# Research Papers — 2025-10 · bundle page 71 of 217 > Full-text markdown of papers #3501–3550 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/71 [← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/70.md) [Next bundle →](https://aipod.dev/papers/archive/2025-10/page/72.md) ### OREN: Octree Residual Network for Real-Time Euclidean Signed Distance Mapping Authors: Zhirui Dai, Qihao Qian, Tianxing Fan, Nikolay Atanasov Published: 2025-10-21 Categories: cs.RO, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2510.18999v3 Reconstructing signed distance functions (SDFs) from point cloud data benefits many robot autonomy capabilities, including localization, mapping, motion planning, and control. Methods that support online and large-scale SDF reconstruction often rely on discrete volumetric data structures, which affects the continuity and differentiability of the SDF estimates. Neural network methods have demonstrated high-fidelity differentiable SDF reconstruction but they tend to be less efficient, experience catastrophic forgetting and memory limitations in large environments, and are often restricted to truncated SDF. This work proposes OREN, a hybrid method that combines an explicit prior from octree interpolation with an implicit residual from neural network regression. Our method achieves non-truncated (Euclidean) SDF reconstruction with computational and memory efficiency comparable to volumetric methods and differentiability and accuracy comparable to neural network methods. Extensive experiments demonstrate that OREN outperforms the state of the art in terms of accuracy and efficiency, providing a scalable solution for downstream tasks in robotics and computer vision. --- ### An Encode-then-Decompose Approach to Unsupervised Time Series Anomaly Detection on Contaminated Training Data--Extended Version Authors: Buang Zhang, Tung Kieu, Xiangfei Qiu, Chenjuan Guo, Jilin Hu, Aoying Zhou, Christian S. Jensen, Bin Yang Published: 2025-10-21 Categories: cs.LG, cs.DB arXiv: https://arxiv.org/abs/2510.18998v1 Time series anomaly detection is important in modern large-scale systems and is applied in a variety of domains to analyze and monitor the operation of diverse systems. Unsupervised approaches have received widespread interest, as they do not require anomaly labels during training, thus avoiding potentially high costs and having wider applications. Among these, autoencoders have received extensive attention. They use reconstruction errors from compressed representations to define anomaly scores. However, representations learned by autoencoders are sensitive to anomalies in training time series, causing reduced accuracy. We propose a novel encode-then-decompose paradigm, where we decompose the encoded representation into stable and auxiliary representations, thereby enhancing the robustness when training with contaminated time series. In addition, we propose a novel mutual information based metric to replace the reconstruction errors for identifying anomalies. Our proposal demonstrates competitive or state-of-the-art performance on eight commonly used multi- and univariate time series benchmarks and exhibits robustness to time series with different contamination ratios. --- ### Solver-Integrated Adversarial Attacking and Training of Neural Operators Authors: Yifei Sun Published: 2025-10-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.18989v3 Neural operators are widely used as fast surrogates for numerical PDE solvers, mapping input functions to solution functions. However, their generalizability and robustness are not yet clearly defined in the operator-learning setting, which differs from traditional adversarial robustness definitions. This paper studies the generalizability and robustness of a learned neural operator from a solver-integrated perspective, addressing the challenge that the output of a learned operator and a numerical solver tends to change in tandem under input perturbation. First, we formalize the definition of generalization and robustness through a model-solver error operator, identifying fixed-input model-solver loss as generalization metric, and norm-bounded adversarial attack loss increase and Jacobian-error function norm as robustness metric. Second, we identify the solver-integrated adversarial attack as appropriate for PDE operator learning and show why model-only or fixed-ground-truth attacks can be insufficient when the solver output also changes with the input. Third, we develop solver-integrated adversarial training methods for neural operators. Experiments on representative PDE benchmarks show that this solver-integrated adversarial training clearly improves both generalizability and robustness. Deeper solver integration yields more effective attacks, more informative samples, and more efficient training than less integrated alternatives. These results provide a general framework for robust operator training and automatic sample selection without heavy manual intervention. More broadly, the formulation applies to adversarial regression whenever a ground-truth oracle can evaluate, and ideally differentiate, the true input-output map; PDE operator learning is one such case. --- ### Timely Clinical Diagnosis through Active Test Selection Authors: Silas Ruhrberg Estévez, Nicolás Astorga, Mihaela van der Schaar Published: 2025-10-21 Categories: cs.AI arXiv: https://arxiv.org/abs/2510.18988v5 There is growing interest in using machine learning (ML) to support clinical diagnosis, but most approaches rely on static, fully observed datasets and fail to reflect the sequential, resource-aware reasoning clinicians use in practice. Diagnosis remains complex and error prone, especially in high-pressure or resource-limited settings, underscoring the need for frameworks that help clinicians make timely and cost-effective decisions. We propose ACTMED (Adaptive Clinical Test selection via Model-based Experimental Design), a diagnostic framework that integrates Bayesian Experimental Design (BED) with large language models (LLMs) to better emulate real-world diagnostic reasoning. At each step, ACTMED selects the test expected to yield the greatest reduction in diagnostic uncertainty for a given patient. LLMs act as flexible simulators, generating plausible patient state distributions and supporting belief updates without requiring structured, task-specific training data. Clinicians can remain in the loop; reviewing test suggestions, interpreting intermediate outputs, and applying clinical judgment throughout. We evaluate ACTMED on real-world datasets and show it can optimize test selection to improve diagnostic accuracy, interpretability, and resource use. This represents a step toward transparent, adaptive, and clinician-aligned diagnostic systems that generalize across settings with reduced reliance on domain-specific data. --- ### Test-time Verification via Optimal Transport: Coverage, ROC, & Sub-optimality Authors: Arpan Mukherjee, Marcello Bullo, Debabrota Basu, Deniz Gündüz Published: 2025-10-21 Categories: cs.AI arXiv: https://arxiv.org/abs/2510.18982v1 While test-time scaling with verification has shown promise in improving the performance of large language models (LLMs), the role of the verifier and its imperfections remain underexplored. The effect of verification manifests through interactions of three quantities: (i) the generator's coverage, (ii) the verifier's region of convergence (ROC), and (iii) the sampling algorithm's sub-optimality. Though recent studies capture subsets of these factors, a unified framework quantifying the geometry of their interplay is missing. We frame verifiable test-time scaling as a transport problem. This characterizes the interaction of coverage, ROC, and sub-optimality, and uncovers that the sub-optimality--coverage curve exhibits three regimes. A transport regime -- where sub-optimality increases with coverage, a policy improvement regime -- where sub-optimality may decrease with coverage, depending on the verifier's ROC, and a saturation regime -- where sub-optimality plateaus, unaffected by coverage. We further propose and analyze two classes of sampling algorithms -- sequential and batched, and examine how their computational complexities shape these trade-offs. Empirical results with Qwen, Llama, and Gemma models corroborate our theoretical findings. --- ### Ninja Codes: Neurally Generated Fiducial Markers for Stealthy 6-DoF Tracking Authors: Yuichiro Takeuchi, Yusuke Imoto, Shunya Kato Published: 2025-10-21 Categories: cs.CV, cs.HC arXiv: https://arxiv.org/abs/2510.18976v2 In this paper we describe Ninja Codes, neurally generated fiducial markers that can be made to naturally blend into various real-world environments. An encoder network converts arbitrary images into Ninja Codes by applying visually modest alterations; the resulting codes, printed and pasted onto surfaces, can provide stealthy 6-DoF location tracking for a wide range of applications including robotics and augmented reality. Ninja Codes can be printed using standard color printers on regular printing paper, and can be detected using any device equipped with a modern RGB camera and capable of running inference. Through experiments, we demonstrate Ninja Codes' ability to provide reliable location tracking under common indoor lighting conditions, while successfully concealing themselves within diverse environmental textures. We expect Ninja Codes to offer particular value in scenarios where the conspicuous appearance of conventional fiducial markers makes them undesirable for aesthetic and other reasons. --- ### ProfBench: Multi-Domain Rubrics requiring Professional Knowledge to Answer and Judge Authors: Zhilin Wang, Jaehun Jung, Ximing Lu, Shizhe Diao, Ellie Evans, Jiaqi Zeng, Pavlo Molchanov, Yejin Choi, Jan Kautz, Yi Dong Published: 2025-10-21 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.18941v2 Evaluating progress in large language models (LLMs) is often constrained by the challenge of verifying responses, limiting assessments to tasks like mathematics, programming, and short-form question-answering. However, many real-world applications require evaluating LLMs in processing professional documents, synthesizing information, and generating comprehensive reports in response to user queries. We introduce ProfBench: a set of over 7000 response-criterion pairs as evaluated by human-experts with professional knowledge across Physics PhD, Chemistry PhD, Finance MBA and Consulting MBA. We build robust and affordable LLM-Judges to evaluate ProfBench rubrics, by mitigating self-enhancement bias and reducing the cost of evaluation by 2-3 orders of magnitude, to make it fair and accessible to the broader community. Our findings reveal that ProfBench poses significant challenges even for state-of-the-art LLMs, with top-performing models like GPT-5-high achieving only 65.9% overall performance. Furthermore, we identify notable performance disparities between proprietary and open-weight models and provide insights into the role that extended thinking plays in addressing complex, professional-domain tasks. Data: https://huggingface.co/datasets/nvidia/ProfBench and Code: https://github.com/NVlabs/ProfBench and Leaderboard: https://huggingface.co/spaces/nvidia/ProfBench --- ### NeuroAda: Activating Each Neuron's Potential for Parameter-Efficient Fine-Tuning Authors: Zhi Zhang, Yixian Shen, Congfeng Cao, Ekaterina Shutova Published: 2025-10-21 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2510.18940v2 Existing parameter-efficient fine-tuning (PEFT) methods primarily fall into two categories: addition-based and selective in-situ adaptation. The former, such as LoRA, introduce additional modules to adapt the model to downstream tasks, offering strong memory efficiency. However, their representational capacity is often limited, making them less suitable for fine-grained adaptation. In contrast, the latter directly fine-tunes a carefully chosen subset of the original model parameters, allowing for more precise and effective adaptation, but at the cost of significantly increased memory consumption. To reconcile this trade-off, we propose NeuroAda, a novel PEFT method that enables fine-grained model finetuning while maintaining high memory efficiency. Our approach first identifies important parameters (i.e., connections within the network) as in selective adaptation, and then introduces bypass connections for these selected parameters. During finetuning, only the bypass connections are updated, leaving the original model parameters frozen. Empirical results on 23+ tasks spanning both natural language generation and understanding demonstrate that NeuroAda achieves state-of-the-art performance with as little as $\leq \textbf{0.02}\%$ trainable parameters, while reducing CUDA memory usage by up to 60%. We release our code here: https://github.com/FightingFighting/NeuroAda.git. --- ### Lost in the Maze: Overcoming Context Limitations in Long-Horizon Agentic Search Authors: Howard Yen, Yoonsang Lee, Ashwin Paranjape, Mengzhou Xia, Thejas Venkatesh, Jack Hessel, Danqi Chen, Yuhao Zhang Published: 2025-10-21 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.18939v2 Long-horizon agentic search requires iteratively exploring the web over long trajectories and synthesizing information across many sources, enabling powerful applications like deep research systems. In this work, we show that popular agentic search frameworks struggle to scale to long trajectories primarily due to context limitations--they accumulate long, noisy content, hit context window and tool budgets, or stop early. We therefore introduce SLIM (Simple Lightweight Information Management), a simple framework that separates retrieval into distinct search and browse tools, and periodically summarizes the trajectory, keeping context concise while enabling longer, more focused searches. Across a wide range of long-horizon tasks, SLIM achieves comparable performance at substantially lower cost and far fewer tool calls than strong open-source frameworks with both proprietary and open-weight models, including RL-trained models for deep research. Specifically, with o3 as the base model, SLIM achieves 56% on BrowseComp and 33% on HLE, outperforming all open-source frameworks by 8 and 6 absolute points, respectively, while incurring 4-6x fewer tool calls. With GLM-4.7 Flash, SLIM achieves 10 points improvement over the next best open-source framework, Search-o1, on BrowseComp using a third of the cost. To systematically understand failure modes in long-horizon agentic search, we develop an automated fine-grained trajectory analysis pipeline and error taxonomy, and find that SLIM exhibits significantly fewer hallucinations than prior systems. We hope our analysis framework and simple tool design inform future long-horizon agents. --- ### StutterZero and StutterFormer: End-to-End Speech Conversion for Stuttering Transcription and Correction Authors: Qianheng Xu Published: 2025-10-21 Categories: eess.AS, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2510.18938v2 Over 70 million people worldwide experience stuttering, yet most automatic speech systems misinterpret disfluent utterances or fail to transcribe them accurately. Existing methods for stutter correction rely on handcrafted feature extraction or multi-stage automatic speech recognition (ASR) and text-to-speech (TTS) pipelines, which separate transcription from audio reconstruction and often amplify distortions. This work introduces StutterZero and StutterFormer, the first end-to-end waveform-to-waveform models that directly convert stuttered speech into fluent speech while jointly predicting its transcription. StutterZero employs a convolutional-bidirectional LSTM encoder-decoder with attention, whereas StutterFormer integrates a dual-stream Transformer with shared acoustic-linguistic representations. Both architectures are trained on paired stuttered-fluent data synthesized from the SEP-28K and LibriStutter corpora and evaluated on unseen speakers from the FluencyBank dataset. Across all benchmarks, StutterZero had a 24% decrease in Word Error Rate (WER) and a 31% improvement in semantic similarity (BERTScore) compared to the leading Whisper-Medium model. StutterFormer achieved better results, with a 28% decrease in WER and a 34% improvement in BERTScore. The results validate the feasibility of direct end-to-end stutter-to-fluent speech conversion, offering new opportunities for inclusive human-computer interaction, speech therapy, and accessibility-oriented AI systems. --- ### Feature Extraction in the Remote Sensing Data Value Chain: A Systematic Review of Methods and Applications Authors: Nathan Mankovich, Kai-Hendrik Cohrs, Homer Durand, Vasileios Sitokonstantinou, Tristan Williams, Gustau Camps-Valls Published: 2025-10-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.18935v3 Earth observation involves collecting, analyzing, and processing an ever-growing mass of data. This planetary data is crucial for addressing relevant societal, economic, and environmental challenges, ranging from environmental monitoring to urban planning and disaster management. However, its high dimensionality entails significant feature redundancy and computational overhead, limiting the effectiveness of machine learning models. Feature extraction (FE) techniques address these challenges by preserving essential data properties while reducing redundancy and enhancing tasks in Remote Sensing (RS). The landscape of FE for RS is diverse, disorganized, and rapidly evolving. We offer a practical guide for this landscape by introducing a framework of FE. Using this framework, we trace the evolution of FE across the data value chain in RS. Finally, we synthesize these trends and offer perspectives for the future of FE in RS by first characterizing this shift from single-task models to unified representations, then identifying two perspectives in the foundation model era: the need for robust and interpretable FE and the potential of bridging classical FE with modern representation learning. --- ### Position: Many generalization measures for deep learning are fragile Authors: Shuofeng Zhang, Ard Louis Published: 2025-10-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.18934v3 In this position paper, we argue that many post-mortem generalization measures -- those computed on trained networks -- are \textbf{fragile}: small training modifications that barely affect the performance of the underlying deep neural network can substantially change a measure's value, trend, or scaling behavior. For example, minor hyperparameter changes, such as learning rate adjustments or switching between SGD variants, can reverse the slope of a learning curve in widely used generalization measures such as the path norm. We also identify subtler forms of fragility. For instance, the PAC-Bayes origin measure is regarded as one of the most reliable, and is indeed less sensitive to hyperparameter tweaks than many other measures. However, it completely fails to capture differences in data complexity across learning curves. This data fragility contrasts with the function-based marginal-likelihood PAC-Bayes bound, which does capture differences in data-complexity, including scaling behavior, in learning curves, but which is not a post-mortem measure. Beyond demonstrating that many post-mortem bounds are fragile, this position paper also argues that developers of new measures should explicitly audit them for fragility. --- ### Evaluating LLM Story Generation through Large-scale Network Analysis of Social Structures Authors: Hiroshi Nonaka, K. E. Perry Published: 2025-10-21 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2510.18932v1 Evaluating the creative capabilities of large language models (LLMs) in complex tasks often requires human assessments that are difficult to scale. We introduce a novel, scalable methodology for evaluating LLM story generation by analyzing underlying social structures in narratives as signed character networks. To demonstrate its effectiveness, we conduct a large-scale comparative analysis using networks from over 1,200 stories, generated by four leading LLMs (GPT-4o, GPT-4o mini, Gemini 1.5 Pro, and Gemini 1.5 Flash) and a human-written corpus. Our findings, based on network properties like density, clustering, and signed edge weights, show that LLM-generated stories consistently exhibit a strong bias toward tightly-knit, positive relationships, which aligns with findings from prior research using human assessment. Our proposed approach provides a valuable tool for evaluating limitations and tendencies in the creative storytelling of current and future LLMs. --- ### A Justice Lens on Fairness and Ethics Courses in Computing Education: LLM-Assisted Multi-Perspective and Thematic Evaluation Authors: Kenya S. Andrews, Deborah Dormah Kanubala, Kehinde Aruleba, Francisco Enrique Vicente Castro, Renata A Revelo Published: 2025-10-21 Categories: cs.CY, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.18931v1 Course syllabi set the tone and expectations for courses, shaping the learning experience for both students and instructors. In computing courses, especially those addressing fairness and ethics in artificial intelligence (AI), machine learning (ML), and algorithmic design, it is imperative that we understand how approaches to navigating barriers to fair outcomes are being addressed.These expectations should be inclusive, transparent, and grounded in promoting critical thinking. Syllabus analysis offers a way to evaluate the coverage, depth, practices, and expectations within a course. Manual syllabus evaluation, however, is time-consuming and prone to inconsistency. To address this, we developed a justice-oriented scoring rubric and asked a large language model (LLM) to review syllabi through a multi-perspective role simulation. Using this rubric, we evaluated 24 syllabi from four perspectives: instructor, departmental chair, institutional reviewer, and external evaluator. We also prompted the LLM to identify thematic trends across the courses. Findings show that multiperspective evaluation aids us in noting nuanced, role-specific priorities, leveraging them to fill hidden gaps in curricula design of AI/ML and related computing courses focused on fairness and ethics. These insights offer concrete directions for improving the design and delivery of fairness, ethics, and justice content in such courses. --- ### BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping Authors: Zhiheng Xi, Xin Guo, Yang Nan, Enyu Zhou, Junrui Shen, Wenxiang Chen, Jiaqi Liu, Jixuan Huang, Zhihao Zhang, Honglin Guo, Xun Deng, Zhikai Lei et al. Published: 2025-10-21 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2510.18927v1 Reinforcement learning (RL) has recently become the core paradigm for aligning and strengthening large language models (LLMs). Yet, applying RL in off-policy settings--where stale data from past policies are used for training--improves sample efficiency, but remains challenging: policy entropy declines sharply, optimization often becomes unstable and may even collapse. Through theoretical and empirical analysis, we identify two key insights: (i) an imbalance in optimization, where negative-advantage samples dominate the policy gradient, suppressing useful behaviors and risking gradient explosions; and (ii) the derived Entropy-Clip Rule, which reveals that the fixed clipping mechanism in PPO-like objectives systematically blocks entropy-increasing updates, thereby driving the policy toward over-exploitation at the expense of exploration. Building on these insights, we propose BAlanced Policy Optimization with Adaptive Clipping (BAPO), a simple yet effective method that dynamically adjusts clipping bounds to adaptively re-balance positive and negative contributions, preserve entropy, and stabilize RL optimization. Across diverse off-policy scenarios--including sample replay and partial rollout--BAPO achieves fast, stable, and data-efficient training. On AIME 2024 and AIME 2025 benchmarks, our 7B BAPO model surpasses open-source counterparts such as SkyWork-OR1-7B, while our 32B BAPO model not only achieves state-of-the-art results among models of the same scale but also outperforms leading proprietary systems like o3-mini and Gemini-2.5-Flash-Thinking. --- ### Application of Reduced-Order Models for Temporal Multiscale Representations in the Prediction of Dynamical Systems Authors: Elias Al Ghazal, Jad Mounayer, Beatriz Moya, Sebastian Rodriguez, Chady Ghnatios, Francisco Chinesta Published: 2025-10-21 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2510.18925v1 Modeling and predicting the dynamics of complex multiscale systems remains a significant challenge due to their inherent nonlinearities and sensitivity to initial conditions, as well as limitations of traditional machine learning methods that fail to capture high frequency behaviours. To overcome these difficulties, we propose three approaches for multiscale learning. The first leverages the Partition of Unity (PU) method, integrated with neural networks, to decompose the dynamics into local components and directly predict both macro- and micro-scale behaviors. The second applies the Singular Value Decomposition (SVD) to extract dominant modes that explicitly separate macro- and micro-scale dynamics. Since full access to the data matrix is rarely available in practice, we further employ a Sparse High-Order SVD to reconstruct multiscale dynamics from limited measurements. Together, these approaches ensure that both coarse and fine dynamics are accurately captured, making the framework effective for real-world applications involving complex, multi-scale phenomena and adaptable to higher-dimensional systems with incomplete observations, by providing an approximation and interpretation in all time scales present in the phenomena under study. --- ### Noise-corrected GRPO: From Noisy Rewards to Unbiased Gradients Authors: Omar El Mansouri, Fathinah Asma Izzati, Mohamed El Amine Seddik, Salem Lahlou Published: 2025-10-21 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2510.18924v3 Reinforcement learning from human feedback (RLHF) or verifiable rewards (RLVR), the standard paradigm for aligning LLMs or building recent SOTA reasoning models, is highly sensitive to noise from inconsistent or erroneous rewards. Yet, the interaction between such noise and widely used group-based policy optimization methods remains underexplored. We introduce a noise-robust Group Relative Policy Optimization (GRPO) and Done Right GRPO (Dr.GRPO) framework that explicitly models reward corruption as Bernoulli noise. Our method applies noise correction after estimating reward flip probabilities to debias the learning signal, yielding provably unbiased gradient estimates. Theoretical analysis shows that group-based methods inherently mitigate individual-level noise, and our correction strategy amplifies this robustness. Empirically, we observe consistent improvements across math and code tasks when applying our noise correction to standard reward model usage, with particular gains of up to 6.7 percentage points in accuracy on math tasks and 1.5 on code tasks under realistic reward model conditions. This work bridges label-noise correction from supervised learning with modern RLHF, offering both theoretical insights and a practical algorithm for noisy real-world deployment. --- ### Benchmarking On-Device Machine Learning on Apple Silicon with MLX Authors: Oluwaseun A. Ajayi, Ogundepo Odunayo Published: 2025-10-21 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2510.18921v1 The recent widespread adoption of Large Language Models (LLMs) and machine learning in general has sparked research interest in exploring the possibilities of deploying these models on smaller devices such as laptops and mobile phones. This creates a need for frameworks and approaches that are capable of taking advantage of on-device hardware. The MLX framework was created to address this need. It is a framework optimized for machine learning (ML) computations on Apple silicon devices, facilitating easier research, experimentation, and prototyping. This paper presents a performance evaluation of MLX, focusing on inference latency of transformer models. We compare the performance of different transformer architecture implementations in MLX with their Pytorch counterparts. For this research we create a framework called MLX-transformers which includes different transformer implementations in MLX and downloads the model checkpoints in pytorch and converts it to the MLX format. By leveraging the advanced architecture and capabilities of Apple Silicon, MLX-Transformers enables seamless execution of transformer models directly sourced from Hugging Face, eliminating the need for checkpoint conversion often required when porting models between frameworks. Our study benchmarks different transformer models on two Apple Silicon macbook devices against an NVIDIA CUDA GPU. Specifically, we compare the inference latency performance of models with the same parameter sizes and checkpoints. We evaluate the performance of BERT, RoBERTa, and XLM-RoBERTa models, with the intention of extending future work to include models of different modalities, thus providing a more comprehensive assessment of MLX's capabilities. The results highlight MLX's potential in enabling efficient and more accessible on-device ML applications within Apple's ecosystem. --- ### Misinformation Detection using Large Language Models with Explainability Authors: Jainee Patel, Chintan Bhatt, Himani Trivedi, Thanh Thi Nguyen Published: 2025-10-21 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2510.18918v1 The rapid spread of misinformation on online platforms undermines trust among individuals and hinders informed decision making. This paper shows an explainable and computationally efficient pipeline to detect misinformation using transformer-based pretrained language models (PLMs). We optimize both RoBERTa and DistilBERT using a two-step strategy: first, we freeze the backbone and train only the classification head; then, we progressively unfreeze the backbone layers while applying layer-wise learning rate decay. On two real-world benchmark datasets, COVID Fake News and FakeNewsNet GossipCop, we test the proposed approach with a unified protocol of preprocessing and stratified splits. To ensure transparency, we integrate the Local Interpretable Model-Agnostic Explanations (LIME) at the token level to present token-level rationales and SHapley Additive exPlanations (SHAP) at the global feature attribution level. It demonstrates that DistilBERT achieves accuracy comparable to RoBERTa while requiring significantly less computational resources. This work makes two key contributions: (1) it quantitatively shows that a lightweight PLM can maintain task performance while substantially reducing computational cost, and (2) it presents an explainable pipeline that retrieves faithful local and global justifications without compromising performance. The results suggest that PLMs combined with principled fine-tuning and interpretability can be an effective framework for scalable, trustworthy misinformation detection. --- ### UNO-Bench: A Unified Benchmark for Exploring the Compositional Law Between Uni-modal and Omni-modal in Omni Models Authors: Chen Chen, ZeYang Hu, Fengjiao Chen, Liya Ma, Jiaxing Liu, Xiaoyu Li, Ziwen Wang, Xuezhi Cao, Xunliang Cai Published: 2025-10-21 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2510.18915v3 Multimodal Large Languages models have been progressing from uni-modal understanding toward unifying visual, audio and language modalities, collectively termed omni models. However, the correlation between uni-modal and omni-modal remains unclear, which requires comprehensive evaluation to drive omni model's intelligence evolution. In this work, we introduce a novel, high-quality, and UNified Omni model benchmark, UNO-Bench. This benchmark is designed to effectively evaluate both UNi-modal and Omni-modal capabilities under a unified ability taxonomy, spanning 44 task types and 5 modality combinations. It includes 1250 human curated samples for omni-modal with 98% cross-modality solvability, and 2480 enhanced uni-modal samples. The human-generated dataset is well-suited to real-world scenarios, particularly within the Chinese context, whereas the automatically compressed dataset offers a 90% increase in speed and maintains 98% consistency across 18 public benchmarks. In addition to traditional multi-choice questions, we propose an innovative multi-step open-ended question format to assess complex reasoning. A general scoring model is incorporated, supporting 6 question types for automated evaluation with 95% accuracy. Experimental result shows the Compositional Law between omni-modal and uni-modal performance and the omni-modal capability manifests as a bottleneck effect on weak models, while exhibiting synergistic promotion on strong models. --- ### Fairness Evaluation and Inference Level Mitigation in LLMs Authors: Afrozah Nadeem, Mark Dras, Usman Naseem Published: 2025-10-21 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2510.18914v4 Large language models often display undesirable behaviors embedded in their internal representations, undermining fairness, inconsistency drift, amplification of harmful content, and the propagation of unwanted patterns during extended dialogue and conversations. Although training-time or data-centric methods attempt to reduce these effects, they are computationally expensive, irreversible once deployed, and slow to adapt to new conversational contexts. Pruning-based methods provide a flexible and transparent way to reduce bias by adjusting the neurons responsible for certain behaviors. However, most existing approaches are static; once a neuron is removed, the model loses the ability to adapt when the conversation or context changes. To address this, we propose a dynamic, reversible, pruning-based framework that detects context-aware neuron activations and applies adaptive masking to modulate their influence during generation. Our inference-time solution provides fine-grained, memory-aware mitigation with knowledge-preserved, more coherent behavior across multilingual single- and multi-turn dialogues, enabling dynamic fairness control in real-world conversational AI. --- ### ADPO: Anchored Direct Preference Optimization Authors: Wang Zixian Published: 2025-10-21 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2510.18913v7 We present Anchored Direct Preference Optimization (ADPO), a policy alignment method derived from first principles of KL-regularized reinforcement learning. Unlike standard approaches that treat the reference policy merely as a regularizer, we show that the optimal policy in reinforcement learning from human feedback inherently operates in a differential coordinate system, optimizing relative advantage in the form of log ratios rather than absolute probabilities. ADPO explicitly parameterizes this optimal structure through anchored logits, effectively decoupling response quality from prior popularity and creating an implicit trust region through curvature scaling. We show that this formulation unifies supervised fine-tuning, reinforcement learning, and ranking-based objectives under a single geometric perspective. Theoretically, ADPO resolves the probability smearing problem of supervised fine-tuning while avoiding the mode-seeking instability characteristic of reverse-KL methods. Empirically, the listwise ranking variant of ADPO achieves state-of-the-art performance on reasoning tasks, outperforming GRPO by 30.9 percent on Qwen3-1.7B and demonstrating superior robustness under distribution shift. --- ### Prospects for Using Artificial Intelligence to Understand Intrinsic Kinetics of Heterogeneous Catalytic Reactions Authors: Andrew J. Medford, Todd N. Whittaker, Bjarne Kreitz, David W. Flaherty, John R. Kitchin Published: 2025-10-21 Categories: physics.chem-ph, cs.AI arXiv: https://arxiv.org/abs/2510.18911v1 Artificial intelligence (AI) is influencing heterogeneous catalysis research by accelerating simulations and materials discovery. A key frontier is integrating AI with multiscale models and multimodal experiments to address the "many-to-one" challenge of linking intrinsic kinetics to observables. Advances in machine-learned force fields, microkinetics, and reactor modeling enable rapid exploration of chemical spaces, while operando and transient data provide unprecedented insight. Yet, inconsistent data quality and model complexity limit mechanistic discovery. Generative and agentic AI can automate model generation, quantify uncertainty, and couple theory with experiment, realizing "self-driving models" that produce interpretable, reproducible, and transferable understanding of catalytic systems. --- ### Large Connectome Model: An fMRI Foundation Model of Brain Connectomes Empowered by Brain-Environment Interaction in Multitask Learning Landscape Authors: Ziquan Wei, Tingting Dan, Guorong Wu Published: 2025-10-21 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2510.18910v1 A reliable foundation model of functional neuroimages is critical to promote clinical applications where the performance of current AI models is significantly impeded by a limited sample size. To that end, tremendous efforts have been made to pretraining large models on extensive unlabeled fMRI data using scalable self-supervised learning. Since self-supervision is not necessarily aligned with the brain-to-outcome relationship, most foundation models are suboptimal to the downstream task, such as predicting disease outcomes. By capitalizing on rich environmental variables and demographic data along with an unprecedented amount of functional neuroimages, we form the brain modeling as a multitask learning and present a scalable model architecture for (i) multitask pretraining by tokenizing multiple brain-environment interactions (BEI) and (ii) semi-supervised finetuning by assigning pseudo-labels of pretrained BEI. We have evaluated our foundation model on a variety of applications, including sex prediction, human behavior recognition, and disease early diagnosis of Autism, Parkinson's disease, Alzheimer's disease, and {Schizophrenia}, where promising results indicate the great potential to facilitate current neuroimaging applications in clinical routines. --- ### Learning from the Best, Differently: A Diversity-Driven Rethinking on Data Selection Authors: Hongyi He, Xiao Liu, Zhenghao Lin, Mingni Tang, Yi Cheng, Jintao Wang, Wenjie Li, Peng Cheng, Yeyun Gong Published: 2025-10-21 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2510.18909v1 High-quality pre-training data is crutial for large language models, where quality captures factual reliability and semantic value, and diversity ensures broad coverage and distributional heterogeneity. Existing approaches typically rely on single or multiple-dimensional score-based selection. However, directly selecting top-scored data often degrades performance, and sampling from a broader range is required to recover results. The above non-monotonicity between dataset scores and downstream benchmark results reveals a fundamental bias: score-based methods collapse correlated dimensions, causing top-scored data to appear high-quality while systematically overlooking diversity. We argue that ensuring diversity requires decomposing correlated metrics into orthogonal feature dimensions, from which the top-scored data can be directly selected. Therefore, we proposed the Orthogonal Diversity-Aware Selection (ODiS) algorithm, which preserves both quality and diversity during data selection. First, ODiS evaluates data from multiple dimensions, covering language quality, knowledge quality, and comprehension difficulty. The multi-dimensional scores are then decorrelated via Principal Component Analysis (PCA), yielding orthogonal evaluation dimensions. For each dimension, a Roberta-based scorer is trained to regress the data onto PCA-projected scores, enabling scalable inference on large corpora. Finally, ODiS constructs the training dataset by selecting top-scored data within each orthogonal dimension, thereby ensuring both quality and diversity. Empirical results show that ODiS-selected data exhibit less than 2\% inter-dimension overlap, confirming orthogonality between dimensions. More importantly, models trained with ODiS-selected data significantly outperform other baselines on downstream benchmarks, highlighting the necessity of orthogonal, diversity-aware data selection for LLMs. --- ### Improving Topic Modeling of Social Media Short Texts with Rephrasing: A Case Study of COVID-19 Related Tweets Authors: Wangjiaxuan Xin, Shuhua Yin, Shi Chen, Yaorong Ge Published: 2025-10-21 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2510.18908v2 Social media platforms such as Twitter (now X) provide rich data for analyzing public discourse, especially during crises such as the COVID-19 pandemic. However, the brevity, informality, and noise of social media short texts often hinder the effectiveness of traditional topic modeling, producing incoherent or redundant topics that are often difficult to interpret. To address these challenges, we have developed \emph{TM-Rephrase}, a model-agnostic framework that leverages large language models (LLMs) to rephrase raw tweets into more standardized and formal language prior to topic modeling. Using a dataset of 25,027 COVID-19-related Twitter posts, we investigate the effects of two rephrasing strategies, general- and colloquial-to-formal-rephrasing, on multiple topic modeling methods. Results demonstrate that \emph{TM-Rephrase} improves three metrics measuring topic modeling performance (i.e., topic coherence, topic uniqueness, and topic diversity) while reducing topic redundancy of most topic modeling algorithms, with the colloquial-to-formal strategy yielding the greatest performance gains and especially for the Latent Dirichlet Allocation (LDA) algorithm. This study contributes to a model-agnostic approach to enhancing topic modeling in public health related social media analysis, with broad implications for improved understanding of public discourse in health crisis as well as other important domains. --- ### 3D Optimization for AI Inference Scaling: Balancing Accuracy, Cost, and Latency Authors: Minseok Jung, Abhas Ricky, Muhammad Rameez Chatni Published: 2025-10-21 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2510.18905v3 AI inference scaling is often tuned through 1D heuristics (a fixed reasoning pass) or 2D bivariate trade-offs (e.g., accuracy vs. compute), which fail to consider cost and latency constraints. We introduce a 3D optimization framework that jointly calibrates accuracy, cost, and latency within a unified decision space, enabling constraints-aware inference scaling. Using Monte Carlo simulations across three representative scenarios and nine simulated large language models, we evaluate four optimization methods to address the 3D multi-objective optimization (MOO) problem. Framing inference scaling in MOO shapes a feasible space that 1D and 2D optimizations fail to capture, enabling environment-adaptive selection of the inference scaling~$k$. Results show that knee-point optimization based on Pareto frontiers achieves the best balance, while accuracy-maximization remains favorable when accuracy is prioritized. Our results further show that smaller models, when combined with optimal inference scaling, can match or exceed the performance of larger models at a fraction of the cost. The framework establishes a theoretical foundation for deployment-aware inference scaling across diverse operational conditions. --- ### DuoLens: A Framework for Robust Detection of Machine-Generated Multilingual Text and Code Authors: Shriyansh Agrawal, Aidan Lau, Sanyam Shah, Ahan M R, Kevin Zhu, Sunishchal Dev, Vasu Sharma Published: 2025-10-21 Categories: cs.CL, cs.AI, cs.IR, cs.LG arXiv: https://arxiv.org/abs/2510.18904v1 The prevalence of Large Language Models (LLMs) for generating multilingual text and source code has only increased the imperative for machine-generated content detectors to be accurate and efficient across domains. Current detectors, predominantly utilizing zero-shot methods, such as Fast DetectGPT or GPTZero, either incur high computational cost or lack sufficient accuracy, often with a trade-off between the two, leaving room for further improvement. To address these gaps, we propose the fine-tuning of encoder-only Small Language Models (SLMs), in particular, the pre-trained models of RoBERTA and CodeBERTa using specialized datasets on source code and other natural language to prove that for the task of binary classification, SLMs outperform LLMs by a huge margin whilst using a fraction of compute. Our encoders achieve AUROC $= 0.97$ to $0.99$ and macro-F1 $0.89$ to $0.94$ while reducing latency by $8$-$12\times$ and peak VRAM by $3$-$5\times$ at $512$-token inputs. Under cross-generator shifts and adversarial transformations (paraphrase, back-translation; code formatting/renaming), performance retains $\geq 92%$ of clean AUROC. We release training and evaluation scripts with seeds and configs; a reproducibility checklist is also included. --- ### Grasp Any Region: Towards Precise, Contextual Pixel Understanding for Multimodal LLMs Authors: Haochen Wang, Yuhao Wang, Tao Zhang, Yikang Zhou, Yanwei Li, Jiacong Wang, Jiani Zheng, Ye Tian, Jiahao Meng, Zilong Huang, Guangcan Mai, Anran Wang et al. Published: 2025-10-21 Categories: cs.CV, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2510.18876v3 While Multimodal Large Language Models (MLLMs) excel at holistic understanding, they struggle in capturing the dense world with complex scenes, requiring fine-grained analysis of intricate details and object inter-relationships. Region-level MLLMs have been a promising step. However, previous attempts are generally optimized to understand given regions in isolation, neglecting crucial global contexts. To address this, we introduce Grasp Any Region (GAR) for comprehen- sive region-level visual understanding. Empowered by an effective RoI-aligned feature replay technique, GAR supports (1) precise perception by leveraging necessary global contexts, and (2) modeling interactions between multiple prompts. Together, it then naturally achieves (3) advanced compositional reasoning to answer specific free-form questions about any region, shifting the paradigm from passive description to active dialogue. Moreover, we construct GAR-Bench, which not only provides a more accurate evaluation of single-region comprehension, but also, more importantly, measures interactions and complex reasoning across multiple regions. Extensive experiments have demonstrated that GAR-1B not only maintains the state-of-the-art captioning capabilities, e.g., outperforming DAM-3B +4.5 on DLC-Bench, but also excels at modeling relationships between multiple prompts with advanced comprehension capabilities, even surpassing InternVL3-78B on GAR-Bench-VQA. More importantly, our zero-shot GAR-8B even outperforms in-domain VideoRefer-7B on VideoRefer-BenchQ, indicating its strong capabilities can be easily transferred to videos. --- ### Retaining by Doing: The Role of On-Policy Data in Mitigating Forgetting Authors: Howard Chen, Noam Razin, Karthik Narasimhan, Danqi Chen Published: 2025-10-21 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2510.18874v3 Adapting language models (LMs) to new tasks via post-training carries the risk of degrading existing capabilities -- a phenomenon classically known as catastrophic forgetting. In this paper, toward identifying guidelines for mitigating this phenomenon, we systematically compare the forgetting patterns of two widely adopted post-training methods: supervised fine-tuning (SFT) and reinforcement learning (RL). Our experiments reveal a consistent trend across LM families (Llama, Qwen) and tasks (instruction following, general knowledge, and arithmetic reasoning): RL leads to less forgetting than SFT while achieving comparable or higher target task performance. To investigate the cause for this difference, we consider a simplified setting in which the LM is modeled as a mixture of two distributions, one corresponding to prior knowledge and the other to the target task. We identify that the mode-seeking nature of RL, which stems from its use of on-policy data, enables keeping prior knowledge intact when learning the target task. We then verify this insight by demonstrating that the use on-policy data underlies the robustness of RL to forgetting in practical settings, as opposed to other algorithmic choices such as the KL regularization or advantage estimation. Lastly, as a practical implication, our results highlight the potential of mitigating forgetting using approximately on-policy data, which can be substantially more efficient to obtain than fully on-policy data. --- ### DSI-Bench: A Benchmark for Dynamic Spatial Intelligence Authors: Ziang Zhang, Zehan Wang, Guanghao Zhang, Weilong Dai, Yan Xia, Ziang Yan, Minjie Hong, Zhou Zhao Published: 2025-10-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.18873v1 Reasoning about dynamic spatial relationships is essential, as both observers and objects often move simultaneously. Although vision-language models (VLMs) and visual expertise models excel in 2D tasks and static scenarios, their ability to fully understand dynamic 3D scenarios remains limited. We introduce Dynamic Spatial Intelligence and propose DSI-Bench, a benchmark with nearly 1,000 dynamic videos and over 1,700 manually annotated questions covering nine decoupled motion patterns of observers and objects. Spatially and temporally symmetric designs reduce biases and enable systematic evaluation of models' reasoning about self-motion and object motion. Our evaluation of 14 VLMs and expert models reveals key limitations: models often conflate observer and object motion, exhibit semantic biases, and fail to accurately infer relative relationships in dynamic scenarios. Our DSI-Bench provides valuable findings and insights about the future development of general and expertise models with dynamic spatial intelligence. --- ### How Do LLMs Use Their Depth? Authors: Akshat Gupta, Jay Yeung, Gopala Anumanchipalli, Anna Ivanova Published: 2025-10-21 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2510.18871v2 Growing evidence suggests that large language models do not use their depth uniformly, yet we still lack a fine-grained understanding of their layer-wise prediction dynamics. In this paper, we trace the intermediate representations of several open-weight models during inference and reveal a structured and nuanced use of depth. Specifically, we propose a "Guess-then-Refine" framework that explains how LLMs internally structure their computations to make predictions. We first show that the top-ranked predictions in early LLM layers are composed primarily of high-frequency tokens, which act as statistical guesses proposed by the model due to the lack of contextual information. As contextual information develops deeper into the model, these initial guesses get refined into contextually appropriate tokens. We then examine the dynamic usage of layer depth through three case studies. (i) Multiple-choice task analysis shows that the model identifies appropriate options within the first half of the model and finalizes the response in the latter half. (ii) Fact recall task analysis shows that in a multi-token answer, the first token requires more computational depth than the rest. (iii) Part-of-speech analysis shows that function words are, on average, the earliest to be predicted correctly. To validate our results, we supplement probe-based analyses with causal manipulations in the form of activation patching and early-exiting experiments. Together, our results provide a detailed view of depth usage in LLMs, shedding light on the layer-by-layer computations that underlie successful predictions and providing insights for future works to improve computational efficiency in transformer-based models. --- ### Triangle Multiplication Is All You Need For Biomolecular Structure Representations Authors: Jeffrey Ouyang-Zhang, Pranav Murugan, Daniel J. Diaz, Gianluca Scarpellini, Richard Strong Bowen, Nate Gruver, Adam Klivans, Philipp Krähenbühl, Aleksandra Faust, Maruan Al-Shedivat Published: 2025-10-21 Categories: q-bio.QM, cs.LG arXiv: https://arxiv.org/abs/2510.18870v2 AlphaFold has transformed protein structure prediction, but emerging applications such as virtual ligand screening, proteome-wide folding, and de novo binder design demand predictions at a massive scale, where runtime and memory costs become prohibitive. A major bottleneck lies in the Pairformer backbone of AlphaFold3-style models, which relies on computationally expensive triangular primitives-especially triangle attention-for pairwise reasoning. We introduce Pairmixer, a streamlined alternative that eliminates triangle attention while preserving higher-order geometric reasoning capabilities that are critical for structure prediction. Pairmixer substantially improves computational efficiency, matching state-of-the-art structure predictors across folding and docking benchmarks, delivering up to 4x faster inference on long sequences while reducing training cost by 34%. Its efficiency alleviates the computational burden of downstream applications such as modeling large protein complexes, high-throughput ligand and binder screening, and hallucination-based design. Within BoltzDesign, for example, Pairmixer delivers over 2x faster sampling and scales to sequences ~30% longer than the memory limits of Pairformer. Code is available at https://github.com/genesistherapeutics/pairmixer. --- ### LightMem: Lightweight and Efficient Memory-Augmented Generation Authors: Jizhan Fang, Xinle Deng, Haoming Xu, Ziyan Jiang, Yuqi Tang, Ziwen Xu, Shumin Deng, Yunzhi Yao, Mengru Wang, Shuofei Qiao, Huajun Chen, Ningyu Zhang Published: 2025-10-21 Categories: cs.CL, cs.AI, cs.CV, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2510.18866v4 Despite their remarkable capabilities, Large Language Models (LLMs) struggle to effectively leverage historical interaction information in dynamic and complex environments. Memory systems enable LLMs to move beyond stateless interactions by introducing persistent information storage, retrieval, and utilization mechanisms. However, existing memory systems often introduce substantial time and computational overhead. To this end, we introduce a new memory system called LightMem, which strikes a balance between the performance and efficiency of memory systems. Inspired by the Atkinson-Shiffrin model of human memory, LightMem organizes memory into three complementary stages. First, cognition-inspired sensory memory rapidly filters irrelevant information through lightweight compression and groups information according to their topics. Next, topic-aware short-term memory consolidates these topic-based groups, organizing and summarizing content for more structured access. Finally, long-term memory with sleep-time update employs an offline procedure that decouples consolidation from online inference. On LongMemEval and LoCoMo, using GPT and Qwen backbones, LightMem consistently surpasses strong baselines, improving QA accuracy by up to 7.7% / 29.3%, reducing total token usage by up to 38x / 20.9x and API calls by up to 30x / 55.5x, while purely online test-time costs are even lower, achieving up to 106x / 117x token reduction and 159x / 310x fewer API calls. The code is available at https://github.com/zjunlp/LightMem. --- ### Every Step Evolves: Scaling Reinforcement Learning for Trillion-Scale Thinking Model Authors: Ling Team, Anqi Shen, Baihui Li, Bin Hu, Bin Jing, Cai Chen, Chao Huang, Chao Zhang, Chaokun Yang, Cheng Lin, Chengyao Wen, Congqi Li et al. Published: 2025-10-21 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2510.18855v2 We present Ring-1T, the first open-source, state-of-the-art thinking model with a trillion-scale parameter. It features 1 trillion total parameters and activates approximately 50 billion per token. Training such models at a trillion-parameter scale introduces unprecedented challenges, including train-inference misalignment, inefficiencies in rollout processing, and bottlenecks in the RL system. To address these, we pioneer three interconnected innovations: (1) IcePop stabilizes RL training via token-level discrepancy masking and clipping, resolving instability from training-inference mismatches; (2) C3PO++ improves resource utilization for long rollouts under a token budget by dynamically partitioning them, thereby obtaining high time efficiency; and (3) ASystem, a high-performance RL framework designed to overcome the systemic bottlenecks that impede trillion-parameter model training. Ring-1T delivers breakthrough results across critical benchmarks: 93.4 on AIME-2025, 86.72 on HMMT-2025, 2088 on CodeForces, and 55.94 on ARC-AGI-1. Notably, it attains a silver medal-level result on the IMO-2025, underscoring its exceptional reasoning capabilities. By releasing the complete 1T parameter MoE model to the community, we provide the research community with direct access to cutting-edge reasoning capabilities. This contribution marks a significant milestone in democratizing large-scale reasoning intelligence and establishes a new baseline for open-source model performance. --- ### Lyapunov-Aware Quantum-Inspired Reinforcement Learning for Continuous-Time Vehicle Control: A Feasibility Study Authors: Nutkritta Kraipatthanapong, Natthaphat Thathong, Pannita Suksawas, Thanunnut Klunklin, Kritin Vongthonglua, Krit Attahakul, Aueaphum Aueawatthanaphisut Published: 2025-10-21 Categories: quant-ph, cs.AI, cs.LG, eess.SY arXiv: https://arxiv.org/abs/2510.18852v1 This paper presents a novel Lyapunov-Based Quantum Reinforcement Learning (LQRL) framework that integrates quantum policy optimization with Lyapunov stability analysis for continuous-time vehicle control. The proposed approach combines the representational power of variational quantum circuits (VQCs) with a stability-aware policy gradient mechanism to ensure asymptotic convergence and safe decision-making under dynamic environments. The vehicle longitudinal control problem was formulated as a continuous-state reinforcement learning task, where the quantum policy network generates control actions subject to Lyapunov stability constraints. Simulation experiments were conducted in a closed-loop adaptive cruise control scenario using a quantum-inspired policy trained under stability feedback. The results demonstrate that the LQRL framework successfully embeds Lyapunov stability verification into quantum policy learning, enabling interpretable and stability-aware control performance. Although transient overshoot and Lyapunov divergence were observed under aggressive acceleration, the system maintained bounded state evolution, validating the feasibility of integrating safety guarantees within quantum reinforcement learning architectures. The proposed framework provides a foundational step toward provably safe quantum control in autonomous systems and hybrid quantum-classical optimization domains. --- ### DP$^2$O-SR: Direct Perceptual Preference Optimization for Real-World Image Super-Resolution Authors: Rongyuan Wu, Lingchen Sun, Zhengqiang Zhang, Shihao Wang, Tianhe Wu, Qiaosi Yi, Shuai Li, Lei Zhang Published: 2025-10-21 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2510.18851v1 Benefiting from pre-trained text-to-image (T2I) diffusion models, real-world image super-resolution (Real-ISR) methods can synthesize rich and realistic details. However, due to the inherent stochasticity of T2I models, different noise inputs often lead to outputs with varying perceptual quality. Although this randomness is sometimes seen as a limitation, it also introduces a wider perceptual quality range, which can be exploited to improve Real-ISR performance. To this end, we introduce Direct Perceptual Preference Optimization for Real-ISR (DP$^2$O-SR), a framework that aligns generative models with perceptual preferences without requiring costly human annotations. We construct a hybrid reward signal by combining full-reference and no-reference image quality assessment (IQA) models trained on large-scale human preference datasets. This reward encourages both structural fidelity and natural appearance. To better utilize perceptual diversity, we move beyond the standard best-vs-worst selection and construct multiple preference pairs from outputs of the same model. Our analysis reveals that the optimal selection ratio depends on model capacity: smaller models benefit from broader coverage, while larger models respond better to stronger contrast in supervision. Furthermore, we propose hierarchical preference optimization, which adaptively weights training pairs based on intra-group reward gaps and inter-group diversity, enabling more efficient and stable learning. Extensive experiments across both diffusion- and flow-based T2I backbones demonstrate that DP$^2$O-SR significantly improves perceptual quality and generalizes well to real-world benchmarks. --- ### Towards Faithful and Controllable Personalization via Critique-Post-Edit Reinforcement Learning Authors: Chenghao Zhu, Meiling Tao, Tiannan Wang, Dongyi Ding, Yuchen Eleanor Jiang, Wangchunshu Zhou Published: 2025-10-21 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2510.18849v1 Faithfully personalizing large language models (LLMs) to align with individual user preferences is a critical but challenging task. While supervised fine-tuning (SFT) quickly reaches a performance plateau, standard reinforcement learning from human feedback (RLHF) also struggles with the nuances of personalization. Scalar-based reward models are prone to reward hacking which leads to verbose and superficially personalized responses. To address these limitations, we propose Critique-Post-Edit, a robust reinforcement learning framework that enables more faithful and controllable personalization. Our framework integrates two key components: (1) a Personalized Generative Reward Model (GRM) that provides multi-dimensional scores and textual critiques to resist reward hacking, and (2) a Critique-Post-Edit mechanism where the policy model revises its own outputs based on these critiques for more targeted and efficient learning. Under a rigorous length-controlled evaluation, our method substantially outperforms standard PPO on personalization benchmarks. Personalized Qwen2.5-7B achieves an average 11\% win-rate improvement, and personalized Qwen2.5-14B model surpasses the performance of GPT-4.1. These results demonstrate a practical path to faithful, efficient, and controllable personalization. --- ### Inference on Variable Importance for Treatment Effect Heterogeneity: Shapley Values and Beyond Authors: Pawel Morzywolek, Peter B. Gilbert, Alex Luedtke Published: 2025-10-21 Categories: stat.ME, math.ST, stat.ML arXiv: https://arxiv.org/abs/2510.18843v2 We provide an inferential framework to assess variable importance for heterogeneous treatment effects. This assessment is especially useful in high-risk domains such as medicine, where decision makers hesitate to rely on black-box treatment recommendation algorithms. The variable importance measures we consider are local in that they may differ across individuals, while the inference is global in that it tests whether a given variable is important for any individual. Our approach builds on recent developments in semiparametric theory for function-valued parameters, and is valid even when statistical machine learning algorithms are employed to quantify treatment effect heterogeneity. We demonstrate the applicability of our method to infectious disease prevention strategies. --- ### A Hybrid Enumeration Framework for Optimal Counterfactual Generation in Post-Acute COVID-19 Heart Failure Authors: Jingya Cheng, Alaleh Azhir, Jiazi Tian, Hossein Estiri Published: 2025-10-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.18841v1 Counterfactual inference provides a mathematical framework for reasoning about hypothetical outcomes under alternative interventions, bridging causal reasoning and predictive modeling. We present a counterfactual inference framework for individualized risk estimation and intervention analysis, illustrated through a clinical application to post-acute sequelae of COVID-19 (PASC) among patients with pre-existing heart failure (HF). Using longitudinal diagnosis, laboratory, and medication data from a large health-system cohort, we integrate regularized predictive modeling with counterfactual search to identify actionable pathways to PASC-related HF hospital admissions. The framework combines exact enumeration with optimization-based methods, including the Nearest Instance Counterfactual Explanations (NICE) and Multi-Objective Counterfactuals (MOC) algorithms, to efficiently explore high-dimensional intervention spaces. Applied to more than 2700 individuals with confirmed SARS-CoV-2 infection and prior HF, the model achieved strong discriminative performance (AUROC: 0.88, 95% CI: 0.84-0.91) and generated interpretable, patient-specific counterfactuals that quantify how modifying comorbidity patterns or treatment factors could alter predicted outcomes. This work demonstrates how counterfactual reasoning can be formalized as an optimization problem over predictive functions, offering a rigorous, interpretable, and computationally efficient approach to personalized inference in complex biomedical systems. --- ### See the Text: From Tokenization to Visual Reading Authors: Ling Xing, Rui Yan, Alex Jinpeng Wang, Zechao Li, Jinhui Tang Published: 2025-10-21 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2510.18840v2 People see text. Humans read by recognizing words as visual objects, including their shapes, layouts, and patterns, before connecting them to meaning, which enables us to handle typos, distorted fonts, and various scripts effectively. Modern large language models (LLMs), however, rely on subword tokenization, fragmenting text into pieces from a fixed vocabulary. While effective for high-resource languages, this approach over-segments low-resource languages, yielding long, linguistically meaningless sequences and inflating computation. In this work, we challenge this entrenched paradigm and move toward a vision-centric alternative. Our method, SeeTok, renders text as images (visual-text) and leverages pretrained multimodal LLMs to interpret them, reusing strong OCR and text-vision alignment abilities learned from large-scale multimodal training. Across three different language tasks, SeeTok matches or surpasses subword tokenizers while requiring 4.43 times fewer tokens and reducing FLOPs by 70.5%, with additional gains in cross-lingual generalization, robustness to typographic noise, and linguistic hierarchy. SeeTok signals a shift from symbolic tokenization to human-like visual reading, and takes a step toward more natural and cognitively inspired language models. --- ### FedDEAP: Adaptive Dual-Prompt Tuning for Multi-Domain Federated Learning Authors: Yubin Zheng, Pak-Hei Yeung, Jing Xia, Tianjie Ju, Peng Tang, Weidong Qiu, Jagath C. Rajapakse Published: 2025-10-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.18837v1 Federated learning (FL) enables multiple clients to collaboratively train machine learning models without exposing local data, balancing performance and privacy. However, domain shift and label heterogeneity across clients often hinder the generalization of the aggregated global model. Recently, large-scale vision-language models like CLIP have shown strong zero-shot classification capabilities, raising the question of how to effectively fine-tune CLIP across domains in a federated setting. In this work, we propose an adaptive federated prompt tuning framework, FedDEAP, to enhance CLIP's generalization in multi-domain scenarios. Our method includes the following three key components: (1) To mitigate the loss of domain-specific information caused by label-supervised tuning, we disentangle semantic and domain-specific features in images by using semantic and domain transformation networks with unbiased mappings; (2) To preserve domain-specific knowledge during global prompt aggregation, we introduce a dual-prompt design with a global semantic prompt and a local domain prompt to balance shared and personalized information; (3) To maximize the inclusion of semantic and domain information from images in the generated text features, we align textual and visual representations under the two learned transformations to preserve semantic and domain consistency. Theoretical analysis and extensive experiments on four datasets demonstrate the effectiveness of our method in enhancing the generalization of CLIP for federated image recognition across multiple domains. --- ### MTraining: Distributed Dynamic Sparse Attention for Efficient Ultra-Long Context Training Authors: Wenxuan Li, Chengruidong Zhang, Huiqiang Jiang, Yucheng Li, Yuqing Yang, Lili Qiu Published: 2025-10-21 Categories: cs.CL, cs.DC, cs.LG arXiv: https://arxiv.org/abs/2510.18830v2 The adoption of long context windows has become a standard feature in Large Language Models (LLMs), as extended contexts significantly enhance their capacity for complex reasoning and broaden their applicability across diverse scenarios. Dynamic sparse attention is a promising approach for reducing the computational cost of long-context. However, efficiently training LLMs with dynamic sparse attention on ultra-long contexts-especially in distributed settings-remains a significant challenge, due in large part to worker- and step-level imbalance. This paper introduces MTraining, a novel distributed methodology leveraging dynamic sparse attention to enable efficient training for LLMs with ultra-long contexts. Specifically, MTraining integrates three key components: a dynamic sparse training pattern, balanced sparse ring attention, and hierarchical sparse ring attention. These components are designed to synergistically address the computational imbalance and communication overheads inherent in dynamic sparse attention mechanisms during the training of models with extensive context lengths. We demonstrate the efficacy of MTraining by training Qwen2.5-3B, successfully expanding its context window from 32K to 512K tokens on a cluster of 32 A100 GPUs. Our evaluations on a comprehensive suite of downstream tasks, including RULER, PG-19, InfiniteBench, and Needle In A Haystack, reveal that MTraining achieves up to a 6x higher training throughput while preserving model accuracy. Our code is available at https://github.com/microsoft/MInference/tree/main/MTraining. --- ### Actor-Free Continuous Control via Structurally Maximizable Q-Functions Authors: Yigit Korkmaz, Urvi Bhuwania, Ayush Jain, Erdem Bıyık Published: 2025-10-21 Categories: cs.LG, cs.AI, cs.RO, stat.ML arXiv: https://arxiv.org/abs/2510.18828v1 Value-based algorithms are a cornerstone of off-policy reinforcement learning due to their simplicity and training stability. However, their use has traditionally been restricted to discrete action spaces, as they rely on estimating Q-values for individual state-action pairs. In continuous action spaces, evaluating the Q-value over the entire action space becomes computationally infeasible. To address this, actor-critic methods are typically employed, where a critic is trained on off-policy data to estimate Q-values, and an actor is trained to maximize the critic's output. Despite their popularity, these methods often suffer from instability during training. In this work, we propose a purely value-based framework for continuous control that revisits structural maximization of Q-functions, introducing a set of key architectural and algorithmic choices to enable efficient and stable learning. We evaluate the proposed actor-free Q-learning approach on a range of standard simulation tasks, demonstrating performance and sample efficiency on par with state-of-the-art baselines, without the cost of learning a separate actor. Particularly, in environments with constrained action spaces, where the value functions are typically non-smooth, our method with structural maximization outperforms traditional actor-critic methods with gradient-based maximization. We have released our code at https://github.com/USC-Lira/Q3C. --- ### SO(3)-invariant PCA with application to molecular data Authors: Michael Fraiman, Paulina Hoyos, Tamir Bendory, Joe Kileel, Oscar Mickelin, Nir Sharon, Amit Singer Published: 2025-10-21 Categories: eess.SP, cs.LG arXiv: https://arxiv.org/abs/2510.18827v1 Principal component analysis (PCA) is a fundamental technique for dimensionality reduction and denoising; however, its application to three-dimensional data with arbitrary orientations -- common in structural biology -- presents significant challenges. A naive approach requires augmenting the dataset with many rotated copies of each sample, incurring prohibitive computational costs. In this paper, we extend PCA to 3D volumetric datasets with unknown orientations by developing an efficient and principled framework for SO(3)-invariant PCA that implicitly accounts for all rotations without explicit data augmentation. By exploiting underlying algebraic structure, we demonstrate that the computation involves only the square root of the total number of covariance entries, resulting in a substantial reduction in complexity. We validate the method on real-world molecular datasets, demonstrating its effectiveness and opening up new possibilities for large-scale, high-dimensional reconstruction problems. --- ### An AI enhanced approach to the tree unimodality conjecture Authors: Eric Ramos, Sunny Sun Published: 2025-10-21 Categories: math.CO, cs.AI, cs.DM, cs.LG arXiv: https://arxiv.org/abs/2510.18826v2 Given a graph $G$, its independence sequence is the integral sequence $a_1,a_2,...,a_n$, where $a_i$ is the number of independent sets of vertices of size i. In the late 80's Alavi, Erdos, Malde, Schwenk showed that this sequence need not be unimodal for general graphs, but conjectured that it is always unimodal whenever $G$ is a tree. This conjecture was then naturally generalized to claim that the independence sequence of trees should be log concave, in the sense that $a_i^2$ is always above $a_{i-1}a_{i+1}$. This conjecture stood for many years, until in 2023, Kadrawi, Levit, Yosef, and Mizrachi proved that there were exactly two trees on 26 vertices whose independence sequence was not log concave. In this paper, we use the AI architecture PatternBoost, developed by Charton, Ellenberg, Wagner, and Williamson to train a machine to find counter-examples to the log-concavity conjecture. We will discuss the successes of this approach - finding tens of thousands of new counter-examples to log-concavity with vertex set sizes varying from 27 to 101 - and some of its fascinating failures. --- ### Unifying and Enhancing Graph Transformers via a Hierarchical Mask Framework Authors: Yujie Xing, Xiao Wang, Bin Wu, Hai Huang, Chuan Shi Published: 2025-10-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.18825v1 Graph Transformers (GTs) have emerged as a powerful paradigm for graph representation learning due to their ability to model diverse node interactions. However, existing GTs often rely on intricate architectural designs tailored to specific interactions, limiting their flexibility. To address this, we propose a unified hierarchical mask framework that reveals an underlying equivalence between model architecture and attention mask construction. This framework enables a consistent modeling paradigm by capturing diverse interactions through carefully designed attention masks. Theoretical analysis under this framework demonstrates that the probability of correct classification positively correlates with the receptive field size and label consistency, leading to a fundamental design principle: an effective attention mask should ensure both a sufficiently large receptive field and a high level of label consistency. While no single existing mask satisfies this principle across all scenarios, our analysis reveals that hierarchical masks offer complementary strengths, motivating their effective integration. Then, we introduce M3Dphormer, a Mixture-of-Experts-based Graph Transformer with Multi-Level Masking and Dual Attention Computation. M3Dphormer incorporates three theoretically grounded hierarchical masks and employs a bi-level expert routing mechanism to adaptively integrate multi-level interaction information. To ensure scalability, we further introduce a dual attention computation scheme that dynamically switches between dense and sparse modes based on local mask sparsity. Extensive experiments across multiple benchmarks demonstrate that M3Dphormer achieves state-of-the-art performance, validating the effectiveness of our unified framework and model design. --- ### BO4Mob: Bayesian Optimization Benchmarks for High-Dimensional Urban Mobility Problem Authors: Seunghee Ryu, Donghoon Kwon, Seongjin Choi, Aryan Deshwal, Seungmo Kang, Carolina Osorio Published: 2025-10-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.18824v1 We introduce \textbf{BO4Mob}, a new benchmark framework for high-dimensional Bayesian Optimization (BO), driven by the challenge of origin-destination (OD) travel demand estimation in large urban road networks. Estimating OD travel demand from limited traffic sensor data is a difficult inverse optimization problem, particularly in real-world, large-scale transportation networks. This problem involves optimizing over high-dimensional continuous spaces where each objective evaluation is computationally expensive, stochastic, and non-differentiable. BO4Mob comprises five scenarios based on real-world San Jose, CA road networks, with input dimensions scaling up to 10,100. These scenarios utilize high-resolution, open-source traffic simulations that incorporate realistic nonlinear and stochastic dynamics. We demonstrate the benchmark's utility by evaluating five optimization methods: three state-of-the-art BO algorithms and two non-BO baselines. This benchmark is designed to support both the development of scalable optimization algorithms and their application for the design of data-driven urban mobility models, including high-resolution digital twins of metropolitan road networks. Code and documentation are available at https://github.com/UMN-Choi-Lab/BO4Mob. --- ### SAM 2++: Tracking Anything at Any Granularity Authors: Jiaming Zhang, Cheng Liang, Yichun Yang, Chenkai Zeng, Yutao Cui, Xinwen Zhang, Xin Zhou, Kai Ma, Gangshan Wu, Limin Wang Published: 2025-10-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.18822v4 Due to the varying granularity of target states across different tasks, most existing trackers are tailored to a single task, which specificity limits their generalization, preventing them from effectively utilizing multi-task training data and leading to redundancy in both model design and parameters. Although recent unified vision models share partial architectures across tasks, they usually retain task-specific interfaces and overlook the common tracking principle behind different granularities, leaving a gap for truly unified video tracking. To unify video tracking tasks, we present SAM 2++, a unified framework that can handle target states at different granularities, including masks, boxes, and points, through an integrated design of prompt encoding, output decoding, and memory representation. First, to handle different target granularities, we design task-specific prompts that map diverse task inputs into general prompt embeddings, together with a Unified Decoder that produces task results in a common output form without redesigning the overall pipeline. Next, to satisfy memory matching, the core operation of tracking, we introduce a task-adaptive memory mechanism that unifies memory across different granularities while preserving their distinct state semantics, preventing full parameter sharing from causing interference across granularities. Finally, we introduce Tracking-Any-Granularity, the first large and diverse video tracking dataset with rich annotations at three granularities. It is constructed through a customized data engine with phased manual annotation and model-assisted completion, providing a comprehensive resource for training, benchmarking, and analyzing unified tracking models. Comprehensive experiments confirm that SAM 2++ sets a new state of the art across diverse tracking tasks at different granularities, establishing a unified and robust tracking framework. --- ### Search Self-play: Pushing the Frontier of Agent Capability without Supervision Authors: Hongliang Lu, Yuhang Wen, Pengyu Cheng, Ruijin Ding, Jiaqi Guo, Haotian Xu, Chutian Wang, Haonan Chen, Xiaoxi Jiang, Guanjun Jiang Published: 2025-10-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.18821v3 Reinforcement learning with verifiable rewards (RLVR) has become the mainstream technique for training LLM agents. However, RLVR highly depends on well-crafted task queries and corresponding ground-truth answers to provide accurate rewards, which requires significant human effort and hinders the scaling of RL processes, especially in agentic scenarios. Although a few recent works explore task synthesis methods, the difficulty of generated agentic tasks can hardly be controlled to provide effective RL training advantages. To achieve agentic RLVR with higher scalability, we explore self-play training for deep search agents, in which the learning LLM utilizes multi-turn search engine calling and acts simultaneously as both a task proposer and a problem solver. The task proposer aims to generate deep search queries with well-defined ground-truth answers and increasing task difficulty. The problem solver tries to handle the generated search queries and output the correct answer predictions. To ensure that each generated search query has accurate ground truth, we collect all the searching results from the proposer's trajectory as external knowledge, then conduct retrieval-augmentation generation (RAG) to test whether the proposed query can be correctly answered with all necessary search documents provided. In this search self-play (SSP) game, the proposer and the solver co-evolve their agent capabilities through both competition and cooperation. With substantial experimental results, we find that SSP can significantly improve search agents' performance uniformly on various benchmarks without any supervision under both from-scratch and continuous RL training setups. The code is at https://github.com/Qwen-Applications/SSP. ---