# Research Papers — 2025-10 · bundle page 96 of 217

> Full-text markdown of papers #4751–4800 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/96
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/95.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/97.md)

### LLM Latent Reasoning as Chain of Superposition

Authors: Jingcheng Deng, Liang Pang, Zihao Wei, Shicheng Xu, Zenghao Duan, Kun Xu, Yang Song, Huawei Shen, Xueqi Cheng
Published: 2025-10-17
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.15522v2

Latent reasoning offers a computation-efficient alternative to Chain-of-Thought but often suffers from performance degradation due to distributional misalignment and ambiguous chain definitions. Ideally, latent reasoning should function as a superposition of multiple reasoning paths. To realize this, we introduce Latent-SFT, a unified framework addressing challenges at three levels: token, chain, and learning. First, we define the Latent-Vocab to constrain hidden states within the pre-trained vocab-space. Second, we construct the Latent-Chain via Induction-Supervision Masking to ensure semantic compactness and sufficiency. Third, we employ Latent-Optim with stochastic Gumbel-Softmax to guide the model toward generalizable solutions. Empirical results demonstrate that Latent-SFT consistently outperforms explicit SFT across six mathematical benchmarks (e.g., GSM8k, AIME24) while achieving a 2.7x to 5.5x reduction in reasoning length. Analysis confirms that our method effectively captures a superposition of diverse reasoning trajectories rather than merely compressing a single path.

---

### Discovering Intersectional Bias via Directional Alignment in Face Recognition Embeddings

Authors: Ignacio Serna
Published: 2025-10-17
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.15520v2

Modern face recognition models embed identities on a unit hypersphere, where identity variation forms tight clusters. Conversely, shared semantic attributes can often be effectively approximated as linear directions in the latent space. Existing bias evaluation methods rely on predefined attribute labels, synthetic counterfactuals, or proximity-based clustering, all of which fail to capture intersectional subpopulations that emerge along latent directions. We introduce LatentAlign, an attribute-free algorithm that discovers semantically coherent and interpretable subpopulations by iteratively aligning embeddings along dominant latent directions. Unlike distance-based clustering, LatentAlign exploits the geometry of hyperspherical embeddings to isolate directional structures shared across identities, allowing for the interpretable discovery of attributes. Across four state-of-the-art recognition backbones (ArcFace, CosFace, ElasticFace, PartialFC) and two benchmarks (RFW, CelebA), LatentAlign consistently yields more semantically coherent groups than $k$-means, spherical $k$-means, nearest-neighbor search, and DBSCAN. Crucially, the discovered subpopulations expose severe intersectional vulnerabilities, with False Match Rates up to 4x higher than groups defined by explicit annotations. Our results show that by treating semantic attributes as directional features rather than spatial clusters, we can effectively isolate intersectional subpopulations and expose hidden biases that standard audits miss.

---

### From Characters to Tokens: Dynamic Grouping with Hierarchical BPE

Authors: Rares Dolga, Lucas Maystre, Tudor Berariu, David Barber
Published: 2025-10-17
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.15517v1

Subword tokenization methods like Byte Pair Encoding (BPE) are widely used in large language models due to their balance of vocabulary compactness and representational power. However, they suffer from inefficiencies in representing rare words and require large embedding matrices. Character-level models address these issues but introduce performance bottlenecks, particularly in Transformer-based architectures. Recent hierarchical models attempt to merge the benefits of both paradigms by grouping characters into patches, but existing patching strategies either rely on whitespace-limiting applicability to certain languages, or require auxiliary models that introduce new dependencies. In this paper, we propose a dynamic character grouping method that leverages the structure of existing BPE tokenization without requiring additional models. By appending explicit end-of-patch markers to BPE tokens and introducing a second-level BPE compression stage to control patch granularity, our method offers efficient, flexible, and language-agnostic representations. Empirical results demonstrate that our approach matches or exceeds the performance of dynamic entropy- and whitespace-based patching strategies, while maintaining a compact vocabulary.

---

### Revisiting Knowledge Distillation: The Hidden Role of Dataset Size

Authors: Giulia Lanzillotta, Felix Sarnthein, Gil Kur, Thomas Hofmann, Bobby He
Published: 2025-10-17
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.15516v1

The concept of knowledge distillation (KD) describes the training of a student model from a teacher model and is a widely adopted technique in deep learning. However, it is still not clear how and why distillation works. Previous studies focus on two central aspects of distillation: model size, and generalisation. In this work we study distillation in a third dimension: dataset size. We present a suite of experiments across a wide range of datasets, tasks and neural architectures, demonstrating that the effect of distillation is not only preserved but amplified in low-data regimes. We call this newly discovered property the data efficiency of distillation. Equipped with this new perspective, we test the predictive power of existing theories of KD as we vary the dataset size. Our results disprove the hypothesis that distillation can be understood as label smoothing, and provide further evidence in support of the dark knowledge hypothesis. Finally, we analyse the impact of modelling factors such as the objective, scale and relative number of samples on the observed phenomenon. Ultimately, this work reveals that the dataset size may be a fundamental but overlooked variable in the mechanisms underpinning distillation.

---

### Voting with the Graph: Stable RLAIF via Topological Consistency Maximization

Authors: Boyin Liu, Zhuo Zhang, Sen Huang, Lipeng Xie, Qingxu Fu, Haoran Chen, LI YU, Tianyi Hu, Zhaoyang Liu, Bolin Ding, Dongbin Zhao
Published: 2025-10-17
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.15514v3

Reinforcement Learning from AI Feedback (RLAIF) relies on LLM judges as preference measurement instruments, yet these instruments are fundamentally limited by random measurement errors -- stochastic fluctuations that manifest as preference cycles (e.g., $A \succ B \succ C \succ A$), occurring in 5-9% of evaluations across state-of-the-art models. While repeated sampling mitigates noise by averaging multiple judgments, it treats each comparison in isolation and fails to exploit the structural constraints that distinguish systematic signals from random noise. We introduce Topological Consensus Rewards (TCR), a framework that leverages transitivity as a denoising mechanism via topological majority voting: systematic signals reinforce each other through transitive chains, while random errors cluster into topologically exposed cycles. TCR approximates the Maximum Acyclic Subgraph to filter stochastic noise from preference signals. We also propose Cycle Incidence Rate (CIR) as a diagnostic metric that measures the proportion of samples containing preference cycles. Under our noise model, these cycles arise primarily from stochastic measurement errors rather than genuine intransitivity. Experiments on Arena-Hard, MT-Bench, and WritingBench demonstrate that TCR consistently outperforms pairwise baselines and classical ranking algorithms, while exhibiting robust performance across different judge models.

---

### Temporal Referential Consistency: Do LLMs Favor Sequences Over Absolute Time References?

Authors: Ashutosh Bajpai, Tanmoy Chakraborty
Published: 2025-10-17
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.15513v1

The increasing acceptance of large language models (LLMs) as an alternative to knowledge sources marks a significant paradigm shift across various domains, including time-sensitive fields such as law, healthcare, and finance. To fulfill this expanded role, LLMs must not only be factually accurate but also demonstrate consistency across temporal dimensions, necessitating robust temporal reasoning capabilities. Despite this critical requirement, efforts to ensure temporal consistency in LLMs remain scarce including noticeable absence of endeavors aimed at evaluating or augmenting LLMs across temporal references in time-sensitive inquiries. In this paper, we seek to address this gap by introducing a novel benchmark entitled temporal referential consistency, accompanied by a resource TEMP-ReCon designed to benchmark a wide range of both open-source and closed-source LLMs with various linguistic contexts characterized by differing resource richness (including English, French, and Romanian). The findings emphasis that LLMs do exhibit insufficient temporal referent consistency. To address this, we propose \newmodel, a reasoning path alignment-based model that aims to enhance the temporal referential consistency of LLMs. Our empirical experiments substantiate the efficacy of UnTRaP compared to several baseline models.

---

### Language Models are Injective and Hence Invertible

Authors: Giorgos Nikolaou, Tommaso Mencattini, Donato Crisostomi, Andrea Santilli, Yannis Panagakis, Emanuele Rodolà
Published: 2025-10-17
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.15511v4

Transformer components such as non-linear activations and normalization are inherently non-injective, suggesting that different inputs could map to the same output and prevent exact recovery of the input from a model's representations. In this paper, we challenge this view. First, we prove mathematically that transformer language models mapping discrete input sequences to their corresponding sequence of continuous representations are injective and therefore lossless, a property established at initialization and preserved during training. Second, we confirm this result empirically through billions of collision tests on six state-of-the-art language models, and observe no collisions. Third, we operationalize injectivity: we introduce SipIt, the first algorithm that provably and efficiently reconstructs the exact input text from hidden activations, establishing linear-time guarantees and demonstrating exact invertibility in practice. Overall, our work establishes injectivity as a fundamental and exploitable property of language models, with direct implications for transparency, interpretability, and safe deployment.

---

### Exploring Conditions for Diffusion models in Robotic Control

Authors: Heeseong Shin, Byeongho Heo, Dongyoon Han, Seungryong Kim, Taekyung Kim
Published: 2025-10-17
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2510.15510v2

While pre-trained visual representations have significantly advanced imitation learning, they are often task-agnostic as they remain frozen during policy learning. In this work, we explore leveraging pre-trained text-to-image diffusion models to obtain task-adaptive visual representations for robotic control, without fine-tuning the model itself. However, we find that naively applying textual conditions - a successful strategy in other vision domains - yields minimal or even negative gains in control tasks. We attribute this to the domain gap between the diffusion model's training data and robotic control environments, leading us to argue for conditions that consider the specific, dynamic visual information required for control. To this end, we propose ORCA, which introduces learnable task prompts that adapt to the control environment and visual prompts that capture fine-grained, frame-specific details. Through facilitating task-adaptive representations with our newly devised conditions, our approach achieves state-of-the-art performance on various robotic control benchmarks, significantly surpassing prior methods.

---

### AI Adoption in NGOs: A Systematic Literature Review

Authors: Janne Rotter, William Bailkoski
Published: 2025-10-17
Categories: cs.CY, cs.AI, econ.GN
arXiv: https://arxiv.org/abs/2510.15509v1

AI has the potential to significantly improve how NGOs utilize their limited resources for societal benefits, but evidence about how NGOs adopt AI remains scattered. In this study, we systematically investigate the types of AI adoption use cases in NGOs and identify common challenges and solutions, contextualized by organizational size and geographic context. We review the existing primary literature, including studies that investigate AI adoption in NGOs related to social impact between 2020 and 2025 in English. Following the PRISMA protocol, two independent reviewers conduct study selection, with regular cross-checking to ensure methodological rigour, resulting in a final literature body of 65 studies. Leveraging a thematic and narrative approach, we identify six AI use case categories in NGOs - Engagement, Creativity, Decision-Making, Prediction, Management, and Optimization - and extract common challenges and solutions within the Technology-Organization-Environment (TOE) framework. By integrating our findings, this review provides a novel understanding of AI adoption in NGOs, linking specific use cases and challenges to organizational and environmental factors. Our results demonstrate that while AI is promising, adoption among NGOs remains uneven and biased towards larger organizations. Nevertheless, following a roadmap grounded in literature can help NGOs overcome initial barriers to AI adoption, ultimately improving effectiveness, engagement, and social impact.

---

### Theoretical Refinement of CLIP by Utilizing Linear Structure of Optimal Similarity

Authors: Naoki Yoshida, Satoshi Hayakawa, Yuhta Takida, Toshimitsu Uesaka, Hiromi Wakaki, Yuki Mitsufuji
Published: 2025-10-17
Categories: cs.LG, math.NA, stat.ML
arXiv: https://arxiv.org/abs/2510.15508v2

In this study, we propose an enhancement to the similarity computation mechanism in multimodal contrastive pretraining frameworks such as CLIP. Prior theoretical research has demonstrated that the optimal similarity metrics between paired modalities should correspond to the pointwise mutual information (PMI) between the two modalities. However, the current implementations of CLIP and its variants fail to fully utilize the underlying linear structure of PMI. We therefore propose KME-CLIP, which leverages this structure through the inner product in a reproducing kernel Hilbert space (RKHS). We theoretically prove that, under our assumptions, the KME-CLIP similarity can bring the contrastive loss arbitrarily close to its optimal value, which is attained by PMI, as the size of the point set grows, and we empirically evaluate KME-CLIP against CLIP and its kernel-based variants across several retrieval and classification tasks.

---

### The Road Less Traveled: Enhancing Exploration in LLMs via Sequential Sampling

Authors: Shijia Kang, Muhan Zhang
Published: 2025-10-17
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.15502v1

Reinforcement learning (RL) has been pivotal in enhancing the reasoning capabilities of large language models (LLMs), but it often suffers from limited exploration and entropy collapse, where models exploit a narrow set of solutions, leading to a loss of sampling diversity and subsequently preventing RL from further improving performance. This issue is exacerbated in parallel sampling methods, where multiple outputs are drawn from the same distribution, potentially causing the model to converge to similar solutions. We propose SESA, a novel SEquential SAmpling framework that mitigates this challenge by generating diverse solution sketches sequentially before expanding them into full reasoning paths. This approach ensures broader exploration by conditioning each new output on previous ones, promoting diversity throughout the process and preventing policy collapse. Our experiments on a synthetic task show that sequential sampling consistently outperforms traditional RL methods in terms of path diversity and recovery from collapse. Further evaluations on real-world tasks demonstrate that SESA improves both the exploration of valid strategies and the overall performance of LLMs. On three agent benchmarks, SESA lifts success rates by $+0.25$, $+0.42$, and $+0.07$ absolute over the base model (up to an additional $211\%$ relative improvement over baseline RL), underscoring its exploration advantage. This work introduces a structured approach to exploration, paving the way for more effective and diverse reasoning in RL-trained LLMs. Our code is released at https://github.com/MuLabPKU/sesa.

---

### DeceptionBench: A Comprehensive Benchmark for AI Deception Behaviors in Real-world Scenarios

Authors: Yao Huang, Yitong Sun, Yichi Zhang, Ruochen Zhang, Yinpeng Dong, Xingxing Wei
Published: 2025-10-17
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.15501v2

Despite the remarkable advances of Large Language Models (LLMs) across diverse cognitive tasks, the rapid enhancement of these capabilities also introduces emergent deceptive behaviors that may induce severe risks in high-stakes deployments. More critically, the characterization of deception across realistic real-world scenarios remains underexplored. To bridge this gap, we establish DeceptionBench, the first benchmark that systematically evaluates how deceptive tendencies manifest across different societal domains, what their intrinsic behavioral patterns are, and how extrinsic factors affect them. Specifically, on the static count, the benchmark encompasses 150 meticulously designed scenarios in five domains, i.e., Economy, Healthcare, Education, Social Interaction, and Entertainment, with over 1,000 samples, providing sufficient empirical foundations for deception analysis. On the intrinsic dimension, we explore whether models exhibit self-interested egoistic tendencies or sycophantic behaviors that prioritize user appeasement. On the extrinsic dimension, we investigate how contextual factors modulate deceptive outputs under neutral conditions, reward-based incentivization, and coercive pressures. Moreover, we incorporate sustained multi-turn interaction loops to construct a more realistic simulation of real-world feedback dynamics. Extensive experiments across LLMs and Large Reasoning Models (LRMs) reveal critical vulnerabilities, particularly amplified deception under reinforcement dynamics, demonstrating that current models lack robust resistance to manipulative contextual cues and the urgent need for advanced safeguards against various deception behaviors. Code and resources are publicly available at https://github.com/Aries-iai/DeceptionBench.

---

### Hierarchical Mixing Architecture for Low-light RAW Image Enhancement

Authors: Xianmin Chen, Peiliang Huang, Longfei Han, Dingwen Zhang, Junwei Han
Published: 2025-10-17
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.15497v2

With the rapid development of deep learning, low-light RAW image enhancement (LLRIE) has achieved remarkable progress. However, the challenge that how to simultaneously achieve strong enhancement quality and high efficiency still remains. Leveraging the inherent efficiency of Channel Attention and Mamba, we introduce a Hierarchical Mixing Architecture (HiMA), a hybrid LLRIE framework built upon two core modules. Specifically, we introduce Large Scale Block (LSB) for upper layers and Small Scale Block (SSB) for lower layers that reduce the parameters while improve the performance. Based on this framework, we also introduce a novel Local Distribution Adjustment (LoDA) module that adaptively aligns local feature statistics in a content-aware manner by learning to adjust regional luminance and contrast distributions. Moreover, to alleviate the domain ambiguity commonly observed in existing LLRIE pipelines, we design a Multi-Prior Fusion (MPF) module that leverages three complementary priors extracted from the first stage of the hybrid architecture to maintain domain consistency. Extensive experiments on multiple public benchmarks demonstrate that our approach outperforms state-of-the-art methods, delivering superior performance with fewer parameters. Code is available at https://github.com/Cynicarlos/HiMA.

---

### OffSim: Offline Simulator for Model-based Offline Inverse Reinforcement Learning

Authors: Woo-Jin Ahn, Sang-Ryul Baek, Yong-Jun Lee, Hyun-Duck Choi, Myo-Taeg Lim
Published: 2025-10-17
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.15495v2

Reinforcement learning algorithms typically utilize an interactive simulator (i.e., environment) with a predefined reward function for policy training. Developing such simulators and manually defining reward functions, however, is often time-consuming and labor-intensive. To address this, we propose an Offline Simulator (OffSim), a novel model-based offline inverse reinforcement learning (IRL) framework, to emulate environmental dynamics and reward structure directly from expert-generated state-action trajectories. OffSim jointly optimizes a high-entropy transition model and an IRL-based reward function to enhance exploration and improve the generalizability of the learned reward. Leveraging these learned components, OffSim can subsequently train a policy offline without further interaction with the real environment. Additionally, we introduce OffSim$^+$, an extension that incorporates a marginal reward for multi-dataset settings to enhance exploration. Extensive MuJoCo experiments demonstrate that OffSim achieves substantial performance gains over existing offline IRL methods, confirming its efficacy and robustness.

---

### Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software

Authors: Lirong Yi, Gregory Gay, Philipp Leitner
Published: 2025-10-17
Categories: cs.SE, cs.AI, cs.PF
arXiv: https://arxiv.org/abs/2510.15494v2

Large Language Models (LLMs) can generate code, but can they generate fast code for complex, real-world software systems? In this study, we investigate this question using a dataset of 65 tasks mined from performance-critical open-source Java projects. Unlike prior studies, which focused on algorithmic puzzles, we conduct experiments on actual performance-sensitive production code and employ developer-written JMH benchmarks to rigorously validate performance gains against human baselines. Our results reveal a nuanced reality -- although LLMs demonstrate a surprisingly high capability to solve these complex engineering problems, their solutions suffer from extreme volatility and still lag behind human developers on average. Consequently, we find that the current benchmarks based on algorithmic tasks yields an overly optimistic assessment of LLM capabilities. We trace this real-world performance gap to two primary limitations: first, LLMs struggle to autonomously pinpoint performance hotspots, and second, even with explicit guidance, they often fall short of synthesizing optimal algorithmic improvements. Our results highlight the need to move beyond static code generation towards more complex agent-based systems that are able to profile and observe runtime behavior for performance improvement.

---

### Iterative Motion Compensation for Canonical 3D Reconstruction from UAV Plant Images Captured in Windy Conditions

Authors: Andre Rochow, Jonas Marcic, Svetlana Seliunina, Sven Behnke
Published: 2025-10-17
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.15491v1

3D phenotyping of plants plays a crucial role for understanding plant growth, yield prediction, and disease control. We present a pipeline capable of generating high-quality 3D reconstructions of individual agricultural plants. To acquire data, a small commercially available UAV captures images of a selected plant. Apart from placing ArUco markers, the entire image acquisition process is fully autonomous, controlled by a self-developed Android application running on the drone's controller. The reconstruction task is particularly challenging due to environmental wind and downwash of the UAV. Our proposed pipeline supports the integration of arbitrary state-of-the-art 3D reconstruction methods. To mitigate errors caused by leaf motion during image capture, we use an iterative method that gradually adjusts the input images through deformation. Motion is estimated using optical flow between the original input images and intermediate 3D reconstructions rendered from the corresponding viewpoints. This alignment gradually reduces scene motion, resulting in a canonical representation. After a few iterations, our pipeline improves the reconstruction of state-of-the-art methods and enables the extraction of high-resolution 3D meshes. We will publicly release the source code of our reconstruction pipeline. Additionally, we provide a dataset consisting of multiple plants from various crops, captured across different points in time.

---

### AI and analytics in sports: Leveraging BERTopic to map the past and chart the future

Authors: Manit Mishra
Published: 2025-10-17
Categories: stat.AP, cs.LG
arXiv: https://arxiv.org/abs/2510.15487v1

Purpose: The purpose of this study is to map the body of scholarly literature at the intersection of artificial intelligence (AI), analytics and sports and thereafter, leverage the insights generated to chart guideposts for future research. Design/methodology/approach: The study carries out systematic literature review (SLR). Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) protocol is leveraged to identify 204 journal articles pertaining to utilization of AI and analytics in sports published during 2002 to 2024. We follow it up with extraction of the latent topics from sampled articles by leveraging the topic modelling technique of BERTopic. Findings: The study identifies the following as predominant areas of extant research on usage of AI and analytics in sports: performance modelling, physical and mental health, social media sentiment analysis, and tactical tracking. Each extracted topic is further examined in terms of its relative prominence, representative studies, and key term associations. Drawing on these insights, the study delineates promising avenues for future inquiry. Research limitations/implications: The study offers insights to academicians and sports administrators on transformational impact of AI and analytics in sports. Originality/value: The study introduces BERTopic as a novel approach for extracting latent structures in sports research, thereby advancing both scholarly understanding and the methodological toolkit of the field.

---

### Fast Best-in-Class Regret for Contextual Bandits

Authors: Samuel Girard, Aurelien Bibaut, Arthur Gretton, Nathan Kallus, Houssam Zenati
Published: 2025-10-17
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2510.15483v3

We study the problem of stochastic contextual bandits in the agnostic setting, where the goal is to compete with the best policy in a given class without assuming realizability or imposing model restrictions on losses or rewards. In this work, we establish the first fast rate for regret relative to the best-in-class policy. Our proposed algorithm updates the policy at every round by minimizing a pessimistic objective, defined as a clipped inverse-propensity estimate of the policy value plus a variance penalty. By leveraging entropy assumptions on the policy class and a Hölderian error-bound condition (a generalization of the margin condition), we achieve fast best-in-class regret rates, including polylogarithmic rates in the parametric case. The analysis is driven by a sequential self-normalized maximal inequality for bounded martingale empirical processes, which yields uniform variance-adaptive confidence bounds and guarantees pessimism under adaptive data collection.

---

### Selecting and Combining Large Language Models for Scalable Code Clone Detection

Authors: Muslim Chochlov, Gul Aftab Ahmed, James Vincent Patten, Yuanhua Han, Guoxian Lu, David Gregg, Jim Buckley
Published: 2025-10-17
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2510.15480v1

Source code clones pose risks ranging from intellectual property violations to unintended vulnerabilities. Effective and efficient scalable clone detection, especially for diverged clones, remains challenging. Large language models (LLMs) have recently been applied to clone detection tasks. However, the rapid emergence of LLMs raises questions about optimal model selection and potential LLM-ensemble efficacy. This paper addresses the first question by identifying 76 LLMs and filtering them down to suitable candidates for large-scale clone detection. The candidates were evaluated on two public industrial datasets, BigCloneBench, and a commercial large-scale dataset. No uniformly 'best-LLM' emerged, though CodeT5+110M, CuBERT and SPTCode were top-performers. Analysis of LLM-candidates suggested that smaller embedding sizes, smaller tokenizer vocabularies and tailored datasets are advantageous. On commercial large-scale dataset a top-performing CodeT5+110M achieved 39.71\% precision: twice the precision of previously used CodeBERT. To address the second question, this paper explores ensembling of the selected LLMs: effort-effective approach to improving effectiveness. Results suggest the importance of score normalization and favoring ensembling methods like maximum or sum over averaging. Also, findings indicate that ensembling approach can be statistically significant and effective on larger datasets: the best-performing ensemble achieved even higher precision of 46.91\% over individual LLM on the commercial large-scale code.

---

### Adversary-Free Counterfactual Prediction via Information-Regularized Representations

Authors: Shiqin Tang, Rong Feng, Shuxin Zhuang, Youzhi Zhang, Hongzong Li
Published: 2025-10-17
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.15479v2

We study counterfactual prediction under assignment bias and propose a mathematically grounded, information-theoretic approach that removes treatment-covariate dependence without adversarial training. Starting from a bound that links the counterfactual-factual risk gap to mutual information, we learn a stochastic representation Z that is predictive of outcomes while minimizing I(Z; T). We derive a tractable variational objective that upper-bounds the information term and couples it with a supervised decoder, yielding a stable, provably motivated training criterion. The framework extends naturally to dynamic settings by applying the information penalty to sequential representations at each decision time. We evaluate the method on controlled numerical simulations and a real-world clinical dataset, comparing against recent state-of-the-art balancing, reweighting, and adversarial baselines. Across metrics of likelihood, counterfactual error, and policy evaluation, our approach performs favorably while avoiding the training instabilities and tuning burden of adversarial schemes.

---

### SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses

Authors: Hanbin Hong, Shuang Wu, Shuya Feng, Nima Naderloui, Shenao Yan, Jingyu Zhang, Ali Arastehfard, Heqing Huang, Yuan Hong
Published: 2025-10-17
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2510.15476v4

Prompt-security claims for large language models (LLMs) are often compared as properties of individual attacks or defenses, although measured harmfulness depends on the target model, access setting, attack and defense configuration, prompt sample, and judger. We systematize 272 studies through three linked, multi-label taxonomies of jailbreak attacks, defenses, and model vulnerabilities. To make these dependencies explicit, we introduce an access-compatible evaluation protocol over configured $\langle M,A,D,S,J\rangle$ tuples and instantiate it in PromptSecurity, an open-source platform that records method settings, outputs, judgments, and query costs. We release two complementary datasets: JailbreakDB, with 445,752 jailbreak system-user prompt pairs and 1,094,122 benign prompts, and PromptSecurity-Eval, with 166,200 harmful-query and 9,200 benign-utility output records. We evaluate 11 target models, 20 attacks, nine defenses, and three automated judgers under a matched, single-turn protocol using 100 harmful queries and separate benign-utility tasks. Lower attack success can reflect failure to execute transformed requests rather than stronger safety; attack-category advantages can reverse when one method is excluded, and attack success varies with assistant choice. Defenses can reduce harmful outputs while degrading benign-task utility or causing backfire. Rejudging identical outputs also shows that measured attack success is sensitive to the behavior supplied to the judger, highlighting the need to report judger configurations alongside ASR. These findings motivate configuration-aware reporting rather than context-free method rankings. Leaderboard: https://datasec-lab.github.io/PromptSecurityLeaderboard/. Dataset: https://huggingface.co/datasets/youbin2014/JailbreakDB. GitHub: https://github.com/datasec-lab/PromptSecurity.

---

### A Novel Combined Optical Flow Approach for Comprehensive Micro-Expression Recognition

Authors: Vu Tram Anh Khuong, Thi Bich Phuong Man, Luu Tu Nguyen, Thanh Ha Le, Thi Duyen Ngo
Published: 2025-10-17
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.15471v1

Facial micro-expressions are brief, involuntary facial movements that reveal hidden emotions. Most Micro-Expression Recognition (MER) methods that rely on optical flow typically focus on the onset-to-apex phase, neglecting the apex-to-offset phase, which holds key temporal dynamics. This study introduces a Combined Optical Flow (COF), integrating both phases to enhance feature representation. COF provides a more comprehensive motion analysis, improving MER performance. Experimental results on CASMEII and SAMM datasets show that COF outperforms single optical flow-based methods, demonstrating its effectiveness in capturing micro-expression dynamics.

---

### MSAM: Multi-Semantic Adaptive Mining for Cross-Modal Drone Video-Text Retrieval

Authors: Jinghao Huang, Yaxiong Chen, Ganchao Liu
Published: 2025-10-17
Categories: cs.CV, cs.IR
arXiv: https://arxiv.org/abs/2510.15470v1

With the advancement of drone technology, the volume of video data increases rapidly, creating an urgent need for efficient semantic retrieval. We are the first to systematically propose and study the drone video-text retrieval (DVTR) task. Drone videos feature overhead perspectives, strong structural homogeneity, and diverse semantic expressions of target combinations, which challenge existing cross-modal methods designed for ground-level views in effectively modeling their characteristics. Therefore, dedicated retrieval mechanisms tailored for drone scenarios are necessary. To address this issue, we propose a novel approach called Multi-Semantic Adaptive Mining (MSAM). MSAM introduces a multi-semantic adaptive learning mechanism, which incorporates dynamic changes between frames and extracts rich semantic information from specific scene regions, thereby enhancing the deep understanding and reasoning of drone video content. This method relies on fine-grained interactions between words and drone video frames, integrating an adaptive semantic construction module, a distribution-driven semantic learning term and a diversity semantic term to deepen the interaction between text and drone video modalities and improve the robustness of feature representation. To reduce the interference of complex backgrounds in drone videos, we introduce a cross-modal interactive feature fusion pooling mechanism that focuses on feature extraction and matching in target regions, minimizing noise effects. Extensive experiments on two self-constructed drone video-text datasets show that MSAM outperforms other existing methods in the drone video-text retrieval task. The source code and dataset will be made publicly available.

---

### MRASfM: Multi-Camera Reconstruction and Aggregation through Structure-from-Motion in Driving Scenes

Authors: Lingfeng Xuan, Chang Nie, Yiqing Xu, Zhe Liu, Yanzi Miao, Hesheng Wang
Published: 2025-10-17
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.15467v1

Structure from Motion (SfM) estimates camera poses and reconstructs point clouds, forming a foundation for various tasks. However, applying SfM to driving scenes captured by multi-camera systems presents significant difficulties, including unreliable pose estimation, excessive outliers in road surface reconstruction, and low reconstruction efficiency. To address these limitations, we propose a Multi-camera Reconstruction and Aggregation Structure-from-Motion (MRASfM) framework specifically designed for driving scenes. MRASfM enhances the reliability of camera pose estimation by leveraging the fixed spatial relationships within the multi-camera system during the registration process. To improve the quality of road surface reconstruction, our framework employs a plane model to effectively remove erroneous points from the triangulated road surface. Moreover, treating the multi-camera set as a single unit in Bundle Adjustment (BA) helps reduce optimization variables to boost efficiency. In addition, MRASfM achieves multi-scene aggregation through scene association and assembly modules in a coarse-to-fine fashion. We deployed multi-camera systems on actual vehicles to validate the generalizability of MRASfM across various scenes and its robustness in challenging conditions through real-world applications. Furthermore, large-scale validation results on public datasets show the state-of-the-art performance of MRASfM, achieving 0.124 absolute pose error on the nuScenes dataset.

---

### Improving Micro-Expression Recognition with Phase-Aware Temporal Augmentation

Authors: Vu Tram Anh Khuong, Luu Tu Nguyen, Thanh Ha Le, Thi Duyen Ngo
Published: 2025-10-17
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.15466v1

Micro-expressions (MEs) are brief, involuntary facial movements that reveal genuine emotions, typically lasting less than half a second. Recognizing these subtle expressions is critical for applications in psychology, security, and behavioral analysis. Although deep learning has enabled significant advances in micro-expression recognition (MER), its effectiveness is limited by the scarcity of annotated ME datasets. This data limitation not only hinders generalization but also restricts the diversity of motion patterns captured during training. Existing MER studies predominantly rely on simple spatial augmentations (e.g., flipping, rotation) and overlook temporal augmentation strategies that can better exploit motion characteristics. To address this gap, this paper proposes a phase-aware temporal augmentation method based on dynamic image. Rather than encoding the entire expression as a single onset-to-offset dynamic image (DI), our approach decomposes each expression sequence into two motion phases: onset-to-apex and apex-to-offset. A separate DI is generated for each phase, forming a Dual-phase DI augmentation strategy. These phase-specific representations enrich motion diversity and introduce complementary temporal cues that are crucial for recognizing subtle facial transitions. Extensive experiments on CASME-II and SAMM datasets using six deep architectures, including CNNs, Vision Transformer, and the lightweight LEARNet, demonstrate consistent performance improvements in recognition accuracy, unweighted F1-score, and unweighted average recall, which are crucial for addressing class imbalance in MER. When combined with spatial augmentations, our method achieves up to a 10\% relative improvement. The proposed augmentation is simple, model-agnostic, and effective in low-resource settings, offering a promising direction for robust and generalizable MER.

---

### Learning to Answer from Correct Demonstrations

Authors: Nirmit Joshi, Gene Li, Siddharth Bhandari, Shiva Prasad Kasiviswanathan, Cong Ma, Nathan Srebro
Published: 2025-10-17
Categories: cs.LG, cs.AI, stat.ML
arXiv: https://arxiv.org/abs/2510.15464v2

We study the problem of learning to generate an answer (or completion) to a question (or prompt), where there could be multiple correct answers, any one of which is acceptable at test time. Learning is based on demonstrations of some correct answer to each training question, as in Supervised Fine Tuning (SFT). We formalize the problem as imitation learning (i.e., apprenticeship learning) in contextual bandits, with offline demonstrations from some expert (optimal, or very good) policy, without explicitly observed rewards. In contrast to prior work, which assumes the demonstrator belongs to a bounded-complexity policy class, we propose relying only on the underlying reward model (i.e., specifying which answers are correct) being in a bounded-complexity class, which we argue is a strictly weaker assumption. We show that likelihood-maximization methods can fail in this setting, and instead present an approach that learns to answer nearly as well as the demonstrator, with sample complexity logarithmic in the cardinality of the reward class. Our method is similar to Syed and Schapire 2007, when adapted to a contextual bandit (i.e., single step) setup, but is a simple one-pass online approach that enjoys an "optimistic rate" (i.e., $1/\varepsilon$ when the demonstrator is optimal, versus $1/\varepsilon^2$ in Syed and Schapire), and works even with arbitrarily adaptive demonstrations.

---

### Robust Optimization in Causal Models and G-Causal Normalizing Flows

Authors: Gabriele Visentin, Patrick Cheridito
Published: 2025-10-17
Categories: stat.ML, cs.AI, cs.LG, q-fin.PM
arXiv: https://arxiv.org/abs/2510.15458v1

In this paper, we show that interventionally robust optimization problems in causal models are continuous under the $G$-causal Wasserstein distance, but may be discontinuous under the standard Wasserstein distance. This highlights the importance of using generative models that respect the causal structure when augmenting data for such tasks. To this end, we propose a new normalizing flow architecture that satisfies a universal approximation property for causal structural models and can be efficiently trained to minimize the $G$-causal Wasserstein distance. Empirically, we demonstrate that our model outperforms standard (non-causal) generative models in data augmentation for causal regression and mean-variance portfolio optimization in causal factor models.

---

### Expediting Reinforcement Learning by Incorporating Knowledge About Temporal Causality in the Environment

Authors: Jan Corazza, Hadi Partovi Aria, Daniel Neider, Zhe Xu
Published: 2025-10-17
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.15456v1

Reinforcement learning (RL) algorithms struggle with learning optimal policies for tasks where reward feedback is sparse and depends on a complex sequence of events in the environment. Probabilistic reward machines (PRMs) are finite-state formalisms that can capture temporal dependencies in the reward signal, along with nondeterministic task outcomes. While special RL algorithms can exploit this finite-state structure to expedite learning, PRMs remain difficult to modify and design by hand. This hinders the already difficult tasks of utilizing high-level causal knowledge about the environment, and transferring the reward formalism into a new domain with a different causal structure. This paper proposes a novel method to incorporate causal information in the form of Temporal Logic-based Causal Diagrams into the reward formalism, thereby expediting policy learning and aiding the transfer of task specifications to new environments. Furthermore, we provide a theoretical result about convergence to optimal policy for our method, and demonstrate its strengths empirically.

---

### CORE: Reducing UI Exposure in Mobile Agents via Collaboration Between Cloud and Local LLMs

Authors: Gucongcong Fan, Chaoyue Niu, Chengfei Lyu, Fan Wu, Guihai Chen
Published: 2025-10-17
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.15455v1

Mobile agents rely on Large Language Models (LLMs) to plan and execute tasks on smartphone user interfaces (UIs). While cloud-based LLMs achieve high task accuracy, they require uploading the full UI state at every step, exposing unnecessary and often irrelevant information. In contrast, local LLMs avoid UI uploads but suffer from limited capacity, resulting in lower task success rates. We propose $\textbf{CORE}$, a $\textbf{CO}$llaborative framework that combines the strengths of cloud and local LLMs to $\textbf{R}$educe UI $\textbf{E}$xposure, while maintaining task accuracy for mobile agents. CORE comprises three key components: (1) $\textbf{Layout-aware block partitioning}$, which groups semantically related UI elements based on the XML screen hierarchy; (2) $\textbf{Co-planning}$, where local and cloud LLMs collaboratively identify the current sub-task; and (3) $\textbf{Co-decision-making}$, where the local LLM ranks relevant UI blocks, and the cloud LLM selects specific UI elements within the top-ranked block. CORE further introduces a multi-round accumulation mechanism to mitigate local misjudgment or limited context. Experiments across diverse mobile apps and tasks show that CORE reduces UI exposure by up to 55.6% while maintaining task success rates slightly below cloud-only agents, effectively mitigating unnecessary privacy exposure to the cloud. The code is available at https://github.com/Entropy-Fighter/CORE.

---

### DPTrack:Directional Kernel-Guided Prompt Learning for Robust Nighttime Aerial Tracking

Authors: Zhiqiang Zhu, Xinbo Gao, Wen Lu, Jie Li, Zhaoyang Wang, Mingqian Ge
Published: 2025-10-17
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.15449v1

Existing nighttime aerial trackers based on prompt learning rely solely on spatial localization supervision, which fails to provide fine-grained cues that point to target features and inevitably produces vague prompts. This limitation impairs the tracker's ability to accurately focus on the object features and results in trackers still performing poorly. To address this issue, we propose DPTrack, a prompt-based aerial tracker designed for nighttime scenarios by encoding the given object's attribute features into the directional kernel enriched with fine-grained cues to generate precise prompts. Specifically, drawing inspiration from visual bionics, DPTrack first hierarchically captures the object's topological structure, leveraging topological attributes to enrich the feature representation. Subsequently, an encoder condenses these topology-aware features into the directional kernel, which serves as the core guidance signal that explicitly encapsulates the object's fine-grained attribute cues. Finally, a kernel-guided prompt module built on channel-category correspondence attributes propagates the kernel across the features of the search region to pinpoint the positions of target features and convert them into precise prompts, integrating spatial gating for robust nighttime tracking. Extensive evaluations on established benchmarks demonstrate DPTrack's superior performance. Our code will be available at https://github.com/zzq-vipsl/DPTrack.

---

### MAVR-Net: Robust Multi-View Learning for MAV Action Recognition with Cross-View Attention

Authors: Nengbo Zhang, Hann Woei Ho
Published: 2025-10-17
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.15448v1

Recognizing the motion of Micro Aerial Vehicles (MAVs) is crucial for enabling cooperative perception and control in autonomous aerial swarms. Yet, vision-based recognition models relying only on RGB data often fail to capture the complex spatial temporal characteristics of MAV motion, which limits their ability to distinguish different actions. To overcome this problem, this paper presents MAVR-Net, a multi-view learning-based MAV action recognition framework. Unlike traditional single-view methods, the proposed approach combines three complementary types of data, including raw RGB frames, optical flow, and segmentation masks, to improve the robustness and accuracy of MAV motion recognition. Specifically, ResNet-based encoders are used to extract discriminative features from each view, and a multi-scale feature pyramid is adopted to preserve the spatiotemporal details of MAV motion patterns. To enhance the interaction between different views, a cross-view attention module is introduced to model the dependencies among various modalities and feature scales. In addition, a multi-view alignment loss is designed to ensure semantic consistency and strengthen cross-view feature representations. Experimental results on benchmark MAV action datasets show that our method clearly outperforms existing approaches, achieving 97.8\%, 96.5\%, and 92.8\% accuracy on the Short MAV, Medium MAV, and Long MAV datasets, respectively.

---

### Particle Dynamics for Latent-Variable Energy-Based Models

Authors: Shiqin Tang, Shuxin Zhuang, Rong Feng, Runsheng Yu, Hongzong Li, Youzhi Zhang
Published: 2025-10-17
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.15447v1

Latent-variable energy-based models (LVEBMs) assign a single normalized energy to joint pairs of observed data and latent variables, offering expressive generative modeling while capturing hidden structure. We recast maximum-likelihood training as a saddle problem over distributions on the latent and joint manifolds and view the inner updates as coupled Wasserstein gradient flows. The resulting algorithm alternates overdamped Langevin updates for a joint negative pool and for conditional latent particles with stochastic parameter ascent, requiring no discriminator or auxiliary networks. We prove existence and convergence under standard smoothness and dissipativity assumptions, with decay rates in KL divergence and Wasserstein-2 distance. The saddle-point view further yields an ELBO strictly tighter than bounds obtained with restricted amortized posteriors. Our method is evaluated on numerical approximations of physical systems and performs competitively against comparable approaches.

---

### A Theoretical Study on Bridging Internal Probability and Self-Consistency for LLM Reasoning

Authors: Zhi Zhou, Yuhao Tan, Zenan Li, Yuan Yao, Lan-Zhe Guo, Yu-Feng Li, Xiaoxing Ma
Published: 2025-10-17
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.15444v1

Test-time scaling seeks to improve the reasoning performance of large language models (LLMs) by adding computational resources. A prevalent approach within the field is sampling-based test-time scaling methods, which enhance reasoning by generating multiple reasoning paths for a given input during inference. However, despite its practical success, the theoretical foundations remain underexplored. In this paper, we provide the first theoretical framework for analyzing sampling-based test-time scaling methods, grounded in the perspective of confidence estimation. Based on the framework, we analyze two dominant paradigms: self-consistency and perplexity, and reveal key limitations: self-consistency suffers from high estimation error while perplexity exhibits substantial modeling error and possible degradation of the estimation error convergence. To address these limitations, we introduce RPC, a hybrid method that leverages our theoretical insights through two key components: Perplexity Consistency and Reasoning Pruning. Perplexity Consistency combines the strengths of self-consistency and perplexity, boosting the convergence rate of estimation error from linear to exponential while preserving model error. Reasoning Pruning prevents degradation by eliminating low-probability reasoning paths. Both theoretical analysis and empirical results across seven benchmark datasets demonstrate that RPC has a strong potential for reducing reasoning error. Notably, RPC achieves reasoning performance comparable to self-consistency while not only enhancing confidence reliability but also reducing sampling costs by 50%. The code and resources are available at https://wnjxyk.github.io/RPC.

---

### Select Less, Reason More: Prioritizing Evidence Purity for Video Reasoning

Authors: Xuchen Li, Xuzhao Li, Shiyu Hu, Kaiqi Huang
Published: 2025-10-17
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.15440v1

Long-form video reasoning remains a major challenge for Video Large Language Models (Video LLMs), as static uniform frame sampling leads to information dilution and obscures critical evidence. Furthermore, existing pixel-space video reasoning agents, which are designed to actively interact with the video to acquire new visual information, remain suboptimal due to their lack of rigorous reward mechanisms to enforce evidence purity and their inability to perform temporal information supplementation beyond pre-sampled frames. To address this critical gap, we propose a novel evidence-prioritized adaptive framework built upon our core philosophy: "Select Less, Reason More." Our core contribution is the evidence-aware reinforcement learning (EARL) framework, which transforms the model into an active interrogator of evidence. EARL is precisely engineered to dynamically select the most relevant frames and, crucially, to perform localized re-sampling around the selected key frames to access fine-grained temporal detail. Extensive experiments on five demanding video reasoning benchmarks demonstrate that our EARL-trained model achieves new state-of-the-art among open-source Video LLMs, simultaneously learning an effective and high-purity visual evidence selection policy. Impressively, our 7B model achieves 59.8% on LongVideoBench, 69.0% on MVBench and 64.9% on VideoMME. These results highlight the importance of prioritizing evidence purity and the effectiveness of our framework.

---

### Rethinking Convergence in Deep Learning: The Predictive-Corrective Paradigm for Anatomy-Informed Brain MRI Segmentation

Authors: Feifei Zhang, Zhenhong Jia, Sensen Song, Fei Shi, Dayong Ren
Published: 2025-10-17
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.15439v1

Despite the remarkable success of the end-to-end paradigm in deep learning, it often suffers from slow convergence and heavy reliance on large-scale datasets, which fundamentally limits its efficiency and applicability in data-scarce domains such as medical imaging. In this work, we introduce the Predictive-Corrective (PC) paradigm, a framework that decouples the modeling task to fundamentally accelerate learning. Building upon this paradigm, we propose a novel network, termed PCMambaNet. PCMambaNet is composed of two synergistic modules. First, the Predictive Prior Module (PPM) generates a coarse approximation at low computational cost, thereby anchoring the search space. Specifically, the PPM leverages anatomical knowledge-bilateral symmetry-to predict a 'focus map' of diagnostically relevant asymmetric regions. Next, the Corrective Residual Network (CRN) learns to model the residual error, focusing the network's full capacity on refining these challenging regions and delineating precise pathological boundaries. Extensive experiments on high-resolution brain MRI segmentation demonstrate that PCMambaNet achieves state-of-the-art accuracy while converging within only 1-5 epochs-a performance unattainable by conventional end-to-end models. This dramatic acceleration highlights that by explicitly incorporating domain knowledge to simplify the learning objective, PCMambaNet effectively mitigates data inefficiency and overfitting.

---

### Controllable Abstraction in Summary Generation for Large Language Models via Prompt Engineering

Authors: Xiangchen Song, Yuchen Liu, Yaxuan Luan, Jinxu Guo, Xiaofan Guo
Published: 2025-10-17
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.15436v1

This study presents a controllable abstract summary generation method for large language models based on prompt engineering. To address the issues of summary quality and controllability in traditional methods, we design a multi-stage prompt generation framework. This framework generates summaries with varying levels of abstraction by performing semantic analysis, topic modeling, and noise control on the input text. The experiment uses the CNN/Daily Mail dataset and provides a detailed analysis of different prompt lengths, data noise, and text types. The experimental results show that prompt length has a significant impact on the quality of generated summaries. Both very short and very long prompt tokens result in a decrease in summary quality. Data noise also negatively affects the summary generation process. As noise levels increase, the ROUGE-L score gradually decreases. Furthermore, different text types have varying effects on the model's ability to generate summaries. The model performs best when handling news texts, while its performance is worse when processing academic articles. This research provides new insights into improving summary generation using large language models, particularly in how controlling prompt strategies and optimizing text preprocessing can enhance summary accuracy and controllability.

---

### Nonlinear Dimensionality Reduction Techniques for Bayesian Optimization

Authors: Luo Long, Coralia Cartis, Paz Fink Shustin
Published: 2025-10-17
Categories: math.OC, cs.LG, math.NA
arXiv: https://arxiv.org/abs/2510.15435v2

Bayesian optimisation (BO) enables sample-efficient global optimisation of expensive black-box functions but remains challenging in high dimensions. We investigate nonlinear dimensionality reduction to a sequence of low-dimensional latent-space BO (LSBO) problems. Early LSBO used linear random and supervised embeddings; building on Grosnit et al., we employ variational autoencoders (VAEs), deep metric loss for structured latent manifolds, and retraining to adapt the encoder-decoder pair to newly sampled regions. We couple LSBO with sequential domain reduction (SDR) directly in latent space (SDR-LSBO), narrowing search domains as evidence accumulates. Implemented in GPU-accelerated BoTorch with Matérn-5/2 Gaussian-process surrogates, our methods improve benchmark optimisation quality, and retraining can enhance BO performance. Comparisons with adaptive supervised linear random embeddings demonstrate the effectiveness of VAE-based BO for nonlinear low-dimensional structures. We analyse BO-VAE with a fixed pretrained representation, decomposing ambient-space simple regret into latent BO error and a fixed VAE-induced representation gap. Under a PAC-Bayes-certified reconstruction condition and standard fixed-prior assumptions for expected improvement with a Matérn-5/2 kernel, latent BO error vanishes as the evaluation budget increases, whereas the representation gap remains fixed and may impose a non-vanishing error floor. Visualisations empirically assess accessibility of the ambient optimum through the learned decoder. To our knowledge, this is the first study combining SDR with VAE-based LSBO. Our analysis clarifies metric shaping and retraining choices critical for scalable latent-space BO. For reproducibility, source code is available at https://github.com/L-Lok/Nonlinear-Dimensionality-Reduction-Techniques-for-Bayesian-Optimization.git.

---

### Semantic4Safety: Causal Insights from Zero-shot Street View Imagery Segmentation for Urban Road Safety

Authors: Huan Chen, Ting Han, Siyu Chen, Zhihao Guo, Yiping Chen, Meiliu Wu
Published: 2025-10-17
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.15434v1

Street-view imagery (SVI) offers a fine-grained lens on traffic risk, yet two fundamental challenges persist: (1) how to construct street-level indicators that capture accident-related features, and (2) how to quantify their causal impacts across different accident types. To address these challenges, we propose Semantic4Safety, a framework that applies zero-shot semantic segmentation to SVIs to derive 11 interpretable streetscape indicators, and integrates road type as contextual information to analyze approximately 30,000 accident records in Austin. Specifically, we train an eXtreme Gradient Boosting (XGBoost) multi-class classifier and use Shapley Additive Explanations (SHAP) to interpret both global and local feature contributions, and then apply Generalized Propensity Score (GPS) weighting and Average Treatment Effect (ATE) estimation to control confounding and quantify causal effects. Results uncover heterogeneous, accident-type-specific causal patterns: features capturing scene complexity, exposure, and roadway geometry dominate predictive power; larger drivable area and emergency space reduce risk, whereas excessive visual openness can increase it. By bridging predictive modeling with causal inference, Semantic4Safety supports targeted interventions and high-risk corridor diagnosis, offering a scalable, data-informed tool for urban road safety planning.

---

### Learning to Detect Unknown Jailbreak Attacks in Large Vision-Language Models

Authors: Shuang Liang, Zhihao Xu, Jialing Tao, Hui Xue, Xiting Wang
Published: 2025-10-17
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.15430v2

Despite extensive alignment efforts, Large Vision-Language Models (LVLMs) remain vulnerable to jailbreak attacks, posing serious safety risks. To address this, existing detection methods either learn attack-specific parameters, which hinders generalization to unseen attacks, or rely on heuristically sound principles, which limit accuracy and efficiency. To overcome these limitations, we propose Learning to Detect (LoD), a general framework that accurately detects unknown jailbreak attacks by shifting the focus from attack-specific learning to task-specific learning. This framework includes a Multi-modal Safety Concept Activation Vector module for safety-oriented representation learning and a Safety Pattern Auto-Encoder module for unsupervised attack classification. Extensive experiments show that our method achieves consistently higher detection AUROC on diverse unknown attacks while improving efficiency. The code is available at https://anonymous.4open.science/r/Learning-to-Detect-51CB.

---

### Safe, Efficient, and Robust Reinforcement Learning for Ranking and Diffusion Models

Authors: Shashank Gupta
Published: 2025-10-17
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.15429v1

This dissertation investigates how reinforcement learning (RL) methods can be designed to be safe, sample-efficient, and robust. Framed through the unifying perspective of contextual-bandit RL, the work addresses two major application domains - ranking and recommendation, and text-to-image diffusion models. The first part of the thesis develops theory and algorithms for safe deployment in ranking systems. An exposure-based generalisation bound is derived, leading to a counterfactual risk-minimisation objective whose solution is guaranteed not to underperform the logging policy, even with sparse feedback. This guarantee is extended to doubly robust estimators, enabling safety even under adversarial or misspecified user models and offering practitioners explicit control over permissible utility loss. The second part turns to single-action bandits, where various off-policy estimators are unified within a baseline-correction framework. A closed-form optimal baseline is proposed and shown to minimise both evaluation and policy-gradient variance, thereby improving off-policy learning reliability. The final part examines the trade-offs between efficiency and effectiveness in generative RL. A systematic study of PPO and REINFORCE motivates the Leave-One-Out PPO (LOOP) algorithm, which combines multiple diffusion trajectories with a REINFORCE-style baseline inside PPO's clipped objective. LOOP achieves PPO-level sample efficiency while producing generations that align more faithfully with textual attributes.

---

### TeamFormer: Shallow Parallel Transformers with Progressive Approximation

Authors: Wei Wang, Xiao-Yong Wei, Qing Li
Published: 2025-10-17
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.15425v2

The widespread 'deeper is better' philosophy has driven the creation of architectures like ResNet and Transformer, which achieve high performance by stacking numerous layers. However, increasing model depth comes with challenges such as longer training times, higher inference latency, and impracticality on resource-constrained devices. To address these issues, we propose TeamFormer, a shallow Transformer architecture designed for true parallelism in both structure and computation. By formulating standard Transformers as function approximators in closed-form, our theoretical analysis shows that their performance relies on inter-layer collaboration for progressive approximation, rather than depth itself. While deep Transformers enforce this collaboration through sequential designs, we demonstrate that such collaboration is not inherently tied to sequential structures. TeamFormer removes the sequential constraint by organizing layers into parallel branches, enforcing inter-layer collaboration algorithmically. Specifically, we implement progressive approximation, ensuring that each new branch further reduces the loss from preceding branches, enabling faster convergence. Extensive experiments validate TeamFormer's effectiveness, outperforming standard Transformers like ViT. Moreover, TeamFormer supports up to 15.07x model compression and facilitates model expansion for adaptive continuous learning. Experimental results on multi-GPU deployment demonstrate that TeamFormer is 3.30x faster than widely used parallelism solutions such as FairScale. These advancements stem from our closed-form formulation of Transformers based on the Universal Approximation Theorem, which not only explains the ``depth belief'' but also opens new avenues for designing efficient Transformer architectures. Source code: https://(open-upon-acceptance)

---

### Information Theory in Open-world Machine Learning Foundations, Frameworks, and Future Direction

Authors: Lin Wang
Published: 2025-10-17
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2510.15422v1

Open world Machine Learning (OWML) aims to develop intelligent systems capable of recognizing known categories, rejecting unknown samples, and continually learning from novel information. Despite significant progress in open set recognition, novelty detection, and continual learning, the field still lacks a unified theoretical foundation that can quantify uncertainty, characterize information transfer, and explain learning adaptability in dynamic, nonstationary environments. This paper presents a comprehensive review of information theoretic approaches in open world machine learning, emphasizing how core concepts such as entropy, mutual information, and Kullback Leibler divergence provide a mathematical language for describing knowledge acquisition, uncertainty suppression, and risk control under open world conditions. We synthesize recent studies into three major research axes: information theoretic open set recognition enabling safe rejection of unknowns, information driven novelty discovery guiding new concept formation, and information retentive continual learning ensuring stable long term adaptation. Furthermore, we discuss theoretical connections between information theory and provable learning frameworks, including PAC Bayes bounds, open-space risk theory, and causal information flow, to establish a pathway toward provable and trustworthy open world intelligence. Finally, the review identifies key open problems and future research directions, such as the quantification of information risk, development of dynamic mutual information bounds, multimodal information fusion, and integration of information theory with causal reasoning and world model learning.

---

### When Seeing Is not Enough: Revealing the Limits of Active Reasoning in MLLMs

Authors: Hongcheng Liu, Pingjie Wang, Yuhao Wang, Siqu Ou, Yanfeng Wang, Yu Wang
Published: 2025-10-17
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.15421v1

Multimodal large language models (MLLMs) have shown strong capabilities across a broad range of benchmarks. However, most existing evaluations focus on passive inference, where models perform step-by-step reasoning under complete information. This setup is misaligned with real-world use, where seeing is not enough. This raises a fundamental question: Can MLLMs actively acquire missing evidence under incomplete information? To bridge this gap, we require the MLLMs to actively acquire missing evidence and iteratively refine decisions under incomplete information, by selecting a target image from a candidate pool without task-specific priors. To support systematic study, we propose GuessBench, a benchmark with both perception-oriented and knowledge-oriented images for evaluating active reasoning in MLLMs. We evaluate 20 superior MLLMs and find that performance on active reasoning lags far behind it on passive settings, indicating substantial room for improvement. Further analysis identifies fine-grained perception and timely decision-making as key challenges. Ablation studies show that perceptual enhancements benefit smaller models, whereas thinking-oriented methods provide consistent gains across model sizes. These results suggest promising directions for future research on multimodal active reasoning.

---

### Fine-Tuning MedGemma for Clinical Captioning to Enhance Multimodal RAG over Malaysia CPGs

Authors: Lee Qi Zun, Mohamad Zulhilmi Bin Abdul Halim, Goh Man Fye
Published: 2025-10-17
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.15418v2

Retrieval-Augmented Generation systems are essential for providing fact-based guidance from Malaysian Clinical Practice Guidelines. However, their effectiveness with image-based queries is limited, as general Vision-Language Model captions often lack clinical specificity and factual grounding. This study proposes and validates a framework to specialize the MedGemma model for generating high-fidelity captions that serve as superior queries. To overcome data scarcity, we employ a knowledge distillation pipeline to create a synthetic dataset across dermatology, fundus, and chest radiography domains, and fine-tune MedGemma using the parameter-efficient QLoRA method. Performance was rigorously assessed through a dual framework measuring both classification accuracy and, via a novel application of the RAGAS framework, caption faithfulness, relevancy, and correctness. The fine-tuned model demonstrated substantial improvements in classification performance, while RAGAS evaluation confirmed significant gains in caption faithfulness and correctness, validating the models ability to produce reliable, factually grounded descriptions. This work establishes a robust pipeline for specializing medical VLMs and validates the resulting model as a high-quality query generator, laying the groundwork for enhancing multimodal RAG systems in evidence-based clinical decision support.

---

### Adaptive Minds: Empowering Agents with LoRA-as-Tools

Authors: Pavan C Shekar, Aswanth Krishnan
Published: 2025-10-17
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.15416v2

We investigate a framework in which LoRA adapters are treated as callable tools that a base language model can dynamically select and invoke. We hypothesize that, when adapters are trained to provide strong domain-specific gains and are exposed with clear metadata, a base model can reliably route queries to the appropriate expert, effectively aggregating the benefits of many specialized adapters within a single framework. We introduce Adaptive Minds, a general framework within which we study both single-step routing and multi-step agentic reasoning. In this setting, the agent can iteratively invoke multiple adapters alongside other tools (e.g., external APIs, retrieval systems, or execution environments) and reason over their outputs across multiple steps. This reframes adapters as modular skills or memory units that can be composed during reasoning rather than statically applied. In our evaluation, the routing layer reaches 98.3% accuracy on a 30-adapter library, and well-trained specialists provide +4.6 to +84.0 percentage points of strict-scorer gain across nine task families under a single shared training recipe; the AM router aggregates these gains within 5 pp of the direct specialist on every benchmark whose queries surface domain signal. Our findings suggest that the effectiveness of this approach depends on the quality and specialization of individual adapters, and that enabling flexible composition of many such experts can significantly expand the practical capabilities of language model agents, moving toward more general, tool-augmented intelligence.

---

### MARSHAL: Incentivizing Multi-Agent Reasoning via Self-Play with Strategic LLMs

Authors: Huining Yuan, Zelai Xu, Zheyue Tan, Xiangmin Yi, Mo Guang, Kaiwen Long, Haojia Hui, Boxun Li, Xinlei Chen, Bo Zhao, Xiao-Ping Zhang, Chao Yu et al.
Published: 2025-10-17
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.15414v3

Developing Large Language Models (LLMs) to cooperate and compete effectively within multi-agent systems (MASs) is a critical step towards more advanced intelligence. While reinforcement learning (RL) has proven effective for enhancing reasoning in single-agent tasks, its extension to multi-turn, multi-agent scenarios remains underexplored due to the challenges of long-horizon credit assignment and agent-specific advantage estimation. To address these challenges, we introduce MARSHAL, an end-to-end RL framework that incentivizes Multi-Agent Reasoning through Self-play witH strAtegic LLMs in both cooperative and competitive games. MARSHAL features a turn-level advantage estimator that aligns learning signals with each interaction for credit assignment, and an agent-specific advantage normalization to stabilize multi-agent training. By learning with self-play across cooperative and competitive games, MARSHAL agents trained from Qwen3-4B develop strong strategic abilities, with up to 28.7% performance improvements in held-out games. More importantly, the capability acquired through self-play generalizes beyond games, yielding consistent performance gains of MASs in reasoning benchmarks. When integrated into leading MASs, our MARSHAL agent achieves significant zero-shot performance gains of up to 10.0% on AIME, 7.6% on GPQA-Diamond, and 3.5% on average across all benchmarks. These results establish self-play in strategic games as a powerful approach for developing generalizable multi-agent reasoning capabilities in LLMs.

---

### Large-scale User Game Lifecycle Representation Learning

Authors: Yanjie Gou, Jiangming Liu, Kouying Xue, Yi Hu
Published: 2025-10-17
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.15412v2

The rapid expansion of video game production necessitates the development of effective advertising and recommendation systems for online game platforms. Recommending and advertising games to users hinges on capturing their interest in games. However, existing representation learning methods crafted for handling billions of items in recommendation systems are unsuitable for game advertising and recommendation. This is primarily due to game sparsity, where the mere hundreds of games fall short for large-scale user representation learning, and game imbalance, where user behaviors are overwhelmingly dominated by a handful of popular games. To address the sparsity issue, we introduce the User Game Lifecycle (UGL), designed to enrich user behaviors in games. Additionally, we propose two innovative strategies aimed at manipulating user behaviors to more effectively extract both short and long-term interests. To tackle the game imbalance challenge, we present an Inverse Probability Masking strategy for UGL representation learning. The offline and online experimental results demonstrate that the UGL representations significantly enhance model by achieving a 1.83% AUC offline increase on average and a 21.67% CVR online increase on average for game advertising and a 0.5% AUC offline increase and a 0.82% ARPU online increase for in-game item recommendation.

---

### VocalBench-DF: A Benchmark for Evaluating Speech LLM Robustness to Disfluency

Authors: Hongcheng Liu, Yixuan Hou, Heyang Liu, Yuhao Wang, Yanfeng Wang, Yu Wang
Published: 2025-10-17
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.15406v1

While Speech Large Language Models (Speech-LLMs) show strong performance in many applications, their robustness is critically under-tested, especially to speech disfluency. Existing evaluations often rely on idealized inputs, overlooking common disfluencies, particularly those associated with conditions like Parkinson's disease. This work investigates whether current Speech-LLMs can maintain performance when interacting with users who have speech impairments. To facilitate this inquiry, we introduce VocalBench-DF, a framework for the systematic evaluation of disfluency across a multi-dimensional taxonomy. Our evaluation of 22 mainstream Speech-LLMs reveals substantial performance degradation, indicating that their real-world readiness is limited. Further analysis identifies phoneme-level processing and long-context modeling as primary bottlenecks responsible for these failures. Strengthening recognition and reasoning capability from components and pipelines can substantially improve robustness. These findings highlight the urgent need for new methods to improve disfluency handling and build truly inclusive Speech-LLMs

---

### Online Kernel Dynamic Mode Decomposition for Streaming Time Series Forecasting with Adaptive Windowing

Authors: Christopher Salazar, Krithika Manohar, Ashis G. Banerjee
Published: 2025-10-17
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.15404v1

Real-time forecasting from streaming data poses critical challenges: handling non-stationary dynamics, operating under strict computational limits, and adapting rapidly without catastrophic forgetting. However, many existing approaches face trade-offs between accuracy, adaptability, and efficiency, particularly when deployed in constrained computing environments. We introduce WORK-DMD (Windowed Online Random Kernel Dynamic Mode Decomposition), a method that combines Random Fourier Features with online Dynamic Mode Decomposition to capture nonlinear dynamics through explicit feature mapping, while preserving fixed computational cost and competitive predictive accuracy across evolving data. WORK-DMD employs Sherman-Morrison updates within rolling windows, enabling continuous adaptation to evolving dynamics from only current data, eliminating the need for lengthy training or large storage requirements for historical data. Experiments on benchmark datasets across several domains show that WORK-DMD achieves higher accuracy than several state-of-the-art online forecasting methods, while requiring only a single pass through the data and demonstrating particularly strong performance in short-term forecasting. Our results show that combining kernel evaluations with adaptive matrix updates achieves strong predictive performance with minimal data requirements. This sample efficiency offers a practical alternative to deep learning for streaming forecasting applications.

---

### Geometric Mixture Models for Electrolyte Conductivity Prediction

Authors: Anyi Li, Jiacheng Cen, Songyou Li, Mingze Li, Yang Yu, Wenbing Huang
Published: 2025-10-17
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.15403v2

Accurate prediction of ionic conductivity in electrolyte systems is crucial for advancing numerous scientific and technological applications. While significant progress has been made, current research faces two fundamental challenges: (1) the lack of high-quality standardized benchmarks, and (2) inadequate modeling of geometric structure and intermolecular interactions in mixture systems. To address these limitations, we first reorganize and enhance the CALiSol and DiffMix electrolyte datasets by incorporating geometric graph representations of molecules. We then propose GeoMix, a novel geometry-aware framework that preserves Set-SE(3) equivariance-an essential but challenging property for mixture systems. At the heart of GeoMix lies the Geometric Interaction Network (GIN), an equivariant module specifically designed for intermolecular geometric message passing. Comprehensive experiments demonstrate that GeoMix consistently outperforms diverse baselines (including MLPs, GNNs, and geometric GNNs) across both datasets, validating the importance of cross-molecular geometric interactions and equivariant message passing for accurate property prediction. This work not only establishes new benchmarks for electrolyte research but also provides a general geometric learning framework that advances modeling of mixture systems in energy materials, pharmaceutical development, and beyond.

---