mIoU by 1.1 points. We observe similar gains when pre-training and fine-tuning on proprietary industrial data, confirming the method's applicability in real-world scenarios. These results demonstrate that DBP can reduce training time and energy use while improving downstream performance for large-scale ViT pre-training. Keywords: Deep learning, Vision transformers, Efficient AI, Decorrelation

---

### Inverse Problems for Partial Differential Equations with Jump Discontinuities in Coefficients via Two-Stage Physics-Informed Deep Learning and Statistical Mixture Models

Authors: Zhikun Zhang, Guanyu Pan, Xiangjun Wang, Yong Xu, Guangtao Zhang
Published: 2025-10-16
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2510.14656v3

This work proposes a two-stage physics-informed deep learning framework that combines neural-network-based sampling with statistical inference and constrained parameter refinement. In the first stage, a dual-network physics-informed architecture is used, where a main network approximates the PDE solution and an auxiliary coefficient sub network provides a relaxed continuous surrogate of the true discontinuous coefficient field. A gradient-adaptive weighting strategy is incorporated into the physics residual to improve residual training and enhance sampling reliability near possible discontinuity regions. The sampled coefficient values are then analyzed using Bayesian learning for Gaussian mixture models and birth-death Markov chain model selection, which estimate the number of coefficient regimes and provide heuristic search intervals for coefficient values and candidate transition regions. In the second stage, the inverse problem is reformulated as a constrained physics-informed estimator, in which the coefficient is represented explicitly as a hard piecewise-constant function over the spatiotemporal domain. Numerical experiments on different PDE types with jump-discontinuous coefficients demonstrate that the proposed framework achieves accurate parameter estimation with acceptable computational costs compared to existing methods. This work provides an effective integrated workflow for inverse problems governed by PDEs with discontinuous parameter structures, particularly in nonstationary and heterogeneous systems.

---

### Galaxy Morphology Classification with Counterfactual Explanation

Authors: Zhuo Cao, Lena Krieger, Hanno Scharr, Ira Assent
Published: 2025-10-16
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.14655v1

Galaxy morphologies play an essential role in the study of the evolution of galaxies. The determination of morphologies is laborious for a large amount of data giving rise to machine learning-based approaches. Unfortunately, most of these approaches offer no insight into how the model works and make the results difficult to understand and explain. We here propose to extend a classical encoder-decoder architecture with invertible flow, allowing us to not only obtain a good predictive performance but also provide additional information about the decision process with counterfactual explanations.

---

### In-Context Learning with Unpaired Clips for Instruction-based Video Editing

Authors: Xinyao Liao, Xianfang Zeng, Ziye Song, Zhoujie Fu, Gang Yu, Guosheng Lin
Published: 2025-10-16
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.14648v1

Despite the rapid progress of instruction-based image editing, its extension to video remains underexplored, primarily due to the prohibitive cost and complexity of constructing large-scale paired video editing datasets. To address this challenge, we introduce a low-cost pretraining strategy for instruction-based video editing that leverages in-context learning from unpaired video clips. We show that pretraining a foundation video generation model with this strategy endows it with general editing capabilities, such as adding, replacing, or deleting operations, according to input editing instructions. The pretrained model can then be efficiently refined with a small amount of high-quality paired editing data. Built upon HunyuanVideoT2V, our framework first pretrains on approximately 1M real video clips to learn basic editing concepts, and subsequently fine-tunes on fewer than 150k curated editing pairs to extend more editing tasks and improve the editing quality. Comparative experiments show that our method surpasses existing instruction-based video editing approaches in both instruction alignment and visual fidelity, achieving a 12\% improvement in editing instruction following and a 15\% improvement in editing quality.

---

### The Bidding Games: Reinforcement Learning for MEV Extraction on Polygon Blockchain

Authors: Andrei Seoev, Leonid Gremyachikh, Anastasiia Smirnova, Yash Madhwal, Alisa Kalacheva, Dmitry Belousov, Ilia Zubov, Aleksei Smirnov, Denis Fedyanin, Vladimir Gorgadze, Yury Yanovich
Published: 2025-10-16
Categories: cs.GT, cs.AI, cs.DC
arXiv: https://arxiv.org/abs/2510.14642v2

In blockchain networks, the strategic ordering of transactions within blocks has emerged as a significant source of profit extraction, known as Maximal Extractable Value (MEV). The transition from spam-based Priority Gas Auctions (PGA) to structured auction mechanisms like Polygon Atlas has transformed MEV extraction from public bidding wars into sealed-bid competitions under extreme time constraints. While this shift reduces network congestion, it introduces complex strategic challenges where searchers must make optimal bidding decisions within a sub-second window without knowledge of competitor behavior or presence. Traditional equilibrium-based game-theoretic models struggle in this high-frequency, partially observable environment. While auction theory provides equilibrium solutions for sealed-bid formats under incomplete information, these models typically assume known bidder value distributions and stationary competition--assumptions that are difficult to satisfy in dynamic, sub-second auctions where competitor presence and strategies evolve rapidly. We present a reinforcement learning framework for MEV extraction on Polygon Atlas and make three contributions: (1) A novel simulation environment that accurately models the stochastic arrival of arbitrage opportunities and probabilistic competition in Atlas auctions; (2) A PPO-based bidding agent optimized for real-time constraints, capable of adaptive strategy formulation in continuous action spaces while maintaining production-ready inference speeds; (3) Empirical validation demonstrating our history-conditioned agent achieves 49\% Maximum-Profit Capture when deployed alongside existing searchers and a 43\% relative profit improvement over the historical market leader in counterfactual replacement, significantly outperforming static bidding strategies.

---

### Causality Enhancement for Cross-Domain Recommendation

Authors: Zhibo Wu, Yunfan Wu, Lin Jiang, Ping Yang, Yao Hu
Published: 2025-10-16
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2510.14641v1

Cross-domain recommendation forms a crucial component in recommendation systems. It leverages auxiliary information through source domain tasks or features to enhance target domain recommendations. However, incorporating inconsistent source domain tasks may result in insufficient cross-domain modeling or negative transfer. While incorporating source domain features without considering the underlying causal relationships may limit their contribution to final predictions. Thus, a natural idea is to directly train a cross-domain representation on a causality-labeled dataset from the source to target domain. Yet this direction has been rarely explored, as identifying unbiased real causal labels is highly challenging in real-world scenarios. In this work, we attempt to take a first step in this direction by proposing a causality-enhanced framework, named CE-CDR. Specifically, we first reformulate the cross-domain recommendation as a causal graph for principled guidance. We then construct a causality-aware dataset heuristically. Subsequently, we derive a theoretically unbiased Partial Label Causal Loss to generalize beyond the biased causality-aware dataset to unseen cross-domain patterns, yielding an enriched cross-domain representation, which is then fed into the target model to enhance target-domain recommendations. Theoretical and empirical analyses, as well as extensive experiments, demonstrate the rationality and effectiveness of CE-CDR and its general applicability as a model-agnostic plugin. Moreover, it has been deployed in production since April 2025, showing its practical value in real-world applications.

---

### LUMI: Unsupervised Intent Clustering with Multiple Pseudo-Labels

Authors: I-Fan Lin, Faegheh Hasibi, Suzan Verberne
Published: 2025-10-16
Categories: cs.CL, cs.IR
arXiv: https://arxiv.org/abs/2510.14640v4

In this paper, we propose an intuitive, training-free and label-free method for intent clustering in conversational search. Current approaches to short text clustering use LLM-generated pseudo-labels to enrich text representations or to identify similar text pairs for pooling. The limitations are: (1) each text is assigned only a single label, and refining representations toward a single label can be unstable; (2) text-level similarity is treated as a binary selection, which fails to account for continuous degrees of similarity. Our method LUMI is designed to amplify similarities between texts by using shared pseudo-labels. We first generate pseudo-labels for each text and collect them into a pseudo-label set. Next, we compute the mean of the pseudo-label embeddings and pool it with the text embedding. Finally, we perform text-level pooling: Each text representation is pooled with its similar pairs, where similarity is determined by the degree of shared labels. Our evaluation on four benchmark sets shows that our approach achieves competitive results, better than recent state-of-the-art baselines, while avoiding the need to estimate the number of clusters during embedding refinement, as is required by most methods. Our findings indicate that LUMI can effectively be applied in unsupervised short-text clustering scenarios.

---

### SteeringTTA: Guiding Diffusion Trajectories for Robust Test-Time-Adaptation

Authors: Jihyun Yu, Yoojin Oh, Wonho Bae, Mingyu Kim, Junhyug Noh
Published: 2025-10-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.14634v1

Test-time adaptation (TTA) aims to correct performance degradation of deep models under distribution shifts by updating models or inputs using unlabeled test data. Input-only diffusion-based TTA methods improve robustness for classification to corruptions but rely on gradient guidance, limiting exploration and generalization across distortion types. We propose SteeringTTA, an inference-only framework that adapts Feynman-Kac steering to guide diffusion-based input adaptation for classification with rewards driven by pseudo-label. SteeringTTA maintains multiple particle trajectories, steered by a combination of cumulative top-K probabilities and an entropy schedule, to balance exploration and confidence. On ImageNet-C, SteeringTTA consistently outperforms the baseline without any model updates or source data.

---

### Adapting Self-Supervised Representations as a Latent Space for Efficient Generation

Authors: Ming Gui, Johannes Schusterbauer, Timy Phan, Felix Krause, Josh Susskind, Miguel Angel Bautista, Björn Ommer
Published: 2025-10-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.14630v2

We introduce Representation Tokenizer (RepTok), a generative modeling framework that represents an image using a single continuous latent token obtained from self-supervised vision transformers. Building on a pre-trained SSL encoder, we fine-tune only the semantic token embedding and pair it with a generative decoder trained jointly using a standard flow matching objective. This adaptation enriches the token with low-level, reconstruction-relevant details, enabling faithful image reconstruction. To preserve the favorable geometry of the original SSL space, we add a cosine-similarity loss that regularizes the adapted token, ensuring the latent space remains smooth and suitable for generation. Our single-token formulation resolves spatial redundancies of 2D latent spaces and significantly reduces training costs. Despite its simplicity and efficiency, RepTok achieves competitive results on class-conditional ImageNet generation and naturally extends to text-to-image synthesis, reaching competitive zero-shot performance on MS-COCO under extremely limited training budgets. Our findings highlight the potential of fine-tuned SSL representations as compact and effective latent spaces for efficient generative modeling.

---

### RLAIF-SPA: Structured AI Feedback for Semantic-Prosodic Alignment in Speech Synthesis

Authors: Qing Yang, Zhenghao Liu, Yangfan Du, Pengcheng Huang, Tong Xiao
Published: 2025-10-16
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.14628v2

Recent advances in Text-To-Speech (TTS) synthesis have achieved near-human speech quality in neutral speaking styles. However, most existing approaches either depend on costly emotion annotations or optimize surrogate objectives that fail to adequately capture perceptual emotional quality. As a result, the generated speech, while semantically accurate, often lacks expressive and emotionally rich characteristics. To address these limitations, we propose RLAIF-SPA, a novel framework that integrates Reinforcement Learning from AI Feedback (RLAIF) to directly optimize both emotional expressiveness and intelligibility without human supervision. Specifically, RLAIF-SPA incorporates Automatic Speech Recognition (ASR) to provide semantic accuracy feedback, while leveraging structured reward modeling to evaluate prosodic-emotional consistency. RLAIF-SPA enables more precise and nuanced control over expressive speech generation along four structured evaluation dimensions: Structure, Emotion, Speed, and Tone. Extensive experiments on Libri-Speech, MELD, and Mandarin ESD datasets demonstrate consistent gains across clean read speech, conversational dialogue, and emotional speech. On Libri-Speech, RLAIF-SPA consistently outperforms Chat-TTS, achieving a 26.1% reduction in word error rate, a 9.1% improvement in SIM-O, and over 10% gains in human subjective evaluations.

---

### GOPLA: Generalizable Object Placement Learning via Synthetic Augmentation of Human Arrangement

Authors: Yao Zhong, Hanzhi Chen, Simon Schaefer, Anran Zhang, Stefan Leutenegger
Published: 2025-10-16
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2510.14627v2

Robots are expected to serve as intelligent assistants, helping humans with everyday household organization. A central challenge in this setting is the task of object placement, which requires reasoning about both semantic preferences (e.g., common-sense object relations) and geometric feasibility (e.g., collision avoidance). We present GOPLA, a hierarchical framework that learns generalizable object placement from augmented human demonstrations. A multi-modal large language model translates human instructions and visual inputs into structured plans that specify pairwise object relationships. These plans are then converted into 3D affordance maps with geometric common sense by a spatial mapper, while a diffusion-based planner generates placement poses guided by test-time costs, considering multi-plan distributions and collision avoidance. To overcome data scarcity, we introduce a scalable pipeline that expands human placement demonstrations into diverse synthetic training data. Extensive experiments show that our approach improves placement success rates by 30.04 percentage points over the runner-up, evaluated on positioning accuracy and physical plausibility, demonstrating strong generalization across a wide range of real-world robotic placement scenarios.

---

### GemiRec: Interest Quantization and Generation for Multi-Interest Recommendation

Authors: Zhibo Wu, Yunfan Wu, Quan Liu, Lin Jiang, Ping Yang, Yao Hu
Published: 2025-10-16
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2510.14626v1

Multi-interest recommendation has gained attention, especially in industrial retrieval stage. Unlike classical dual-tower methods, it generates multiple user representations instead of a single one to model comprehensive user interests. However, prior studies have identified two underlying limitations: the first is interest collapse, where multiple representations homogenize. The second is insufficient modeling of interest evolution, as they struggle to capture latent interests absent from a user's historical behavior. We begin with a thorough review of existing works in tackling these limitations. Then, we attempt to tackle these limitations from a new perspective. Specifically, we propose a framework-level refinement for multi-interest recommendation, named GemiRec. The proposed framework leverages interest quantization to enforce a structural interest separation and interest generation to learn the evolving dynamics of user interests explicitly. It comprises three modules: (a) Interest Dictionary Maintenance Module (IDMM) maintains a shared quantized interest dictionary. (b) Multi-Interest Posterior Distribution Module (MIPDM) employs a generative model to capture the distribution of user future interests. (c) Multi-Interest Retrieval Module (MIRM) retrieves items using multiple user-interest representations. Both theoretical and empirical analyses, as well as extensive experiments, demonstrate its advantages and effectiveness. Moreover, it has been deployed in production since March 2025, showing its practical value in industrial applications.

---

### Efficient Video Sampling: Pruning Temporally Redundant Tokens for Faster VLM Inference

Authors: Natan Bagrov, Eugene Khvedchenia, Borys Tymchenko, Shay Aharon, Lior Kadoch, Tomer Keren, Ofri Masad, Yonatan Geifman, Ran Zilberstein, Tuomas Rintamaki, Matthieu Le, Andrew Tao
Published: 2025-10-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.14624v1

Vision-language models (VLMs) have recently expanded from static image understanding to video reasoning, but their scalability is fundamentally limited by the quadratic cost of processing dense frame sequences. Long videos often exceed the token budget of modern language models, leading to severe context limitations and latency issues. We introduce Efficient Video Sampling (EVS), a simple, plug-and-play method for reducing token redundancy in videos by identifying and pruning temporally static patches -- spatial regions that remain unchanged across consecutive frames. EVS preserves positional identity, requires no architectural changes or retraining. We show that EVS substantially reduces token count while maintaining semantic fidelity, enabling faster inference and longer input sequences. Applied at inference time, EVS reduces large language model (LLM) time-to-first-token (TTFT) by up to 4x with minimal accuracy loss. When combined with an uptraining phase using stochastic pruning rates, EVS yields models that are robust to varying compression levels and retain full performance under aggressive pruning. Extensive experiments demonstrate that EVS consistently improves efficiency-accuracy trade-offs, unlocking scalable video-language understanding without sacrificing quality.

---

### LeapFactual: Reliable Visual Counterfactual Explanation Using Conditional Flow Matching

Authors: Zhuo Cao, Xuan Zhao, Lena Krieger, Hanno Scharr, Ira Assent
Published: 2025-10-16
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.14623v3

The growing integration of machine learning (ML) and artificial intelligence (AI) models into high-stakes domains such as healthcare and scientific research calls for models that are not only accurate but also interpretable. Among the existing explainable methods, counterfactual explanations offer interpretability by identifying minimal changes to inputs that would alter a model's prediction, thus providing deeper insights. However, current counterfactual generation methods suffer from critical limitations, including gradient vanishing, discontinuous latent spaces, and an overreliance on the alignment between learned and true decision boundaries. To overcome these limitations, we propose LeapFactual, a novel counterfactual explanation algorithm based on conditional flow matching. LeapFactual generates reliable and informative counterfactuals, even when true and learned decision boundaries diverge. Following a model-agnostic approach, LeapFactual is not limited to models with differentiable loss functions. It can even handle human-in-the-loop systems, expanding the scope of counterfactual explanations to domains that require the participation of human annotators, such as citizen science. We provide extensive experiments on benchmark and real-world datasets showing that LeapFactual generates accurate and in-distribution counterfactual explanations that offer actionable insights. We observe, for instance, that our reliable counterfactual samples with labels aligning to ground truth can be beneficially used as new training data to enhance the model. The proposed method is broadly applicable and enhances both scientific knowledge discovery and non-expert interpretability.

---

### ColorBench: Benchmarking Mobile Agents with Graph-Structured Framework for Complex Long-Horizon Tasks

Authors: Yuanyi Song, Heyuan Huang, Qiqiang Lin, Yin Zhao, Xiangmou Qu, Jun Wang, Xingyu Lou, Weiwen Liu, Zhuosheng Zhang, Jun Wang, Yong Yu, Weinan Zhang et al.
Published: 2025-10-16
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.14621v1

The rapid advancement of multimodal large language models has enabled agents to operate mobile devices by directly interacting with graphical user interfaces, opening new possibilities for mobile automation. However, real-world mobile tasks are often complex and allow for multiple valid solutions. This contradicts current mobile agent evaluation standards: offline static benchmarks can only validate a single predefined "golden path", while online dynamic testing is constrained by the complexity and non-reproducibility of real devices, making both approaches inadequate for comprehensively assessing agent capabilities. To bridge the gap between offline and online evaluation and enhance testing stability, this paper introduces a novel graph-structured benchmarking framework. By modeling the finite states observed during real-device interactions, it achieves static simulation of dynamic behaviors. Building on this, we develop ColorBench, a benchmark focused on complex long-horizon tasks. It supports evaluation of multiple valid solutions, subtask completion rate statistics, and atomic-level capability analysis. ColorBench contains 175 tasks (74 single-app, 101 cross-app) with an average length of over 13 steps. Each task includes at least two correct paths and several typical error paths, enabling quasi-dynamic interaction. By evaluating ColorBench across various baselines, we discover limitations of existing models and propose improvement directions and feasible technical pathways to enhance agents' performance on complex, long-horizon problems based on experimental results. Code and data are available at: https://github.com/MadeAgents/ColorBench.

---

### Code-driven Number Sequence Calculation: Enhancing the inductive Reasoning Abilities of Large Language Models

Authors: Kedi Chen, Zhikai Lei, Xu Guo, Xuecheng Wu, Siyuan Zeng, Jianghao Yin, Yinqi Zhang, Qin Chen, Jie Zhou, Liang He, Qipeng Guo, Kai Chen et al.
Published: 2025-10-16
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.14620v1

Large language models (LLMs) make remarkable progress in reasoning tasks. Among different reasoning modes, inductive reasoning, due to its better alignment with human learning, attracts increasing interest. However, research on inductive reasoning faces certain challenges. First, existing inductive data mostly focuses on superficial regularities while lacking more complex internal patterns. Second, current works merely prompt LLMs or finetune on simple prompt-response pairs, but do not provide precise thinking processes nor implement difficulty control. Unlike previous work, we address these challenges by introducing \textit{CodeSeq}, a synthetic post-training dataset built from number sequences. We package number sequences into algorithmic problems to discover their general terms, defining a general term generation (GTG) task correspondingly. Our pipeline generates supervised finetuning data by reflecting on failed test cases and incorporating iterative corrections, thereby teaching LLMs to learn autonomous case generation and self-checking. Additionally, it leverages reinforcement learning with a novel Case-Synergy Solvability Scaling Reward based on both solvability, estimated from the problem pass rate, and the success rate of self-directed case generation, enabling models to learn more effectively from both successes and failures. Experimental results show that the models trained with \textit{CodeSeq} improve on various reasoning tasks and can preserve the models' OOD performance.

---

### Shot2Tactic-Caption: Multi-Scale Captioning of Badminton Videos for Tactical Understanding

Authors: Ning Ding, Keisuke Fujii, Toru Tamaki
Published: 2025-10-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.14617v1

Tactical understanding in badminton involves interpreting not only individual actions but also how tactics are dynamically executed over time. In this paper, we propose \textbf{Shot2Tactic-Caption}, a novel framework for semantic and temporal multi-scale video captioning in badminton, capable of generating shot-level captions that describe individual actions and tactic-level captions that capture how these actions unfold over time within a tactical execution. We also introduce the Shot2Tactic-Caption Dataset, the first badminton captioning dataset containing 5,494 shot captions and 544 tactic captions. Shot2Tactic-Caption adopts a dual-branch design, with both branches including a visual encoder, a spatio-temporal Transformer encoder, and a Transformer-based decoder to generate shot and tactic captions. To support tactic captioning, we additionally introduce a Tactic Unit Detector that identifies valid tactic units, tactic types, and tactic states (e.g., Interrupt, Resume). For tactic captioning, we further incorporate a shot-wise prompt-guided mechanism, where the predicted tactic type and state are embedded as prompts and injected into the decoder via cross-attention. The shot-wise prompt-guided mechanism enables our system not only to describe successfully executed tactics but also to capture tactical executions that are temporarily interrupted and later resumed. Experimental results demonstrate the effectiveness of our framework in generating both shot and tactic captions. Ablation studies show that the ResNet50-based spatio-temporal encoder outperforms other variants, and that shot-wise prompt structuring leads to more coherent and accurate tactic captioning.

---

### Beyond Correctness: Evaluating Subjective Writing Preferences Across Cultures

Authors: Shuangshuang Ying, Yunwen Li, Xingwei Qu, Xin Li, Sheng Jin, Minghao Liu, Zhoufutu Wen, Xeron Du, Tianyu Zheng, Yichi Zhang, Letian Ni, Yuyang Cheng et al.
Published: 2025-10-16
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.14616v2

Current preference learning methods achieve high accuracy on standard benchmarks but exhibit significant performance degradation when objective quality signals are removed. We introduce WritingPreferenceBench, a dataset of 1,800 human-annotated preference pairs (1,200 English, 600 Chinese) across 8 creative writing genres, where responses are matched for objective correctness, factual accuracy, and length. On this benchmark, sequence-based reward models--the standard architecture for RLHF--achieve only 52.7% mean accuracy, while zero-shot language model judges perform at 53.9%. In contrast, generative reward models that produce explicit reasoning chains achieve 81.8% accuracy. We observe high within-model variance across genres: individual models range from 18.2% to 81.8% accuracy across different writing categories, with standard deviations averaging 10.1%. This variance persists regardless of model scale, with 27B parameter models showing no consistent improvement over 8B variants. Our results suggest that current RLHF methods primarily learn to detect objective errors rather than capture subjective quality preferences (e.g., creativity, stylistic flair, and emotional resonance), and that successful preference modeling may require intermediate reasoning representations rather than direct classification.

---

### First Attentions Last: Better Exploiting First Attentions for Efficient Transformer Training

Authors: Gyudong Kim, Hyukju Na, Jin Hyeon Kim, Hyunsung Jang, Jaemin Park, Jaegi Hwang, Namkoo Ha, Seungryong Kim, Young Geun Kim
Published: 2025-10-16
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.14614v2

As training billion-scale transformers becomes increasingly common, employing multiple distributed GPUs along with parallel training methods has become a standard practice. However, existing transformer designs suffer from significant communication overhead, especially in Tensor Parallelism (TP), where each block's MHA-MLP connection requires an all-reduce communication. Through our investigation, we show that the MHA-MLP connections can be bypassed for efficiency, while the attention output of the first layer can serve as an alternative signal for the bypassed connection. Motivated by the observations, we propose FAL (First Attentions Last), an efficient transformer architecture that redirects the first MHA output to the MLP inputs of the following layers, eliminating the per-block MHA-MLP connections. This removes the all-reduce communication and enables parallel execution of MHA and MLP on a single GPU. We also introduce FAL+, which adds the normalized first attention output to the MHA outputs of the following layers to augment the MLP input for the model quality. Our evaluation shows that FAL reduces multi-GPU training time by up to 44%, improves single-GPU throughput by up to 1.18x, and achieves better perplexity compared to the baseline GPT. FAL+ achieves even lower perplexity without increasing the training time than the baseline. Codes are available at: https://github.com/CASL-KU/FAL

---

### An Active Inference Model of Mouse Point-and-Click Behaviour

Authors: Markus Klar, Sebastian Stein, Fraser Paterson, John H. Williamson, Roderick Murray-Smith
Published: 2025-10-16
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2510.14611v1

We explore the use of Active Inference (AIF) as a computational user model for spatial pointing, a key problem in Human-Computer Interaction (HCI). We present an AIF agent with continuous state, action, and observation spaces, performing one-dimensional mouse pointing and clicking. We use a simple underlying dynamic system to model the mouse cursor dynamics with realistic perceptual delay. In contrast to previous optimal feedback control-based models, the agent's actions are selected by minimizing Expected Free Energy, solely based on preference distributions over percepts, such as observing clicking a button correctly. Our results show that the agent creates plausible pointing movements and clicks when the cursor is over the target, with similar end-point variance to human users. In contrast to other models of pointing, we incorporate fully probabilistic, predictive delay compensation into the agent. The agent shows distinct behaviour for differing target difficulties without the need to retune system parameters, as done in other approaches. We discuss the simulation results and emphasize the challenges in identifying the correct configuration of an AIF agent interacting with continuous systems.

---

### Knowledge-based Visual Question Answer with Multimodal Processing, Retrieval and Filtering

Authors: Yuyang Hong, Jiaqi Gu, Qi Yang, Lubin Fan, Yue Wu, Ying Wang, Kun Ding, Shiming Xiang, Jieping Ye
Published: 2025-10-16
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.14605v2

Knowledge-based visual question answering (KB-VQA) requires visual language models (VLMs) to integrate visual understanding with external knowledge retrieval. Although retrieval-augmented generation (RAG) achieves significant advances in this task by combining knowledge-base querying, it still struggles with the quality of multimodal queries and the relevance of retrieved results. To overcome these challenges, we propose a novel three-stage method, termed Wiki-PRF, including Processing, Retrieval and Filtering stages. The processing stage dynamically invokes visual tools to extract precise multimodal information for retrieval. The retrieval stage integrates visual and text features to achieve multimodal knowledge retrieval. The filtering stage performs relevance filtering and concentration on retrieval results. To this end, we introduce a visual language model trained with answer accuracy and format consistency as reward signals via a reinforcement learning manner. This enhances the model's reasoning, tool invocation for accurate queries, and filtering of irrelevant content. Experiments on benchmark datasets (E-VQA and InfoSeek) show significant improvements~(36.0 and 42.8) in answer quality, achieving state-of-the-art performance. Code is available at https://github.com/cqu-student/Wiki-PRF

---

### Zero-Shot Wildlife Sorting Using Vision Transformers: Evaluating Clustering and Continuous Similarity Ordering

Authors: Hugo Markoff, Jevgenijs Galaktionovs
Published: 2025-10-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.14596v1

Camera traps generate millions of wildlife images, yet many datasets contain species that are absent from existing classifiers. This work evaluates zero-shot approaches for organizing unlabeled wildlife imagery using self-supervised vision transformers, developed and tested within the Animal Detect platform for camera trap analysis. We compare unsupervised clustering methods (DBSCAN, GMM) across three architectures (CLIP, DINOv2, MegaDescriptor) combined with dimensionality reduction techniques (PCA, UMAP), and we demonstrate continuous 1D similarity ordering via t-SNE projection. On a 5-species test set with ground truth labels used only for evaluation, DINOv2 with UMAP and GMM achieves 88.6 percent accuracy (macro-F1 = 0.874), while 1D sorting reaches 88.2 percent coherence for mammals and birds and 95.2 percent for fish across 1,500 images. Based on these findings, we deployed continuous similarity ordering in production, enabling rapid exploratory analysis and accelerating manual annotation workflows for biodiversity monitoring.

---

### Hierarchical Re-Classification: Combining Animal Classification Models with Vision Transformers

Authors: Hugo Markoff, Jevgenijs Galaktionovs
Published: 2025-10-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.14594v1

State-of-the-art animal classification models like SpeciesNet provide predictions across thousands of species but use conservative rollup strategies, resulting in many animals labeled at high taxonomic levels rather than species. We present a hierarchical re-classification system for the Animal Detect platform that combines SpeciesNet EfficientNetV2-M predictions with CLIP embeddings and metric learning to refine high-level taxonomic labels toward species-level identification. Our five-stage pipeline (high-confidence acceptance, bird override, centroid building, triplet-loss metric learning, and adaptive cosine-distance scoring) is evaluated on a segment of the LILA BC Desert Lion Conservation dataset (4,018 images, 15,031 detections). After recovering 761 bird detections from "blank" and "animal" labels, we re-classify 456 detections labeled animal, mammal, or blank with 96.5% accuracy, achieving species-level identification for 64.9 percent

---

### Multimodal RAG for Unstructured Data:Leveraging Modality-Aware Knowledge Graphs with Hybrid Retrieval

Authors: Rashmi R, Vidyadhar Upadhya
Published: 2025-10-16
Categories: cs.LG, cs.IR
arXiv: https://arxiv.org/abs/2510.14592v1

Current Retrieval-Augmented Generation (RAG) systems primarily operate on unimodal textual data, limiting their effectiveness on unstructured multimodal documents. Such documents often combine text, images, tables, equations, and graphs, each contributing unique information. In this work, we present a Modality-Aware Hybrid retrieval Architecture (MAHA), designed specifically for multimodal question answering with reasoning through a modality-aware knowledge graph. MAHA integrates dense vector retrieval with structured graph traversal, where the knowledge graph encodes cross-modal semantics and relationships. This design enables both semantically rich and context-aware retrieval across diverse modalities. Evaluations on multiple benchmark datasets demonstrate that MAHA substantially outperforms baseline methods, achieving a ROUGE-L score of 0.486, providing complete modality coverage. These results highlight MAHA's ability to combine embeddings with explicit document structure, enabling effective multimodal retrieval. Our work establishes a scalable and interpretable retrieval framework that advances RAG systems by enabling modality-aware reasoning over unstructured multimodal data.

---

### Just-In-Time Objectives: A General Approach for Specialized AI Interactions

Authors: Michelle S. Lam, Omar Shaikh, Hallie Xu, Alice Guo, Diyi Yang, Jeffrey Heer, James A. Landay, Michael S. Bernstein
Published: 2025-10-16
Categories: cs.HC, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.14591v2

Large language models promise a broad set of functions, but when not given a specific objective, they default to generic results. We demonstrate that inferring the user's in-the-moment objective, then rapidly optimizing for that singular objective, enables LLMs to produce specialized tools, interfaces, and responses. Our work introduces just-in-time objectives, which model a user's goals to specialize LLM systems on the fly. We contribute an architecture for automatically inducing such objectives by passively observing user behavior, then steering downstream AI systems through generation and evaluation against this objective. Inducing just-in-time objectives (e.g., "Clarify the abstract's research contribution") enables automatic generation of tools, e.g., those that critique a draft based on relevant HCI methodologies, anticipate related researchers' reactions, or surface ambiguous terminology. In a series of experiments on participants' own tasks, JIT objectives enable LLM outputs that achieve 66-86% win rates over typical LLMs. In-person use sessions confirm that JIT objectives produce specialized tools that are unique to each participant and are rated as significantly higher quality than a standard LLM chat tool.

---

### STANCE: Motion Coherent Video Generation Via Sparse-to-Dense Anchored Encoding

Authors: Zhifei Chen, Tianshuo Xu, Leyi Wu, Luozhou Wang, Dongyu Yan, Zihan You, Wenting Luo, Guo Zhang, Yingcong Chen
Published: 2025-10-16
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.14588v2

Video generation has recently made striking visual progress, but maintaining coherent object motion and interactions remains difficult. We trace two practical bottlenecks: (i) human-provided motion hints (e.g., small 2D maps) often collapse to too few effective tokens after encoding, weakening guidance; and (ii) optimizing for appearance and motion in a single head can favor texture over temporal consistency. We present STANCE, an image-to-video framework that addresses both issues with two simple components. First, we introduce Instance Cues -- a pixel-aligned control signal that turns sparse, user-editable hints into a dense 2.5D (camera-relative) motion field by averaging per-instance flow and augmenting with monocular depth over the instance mask. This reduces depth ambiguity compared to 2D arrow inputs while remaining easy to use. Second, we preserve the salience of these cues in token space with Dense RoPE, which tags a small set of motion tokens (anchored on the first frame) with spatial-addressable rotary embeddings. Paired with joint RGB \(+\) auxiliary-map prediction (segmentation or depth), our model anchors structure while RGB handles appearance, stabilizing optimization and improving temporal coherence without requiring per-frame trajectory scripts.

---

### Matcha: Multi-Stage Riemannian Flow Matching for Accurate and Physically Valid Molecular Docking

Authors: Daria Frolova, Talgat Daulbaev, Egor Sevriugov, Sergei A. Nikolenko, Dmitry N. Ivankov, Ivan Oseledets, Marina A. Pak
Published: 2025-10-16
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.14586v3

Accurate prediction of protein-ligand binding poses is crucial for structure-based drug design, yet existing methods struggle to balance speed, accuracy, and physical plausibility. We introduce Matcha, a novel molecular docking pipeline that combines multi-stage flow matching with physically-aware post-processing. Our approach consists of three sequential stages applied consecutively to progressively refine docking predictions, each implemented as a flow matching model operating on appropriate geometric spaces ($\mathbb{R}^3$, $\mathrm{SO}(3)$, and $\mathrm{SO}(2)$). We enhance the prediction quality through GNINA energy minimization and apply unsupervised physical validity filters to eliminate unrealistic poses. Compared to various approaches, Matcha demonstrates superior physical plausibility across all considered benchmarks. Moreover, our method works approximately 31 times faster than modern large-scale co-folding models. The model weights and inference code to reproduce our results are available at https://github.com/LigandPro/Matcha.

---

### Talking Points: Describing and Localizing Pixels

Authors: Matan Rusanovsky, Shimon Malnick, Shai Avidan
Published: 2025-10-16
Categories: cs.CV, cs.CL
arXiv: https://arxiv.org/abs/2510.14583v1

Vision-language models have achieved remarkable success in cross-modal understanding. Yet, these models remain limited to object-level or region-level grounding, lacking the capability for pixel-precise keypoint comprehension through natural language. We introduce a novel framework for pixel level grounding. The framework consists of two complementary components: a Point Descriptor that generates rich, contextual descriptions of individual keypoints, and a Point Localizer that regresses precise pixel coordinates from these descriptions. Unlike prior work that relies on templated prompts or keypoint names, our approach produces free-form, coarse-to-fine descriptions that situate keypoints within their visual context. Since there is no available dataset to train such a system, we introduce LlamaPointInPart, a carefully curated dataset of 20K+ image-keypoint-description triplets synthesized from multiple vision-language models, capturing multi-scale information from scene-level context to visual features around the keypoint. For cross-category generalization, we optimize the Point Descriptor on AP-10K via GRPO, using the frozen Point Localizer as a reward model to produce descriptions that maximize localization accuracy. To evaluate our results we establish a new evaluation protocol. Instead of comparing the text description produced by our method to the ground truth, we use the localizer to determine how close is the predicted point generated to the ground truth point. Experiments demonstrate superior performance compared to baseline models on LlamaPointInPart.The bidirectional nature of our framework should enable future applications in both keypoint-guided image understanding and language-guided precise localization. Our code and dataset are publicly available at https://github.com/matanr/Talking_Points.

---

### Local Causal Discovery for Statistically Efficient Causal Inference

Authors: Mátyás Schubert, Tom Claassen, Sara Magliacane
Published: 2025-10-16
Categories: stat.ML, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.14582v2

Causal discovery methods can identify valid adjustment sets for causal effect estimation for a pair of target variables, even when the underlying causal graph is unknown. Global causal discovery methods focus on learning the whole causal graph and therefore enable the recovery of optimal adjustment sets, i.e., sets with the lowest asymptotic variance, but they quickly become computationally prohibitive as the number of variables grows. Local causal discovery methods offer a more scalable alternative by focusing on the local neighborhood of the target variables, but are restricted to statistically suboptimal adjustment sets. In this work, we propose Local Optimal Adjustments Discovery (LOAD), a sound and complete causal discovery approach that combines the computational efficiency of local methods with the statistical optimality of global methods. First, LOAD identifies the causal relation between the targets and tests if the causal effect is identifiable by using only local information. If it is identifiable, it finds the possible descendants of the treatment and infers the optimal adjustment set as the parents of the outcome in a modified forbidden projection. Otherwise, it returns the locally valid parent adjustment sets. In our experiments on synthetic and realistic data LOAD outperforms global methods in scalability, while providing more accurate effect estimation than local methods.

---

### Model-agnostic Selective Labeling with Provable Statistical Guarantees

Authors: Huipeng Huang, Wenbo Liao, Huajun Xi, Hao Zeng, Mengchen Zhao, Hongxin Wei
Published: 2025-10-16
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.14581v3

Obtaining high-quality labels for large datasets is expensive, requiring massive annotations from human experts. While AI models offer a cost-effective alternative by predicting labels, their label quality is compromised by the unavoidable labeling errors. Existing methods mitigate this issue through selective labeling, where AI labels a subset and human labels the remainder. However, these methods lack theoretical guarantees on the quality of AI-assigned labels, often resulting in unacceptably high labeling error within the AI-labeled subset. To address this, we introduce \textbf{Conformal Labeling}, a novel method to identify instances where AI predictions can be provably trusted. This is achieved by controlling the false discovery rate (FDR), the proportion of incorrect labels within the selected subset. In particular, we construct a conformal $p$-value for each test instance by comparing AI models' predicted confidence to those of calibration instances mislabeled by AI models. Then, we select test instances whose $p$-values are below a data-dependent threshold, certifying AI models' predictions as trustworthy. We provide theoretical guarantees that Conformal Labeling controls the FDR below the nominal level, ensuring that a predefined fraction of AI-assigned labels is correct on average. Extensive experiments demonstrate that our method achieves tight FDR control with high power across various tasks, including image and text labeling, and LLM QA.

---

### CALM-Net: Curvature-Aware LiDAR Point Cloud-based Multi-Branch Neural Network for Vehicle Re-Identification

Authors: Dongwook Lee, Sol Han, Jinwhan Kim
Published: 2025-10-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.14576v1

This paper presents CALM-Net, a curvature-aware LiDAR point cloud-based multi-branch neural network for vehicle re-identification. The proposed model addresses the challenge of learning discriminative and complementary features from three-dimensional point clouds to distinguish between vehicles. CALM-Net employs a multi-branch architecture that integrates edge convolution, point attention, and a curvature embedding that characterizes local surface variation in point clouds. By combining these mechanisms, the model learns richer geometric and contextual features that are well suited for the re-identification task. Experimental evaluation on the large-scale nuScenes dataset demonstrates that CALM-Net achieves a mean re-identification accuracy improvement of approximately 1.97\% points compared with the strongest baseline in our study. The results confirms the effectiveness of incorporating curvature information into deep learning architectures and highlight the benefit of multi-branch feature learning for LiDAR point cloud-based vehicle re-identification.

---

### State-Space Models for Tabular Prior-Data Fitted Networks

Authors: Felix Koch, Marcel Wever, Fabian Raisch, Benjamin Tischler
Published: 2025-10-16
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.14573v2

Recent advancements in foundation models for tabular data, such as TabPFN, demonstrated that pretrained Transformer architectures can approximate Bayesian inference with high predictive performance. However, Transformers suffer from quadratic complexity with respect to sequence length, motivating the exploration of more efficient sequence models. In this work, we investigate the potential of using Hydra, a bidirectional linear-time structured state space model (SSM), as an alternative to Transformers in TabPFN. A key challenge lies in SSM's inherent sensitivity to the order of input tokens - an undesirable property for tabular datasets where the row order is semantically meaningless. We investigate to what extent a bidirectional approach can preserve efficiency and enable symmetric context aggregation. Our experiments show that this approach reduces the order-dependence, achieving predictive performance competitive to the original TabPFN model.

---

### Assessing Socio-Cultural Alignment and Technical Safety of Sovereign LLMs

Authors: Kyubyung Chae, Gihoon Kim, Gyuseong Lee, Taesup Kim, Jaejin Lee, Heejin Kim
Published: 2025-10-16
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.14565v1

Recent trends in LLMs development clearly show growing interest in the use and application of sovereign LLMs. The global debate over sovereign LLMs highlights the need for governments to develop their LLMs, tailored to their unique socio-cultural and historical contexts. However, there remains a shortage of frameworks and datasets to verify two critical questions: (1) how well these models align with users' socio-cultural backgrounds, and (2) whether they maintain safety and technical robustness without exposing users to potential harms and risks. To address this gap, we construct a new dataset and introduce an analytic framework for extracting and evaluating the socio-cultural elements of sovereign LLMs, alongside assessments of their technical robustness. Our experimental results demonstrate that while sovereign LLMs play a meaningful role in supporting low-resource languages, they do not always meet the popular claim that these models serve their target users well. We also show that pursuing this untested claim may lead to underestimating critical quality attributes such as safety. Our study suggests that advancing sovereign LLMs requires a more extensive evaluation that incorporates a broader range of well-grounded and practical criteria.

---

### BalanceGS: Algorithm-System Co-design for Efficient 3D Gaussian Splatting Training on GPU

Authors: Junyi Wu, Jiaming Xu, Jinhao Li, Yongkang Zhou, Jiayi Pan, Xingyang Li, Guohao Dai
Published: 2025-10-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.14564v1

3D Gaussian Splatting (3DGS) has emerged as a promising 3D reconstruction technique. The traditional 3DGS training pipeline follows three sequential steps: Gaussian densification, Gaussian projection, and color splatting. Despite its promising reconstruction quality, this conventional approach suffers from three critical inefficiencies: (1) Skewed density allocation during Gaussian densification, (2) Imbalanced computation workload during Gaussian projection and (3) Fragmented memory access during color splatting. To tackle the above challenges, we introduce BalanceGS, the algorithm-system co-design for efficient training in 3DGS. (1) At the algorithm level, we propose heuristic workload-sensitive Gaussian density control to automatically balance point distributions - removing 80% redundant Gaussians in dense regions while filling gaps in sparse areas. (2) At the system level, we propose Similarity-based Gaussian sampling and merging, which replaces the static one-to-one thread-pixel mapping with adaptive workload distribution - threads now dynamically process variable numbers of Gaussians based on local cluster density. (3) At the mapping level, we propose reordering-based memory access mapping strategy that restructures RGB storage and enables batch loading in shared memory. Extensive experiments demonstrate that compared with 3DGS, our approach achieves a 1.44$\times$ training speedup on a NVIDIA A100 GPU with negligible quality degradation.

---

### Redundancy-Aware Test-Time Graph Out-of-Distribution Detection

Authors: Yue Hou, He Zhu, Ruomei Liu, Yingke Su, Junran Wu, Ke Xu
Published: 2025-10-16
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.14562v1

Distributional discrepancy between training and test data can lead models to make inaccurate predictions when encountering out-of-distribution (OOD) samples in real-world applications. Although existing graph OOD detection methods leverage data-centric techniques to extract effective representations, their performance remains compromised by structural redundancy that induces semantic shifts. To address this dilemma, we propose RedOUT, an unsupervised framework that integrates structural entropy into test-time OOD detection for graph classification. Concretely, we introduce the Redundancy-aware Graph Information Bottleneck (ReGIB) and decompose the objective into essential information and irrelevant redundancy. By minimizing structural entropy, the decoupled redundancy is reduced, and theoretically grounded upper and lower bounds are proposed for optimization. Extensive experiments on real-world datasets demonstrate the superior performance of RedOUT on OOD detection. Specifically, our method achieves an average improvement of 6.7%, significantly surpassing the best competitor by 17.3% on the ClinTox/LIPO dataset pair.

---