# Research Papers — 2025-10 · bundle page 187 of 217

> Full-text markdown of papers #9301–9350 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/187
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/186.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/188.md)

### PolyKAN: A Polyhedral Analysis Framework for Provable and Approximately Optimal KAN Compression

Authors: Di Zhang
Published: 2025-10-05
Categories: cs.LG, cs.AI, math.NA, math.OC
arXiv: https://arxiv.org/abs/2510.04205v2

Kolmogorov-Arnold Networks (KANs) have emerged as a promising alternative to traditional Multi-Layer Perceptrons (MLPs), offering enhanced interpretability and a solid mathematical foundation. However, their parameter efficiency remains a significant challenge for practical deployment. This paper introduces PolyKAN, a novel theoretical framework for KAN compression that provides formal guarantees on both model size reduction and approximation error. By leveraging the inherent piecewise polynomial structure of KANs, we formulate the compression problem as a polyhedral region merging task. We establish a rigorous polyhedral characterization of KANs, develop a complete theory of $ε$-equivalent compression, and design a dynamic programming algorithm that achieves approximately optimal compression under specified error bounds. Our theoretical analysis demonstrates that PolyKAN achieves provably near-optimal compression while maintaining strict error control, with guaranteed global optimality for univariate spline functions. This framework provides the first formal foundation for KAN compression with mathematical guarantees, opening new directions for the efficient deployment of interpretable neural architectures.

---

### CALM Before the STORM: Unlocking Native Reasoning for Optimization Modeling

Authors: Zhengyang Tang, Zihan Ye, Chenyu Huang, Xuhan Huang, Chengpeng Li, Sihang Li, Guanhua Chen, Ming Yan, Zizhuo Wang, Hongyuan Zha, Dayiheng Liu, Benyou Wang
Published: 2025-10-05
Categories: cs.CL, cs.AI, cs.CE, cs.LG
arXiv: https://arxiv.org/abs/2510.04204v1

Large Reasoning Models (LRMs) have demonstrated strong capabilities in complex multi-step reasoning, opening new opportunities for automating optimization modeling. However, existing domain adaptation methods, originally designed for earlier instruction-tuned models, often fail to exploit the advanced reasoning patterns of modern LRMs -- In particular, we show that direct fine-tuning on traditional \textit{non-reflective} datasets leads to limited gains. To fully leverage LRMs' inherent reasoning abilities, we propose \textbf{CALM} (\textit{Corrective Adaptation with Lightweight Modification}), a framework that progressively refines LRMs within their native reasoning modes for optimization modeling tasks. In CALM, an expert intervener identifies reasoning flaws and provides concise corrective hints, which the LRM incorporates to produce improved reasoning trajectories. These interventions modify fewer than 2.6\% of generated tokens, but generate high-quality data for soft adaptation through supervised fine-tuning. The adapted model is then further improved through reinforcement learning. Building on CALM, we develop \textbf{STORM} (\textit{Smart Thinking Optimization Reasoning Model}), a 4B-parameter LRM that achieves a new state-of-the-art average accuracy of 68.9\% across five popular optimization modeling benchmarks, matching the performance of a 671B LRM. These results demonstrate that dynamic, hint-based data synthesis both preserves and amplifies the native reasoning patterns of modern LRMs, offering a more effective and scalable path towards expert-level performance on challenging optimization modeling tasks.

---

### Adaptive Federated Learning via Dynamical System Model

Authors: Aayushya Agarwal, Larry Pileggi, Gauri Joshi
Published: 2025-10-05
Categories: cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2510.04203v1

Hyperparameter selection is critical for stable and efficient convergence of heterogeneous federated learning, where clients differ in computational capabilities, and data distributions are non-IID. Tuning hyperparameters is a manual and computationally expensive process as the hyperparameter space grows combinatorially with the number of clients. To address this, we introduce an end-to-end adaptive federated learning method in which both clients and central agents adaptively select their local learning rates and momentum parameters. Our approach models federated learning as a dynamical system, allowing us to draw on principles from numerical simulation and physical design. Through this perspective, selecting momentum parameters equates to critically damping the system for fast, stable convergence, while learning rates for clients and central servers are adaptively selected to satisfy accuracy properties from numerical simulation. The result is an adaptive, momentum-based federated learning algorithm in which the learning rates for clients and servers are dynamically adjusted and controlled by a single, global hyperparameter. By designing a fully integrated solution for both adaptive client updates and central agent aggregation, our method is capable of handling key challenges of heterogeneous federated learning, including objective inconsistency and client drift. Importantly, our approach achieves fast convergence while being insensitive to the choice of the global hyperparameter, making it well-suited for rapid prototyping and scalable deployment. Compared to state-of-the-art adaptive methods, our framework is shown to deliver superior convergence for heterogeneous federated learning while eliminating the need for hyperparameter tuning both client and server updates.

---

### Spectral Alignment as Predictor of Loss Explosion in Neural Network Training

Authors: Haiquan Qiu, You Wu, Yingjie Tan, Yaqing Wang, Quanming Yao
Published: 2025-10-05
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.04202v1

Loss explosions in training deep neural networks can nullify multi-million dollar training runs. Conventional monitoring metrics like weight and gradient norms are often lagging and ambiguous predictors, as their values vary dramatically across different models and even between layers of the same model, making it difficult to establish a unified standard for detecting impending failure. We introduce Spectral Alignment (SA), a novel, theoretically-grounded metric that monitors the distributional alignment between layer inputs and the principal singular vectors of weight matrices. We show that a collapse in the sign diversity of this alignment is a powerful early predictor of representational collapse and training divergence. Empirical results on language models demonstrate that monitoring the SA distribution provides a significantly earlier and clearer warning of loss explosions than traditional scalar metrics. SA's low computational overhead makes it a practical tool for safeguarding model training.

---

### World-To-Image: Grounding Text-to-Image Generation with Agent-Driven World Knowledge

Authors: Moo Hyun Son, Jintaek Oh, Sun Bin Mun, Jaechul Roh, Sehyun Choi
Published: 2025-10-05
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.04201v1

While text-to-image (T2I) models can synthesize high-quality images, their performance degrades significantly when prompted with novel or out-of-distribution (OOD) entities due to inherent knowledge cutoffs. We introduce World-To-Image, a novel framework that bridges this gap by empowering T2I generation with agent-driven world knowledge. We design an agent that dynamically searches the web to retrieve images for concepts unknown to the base model. This information is then used to perform multimodal prompt optimization, steering powerful generative backbones toward an accurate synthesis. Critically, our evaluation goes beyond traditional metrics, utilizing modern assessments like LLMGrader and ImageReward to measure true semantic fidelity. Our experiments show that World-To-Image substantially outperforms state-of-the-art methods in both semantic alignment and visual aesthetics, achieving +8.1% improvement in accuracy-to-prompt on our curated NICE benchmark. Our framework achieves these results with high efficiency in less than three iterations, paving the way for T2I systems that can better reflect the ever-changing real world. Our demo code is available here\footnote{https://github.com/mhson-kyle/World-To-Image}.

---

### COSMO-RL: Towards Trustworthy LMRMs via Joint Safety and Stability

Authors: Yizhuo Ding, Mingkang Chen, Qiuhua Liu, Fenghua Weng, Wanying Qu, Yue Yang, Yugang Jiang, Zuxuan Wu, Yanwei Fu, Wenqi Shao
Published: 2025-10-05
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.04196v1

Large Multimodal Reasoning Models (LMRMs) are moving into real applications, where they must be both useful and safe. Safety is especially challenging in multimodal settings: images and text can be combined to bypass guardrails, and single objective training can cause policy drift that yields over-refusal on benign inputs or unsafe compliance on risky ones. We present COSMO-RL, a mixed reinforcement learning framework that trains reasoning oriented LMRMs under multimodal, multitask, and multiobjective signals, and we release the resulting model, COSMO-R1. Our approach aims to let safety and capability grow together in one stable pipeline rather than competing during alignment. In experiments, COSMO-R1 improves safety while maintaining-and often improving multimodal reasoning and instruction following, shows stronger robustness to multimodal jailbreaks, and reduces unnecessary refusals. The framework also transfers across backbones with consistent gains. Ablations support the design choices, indicating a simple path to advancing safety and general capability together in LMRMs.

---

### Constructing coherent spatial memory in LLM agents through graph rectification

Authors: Puzhen Zhang, Xuyang Chen, Yu Feng, Yuhan Jiang, Liqiu Meng
Published: 2025-10-05
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.04195v2

Given a map description through global traversal navigation instructions, an LLM can often infer the implicit spatial layout and answer user queries by providing shortest paths. However, such context-dependent querying becomes incapable as environments grow larger, motivating the need for incremental map construction that builds a complete topological graph from stepwise observations. We propose LLM-MapRepair, a framework for LLM-driven construction and map repair, designed to detect, localize, and correct structural inconsistencies in incrementally constructed navigation graphs. Our contributions include a Version Control mechanism for graph construction, an Edge Impact Score for repair prioritization, and a cleaned variant of the MANGO benchmark tailored for LLM-driven map construction and repair. We evaluate the framework on four evaluation settings: a synthetic per-component ablation (gpt-4.1, n=20 seeds per cell), a cross-vendor sweep over seven LLMs from OpenAI, Anthropic, and Google on both synthetic and TextWorld procedurally-generated text-adventure games, a repair-stage evaluation on all 42 cleaned-MANGO games with non-zero residual conflicts (534 conflicts; three vendors x three modes plus two non-LLM references), and an end-to-end natural-text deployment on Chapters 16-17 of Dream of the Red Chamber. On the DRC deployment, LLM-MapRepair achieves 94.3% node recall (+8.6 pp over direct LLM mapping) and 88.2% edge recall (+55.8 pp), using GPT-4.1; the recall improvements come with predicted node and edge counts that are roughly 4x the ground-truth counts (Table 4), reflecting the discretization-driven over-generation trade-off we discuss in the Limitations.

---

### Cooperative Flexibility Exchange: Fair and Comfort-Aware Decentralized Resource Allocation

Authors: Rabiya Khalid, Evangelos Pournaras
Published: 2025-10-05
Categories: cs.MA, cs.AI
arXiv: https://arxiv.org/abs/2510.04192v2

The growing electricity demand and use of smart appliances are placing pressure on power grids, making efficient energy management more important than ever. The existing energy management systems often prioritize system efficiency (balanced energy demand and supply) at the expense of consumer comfort. This paper addresses this gap by proposing a novel decentralized multi-agent coordination-based demand-side management system. The proposed system enables individual agents to coordinate for demand-side energy optimization while improving consumer comfort and maintaining system efficiency. A key innovation of this work is the introduction of a slot exchange mechanism, where agents first receive optimized appliance-level energy consumption schedules and then coordinate with each other to adjust these schedules through slot exchanges to improve their comfort even when agents show non-altruistic behaviour. It also scales well with large populations and promotes fairness by balancing satisfaction levels across consumers. For performance evaluation, a real-world dataset is used, and the results demonstrate that the proposed slot exchange mechanism increases consumer comfort and fairness without raising system inefficiency cost, making it a practical and scalable solution for future smart grids.

---

### Finite Time Analysis of Constrained Natural Critic-Actor Algorithm with Improved Sample Complexity

Authors: Prashansa Panda, Shalabh Bhatnagar
Published: 2025-10-05
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.04189v1

Recent studies have increasingly focused on non-asymptotic convergence analyses for actor-critic (AC) algorithms. One such effort introduced a two-timescale critic-actor algorithm for the discounted cost setting using a tabular representation, where the usual roles of the actor and critic are reversed. However, only asymptotic convergence was established there. Subsequently, both asymptotic and non-asymptotic analyses of the critic-actor algorithm with linear function approximation were conducted. In our work, we introduce the first natural critic-actor algorithm with function approximation for the long-run average cost setting and under inequality constraints. We provide the non-asymptotic convergence guarantees for this algorithm. Our analysis establishes optimal learning rates and we also propose a modification to enhance sample complexity. We further show the results of experiments on three different Safety-Gym environments where our algorithm is found to be competitive in comparison with other well known algorithms.

---

### Let Features Decide Their Own Solvers: Hybrid Feature Caching for Diffusion Transformers

Authors: Shikang Zheng, Guantao Chen, Qinming Zhou, Yuqi Lin, Lixuan He, Chang Zou, Peiliang Cai, Jiacheng Liu, Linfeng Zhang
Published: 2025-10-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.04188v1

Diffusion Transformers offer state-of-the-art fidelity in image and video synthesis, but their iterative sampling process remains a major bottleneck due to the high cost of transformer forward passes at each timestep. To mitigate this, feature caching has emerged as a training-free acceleration technique that reuses or forecasts hidden representations. However, existing methods often apply a uniform caching strategy across all feature dimensions, ignoring their heterogeneous dynamic behaviors. Therefore, we adopt a new perspective by modeling hidden feature evolution as a mixture of ODEs across dimensions, and introduce HyCa, a Hybrid ODE solver inspired caching framework that applies dimension-wise caching strategies. HyCa achieves near-lossless acceleration across diverse domains and models, including 5.55 times speedup on FLUX, 5.56 times speedup on HunyuanVideo, 6.24 times speedup on Qwen-Image and Qwen-Image-Edit without retraining.

---

### A Complement to Neural Networks for Anisotropic Inelasticity at Finite Strains

Authors: Hagen Holthusen, Ellen Kuhl
Published: 2025-10-05
Categories: cs.CE, cs.AI
arXiv: https://arxiv.org/abs/2510.04187v1

We propose a complement to constitutive modeling that augments neural networks with material principles to capture anisotropy and inelasticity at finite strains. The key element is a dual potential that governs dissipation, consistently incorporates anisotropy, and-unlike conventional convex formulations-satisfies the dissipation inequality without requiring convexity. Our neural network architecture employs invariant-based input representations in terms of mixed elastic, inelastic and structural tensors. It adapts Input Convex Neural Networks, and introduces Input Monotonic Neural Networks to broaden the admissible potential class. To bypass exponential-map time integration in the finite strain regime and stabilize the training of inelastic materials, we employ recurrent Liquid Neural Networks. The approach is evaluated at both material point and structural scales. We benchmark against recurrent models without physical constraints and validate predictions of deformation and reaction forces for unseen boundary value problems. In all cases, the method delivers accurate and stable performance beyond the training regime. The neural network and finite element implementations are available as open-source and are accessible to the public via https://doi.org/10.5281/zenodo.17199965.

---

### Thinking on the Fly: Test-Time Reasoning Enhancement via Latent Thought Policy Optimization

Authors: Wengao Ye, Yan Liang, Lianlei Shan
Published: 2025-10-05
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.04182v4

Recent advancements in Large Language Models (LLMs) have shifted from explicit Chain-of-Thought (CoT) reasoning to more efficient latent reasoning, where intermediate thoughts are represented as vectors rather than text. However, latent reasoning can be brittle on challenging, out-of-distribution tasks where robust reasoning is most critical. To overcome these limitations, we introduce Latent Thought Policy Optimization (LTPO), a parameter-free framework that enhances LLM reasoning entirely at test time, without requiring model parameter updates. LTPO treats intermediate latent "thought" vectors as dynamic parameters that are actively optimized for each problem instance. It employs an online policy gradient method guided by an intrinsic, confidence-based reward signal computed directly from the frozen LLM's own output distributions, eliminating the need for external supervision or expensive text generation during optimization. Extensive experiments on five reasoning benchmarks show that LTPO not only matches or surpasses strong baselines on standard tasks but also demonstrates remarkable robustness where others fail. Most notably, on highly challenging AIME benchmarks where existing latent reasoning baselines collapse to near-zero accuracy, LTPO delivers substantial improvements, showcasing a unique capability for complex reasoning.

---

### Spatially Grounded Concept-Based Image Classification

Authors: Ran Eisenberg, Amit Rozner, Ethan Fetaya, Ofir Lindenbaum
Published: 2025-10-05
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.04180v2

Deep neural networks can achieve high accuracy while relying on evidence that is hard to inspect or misaligned with the intended task. Concept Bottleneck Models (CBMs) expose human-interpretable concepts, but most treat concepts as global attributes and do not show how localized evidence is aggregated into a decision. We propose \textbf{SEG-MIL-CBM}, a spatially grounded CBM that decomposes each image into concept-guided regions and classifies it by attention-based aggregation of segment-level concept evidence. The same segment evidence terms form the prediction and the explanation, exposing which regions and concepts support the predicted logit without a separate post-hoc attribution module. Among evaluated CBM-family baselines, SEG-MIL-CBM improves Waterbirds worst-group accuracy from $65.1\%$ to $72.0\%$, reaches $87.4\%$ worst-group accuracy on Pawrious, remains competitive on standard recognition, and attains the best CBM accuracy on CIFAR-100 ($85.3\%$). Segment-level faithfulness experiments on CUB further show that its learned segment ranking matches or improves over evaluated segment-ranking controls.

---

### BLADE: Bias-Linked Adaptive DEbiasing

Authors: Piyush Arora, Navlika Singh, Vasubhya Diwan, Pratik Mazumder
Published: 2025-10-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.04174v1

Neural networks have revolutionized numerous fields, yet they remain vulnerable to a critical flaw: the tendency to learn implicit biases, spurious correlations between certain attributes and target labels in training data. These biases are often more prevalent and easier to learn, causing models to rely on superficial patterns rather than task-relevant features necessary for generalization. Existing methods typically rely on strong assumptions, such as prior knowledge of these biases or access to bias-conflicting samples, i.e., samples that contradict spurious correlations and counterbalance bias-aligned samples, samples that conform to these spurious correlations. However, such assumptions are often impractical in real-world settings. We propose BLADE ({B}ias-{L}inked {A}daptive {DE}biasing), a generative debiasing framework that requires no prior knowledge of bias or bias-conflicting samples. BLADE first trains a generative model to translate images across bias domains while preserving task-relevant features. Then, it adaptively refines each image with its synthetic counterpart based on the image's susceptibility to bias. To encourage robust representations, BLADE aligns an image with its bias-translated synthetic counterpart that shares task-relevant features but differs in bias, while misaligning it with samples sharing the same bias. We evaluate BLADE on multiple benchmark datasets and show that it significantly outperforms state-of-the-art methods. Notably, it exceeds the closest baseline by an absolute margin of around 18% on the corrupted CIFAR-10 dataset under the worst group setting, establishing a new benchmark in bias mitigation and demonstrating its potential for developing more robust deep learning models without explicit supervision.

---

### Open Agent Specification (Agent Spec): A Unified Representation for AI Agents

Authors: Soufiane Amini, Yassine Benajiba, Cesare Bernardis, Paul Cayet, Hassan Chafi, Abderrahim Fathan, Louis Faucon, Damien Hilloulin, Sungpack Hong, Ingo Kossyk, Tran Minh Son Le, Rhicheek Patra et al.
Published: 2025-10-05
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.04173v4

The proliferation of agent frameworks has led to fragmentation in how agents are defined, executed, and evaluated. Existing systems differ in their abstractions, data flow semantics, and tool integrations, making it difficult to share or reproduce workflows. We introduce Open Agent Specification (Agent Spec), a declarative language that defines AI agents and agentic workflows in a way that is compatible across frameworks, promoting reusability, portability and interoperability of AI agents. Agent Spec defines a common set of components, control and data flow semantics, and schemas that allow an agent to be defined once and executed across different runtimes. Agent Spec also introduces a standardized Evaluation harness to assess agent behavior and agentic workflows across runtimes - analogous to how HELM and related harnesses standardized LLM evaluation - so that performance, robustness, and efficiency can be compared consistently across frameworks. We demonstrate this using four distinct runtimes (LangGraph, CrewAI, AutoGen, and WayFlow) evaluated over three different benchmarks (SimpleQA Verified, $τ^2$-Bench and BIRD-SQL). We provide accompanying toolsets: a Python SDK (PyAgentSpec), a reference runtime (WayFlow), and adapters for popular frameworks (e.g., LangGraph, AutoGen, CrewAI). Agent Spec bridges the gap between model-centric and agent-centric standardization & evaluation, laying the groundwork for reliable, reusable, and portable agentic systems.

---

### Multi Language Models for On-the-Fly Syntax Highlighting

Authors: Marco Edoardo Palma, Pooja Rani, Harald C. Gall
Published: 2025-10-05
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2510.04166v2

Syntax highlighting is a critical feature in modern software development environments, enhancing code readability and developer productivity. However, delivering accurate highlighting in real time remains challenging for online and web-based development tools due to strict time and memory constraints on backend services. These systems must serve highlights rapidly and frequently, even when code is partially valid or invalid. This has led to on-the-fly syntax highlighting, where visual annotations are generated just before content is served, often at high request rates and under incomplete input conditions. To meet these demands efficiently, state-of-the-art models use deep learning to learn the behavior of brute-force syntax highlighting resolvers, tools that are easy to implement but too slow for production. Through the Deep Abstraction process, brute-force strategies are encoded into fast statistical models that achieve both high accuracy and low-latency inference. Despite their success, such models face key challenges: they support only one programming language per model, require large datasets from slow brute-force generators, and involve resource-intensive training. In multi-language environments, this means maintaining multiple independent models, increasing system complexity and operational cost. This work addresses these issues by introducing a unified model capable of highlighting up to six mainstream programming languages, reducing deployment complexity by a factor of six and improving performance on unseen languages. A novel normalization technique significantly enhances model generalization, while few-shot learning experiments show that a small number of oracle samples can replace large datasets, minimizing dependence on brute-force generators. Combined, these innovations enable efficient, scalable, and cost-effective syntax highlighting across diverse programming languages.

---

### Drax: Speech Recognition with Discrete Flow Matching

Authors: Aviv Navon, Aviv Shamsian, Neta Glazer, Yael Segal-Feldman, Gill Hetz, Joseph Keshet, Ethan Fetaya
Published: 2025-10-05
Categories: eess.AS, cs.LG, cs.SD
arXiv: https://arxiv.org/abs/2510.04162v1

Diffusion and flow-based non-autoregressive (NAR) models have shown strong promise in large language modeling, however, their potential for automatic speech recognition (ASR) remains largely unexplored. We propose Drax, a discrete flow matching framework for ASR that enables efficient parallel decoding. To better align training with inference, we construct an audio-conditioned probability path that guides the model through trajectories resembling likely intermediate inference errors, rather than direct random noise to target transitions. Our theoretical analysis links the generalization gap to divergences between training and inference occupancies, controlled by cumulative velocity errors, thereby motivating our design choice. Empirical evaluation demonstrates that our approach attains recognition accuracy on par with state-of-the-art speech models while offering improved accuracy-efficiency trade-offs, highlighting discrete flow matching as a promising direction for advancing NAR ASR.

---

### ObCLIP: Oblivious CLoud-Device Hybrid Image Generation with Privacy Preservation

Authors: Haoqi Wu, Wei Dai, Ming Xu, Li Wang, Qiang Yan
Published: 2025-10-05
Categories: cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2510.04153v1

Diffusion Models have gained significant popularity due to their remarkable capabilities in image generation, albeit at the cost of intensive computation requirement. Meanwhile, despite their widespread deployment in inference services such as Midjourney, concerns about the potential leakage of sensitive information in uploaded user prompts have arisen. Existing solutions either lack rigorous privacy guarantees or fail to strike an effective balance between utility and efficiency. To bridge this gap, we propose ObCLIP, a plug-and-play safeguard that enables oblivious cloud-device hybrid generation. By oblivious, each input prompt is transformed into a set of semantically similar candidate prompts that differ only in sensitive attributes (e.g., gender, ethnicity). The cloud server processes all candidate prompts without knowing which one is the real one, thus preventing any prompt leakage. To mitigate server cost, only a small portion of denoising steps is performed upon the large cloud model. The intermediate latents are then sent back to the client, which selects the targeted latent and completes the remaining denoising using a small device model. Additionally, we analyze and incorporate several cache-based accelerations that leverage temporal and batch redundancy, effectively reducing computation cost with minimal utility degradation. Extensive experiments across multiple datasets demonstrate that ObCLIP provides rigorous privacy and comparable utility to cloud models with slightly increased server cost.

---

### Self Speculative Decoding for Diffusion Large Language Models

Authors: Yifeng Gao, Ziang Ji, Yuxuan Wang, Biqing Qi, Hanlin Xu, Linfeng Zhang
Published: 2025-10-05
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.04147v1

Diffusion-based Large Language Models (dLLMs) have emerged as a competitive alternative to autoregressive models, offering unique advantages through bidirectional attention and parallel generation paradigms. However, the generation results of current parallel decoding methods deviate from stepwise decoding, introducing potential performance degradation, which limits their practical deployment. To address this problem, we propose \textbf{S}elf \textbf{S}peculative \textbf{D}ecoding (SSD), a lossless inference acceleration method that leverages the dLLM itself as both speculative decoding drafter and verifier without auxiliary modules. SSD introduces a self-drafting mechanism where the model generates predictions for multiple positions, then verifies them through hierarchical verification trees in a single forward pass. Unlike traditional speculative decoding that requires separate draft models, SSD eliminates model redundancy and memory overhead by exploiting the dLLM's inherent parallel prediction capability for multiple positions. This self-speculative approach allows the model to progressively verify and accept multiple tokens in a single forward pass. Our experiments demonstrate that SSD achieves up to 3.46$\times$ speedup while keeping the output identical to stepwise decoding on open source models such as LLaDA and Dream. Code will be made publicly available on GitHub.

---

### Beyond Next-Token Prediction: A Performance Characterization of Diffusion versus Autoregressive Language Models

Authors: Minseo Kim, Coleman Hooper, Aditya Tomar, Chenfeng Xu, Mehrdad Farajtabar, Michael W. Mahoney, Kurt Keutzer, Amir Gholami
Published: 2025-10-05
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.04146v2

Large Language Models (LLMs) have achieved state-of-the-art performance on a broad range of Natural Language Processing (NLP) tasks, including document processing and code generation. Autoregressive Language Models (ARMs), which generate tokens sequentially conditioned on all previous tokens, have been the predominant paradigm for LLMs. While these models have achieved high accuracy across a range of downstream tasks, they exhibit low arithmetic intensity due to the inherent sequential dependency in next-token prediction. Recently, Diffusion Language Models (DLMs) have emerged as a promising alternative architecture. DLMs generate output tokens in parallel, mitigating the limitations of sequential decoding. However, the performance implications of DLMs relative to commonly deployed ARMs are not fully understood. In this work, we present a comprehensive study of the performance characteristics of ARMs and DLMs, combining theoretical analysis with empirical profiling to characterize the trade-offs between these approaches. We show that although DLMs can achieve higher arithmetic intensity than ARMs by leveraging parallelism across token positions, they fail to scale effectively with longer contexts. We then explore block-wise decoding for DLMs, which decouples arithmetic intensity from sequence length and enables better scaling to long contexts (similar to ARMs). We also examine batched inference and find that ARMs exhibit superior throughput as they benefit more from parallelism across sequences in the batch. Finally, we highlight opportunities for accelerating DLM inference, emphasizing that reducing the number of sampling steps is key for open-source DLMs to achieve lower latency relative to ARMs.

---

### Automating construction safety inspections using a multi-modal vision-language RAG framework

Authors: Chenxin Wang, Elyas Asadi Shamsabadi, Zhaohui Chen, Luming Shen, Alireza Ahmadian Fard Fini, Daniel Dias-da-Costa
Published: 2025-10-05
Categories: cs.CV, cs.CL, cs.IR
arXiv: https://arxiv.org/abs/2510.04145v1

Conventional construction safety inspection methods are often inefficient as they require navigating through large volume of information. Recent advances in large vision-language models (LVLMs) provide opportunities to automate safety inspections through enhanced visual and linguistic understanding. However, existing applications face limitations including irrelevant or unspecific responses, restricted modal inputs and hallucinations. Utilisation of Large Language Models (LLMs) for this purpose is constrained by availability of training data and frequently lack real-time adaptability. This study introduces SiteShield, a multi-modal LVLM-based Retrieval-Augmented Generation (RAG) framework for automating construction safety inspection reports by integrating visual and audio inputs. Using real-world data, SiteShield outperformed unimodal LLMs without RAG with an F1 score of 0.82, hamming loss of 0.04, precision of 0.76, and recall of 0.96. The findings indicate that SiteShield offers a novel pathway to enhance information retrieval and efficiency in generating safety reports.

---

### Turning Drift into Constraint: Robust Reasoning Alignment in Non-Stationary Multi-Stream Environments

Authors: Xiaoyu Yang, En Yu, Wei Duan, Jie Lu
Published: 2025-10-05
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.04142v3

This paper identifies a critical yet underexplored challenge in reasoning alignment from multiple multi-modal large language models (MLLMs): In non-stationary environments, the diverse reasoning distributions of source models often evolve unpredictably, transmitting systematic biases and drift to the target model. To address this, we formulate multi-source reasoning alignment as a constraint satisfaction problem under concept drift theory. We propose Autonomous Preference Optimization (APO), a novel framework that treats inter-model divergences not as noise, but as dynamic negative constraints. APO operates via a two-stage protocol: first, supervised bootstrapping projects the target model into the capability union of source models; second, constraint-aware optimization synthesizes a consistent consensus manifold by explicitly suppressing drifting trajectories via a multi-negative Plackett-Luce objective. Extensive experiments on chest X-ray interpretation demonstrate that our 7B model achieves superior robustness, outperforming even proprietary source models in average accuracy. Furthermore, we release CXR-MAX, a large-scale benchmark comprising 170,982 reasoning trajectories from seven large-scale MLLMs to facilitate research on reasoning alignment under drift. Code and data are available at: https://github.com/XiaoyuYoung/APO.

---

### The Artificial Intelligence Cognitive Examination: A Survey on the Evolution of Multimodal Evaluation from Recognition to Reasoning

Authors: Mayank Ravishankara, Varindra V. Persad Maharaj
Published: 2025-10-05
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.04141v2

This survey paper chronicles the evolution of evaluation in multimodal artificial intelligence (AI), framing it as a progression of increasingly sophisticated "cognitive examinations." We argue that the field is undergoing a paradigm shift, moving from simple recognition tasks that test "what" a model sees, to complex reasoning benchmarks that probe "why" and "how" it understands. This evolution is driven by the saturation of older benchmarks, where high performance often masks fundamental weaknesses. We chart the journey from the foundational "knowledge tests" of the ImageNet era to the "applied logic and comprehension" exams such as GQA and Visual Commonsense Reasoning (VCR), which were designed specifically to diagnose systemic flaws such as shortcut learning and failures in compositional generalization. We then survey the current frontier of "expert-level integration" benchmarks (e.g., MMBench, SEED-Bench, MMMU) designed for today's powerful multimodal large language models (MLLMs), which increasingly evaluate the reasoning process itself. Finally, we explore the uncharted territories of evaluating abstract, creative, and social intelligence. We conclude that the narrative of AI evaluation is not merely a history of datasets, but a continuous, adversarial process of designing better examinations that, in turn, redefine our goals for creating truly intelligent systems.

---

### Selective Expert Guidance for Effective and Diverse Exploration in Reinforcement Learning of LLMs

Authors: Zishang Jiang, Jinyi Han, Tingyun Li, Xinyi Wang, Sihang Jiang, Jiaqing Liang, Zhaoqian Dai, Shuguang Ma, Fei Yu, Yanghua Xiao
Published: 2025-10-05
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.04140v2

Reinforcement Learning with Verifiable Rewards (RLVR) has become a widely adopted technique for enhancing the reasoning ability of Large Language Models (LLMs). However, the effectiveness of RLVR strongly depends on the capability of base models. This issue arises because it requires the model to have sufficient capability to perform high-quality exploration, which involves both effectiveness and diversity. Unfortunately, existing methods address this issue by imitating expert trajectories, which improve effectiveness but neglect diversity. To address this, we argue that the expert only needs to provide guidance only at critical decision points rather than the entire reasoning path. Based on this insight, we propose MENTOR: Mixed-policy Expert Navigation for Token-level Optimization of Reasoning, a framework that provides expert guidance only at critical decision points to perform effective and diverse exploration in RLVR. Extensive experiments show that MENTOR enables models capture the essence of expert strategies rather than surface imitation, thereby performing high-quality exploration and achieving superior overall performance. Our code is available online.

---

### Fine Tuning Methods for Low-resource Languages

Authors: Tim Bakkenes, Daniel Wang, Anton Johansson
Published: 2025-10-05
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2510.04139v1

The rise of Large Language Models has not been inclusive of all cultures. The models are mostly trained on English texts and culture which makes them underperform in other languages and cultural contexts. By developing a generalizable method for preparing culturally relevant datasets and post-training the Gemma 2 model, this project aimed to increase the performance of Gemma 2 for an underrepresented language and showcase how others can do the same to unlock the power of Generative AI in their country and preserve their cultural heritage.

---

### Efficient Manifold-Constrained Neural ODE for High-Dimensional Datasets

Authors: Muhao Guo, Haoran Li, Yang Weng
Published: 2025-10-05
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.04138v1

Neural ordinary differential equations (NODE) have garnered significant attention for their design of continuous-depth neural networks and the ability to learn data/feature dynamics. However, for high-dimensional systems, estimating dynamics requires extensive calculations and suffers from high truncation errors for the ODE solvers. To address the issue, one intuitive approach is to consider the non-trivial topological space of the data distribution, i.e., a low-dimensional manifold. Existing methods often rely on knowledge of the manifold for projection or implicit transformation, restricting the ODE solutions on the manifold. Nevertheless, such knowledge is usually unknown in realistic scenarios. Therefore, we propose a novel approach to explore the underlying manifold to restrict the ODE process. Specifically, we employ a structure-preserved encoder to process data and find the underlying graph to approximate the manifold. Moreover, we propose novel methods to combine the NODE learning with the manifold, resulting in significant gains in computational speed and accuracy. Our experimental evaluations encompass multiple datasets, where we compare the accuracy, number of function evaluations (NFEs), and convergence speed of our model against existing baselines. Our results demonstrate superior performance, underscoring the effectiveness of our approach in addressing the challenges of high-dimensional datasets.

---

### MoME: Mixture of Matryoshka Experts for Audio-Visual Speech Recognition

Authors: Umberto Cappellazzo, Minsu Kim, Pingchuan Ma, Honglie Chen, Xubo Liu, Stavros Petridis, Maja Pantic
Published: 2025-10-05
Categories: eess.AS, cs.CV, cs.SD
arXiv: https://arxiv.org/abs/2510.04136v1

Large language models (LLMs) have recently shown strong potential in audio-visual speech recognition (AVSR), but their high computational demands and sensitivity to token granularity limit their practicality in resource-constrained settings. Token compression methods can reduce inference cost, but they require fixing a compression rate in advance and produce a single fixed-length output, offering no flexibility to balance information density and efficiency at inference time. Matryoshka representation learning (MRL) addresses this by enabling a single model to operate across multiple token granularities, allowing compression rates to be adjusted dynamically. However, current MRL-based methods treat each scale independently during training, limiting cross-scale generalization, robustness at high compression, and interpretability. To overcome these limitations, we propose MoME (Mixture of Matryoshka Experts), a novel framework that integrates sparse Mixture-of-Experts (MoE) into MRL-based LLMs for AVSR. MoME augments a frozen LLM with top-k routed and shared experts, allowing dynamic capacity allocation across scales and modalities. A shared router promotes consistent expert activation across granularities, enabling compressed sequences to benefit from representations learned at lower compression. Experiments on LRS2 and LRS3 demonstrate that MoME achieves state-of-the-art performance across AVSR, ASR, and VSR tasks, while requiring significantly fewer parameters and maintaining robustness under noise. MoME unifies the adaptability of MRL with the efficiency of MoE, offering a scalable and interpretable solution for resource-aware speech recognition.

---

### GA4GC: Greener Agent for Greener Code via Multi-Objective Configuration Optimization

Authors: Jingzhi Gong, Yixin Bian, Luis de la Cal, Giovanni Pinna, Anisha Uteem, David Williams, Mar Zamorano, Karine Even-Mendoza, W. B. Langdon, Hector Menendez, Federica Sarro
Published: 2025-10-05
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2510.04135v1

Coding agents powered by LLMs face critical sustainability and scalability challenges in industrial deployment, with single runs consuming over 100k tokens and incurring environmental costs that may exceed optimization benefits. This paper introduces GA4GC, the first framework to systematically optimize coding agent runtime (greener agent) and code performance (greener code) trade-offs by discovering Pareto-optimal agent hyperparameters and prompt templates. Evaluation on the SWE-Perf benchmark demonstrates up to 135x hypervolume improvement, reducing agent runtime by 37.7% while improving correctness. Our findings establish temperature as the most critical hyperparameter, and provide actionable strategies to balance agent sustainability with code optimization effectiveness in industrial deployment.

---

### PhaseFormer: From Patches to Phases for Efficient and Effective Time Series Forecasting

Authors: Yiming Niu, Jinliang Deng, Yongxin Tong
Published: 2025-10-05
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.04134v1

Periodicity is a fundamental characteristic of time series data and has long played a central role in forecasting. Recent deep learning methods strengthen the exploitation of periodicity by treating patches as basic tokens, thereby improving predictive effectiveness. However, their efficiency remains a bottleneck due to large parameter counts and heavy computational costs. This paper provides, for the first time, a clear explanation of why patch-level processing is inherently inefficient, supported by strong evidence from real-world data. To address these limitations, we introduce a phase perspective for modeling periodicity and present an efficient yet effective solution, PhaseFormer. PhaseFormer features phase-wise prediction through compact phase embeddings and efficient cross-phase interaction enabled by a lightweight routing mechanism. Extensive experiments demonstrate that PhaseFormer achieves state-of-the-art performance with around 1k parameters, consistently across benchmark datasets. Notably, it excels on large-scale and complex datasets, where models with comparable efficiency often struggle. This work marks a significant step toward truly efficient and effective time series forecasting. Code is available at this repository: https://github.com/neumyor/PhaseFormer_TSL

---

### Modeling Time Series Dynamics with Fourier Ordinary Differential Equations

Authors: Muhao Guo, Yang Weng
Published: 2025-10-05
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.04133v1

Neural ODEs (NODEs) have emerged as powerful tools for modeling time series data, offering the flexibility to adapt to varying input scales and capture complex dynamics. However, they face significant challenges: first, their reliance on time-domain representations often limits their ability to capture long-term dependencies and periodic structures; second, the inherent mismatch between their continuous-time formulation and the discrete nature of real-world data can lead to loss of granularity and predictive accuracy. To address these limitations, we propose Fourier Ordinary Differential Equations (FODEs), an approach that embeds the dynamics in the Fourier domain. By transforming time-series data into the frequency domain using the Fast Fourier Transform (FFT), FODEs uncover global patterns and periodic behaviors that remain elusive in the time domain. Additionally, we introduce a learnable element-wise filtering mechanism that aligns continuous model outputs with discrete observations, preserving granularity and enhancing accuracy. Experiments on various time series datasets demonstrate that FODEs outperform existing methods in terms of both accuracy and efficiency. By effectively capturing both long- and short-term patterns, FODEs provide a robust framework for modeling time series dynamics.

---

### On the Limitations and Capabilities of Position Embeddings for Length Generalization

Authors: Yang Chen, Yitao Liang, Zhouchen Lin
Published: 2025-10-05
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.04130v1

In Transformers, Position Embeddings (PEs) significantly influence Length Generalization (LG) performance, yet their fundamental role remains unclear. In this work, we investigate the limitations and capabilities of PEs in achieving LG. We theoretically analyze PEs in Position-Only Linear Attentions (POLAs), introducing Linear Representation Complexity (LRC) to characterize when PEs enable LG. Our analysis shows that PEs do not expand computational capabilities but structure learned computations across positions. Extending to practical Transformers, we propose Sequential Representation Complexity (SRC) and conjecture that LG is possible if and only if SRC remains invariant across scales. We support this hypothesis with empirical evidence in various reasoning tasks. To enhance LG, we introduce Scale Hint, allowing flexible instance scaling, and a Learning-Based Position Embedding framework that automatically learns positional relations. Our work provides theoretical insights and practical strategies for improving LG in Transformers.

---

### Internal states before wait modulate reasoning patterns

Authors: Dmitrii Troitskii, Koyena Pal, Chris Wendler, Callum Stuart McDougall, Neel Nanda
Published: 2025-10-05
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.04128v1

Prior work has shown that a significant driver of performance in reasoning models is their ability to reason and self-correct. A distinctive marker in these reasoning traces is the token wait, which often signals reasoning behavior such as backtracking. Despite being such a complex behavior, little is understood of exactly why models do or do not decide to reason in this particular manner, which limits our understanding of what makes a reasoning model so effective. In this work, we address the question whether model's latents preceding wait tokens contain relevant information for modulating the subsequent reasoning process. We train crosscoders at multiple layers of DeepSeek-R1-Distill-Llama-8B and its base version, and introduce a latent attribution technique in the crosscoder setting. We locate a small set of features relevant for promoting/suppressing wait tokens' probabilities. Finally, through a targeted series of experiments analyzing max activating examples and causal interventions, we show that many of our identified features indeed are relevant for the reasoning process and give rise to different types of reasoning patterns such as restarting from the beginning, recalling prior knowledge, expressing uncertainty, and double-checking.

---

### Projection and Quantisation: A Unifying View of Learning to Hash, from Random Projections to the RAG Era

Authors: Sean Moran
Published: 2025-10-05
Categories: cs.IR, cs.AI, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.04127v3

Approximate nearest-neighbour search underpins large-scale retrieval and retrieval-augmented generation, yet its methods are studied in communities that seldom read one another. We argue that they form one field with three design choices. We develop the projection-quantisation-organisation lens: every method places its projections, places its quantisation thresholds, and organises the resulting codes for search. We test the lens with a reproducible measurement, released as the open BitBudget benchmark, and report three findings. First, the quantisation axis delivers the largest memory savings: a one-bit code with full-precision re-ranking matches uncompressed quality for six of seven embedders, the scanned code one thirty-second of the float's size. Second, the orderings the lens anticipates, including a learned-embedding regime where binary codes overtake an inverted-file product quantiser at a matched byte budget, recur as the embedding is enlarged. Third, given class labels, an eight-byte supervised code more than doubles the retrieval quality of the two-kilobyte task-agnostic float it replaces. We also recast the semantic identifiers of generative retrieval as quantisation codes. The main contribution is a single, tested account of compact-code search, from random projections to the retrieval-augmented era.

---

### Attending on Multilevel Structure of Proteins enables Accurate Prediction of Cold-Start Drug-Target Interactions

Authors: Ziying Zhang, Yaqing Wang, Yuxuan Sun, Min Ye, Quanming Yao
Published: 2025-10-05
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.04126v1

Cold-start drug-target interaction (DTI) prediction focuses on interaction between novel drugs and proteins. Previous methods typically learn transferable interaction patterns between structures of drug and proteins to tackle it. However, insight from proteomics suggest that protein have multi-level structures and they all influence the DTI. Existing works usually represent protein with only primary structures, limiting their ability to capture interactions involving higher-level structures. Inspired by this insight, we propose ColdDTI, a framework attending on protein multi-level structure for cold-start DTI prediction. We employ hierarchical attention mechanism to mine interaction between multi-level protein structures (from primary to quaternary) and drug structures at both local and global granularities. Then, we leverage mined interactions to fuse structure representations of different levels for final prediction. Our design captures biologically transferable priors, avoiding the risk of overfitting caused by excessive reliance on representation learning. Experiments on benchmark datasets demonstrate that ColdDTI consistently outperforms previous methods in cold-start settings.

---

### Joint Learning of Pose Regression and Denoising Diffusion with Score Scaling Sampling for Category-level 6D Pose Estimation

Authors: Seunghyun Lee, Tae-Kyun Kim
Published: 2025-10-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.04125v1

Latest diffusion models have shown promising results in category-level 6D object pose estimation by modeling the conditional pose distribution with depth image input. The existing methods, however, suffer from slow convergence during training, learning its encoder with the diffusion denoising network in end-to-end fashion, and require an additional network that evaluates sampled pose hypotheses to filter out low-quality pose candidates. In this paper, we propose a novel pipeline that tackles these limitations by two key components. First, the proposed method pretrains the encoder with the direct pose regression head, and jointly learns the networks via the regression head and the denoising diffusion head, significantly accelerating training convergence while achieving higher accuracy. Second, sampling guidance via time-dependent score scaling is proposed s.t. the exploration-exploitation trade-off is effectively taken, eliminating the need for the additional evaluation network. The sampling guidance maintains multi-modal characteristics of symmetric objects at early denoising steps while ensuring high-quality pose generation at final steps. Extensive experiments on multiple benchmarks including REAL275, HouseCat6D, and ROPE, demonstrate that the proposed method, simple yet effective, achieves state-of-the-art accuracies even with single-pose inference, while being more efficient in both training and inference.

---

### Sri Lanka Document Datasets: A Large-Scale, Multilingual Resource for Law, News, and Policy

Authors: Nuwan I. Senaratna
Published: 2025-10-05
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.04124v9

We present a collection of open, machine-readable document datasets covering parliamentary proceedings, legal judgments, government publications, news, and tourism statistics from Sri Lanka. The collection currently comprises of 299,131 documents (85.4 GB) across 26 datasets in Sinhala, Tamil, and English. The datasets are updated daily and mirrored on GitHub and Hugging Face. These resources aim to support research in computational linguistics, legal analytics, socio-political studies, and multilingual natural language processing. We describe the data sources, collection pipeline, formats, and potential use cases, while discussing licensing and ethical considerations. This manuscript is at version v2026-10-12-0839.

---

### Probing Semantic Alignment, Lexical Invariance, and Syntactic Influence in LLM Metaphor Processing

Authors: Fengying Ye, Shanshan Wang, Lidia S. Chao, Derek F. Wong
Published: 2025-10-05
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.04120v2

Large language models (LLMs) achieve strong performance on metaphor detection and interpretation tasks, yet it remains unclear what such behavioral success reveals about metaphor processing. We present a diagnostic analysis that examines the limits of behavioral evidence by probing three complementary dimensions: semantic attribute alignment, lexical invariance, and syntactic sensitivity. Using geometric probing, we assess whether model-generated interpretations align with reference semantic attributes; through context-varying substitution, we analyze the stability of lexical associations between metaphorical and literal expressions; and via controlled syntactic perturbations, we examine sensitivity in metaphor detection. Our analysis reveals that LLM-generated interpretations can exhibit semantic drift relative to reference attributes; stable lexical anchors persist across contextual conditions, potentially supporting conventional metaphors while biasing novel metaphors requiring contextual integration; and detection performance is sensitive to syntactic irregularities. These findings suggest that strong behavioral performance may reflect heterogeneous underlying signals, highlighting the need for caution when interpreting metaphor benchmarks as evidence of robust, integrated semantic understanding.

---

### Searching Meta Reasoning Skeleton to Guide LLM Reasoning

Authors: Ziying Zhang, Yaqing Wang, Quanming Yao
Published: 2025-10-05
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.04116v4

Meta reasoning behaviors work as a skeleton to guide large language model (LLM) reasoning, thus help to improve reasoning performance. However, prior researches implement meta reasoning skeleton with manually designed structure, limiting ability to adapt to query-specific requirement and capture intricate logical dependency among reasoning steps. To deal with the challenges, we represent meta reasoning skeleton with directed acyclic graph (DAG) to unify skeletons proposed in prior works and model intricate logical dependency. Then we propose AutoMR, a framework that searches for query-aware meta reasoning skeleton automatically inspired by automated machine learning (AutoML). Specifically, we construct search space based on DAG representation of skeleton and then formulate the search problem. We design a dynamic skeleton sampling algorithm by expanding meta reasoning skeleton along with reasoning context at inference time. This algorithm can derive any meta reasoning skeleton in search space efficiently and adapt skeleton to evolving base reasoning context, thus enable efficient query-aware skeleton search. We conduct experiments on extensive benchmark datasets. Experimental results show that AutoMR achieves better reasoning performance than previous works broadly.

---

### On the Statistical Query Complexity of Learning Semiautomata: a Random Walk Approach

Authors: George Giapitzakis, Kimon Fountoulakis, Eshaan Nichani, Jason D. Lee
Published: 2025-10-05
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.04115v1

Semiautomata form a rich class of sequence-processing algorithms with applications in natural language processing, robotics, computational biology, and data mining. We establish the first Statistical Query hardness result for semiautomata under the uniform distribution over input words and initial states. We show that Statistical Query hardness can be established when both the alphabet size and input length are polynomial in the number of states. Unlike the case of deterministic finite automata, where hardness typically arises through the hardness of the language they recognize (e.g., parity), our result is derived solely from the internal state-transition structure of semiautomata. Our analysis reduces the task of distinguishing the final states of two semiautomata to studying the behavior of a random walk on the group $S_{N} \times S_{N}$. By applying tools from Fourier analysis and the representation theory of the symmetric group, we obtain tight spectral gap bounds, demonstrating that after a polynomial number of steps in the number of states, distinct semiautomata become nearly uncorrelated, yielding the desired hardness result.

---

### Wasserstein projection distance for fairness testing of regression models

Authors: Wanxin Li, Yongjin P. Park, Khanh Dao Duc
Published: 2025-10-05
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.04114v2

Fairness testing evaluates whether a model satisfies a specified fairness criterion across different groups, yet most research has focused on classification models, leaving regression models underexplored. This paper introduces a framework for fairness testing in regression models, leveraging Wasserstein distance to project data distribution and focusing on expectation-based criteria. Upon categorizing fairness criteria for regression, we derive a Wasserstein projection test statistic from dual reformulation, and derive asymptotic bounds and limiting distributions, allowing us to formulate both a hypothesis-testing procedure and an optimal data perturbation method to improve fairness while balancing accuracy. Experiments on synthetic data demonstrate that the proposed hypothesis-testing approach offers higher specificity compared to permutation-based tests. To illustrate its potential applications, we apply our framework to two case studies on real data, showing (1) statistically significant gender disparities that appear on student performance data across multiple models, and (2) significant unfairness between pollution areas under multiple fairness criteria affecting housing price data, robust to different group divisions, with feature-level analysis identifying spatial and socioeconomic drivers.

---

### Learning Efficient Meshflow and Optical Flow from Event Cameras

Authors: Xinglong Luo, Ao Luo, Kunming Luo, Zhengning Wang, Ping Tan, Bing Zeng, Shuaicheng Liu
Published: 2025-10-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.04111v1

In this paper, we explore the problem of event-based meshflow estimation, a novel task that involves predicting a spatially smooth sparse motion field from event cameras. To start, we review the state-of-the-art in event-based flow estimation, highlighting two key areas for further research: i) the lack of meshflow-specific event datasets and methods, and ii) the underexplored challenge of event data density. First, we generate a large-scale High-Resolution Event Meshflow (HREM) dataset, which showcases its superiority by encompassing the merits of high resolution at 1280x720, handling dynamic objects and complex motion patterns, and offering both optical flow and meshflow labels. These aspects have not been fully explored in previous works. Besides, we propose Efficient Event-based MeshFlow (EEMFlow) network, a lightweight model featuring a specially crafted encoder-decoder architecture to facilitate swift and accurate meshflow estimation. Furthermore, we upgrade EEMFlow network to support dense event optical flow, in which a Confidence-induced Detail Completion (CDC) module is proposed to preserve sharp motion boundaries. We conduct comprehensive experiments to show the exceptional performance and runtime efficiency (30x faster) of our EEMFlow model compared to the recent state-of-the-art flow method. As an extension, we expand HREM into HREM+, a multi-density event dataset contributing to a thorough study of the robustness of existing methods across data with varying densities, and propose an Adaptive Density Module (ADM) to adjust the density of input event data to a more optimal range, enhancing the model's generalization ability. We empirically demonstrate that ADM helps to significantly improve the performance of EEMFlow and EEMFlow+ by 8% and 10%, respectively. Code and dataset are released at https://github.com/boomluo02/EEMFlowPlus.

---

### Can Linear Probes Measure LLM Uncertainty?

Authors: Ramzi Dakhmouche, Adrien Letellier, Hossein Gorji
Published: 2025-10-05
Categories: cs.LG, math.NA, math.ST
arXiv: https://arxiv.org/abs/2510.04108v2

Effective Uncertainty Quantification (UQ) represents a key aspect for reliable deployment of Large Language Models (LLMs) in automated decision-making and beyond. Yet, for LLM generation with multiple choice structure, the state-of-the-art in UQ is still dominated by the naive baseline given by the maximum softmax score. To address this shortcoming, we demonstrate that taking a principled approach via Bayesian statistics leads to improved performance despite leveraging the simplest possible model, namely linear regression. More precisely, we propose to train multiple Bayesian linear models, each predicting the output of a layer given the output of the previous one. Based on the obtained layer-level posterior distributions, we infer the global uncertainty level of the LLM by identifying a sparse combination of distributional features, leading to an efficient UQ scheme. Numerical experiments on various LLMs show consistent improvement over state-of-the-art baselines.

---

### Why Cannot Neural Networks Master Extrapolation? Insights from Physical Laws

Authors: Ramzi Dakhmouche, Hossein Gorji
Published: 2025-10-05
Categories: cs.LG, math.NA, math.PR
arXiv: https://arxiv.org/abs/2510.04102v2

Motivated by the remarkable success of Foundation Models (FMs) in language modeling, there has been growing interest in developing FMs for time series prediction, given the transformative power such models hold for science and engineering. This culminated in significant success of FMs in short-range forecasting settings. However, extrapolation or long-range forecasting remains elusive for FMs, which struggle to outperform even simple baselines. This contrasts with physical laws which have strong extrapolation properties, and raises the question of the fundamental difference between the structure of neural networks and physical laws. In this work, we identify and formalize a fundamental property characterizing the ability of statistical learning models to predict more accurately outside of their training domain, hence explaining performance deterioration for deep learning models in extrapolation settings. In addition to a theoretical analysis, we present empirical results showcasing the implications of this property on current deep learning architectures. Our results not only clarify the root causes of the extrapolation gap but also suggest directions for designing next-generation forecasting models capable of mastering extrapolation.

---

### TOPO-Bench: An Open-Source Topological Mapping Evaluation Framework with Quantifiable Perceptual Aliasing

Authors: Jiaming Wang, Jizhuo Chen, Diwen Liu, Jiaxuan Da, Jiamo Hu, Zhiwei Xue, Linh Kästner, Harold Soh
Published: 2025-10-05
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.04100v3

Topological mapping offers a compact and robust representation for navigation, but progress in the field is hindered by the lack of standardized evaluation metrics, datasets, and protocols. Existing systems are assessed using different environments and criteria, preventing fair and reproducible comparisons. Moreover, a key challenge - perceptual aliasing - remains under-quantified, despite its strong influence on system performance. We address these gaps by (1) formalizing topological consistency as the fundamental property of topological maps and showing that localization accuracy provides an efficient and interpretable surrogate metric, and (2) proposing the first quantitative measure of dataset ambiguity to enable fair comparisons across environments. To support this protocol, we curate a diverse benchmark dataset with calibrated ambiguity levels, implement and release deep-learned baseline systems, and evaluate them alongside classical methods. Our experiments and analysis yield new insights into the limitations of current approaches under perceptual aliasing. All datasets, baselines, and evaluation tools are fully open-sourced to foster consistent and reproducible research in topological mapping.

---

### Efficient Training of Spiking Neural Networks by Spike-aware Data Pruning

Authors: Chenxiang Ma, Xinyi Chen, Yujie Wu, Kay Chen Tan, Jibin Wu
Published: 2025-10-05
Categories: cs.NE, cs.AI
arXiv: https://arxiv.org/abs/2510.04098v1

Spiking neural networks (SNNs), recognized as an energy-efficient alternative to traditional artificial neural networks (ANNs), have advanced rapidly through the scaling of models and datasets. However, such scaling incurs considerable training overhead, posing challenges for researchers with limited computational resources and hindering the sustained development of SNNs. Data pruning is a promising strategy for accelerating training by retaining the most informative examples and discarding redundant ones, but it remains largely unexplored in SNNs. Directly applying ANN-based data pruning methods to SNNs fails to capture the intrinsic importance of examples and suffers from high gradient variance. To address these challenges, we propose a novel spike-aware data pruning (SADP) method. SADP reduces gradient variance by determining each example's selection probability to be proportional to its gradient norm, while avoiding the high cost of direct gradient computation through an efficient upper bound, termed spike-aware importance score. This score accounts for the influence of all-or-nothing spikes on the gradient norm and can be computed with negligible overhead. Extensive experiments across diverse datasets and architectures demonstrate that SADP consistently outperforms data pruning baselines and achieves training speedups close to the theoretical maxima at different pruning ratios. Notably, SADP reduces training time by 35% on ImageNet while maintaining accuracy comparable to that of full-data training. This work, therefore, establishes a data-centric paradigm for efficient SNN training and paves the way for scaling SNNs to larger models and datasets. The source code will be released publicly after the review process.

---

### WebRenderBench: Enhancing Web Interface Generation through Layout-Style Consistency and Reinforcement Learning

Authors: Peichao Lai, Jinhui Zhuang, Kexuan Zhang, Ningchang Xiong, Shengjie Wang, Yanwei Xu, Chong Chen, Yilei Wang, Bin Cui
Published: 2025-10-05
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.04097v2

Automating the conversion of UI images into web code is a critical task for front-end development and rapid prototyping. Advances in multimodal large language models (MLLMs) have made WebUI-to-Code increasingly feasible, yet existing benchmarks remain limited in data diversity and evaluation reliability. To address these issues, we present WebRenderBench, a large-scale benchmark of 45.1k webpages collected from real-world portal sites, offering greater diversity, complexity, and realism than prior benchmarks. We further propose a novel evaluation metric that measures layout and style consistency from the final rendered pages. Unlike vision-based methods that rely on costly LLM reasoning or structure-based comparisons vulnerable to noise and asymmetry, our approach enables more efficient, objective, and reliable UI quality assessment. Finally, we introduce the Automated Layout and Style Inspection Agent (ALISA), which integrates this metric into reinforcement learning as a reward signal to enhance training on crawled asymmetric webpages. Experiments show that ALISA significantly boosts generation performance, achieving state-of-the-art results across multiple metrics.

---

### RLRF: Competitive Search Agent Design via Reinforcement Learning from Ranker Feedback

Authors: Tommy Mordo, Sagie Dekel, Omer Madmon, Moshe Tennenholtz, Oren Kurland
Published: 2025-10-05
Categories: cs.IR, cs.GT, cs.LG
arXiv: https://arxiv.org/abs/2510.04096v1

Competitive search is a setting where document publishers modify them to improve their ranking in response to a query. Recently, publishers have increasingly leveraged LLMs to generate and modify competitive content. We introduce Reinforcement Learning from Ranker Feedback (RLRF), a framework that trains LLMs using preference datasets derived from ranking competitions. The goal of a publisher (LLM-based) agent is to optimize content for improved ranking while accounting for the strategies of competing agents. We generate the datasets using approaches that do not rely on human-authored data. We show that our proposed agents consistently and substantially outperform previously suggested approaches for LLM-based competitive document modification. We further show that our agents are effective with ranking functions they were not trained for (i.e., out of distribution) and they adapt to strategic opponents. These findings provide support to the significant potential of using reinforcement learning in competitive search.

---

### Harnessing LLM for Noise-Robust Cognitive Diagnosis in Web-Based Intelligent Education Systems

Authors: Guixian Zhang, Guan Yuan, Ziqi Xu, Yanmei Zhang, Jing Ren, Zhenyun Deng, Debo Cheng
Published: 2025-10-05
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.04093v2

Cognitive diagnostics in the Web-based Intelligent Education System (WIES) aims to assess students' mastery of knowledge concepts from heterogeneous, noisy interactions. Recent work has tried to utilize Large Language Models (LLMs) for cognitive diagnosis, yet LLMs struggle with structured data and are prone to noise-induced misjudgments. Specially, WIES's open environment continuously attracts new students and produces vast amounts of response logs, exacerbating the data imbalance and noise issues inherent in traditional educational systems. To address these challenges, we propose DLLM, a Diffusion-based LLM framework for noise-robust cognitive diagnosis. DLLM first constructs independent subgraphs based on response correctness, then applies relation augmentation alignment module to mitigate data imbalance. The two subgraph representations are then fused and aligned with LLM-derived, semantically augmented representations. Importantly, before each alignment step, DLLM employs a two-stage denoising diffusion module to eliminate intrinsic noise while assisting structural representation alignment. Specifically, unconditional denoising diffusion first removes erroneous information, followed by conditional denoising diffusion based on graph-guided to eliminate misleading information. Finally, the noise-robust representation that integrates semantic knowledge and structural information is fed into existing cognitive diagnosis models for prediction. Experimental results on three publicly available web-based educational platform datasets demonstrate that our DLLM achieves optimal predictive performance across varying noise levels, which demonstrates that DLLM achieves noise robustness while effectively leveraging semantic knowledge from LLM.

---

### Rethinking Consistent Multi-Label Classification Under Inexact Supervision

Authors: Wei Wang, Tianhao Ma, Ming-Kun Xie, Gang Niu, Masashi Sugiyama
Published: 2025-10-05
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.04091v2

Partial multi-label learning and complementary multi-label learning are two popular weakly supervised multi-label classification paradigms that aim to alleviate the high annotation costs of collecting precisely annotated multi-label data. In partial multi-label learning, each instance is annotated with a candidate label set, among which only some labels are relevant; in complementary multi-label learning, each instance is annotated with complementary labels indicating the classes to which the instance does not belong. Existing consistent approaches for the two paradigms either require accurate estimation of the generation process of candidate or complementary labels or assume a uniform distribution to eliminate the estimation problem. However, both conditions are usually difficult to satisfy in real-world scenarios. In this paper, we propose consistent approaches that do not rely on the aforementioned conditions to handle both problems in a unified way. Specifically, we propose two risk estimators based on first- and second-order strategies. Theoretically, we prove consistency w.r.t. two widely used multi-label classification evaluation metrics and derive convergence rates for the estimation errors of the proposed risk estimators. Empirically, extensive experimental results on both real-world and synthetic datasets validate the effectiveness of our proposed approaches against state-of-the-art methods.

---

### Using predefined vector systems as latent space configuration for neural network supervised training on data with arbitrarily large number of classes

Authors: Nikita Gabdullin
Published: 2025-10-05
Categories: cs.LG, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2510.04090v1

Supervised learning (SL) methods are indispensable for neural network (NN) training used to perform classification tasks. While resulting in very high accuracy, SL training often requires making NN parameter number dependent on the number of classes, limiting their applicability when the number of classes is extremely large or unknown in advance. In this paper we propose a methodology that allows one to train the same NN architecture regardless of the number of classes. This is achieved by using predefined vector systems as the target latent space configuration (LSC) during NN training. We discuss the desired properties of target configurations and choose randomly perturbed vectors of An root system for our experiments. These vectors are used to successfully train encoders and visual transformers (ViT) on Cinic-10 and ImageNet-1K in low- and high-dimensional cases by matching NN predictions with the predefined vectors. Finally, ViT is trained on a dataset with 1.28 million classes illustrating the applicability of the method to training on datasets with extremely large number of classes. In addition, potential applications of LSC in lifelong learning and NN distillation are discussed illustrating versatility of the proposed methodology.

---