# Research Papers — 2025-10 · bundle page 135 of 217

> Full-text markdown of papers #6701–6750 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/135
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/134.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/136.md)

### Integrating Large Language Models and Reinforcement Learning for Sentiment-Driven Quantitative Trading

Authors: Wo Long, Wenxin Zeng, Xiaoyu Zhang, Ziyao Zhou
Published: 2025-10-12
Categories: q-fin.CP, cs.LG
arXiv: https://arxiv.org/abs/2510.10526v1

This research develops a sentiment-driven quantitative trading system that leverages a large language model, FinGPT, for sentiment analysis, and explores a novel method for signal integration using a reinforcement learning algorithm, Twin Delayed Deep Deterministic Policy Gradient (TD3). We compare the performance of strategies that integrate sentiment and technical signals using both a conventional rule-based approach and a reinforcement learning framework. The results suggest that sentiment signals generated by FinGPT offer value when combined with traditional technical indicators, and that reinforcement learning algorithm presents a promising approach for effectively integrating heterogeneous signals in dynamic trading environments.

---

### Unified Open-World Segmentation with Multi-Modal Prompts

Authors: Yang Liu, Yufei Yin, Chenchen Jing, Muzhi Zhu, Hao Chen, Yuling Xi, Bo Feng, Hao Wang, Shiyu Li, Chunhua Shen
Published: 2025-10-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.10524v1

In this work, we present COSINE, a unified open-world segmentation model that consolidates open-vocabulary segmentation and in-context segmentation with multi-modal prompts (e.g., text and image). COSINE exploits foundation models to extract representations for an input image and corresponding multi-modal prompts, and a SegDecoder to align these representations, model their interaction, and obtain masks specified by input prompts across different granularities. In this way, COSINE overcomes architectural discrepancies, divergent learning objectives, and distinct representation learning strategies of previous pipelines for open-vocabulary segmentation and in-context segmentation. Comprehensive experiments demonstrate that COSINE has significant performance improvements in both open-vocabulary and in-context segmentation tasks. Our exploratory analyses highlight that the synergistic collaboration between using visual and textual prompts leads to significantly improved generalization over single-modality approaches.

---

### Receptive Field Expanded Look-Up Tables for Vision Inference: Advancing from Low-level to High-level Tasks

Authors: Xi Zhang, Xiaolin Wu
Published: 2025-10-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.10522v1

Recently, several look-up table (LUT) methods were developed to greatly expedite the inference of CNNs in a classical strategy of trading space for speed. However, these LUT methods suffer from a common drawback of limited receptive field of the convolution kernels due to the combinatorial explosion of table size. This research aims to expand the CNN receptive field with a fixed table size, thereby enhancing the performance of LUT-driven fast CNN inference while maintaining the same space complexity. To achieve this goal, various techniques are proposed. The main contribution is a novel approach of learning an optimal lattice vector quantizer that adaptively allocates the quantization resolution across data dimensions based on their significance to the inference task. In addition, the lattice vector quantizer offers an inherently more accurate approximation of CNN kernels than scalar quantizer as used in current practice. Furthermore, we introduce other receptive field expansion strategies, including irregular dilated convolutions and a U-shaped cascaded LUT structure, designed to capture multi-level contextual information without inflating table size. Together, these innovations allow our approach to effectively balance speed, accuracy, and memory efficiency, demonstrating significant improvements over existing LUT methods.

---

### VR-Thinker: Boosting Video Reward Models through Thinking-with-Image Reasoning

Authors: Qunzhong Wang, Jie Liu, Jiajun Liang, Yilei Jiang, Yuanxing Zhang, Yaozhi Zheng, Xintao Wang, Pengfei Wan, Xiangyu Yue, Jiaheng Liu
Published: 2025-10-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.10518v4

Recent advancements in multimodal reward models (RMs) have substantially improved post-training for visual generative models. However, current RMs face inherent limitations: (1) visual inputs consume large context budgets, forcing fewer frames and causing loss of fine-grained details; and (2) all visual information is packed into the initial prompt, exacerbating hallucination and forgetting during chain-of-thought reasoning. To overcome these issues, we introduce VideoReward Thinker (VR-Thinker), a thinking-with-image framework that equips the RM with visual reasoning operations (e.g., select frame) and a configurable visual memory window. This allows the RM to actively acquire and update visual evidence within context limits, improving reasoning fidelity and reliability. We activate visual reasoning via a reinforcement fine-tuning pipeline: (i) Cold Start with curated visual chain-of-thought data to distill basic reasoning skills and operation formatting; (ii) select samples whose per-dimension and overall judgments are all correct, then conduct Rejection sampling Fine-Tuning on these high-quality traces to further enhance reasoning; and (iii) apply Group Relative Policy Optimization (GRPO) to strengthen reasoning. Our approach delivers state-of-the-art accuracy among open-source models on video preference benchmarks, especially for longer videos: a 7B VR-Thinker achieves 80.5% on VideoGen Reward, 82.3% on GenAI-Bench, and 75.6% on MJ-Bench-Video. These results validate the effectiveness and promise of thinking-with-image multimodal reward modeling.

---

### ECO: Enhanced Code Optimization via Performance-Aware Prompting for Code-LLMs

Authors: Su-Hyeon Kim, Joonghyuk Hahn, Sooyoung Cha, Yo-Sub Han
Published: 2025-10-12
Categories: cs.PL, cs.AI, cs.SE
arXiv: https://arxiv.org/abs/2510.10517v1

Code runtime optimization-the task of rewriting a given code to a faster one-remains challenging, as it requires reasoning about performance trade-offs involving algorithmic and structural choices. Recent approaches employ code-LLMs with slow-fast code pairs provided as optimization guidance, but such pair-based methods obscure the causal factors of performance gains and often lead to superficial pattern imitation rather than genuine performance reasoning. We introduce ECO, a performance-aware prompting framework for code optimization. ECO first distills runtime optimization instructions (ROIs) from reference slow-fast code pairs; Each ROI describes root causes of inefficiency and the rationales that drive performance improvements. For a given input code, ECO in parallel employs (i) a symbolic advisor to produce a bottleneck diagnosis tailored to the code, and (ii) an ROI retriever to return related ROIs. These two outputs are then composed into a performance-aware prompt, providing actionable guidance for code-LLMs. ECO's prompts are model-agnostic, require no fine-tuning, and can be easily prepended to any code-LLM prompt. Our empirical studies highlight that ECO prompting significantly improves code-LLMs' ability to generate efficient code, achieving speedups of up to 7.81x while minimizing correctness loss.

---

### Population-Coded Spiking Neural Networks for High-Dimensional Robotic Control

Authors: Kanishkha Jaisankar, Xiaoyang Jiang, Feifan Liao, Jeethu Sreenivas Amuthan
Published: 2025-10-12
Categories: cs.RO, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.10516v1

Energy-efficient and high-performance motor control remains a critical challenge in robotics, particularly for high-dimensional continuous control tasks with limited onboard resources. While Deep Reinforcement Learning (DRL) has achieved remarkable results, its computational demands and energy consumption limit deployment in resource-constrained environments. This paper introduces a novel framework combining population-coded Spiking Neural Networks (SNNs) with DRL to address these challenges. Our approach leverages the event-driven, asynchronous computation of SNNs alongside the robust policy optimization capabilities of DRL, achieving a balance between energy efficiency and control performance. Central to this framework is the Population-coded Spiking Actor Network (PopSAN), which encodes high-dimensional observations into neuronal population activities and enables optimal policy learning through gradient-based updates. We evaluate our method on the Isaac Gym platform using the PixMC benchmark with complex robotic manipulation tasks. Experimental results on the Franka robotic arm demonstrate that our approach achieves energy savings of up to 96.10% compared to traditional Artificial Neural Networks (ANNs) while maintaining comparable control performance. The trained SNN policies exhibit robust finger position tracking with minimal deviation from commanded trajectories and stable target height maintenance during pick-and-place operations. These results position population-coded SNNs as a promising solution for energy-efficient, high-performance robotic control in resource-constrained applications, paving the way for scalable deployment in real-world robotics systems.

---

### A Hybrid Machine Learning Approach for Synthetic Data Generation with Post Hoc Calibration for Clinical Tabular Datasets

Authors: Md Ibrahim Shikder Mahin, Md Shamsul Arefin, Md Tanvir Hasan
Published: 2025-10-12
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.10513v2

Healthcare research and development face significant obstacles due to data scarcity and stringent privacy regulations, such as HIPAA and the GDPR, restricting access to essential real-world medical data. These limitations impede innovation, delay robust AI model creation, and hinder advancements in patient-centered care. Synthetic data generation offers a transformative solution by producing artificial datasets that emulate real data statistics while safeguarding patient privacy. We introduce a novel hybrid framework for high-fidelity healthcare data synthesis integrating five augmentation methods: noise injection, interpolation, Gaussian Mixture Model (GMM) sampling, Conditional Variational Autoencoder (CVAE) sampling, and SMOTE, combined via a reinforcement learning-based dynamic weight selection mechanism. Its key innovations include advanced calibration techniques -- moment matching, full histogram matching, soft and adaptive soft histogram matching, and iterative refinement -- that align marginal distributions and preserve joint feature dependencies. Evaluated on the Breast Cancer Wisconsin (UCI Repository) and Khulna Medical College cardiology datasets, our calibrated hybrid achieves Wasserstein distances as low as 0.001 and Kolmogorov-Smirnov statistics around 0.01, demonstrating near-zero marginal discrepancy. Pairwise trend scores surpass 90%, and Nearest Neighbor Adversarial Accuracy approaches 50%, confirming robust privacy protection. Downstream classifiers trained on synthetic data achieve up to 94% accuracy and F1 scores above 93%, comparable to models trained on real data. This scalable, privacy-preserving approach matches state-of-the-art methods, sets new benchmarks for joint-distribution fidelity in healthcare, and supports sensitive AI applications.

---

### f-INE: A Hypothesis Testing Framework for Estimating Influence under Training Randomness

Authors: Subhodip Panda, Dhruv Tarsadiya, Shashwat Sourav, Prathosh A. P, Sai Praneeth Karimireddy
Published: 2025-10-12
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.10510v2

Influence estimation methods promise to explain and debug machine learning by estimating the impact of individual samples on the final model. Yet, existing methods collapse under training randomness: the same example may appear critical in one run and irrelevant in the next. Such instability undermines their use in data curation or cleanup since it is unclear if we indeed deleted/kept the correct datapoints. To overcome this, we introduce *f-influence* -- a new influence estimation framework grounded in hypothesis testing that explicitly accounts for training randomness, and establish desirable properties that make it suitable for reliable influence estimation. We also design a highly efficient algorithm **f**-**IN**fluence **E**stimation (**f-INE**) that computes f-influence **in a single training run**. Finally, we scale up f-INE to estimate influence of instruction tuning data on Llama-3.1-8B and show it can reliably detect poisoned samples that steer model opinions, demonstrating its utility for data cleanup and attributing model behavior.

---

### MARS-Sep: Multimodal-Aligned Reinforced Sound Separation

Authors: Zihan Zhang, Xize Cheng, Zhennan Jiang, Dongjie Fu, Jingyuan Chen, Zhou Zhao, Tao Jin
Published: 2025-10-12
Categories: cs.SD, cs.AI
arXiv: https://arxiv.org/abs/2510.10509v2

Universal sound separation faces a fundamental misalignment: models optimized for low-level signal metrics often produce semantically contaminated outputs, failing to suppress perceptually salient interference from acoustically similar sources. We introduce a preference alignment perspective, analogous to aligning LLMs with human intent. To address this, we introduce MARS-Sep, a reinforcement learning framework that reformulates separation as decision making. Instead of simply regressing ground-truth masks, MARS-Sep learns a factorized Beta mask policy that is steered by a preference reward model and optimized by a stable, clipped trust-region surrogate. The reward, derived from a progressively-aligned audio-text-vision encoder, directly incentivizes semantic consistency with query prompts. Extensive experiments on multiple benchmarks demonstrate consistent gains in Text-, Audio-, and Image-Queried separation, with notable improvements in signal metrics and semantic quality. Our code is available at https://github.com/mars-sep/MARS-Sep. Sound separation samples are available at https://mars-sep.github.io/.

---

### SuperEx: Enhancing Indoor Mapping and Exploration using Non-Line-of-Sight Perception

Authors: Kush Garg, Akshat Dave
Published: 2025-10-12
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2510.10506v1

Efficient exploration and mapping in unknown indoor environments is a fundamental challenge, with high stakes in time-critical settings. In current systems, robot perception remains confined to line-of-sight; occluded regions remain unknown until physically traversed, leading to inefficient exploration when layouts deviate from prior assumptions. In this work, we bring non-line-of-sight (NLOS) sensing to robotic exploration. We leverage single-photon LiDARs, which capture time-of-flight histograms that encode the presence of hidden objects - allowing robots to look around blind corners. Recent single-photon LiDARs have become practical and portable, enabling deployment beyond controlled lab settings. Prior NLOS works target 3D reconstruction in static, lab-based scenarios, and initial efforts toward NLOS-aided navigation consider simplified geometries. We introduce SuperEx, a framework that integrates NLOS sensing directly into the mapping-exploration loop. SuperEx augments global map prediction with beyond-line-of-sight cues by (i) carving empty NLOS regions from timing histograms and (ii) reconstructing occupied structure via a two-step physics-based and data-driven approach that leverages structural regularities. Evaluations on complex simulated maps and the real-world KTH Floorplan dataset show a 12% gain in mapping accuracy under < 30% coverage and improved exploration efficiency compared to line-of-sight baselines, opening a path to reliable mapping beyond direct visibility.

---

### Align2Act: Instruction-Tuned Models for Human-Aligned Autonomous Driving

Authors: Kanishkha Jaisankar, Sunidhi Tandel
Published: 2025-10-12
Categories: cs.LG, cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2510.10503v1

Motion planning in complex scenarios is a core challenge in autonomous driving. Conventional methods apply predefined rules or learn from driving data to generate trajectories, while recent approaches leverage large language models (LLMs) for decision-making. However, it remains unclear whether LLMs truly capture human driving logic. We propose Align2Act, a motion planning framework that transforms instruction-tuned LLMs into interpretable planners aligned with human behavior. We derive structured driving instructions based on human reasoning patterns (e.g., anticipate hazards, yield at intersections) and traffic rules (e.g., stop at red lights, maintain lane boundaries). Our Align2ActChain module guides step-by-step reasoning to produce both an interpretable rationale and a safe trajectory. By fine-tuning LLaMA-2-7B with LoRA on one million scenarios from the nuPlan dataset, our method achieves an open-loop score of 85.17 and closed-loop scores of 70.31 (non-reactive) and 66.96 (reactive) on Test14-random. Unlike prior work focused on synthetic or open-loop settings, we demonstrate improved planning quality and human-likeness on the real-world nuPlan closed-loop benchmark. Ablation studies confirm that structured reasoning significantly improves performance over baseline LLM planners.

---

### Jigsaw3D: Disentangled 3D Style Transfer via Patch Shuffling and Masking

Authors: Yuteng Ye, Zheng Zhang, Qinchuan Zhang, Di Wang, Youjia Zhang, Wenxiao Zhang, Wei Yang, Yuan Liu
Published: 2025-10-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.10497v1

Controllable 3D style transfer seeks to restyle a 3D asset so that its textures match a reference image while preserving the integrity and multi-view consistency. The prevalent methods either rely on direct reference style token injection or score-distillation from 2D diffusion models, which incurs heavy per-scene optimization and often entangles style with semantic content. We introduce Jigsaw3D, a multi-view diffusion based pipeline that decouples style from content and enables fast, view-consistent stylization. Our key idea is to leverage the jigsaw operation - spatial shuffling and random masking of reference patches - to suppress object semantics and isolate stylistic statistics (color palettes, strokes, textures). We integrate these style cues into a multi-view diffusion model via reference-to-view cross-attention, producing view-consistent stylized renderings conditioned on the input mesh. The renders are then style-baked onto the surface to yield seamless textures. Across standard 3D stylization benchmarks, Jigsaw3D achieves high style fidelity and multi-view consistency with substantially lower latency, and generalizes to masked partial reference stylization, multi-object scene styling, and tileable texture generation. Project page is available at: https://babahui.github.io/jigsaw3D.github.io/

---

### Personalized Motion Guidance Framework for Athlete-Centric Coaching

Authors: Ryota Takamido, Chiharu Suzuki, Hiroki Nakamoto
Published: 2025-10-12
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2510.10496v2

A critical challenge in contemporary sports science lies in filling the gap between group-level insights derived from controlled hypothesis-driven experiments and the real-world need for personalized coaching tailored to individual athletes' unique movement patterns. This study developed a Personalized Motion Guidance Framework (PMGF) to enhance athletic performance by generating individualized motion-refinement guides using generative artificial intelligence techniques. PMGF leverages a vertical autoencoder to encode motion sequences into athlete-specific latent representations, which can then be directly manipulated to generate meaningful guidance motions. Two manipulation strategies were explored: (1) smooth interpolation between the learner's motion and a target (e.g., expert) motion to facilitate observational learning, and (2) shifting the motion pattern in an optimal direction in the latent space using a local optimization technique. The results of the validation experiment with data from 51 baseball pitchers revealed that (1) PMGF successfully generated smooth transitions in motion patterns between individuals across all 1,275 pitcher pairs, and (2) the features significantly altered through PMGF manipulations reflected known performance-enhancing characteristics, such as increased stride length and knee extension associated with higher ball velocity, indicating that PMGF induces biomechanically plausible improvements. We propose a future extension called general-PMGF to enhance the applicability of this framework. This extension incorporates bodily, environmental, and task constraints into the generation process, aiming to provide more realistic and versatile guidance across diverse sports contexts.

---

### Tracing the Traces: Latent Temporal Signals for Efficient and Accurate Reasoning

Authors: Martina G. Vilas, Safoora Yousefi, Besmira Nushi, Eric Horvitz, Vidhisha Balachandran
Published: 2025-10-12
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.10494v1

Reasoning models improve their problem-solving ability through inference-time scaling, allocating more compute via longer token budgets. Identifying which reasoning traces are likely to succeed remains a key opportunity: reliably predicting productive paths can substantially reduce wasted computation and improve overall efficiency. We introduce Latent-Trajectory signals that characterize the temporal evolution of a model's internal representations during the generation of intermediate reasoning tokens. By measuring the overall change in latent representations between the start and end of reasoning, the change accumulated across intermediate steps, and the extent to which these changes advance toward the final state, we show that these signals predict solution accuracy more reliably than both cross-layer metrics and output-based confidence measures. When used to guide answer selection across multiple sampled generations, Latent-Trajectory signals make test-time scaling more effective and efficient than majority voting, reducing token usage by up to 70% while preserving and even improving accuracy by 2.6% on average. Moreover, these predictive signals often emerge early in the reasoning trace, enabling early selection and allocation of compute to the most promising candidates. Our findings contribute not only practical strategies for inference-time efficiency, but also a deeper interpretability perspective on how reasoning processes are represented and differentiated in latent space.

---

### The Hidden DNA of LLM-Generated JavaScript: Structural Patterns Enable High-Accuracy Authorship Attribution

Authors: Norbert Tihanyi, Bilel Cherif, Richard A. Dubniczky, Mohamed Amine Ferrag, Tamás Bisztray
Published: 2025-10-12
Categories: cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2510.10493v2

In this paper, we present the first large-scale study exploring whether JavaScript code generated by Large Language Models (LLMs) can reveal which model produced it, enabling reliable authorship attribution and model fingerprinting. With the rapid rise of AI-generated code, attribution is playing a critical role in detecting vulnerabilities, flagging malicious content, and ensuring accountability. While AI-vs-human detection usually treats AI as a single category we show that individual LLMs leave unique stylistic signatures, even among models belonging to the same family or parameter size. To this end, we introduce LLM-NodeJS, a dataset of 50,000 Node.js back-end programs from 20 large language models. Each has four transformed variants, yielding 250,000 unique JavaScript samples and two additional representations (JSIR and AST) for diverse research applications. Using this dataset, we benchmark traditional machine learning classifiers against fine-tuned Transformer encoders and introduce CodeT5-JSA, a custom architecture derived from the 770M-parameter CodeT5 model with its decoder removed and a modified classification head. It achieves 95.8% accuracy on five-class attribution, 94.6% on ten-class, and 88.5% on twenty-class tasks, surpassing other tested models such as BERT, CodeBERT, and Longformer. We demonstrate that classifiers capture deeper stylistic regularities in program dataflow and structure, rather than relying on surface-level features. As a result, attribution remains effective even after mangling, comment removal, and heavy code transformations. To support open science and reproducibility, we release the LLM-NodeJS dataset, Google Colab training scripts, and all related materials on GitHub: https://github.com/LLM-NodeJS-dataset.

---

### Towards Efficient 3D Gaussian Human Avatar Compression: A Prior-Guided Framework

Authors: Shanzhi Yin, Bolin Chen, Xinju Wu, Ru-Ling Liao, Jie Chen, Shiqi Wang, Yan Ye
Published: 2025-10-12
Categories: eess.IV, cs.CV, cs.MM
arXiv: https://arxiv.org/abs/2510.10492v1

This paper proposes an efficient 3D avatar coding framework that leverages compact human priors and canonical-to-target transformation to enable high-quality 3D human avatar video compression at ultra-low bit rates. The framework begins by training a canonical Gaussian avatar using articulated splatting in a network-free manner, which serves as the foundation for avatar appearance modeling. Simultaneously, a human-prior template is employed to capture temporal body movements through compact parametric representations. This decomposition of appearance and temporal evolution minimizes redundancy, enabling efficient compression: the canonical avatar is shared across the sequence, requiring compression only once, while the temporal parameters, consisting of just 94 parameters per frame, are transmitted with minimal bit-rate. For each frame, the target human avatar is generated by deforming canonical avatar via Linear Blend Skinning transformation, facilitating temporal coherent video reconstruction and novel view synthesis. Experimental results demonstrate that the proposed method significantly outperforms conventional 2D/3D codecs and existing learnable dynamic 3D Gaussian splatting compression method in terms of rate-distortion performance on mainstream multi-view human video datasets, paving the way for seamless immersive multimedia experiences in meta-verse applications.

---

### VOLTAGE: A Versatile Contrastive Learning based OCR Methodology for ultra low-resource scripts through Auto Glyph Feature Extraction

Authors: Prawaal Sharma, Poonam Goyal, Vidisha Sharma, Navneet Goyal
Published: 2025-10-12
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.10490v1

UNESCO has classified 2500 out of 7000 languages spoken worldwide as endangered. Attrition of a language leads to loss of traditional wisdom, folk literature, and the essence of the community that uses it. It is therefore imperative to bring digital inclusion to these languages and avoid its extinction. Low resource languages are at a greater risk of extinction. Lack of unsupervised Optical Character Recognition(OCR) methodologies for low resource languages is one of the reasons impeding their digital inclusion. We propose VOLTAGE - a contrastive learning based OCR methodology, leveraging auto-glyph feature recommendation for cluster-based labelling. We augment the labelled data for diversity and volume using image transformations and Generative Adversarial Networks. Voltage has been designed using Takri - a family of scripts used in 16th to 20th century in the Himalayan regions of India. We present results for Takri along with other Indic scripts (both low and high resource) to substantiate the universal behavior of the methodology. An accuracy of 95% for machine printed and 87% for handwritten samples on Takri script has been achieved. We conduct baseline and ablation studies along with building downstream use cases for Takri, demonstrating the usefulness of our work.

---

### Head-wise Adaptive Rotary Positional Encoding for Fine-Grained Image Generation

Authors: Jiaye Li, Baoyou Chen, Hui Li, Zilong Dong, Jingdong Wang, Siyu Zhu
Published: 2025-10-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.10489v2

Transformers rely on explicit positional encoding to model structure in data. While Rotary Position Embedding (RoPE) excels in 1D domains, its application to image generation reveals significant limitations such as fine-grained spatial relation modeling, color cues, and object counting. This paper identifies key limitations of standard multi-dimensional RoPE-rigid frequency allocation, axis-wise independence, and uniform head treatment-in capturing the complex structural biases required for fine-grained image generation. We propose HARoPE, a head-wise adaptive extension that inserts a learnable linear transformation parameterized via singular value decomposition (SVD) before the rotary mapping. This lightweight modification enables dynamic frequency reallocation, semantic alignment of rotary planes, and head-specific positional receptive fields while rigorously preserving RoPE's relative-position property. Extensive experiments on class-conditional ImageNet and text-to-image generation (Flux and MMDiT) demonstrate that HARoPE consistently improves performance over strong RoPE baselines and other extensions. The method serves as an effective drop-in replacement, offering a principled and adaptable solution for enhancing positional awareness in transformer-based image generative models.

---

### Towards Self-Refinement of Vision-Language Models with Triangular Consistency

Authors: Yunlong Deng, Guangyi Chen, Tianpei Gu, Lingjing Kong, Yan Li, Zeyu Tang, Kun Zhang
Published: 2025-10-12
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.10487v1

Vision-Language Models (VLMs) integrate visual knowledge with the analytical capabilities of Large Language Models (LLMs) through supervised visual instruction tuning, using image-question-answer triplets. However, the potential of VLMs trained without supervised instruction remains largely unexplored. This study validates that VLMs possess inherent self-refinement capabilities, enabling them to generate high-quality supervised data without external inputs and thereby learn autonomously. Specifically, to stimulate the self-refinement ability of VLMs, we propose a self-refinement framework based on a Triangular Consistency principle: within the image-query-answer triangle, any masked elements should be consistently and accurately reconstructed. The framework involves three steps: (1) We enable the instruction generation ability of VLMs by adding multi-task instruction tuning like image$\rightarrow$question-answer or image-answer$\rightarrow$question. (2) We generate image-query-answer triplets from unlabeled images and use the Triangular Consistency principle for filtering. (3) The model is further updated using the filtered synthetic data. To investigate the underlying mechanisms behind this self-refinement capability, we conduct a theoretical analysis from a causal perspective. Using the widely recognized LLaVA-1.5 as our baseline, our experiments reveal that the model can autonomously achieve consistent, though deliberately modest, improvements across multiple benchmarks without any external supervision, such as human annotations or environmental feedback. We expect that the insights of this study on the self-refinement ability of VLMs can inspire future research on the learning mechanism of VLMs. Code is available at https://github.com/dengyl20/SRF-LLaVA-1.5.

---

### MEASER: Malware embedding attacks on open-source LLMs

Authors: Ming Tan, Wei Li, Hu Tao, Hailong Ma, Aodi Liu, Qian Chen, Zilong Wang
Published: 2025-10-12
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2510.10486v2

Open-source large language models (LLMs) have demonstrated considerable dominance over proprietary LLMs in resolving neural processing tasks, thanks to the collaborative and sharing nature. Although full access to source codes, model parameters, and training data lays the groundwork for transparency, we argue that such a full-access manner is vulnerable to MEAs, and their ill-effects are not fully understood. In this paper, we conduct a systematic formalization for MEAs on open-source LLMs by enumerating all possible threat models associated with adversary objectives, knowledge, and capabilities. Therein, the threat posed by adversaries with internal knowledge, who inject payloads and triggers during the model sharing phase, is of practical interest. We go even further and propose the first MEA against open-source LLMs, dubbed MEASER, which wields impacts through identifying targeted parameters, embedding payloads, injecting triggers, and executing payloads sequentially. Particularly, MEASER enhances the attack robustness against quantization and parameter-efficient fine-tuning (PEFT) by employing the Magnitude-Adaptive Relative Quantization Index Modulation (MAR-QIM) mechanism, synergized with LDPC codes and spread spectrum modulation. In addition, to achieve stealthiness, MEASER devises the performance-aware importance metric to identify targeted parameters with the least degradation of model performance. Extensive experiments on four popular open-source LLMs show that the stealth rate of MEASER outperforms existing MEAs (for general DNNs) significantly, while consistently achieving a 0 bit error rate (BER) in all settings. Moreover, MEASER also maintains superior stealthiness on quantized models. We appeal for investigations on countermeasures against MEASER in view of the significant attack effectiveness.

---

### Gradient Enhanced Self-Training Physics-Informed Neural Network (gST-PINN) for Solving Nonlinear Partial Differential Equations

Authors: Narayan S Iyer, Bivas Bhaumik, Ram S Iyer, Satyasaran Changdar
Published: 2025-10-12
Categories: cs.LG, physics.comp-ph
arXiv: https://arxiv.org/abs/2510.10483v1

Partial differential equations (PDEs) provide a mathematical foundation for simulating and understanding intricate behaviors in both physical sciences and engineering. With the growing capabilities of deep learning, data$-$driven approaches like Physics$-$Informed Neural Networks (PINNs) have been developed, offering a mesh$-$free, analytic type framework for efficiently solving PDEs across a wide range of applications. However, traditional PINNs often struggle with challenges such as limited precision, slow training dynamics, lack of labeled data availability, and inadequate handling of multi$-$physics interactions. To overcome these challenging issues of PINNs, we proposed a Gradient Enhanced Self$-$Training PINN (gST$-$PINN) method that specifically introduces a gradient based pseudo point self$-$learning algorithm for solving PDEs. We tested the proposed method on three different types of PDE problems from various fields, each representing distinct scenarios. The effectiveness of the proposed method is evident, as the PINN approach for solving the Burgers$'$ equation attains a mean square error (MSE) on the order of $10^{-3}$, while the diffusion$-$sorption equation achieves an MSE on the order of $10^{-4}$ after 12,500 iterations, with no further improvement as the iterations increase. In contrast, the MSE for both PDEs in the gST$-$PINN model continues to decrease, demonstrating better generalization and reaching an MSE on the order of $10^{-5}$ after 18,500 iterations. Furthermore, the results show that the proposed purely semi$-$supervised gST$-$PINN consistently outperforms the standard PINN method in all cases, even when solution of the PDEs are unavailable. It generalizes both PINN and Gradient$-$enhanced PINN (gPINN), and can be effectively applied in scenarios prone to low accuracy and convergence issues, particularly in the absence of labeled data.

---

### UltraLLaDA: Scaling the Context Length to 128K for Diffusion Large Language Models

Authors: Guangxin He, Shen Nie, Fengqi Zhu, Yuankang Zhao, Tianyi Bai, Ran Yan, Jie Fu, Chongxuan Li, Binhang Yuan
Published: 2025-10-12
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.10481v1

Diffusion LLMs have attracted growing interest, with plenty of recent work emphasizing their great potential in various downstream tasks; yet the long-context behavior of diffusion LLMs remains largely uncharted. We present a case study of post-training techniques for extending the context window of diffusion LLMs (i.e., LLaDA) without retraining from scratch. We show that a simple modification to the standard Rotary Positional Embeddings (RoPE) extension effectively accommodates the probabilistic modeling inherent in the diffusion process, enabling stable scaling to longer context ranges. We further compare masking strategies used during post-training and analyze their impact on optimization stability and long-range recall. Instantiating these insights, we introduce UltraLLaDA, a diffusion LLM with a 128K-token context window that, in our empirical evaluation on long-context tasks, significantly outperforms training-free baselines. Our experimental results highlight the special positional extension as a key lever for scaling diffusion LLMs to extended contexts and offer practical guidance for practitioners seeking 128K-scale context via efficient post-training.

---

### Latent Retrieval Augmented Generation of Cross-Domain Protein Binders

Authors: Zishen Zhang, Xiangzhe Kong, Wenbing Huang, Yang Liu
Published: 2025-10-12
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.10480v2

Designing protein binders targeting specific sites, which requires to generate realistic and functional interaction patterns, is a fundamental challenge in drug discovery. Current structure-based generative models are limited in generating nterfaces with sufficient rationality and interpretability. In this paper, we propose Retrieval-Augmented Diffusion for Aligned interface (RADiAnce), a new framework that leverages known interfaces to guide the design of novel binders. By unifying retrieval and generation in a shared contrastive latent space, our model efficiently identifies relevant interfaces for a given binding site and seamlessly integrates them through a conditional latent diffusion generator, enabling cross-domain interface transfer. Extensive exeriments show that RADiAnce significantly outperforms baseline models across multiple metrics, including binding affinity and recovery of geometries and interactions. Additional experimental results validate cross-domain generalization, demonstrating that retrieving interfaces from diverse domains, such as peptides, antibodies, and protein fragments, enhances the generation performance of binders for other domains. Our work establishes a new paradigm for protein binder design that successfully bridges retrieval-based knowledge and generative AI, opening new possibilities for drug discovery.

---

### MSF-Mamba: Motion-aware State Fusion Mamba for Efficient Micro-Gesture Recognition

Authors: Deng Li, Jun Shao, Bohao Xing, Rong Gao, Bihan Wen, Heikki Kälviäinen, Xin Liu
Published: 2025-10-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.10478v2

Micro-gesture recognition (MGR) targets the identification of subtle and fine-grained human motions and requires accurate modeling of both long-range and local spatiotemporal dependencies. While CNNs are effective at capturing local patterns, they struggle with long-range dependencies due to their limited receptive fields. Transformer-based models address this limitation through self-attention mechanisms but suffer from high computational costs. Recently, Mamba has shown promise as an efficient model, leveraging state space models (SSMs) to enable linear-time processing However, directly applying the vanilla Mamba to MGR may not be optimal. This is because Mamba processes inputs as 1D sequences, with state updates relying solely on the previous state, and thus lacks the ability to model local spatiotemporal dependencies. In addition, previous methods lack a design of motion-awareness, which is crucial in MGR. To overcome these limitations, we propose motion-aware state fusion mamba (MSF-Mamba), which enhances Mamba with local spatiotemporal modeling by fusing local contextual neighboring states. Our design introduces a motion-aware state fusion module based on central frame difference (CFD). Furthermore, a multiscale version named MSF-Mamba+ has been proposed. Specifically, MSF-Mamba supports multiscale motion-aware state fusion, as well as an adaptive scale weighting module that dynamically weighs the fused states across different scales. These enhancements explicitly address the limitations of vanilla Mamba by enabling motion-aware local spatiotemporal modeling, allowing MSF-Mamba and MSF-Mamba to effectively capture subtle motion cues for MGR. Experiments on two public MGR datasets demonstrate that even the lightweight version, namely, MSF-Mamba, achieves SoTA performance, outperforming existing CNN-, Transformer-, and SSM-based models while maintaining high efficiency.

---

### Anchor-based Maximum Discrepancy for Relative Similarity Testing

Authors: Zhijian Zhou, Liuhua Peng, Xunye Tian, Feng Liu
Published: 2025-10-12
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.10477v1

The relative similarity testing aims to determine which of the distributions, P or Q, is closer to an anchor distribution U. Existing kernel-based approaches often test the relative similarity with a fixed kernel in a manually specified alternative hypothesis, e.g., Q is closer to U than P. Although kernel selection is known to be important to kernel-based testing methods, the manually specified hypothesis poses a significant challenge for kernel selection in relative similarity testing: Once the hypothesis is specified first, we can always find a kernel such that the hypothesis is rejected. This challenge makes relative similarity testing ill-defined when we want to select a good kernel after the hypothesis is specified. In this paper, we cope with this challenge via learning a proper hypothesis and a kernel simultaneously, instead of learning a kernel after manually specifying the hypothesis. We propose an anchor-based maximum discrepancy (AMD), which defines the relative similarity as the maximum discrepancy between the distances of (U, P) and (U, Q) in a space of deep kernels. Based on AMD, our testing incorporates two phases. In Phase I, we estimate the AMD over the deep kernel space and infer the potential hypothesis. In Phase II, we assess the statistical significance of the potential hypothesis, where we propose a unified testing framework to derive thresholds for tests over different possible hypotheses from Phase I. Lastly, we validate our method theoretically and demonstrate its effectiveness via extensive experiments on benchmark datasets. Codes are publicly available at: https://github.com/zhijianzhouml/AMD.

---

### Assessing Large Language Models for Structured Medical Order Extraction

Authors: A H M Rezaul Karim, Ozlem Uzuner
Published: 2025-10-12
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.10475v1

Medical order extraction is essential for structuring actionable clinical information, supporting decision-making, and enabling downstream applications such as documentation and workflow automation. Orders may be embedded in diverse sources, including electronic health records, discharge summaries, and multi-turn doctor-patient dialogues, and can span categories such as medications, laboratory tests, imaging studies, and follow-up actions. The MEDIQA-OE 2025 shared task focuses on extracting structured medical orders from extended conversational transcripts, requiring the identification of order type, description, reason, and provenance. We present the MasonNLP submission, which ranked 5th among 17 participating teams with 105 total submissions. Our approach uses a general-purpose, instruction-tuned LLaMA-4 17B model without domain-specific fine-tuning, guided by a single in-context example. This few-shot configuration achieved an average F1 score of 37.76, with notable improvements in reason and provenance accuracy. These results demonstrate that large, non-domain-specific LLMs, when paired with effective prompt engineering, can serve as strong, scalable baselines for specialized clinical NLP tasks.

---

### When or What? Understanding Consumer Engagement on Digital Platforms

Authors: Jingyi Wu, Junying Liang
Published: 2025-10-12
Categories: cs.CL, cs.CY
arXiv: https://arxiv.org/abs/2510.10474v1

Understanding what drives popularity is critical in today's digital service economy, where content creators compete for consumer attention. Prior studies have primarily emphasized the role of content features, yet creators often misjudge what audiences actually value. This study applies Latent Dirichlet Allocation (LDA) modeling to a large corpus of TED Talks, treating the platform as a case of digital service provision in which creators (speakers) and consumers (audiences) interact. By comparing the thematic supply of creators with the demand expressed in audience engagement, we identify persistent mismatches between producer offerings and consumer preferences. Our longitudinal analysis further reveals that temporal dynamics exert a stronger influence on consumer engagement than thematic content, suggesting that when content is delivered may matter more than what is delivered. These findings challenge the dominant assumption that content features are the primary drivers of popularity and highlight the importance of timing and contextual factors in shaping consumer responses. The results provide new insights into consumer attention dynamics on digital platforms and carry practical implications for marketers, platform managers, and content creators seeking to optimize audience engagement strategies.

---

### FML-bench: Benchmarking Machine Learning Agents for Scientific Research

Authors: Qiran Zou, Hou Hei Lam, Wenhao Zhao, Yiming Tang, Tingting Chen, Samson Yu, Tianyi Zhang, Chang Liu, Xiangyang Ji, Dianbo Liu
Published: 2025-10-12
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.10472v2

Large language models (LLMs) have sparked growing interest in machine learning research agents that can autonomously propose ideas and conduct experiments. However, existing benchmarks predominantly adopt an engineering-oriented perspective: they emphasize application-oriented tasks and evaluate primarily on final performance and computational cost, overlooking agents' research processes and limiting assessment of their capabilities in scientific research settings. To more comprehensively evaluate agents in scientific research settings, we introduce FML-bench, a benchmark comprising 8 diverse and fundamental ML research tasks, and further propose complementary metrics, notably Exploration Diversity, which quantifies the variance of proposals across iterations and reveals how exploration patterns influence research outcomes. We evaluate state-of-the-art research agents on FML-bench, showing that agents employing broad exploration strategies exhibit higher exploration diversity and achieve superior performance, and that exploration diversity positively correlates with performance improvements across multiple tasks. We hope these findings and our benchmark inform future agent design and support the community in further investigating agent behavior. Our benchmark is available at https://github.com/qrzou/FML-bench.

---

### DAGLFNet: Deep Feature Attention Guided Global and Local Feature Fusion for Pseudo-Image Point Cloud Segmentation

Authors: Chuang Chen, Yi Lin, Bo Wang, Jing Hu, Xi Wu, Wenyi Ge
Published: 2025-10-12
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.10471v3

Environmental perception systems are crucial for high-precision mapping and autonomous navigation, with LiDAR serving as a core sensor providing accurate 3D point cloud data. Efficiently processing unstructured point clouds while extracting structured semantic information remains a significant challenge. In recent years, numerous pseudo-image-based representation methods have emerged to balance efficiency and performance by fusing 3D point clouds with 2D grids. However, the fundamental inconsistency between the pseudo-image representation and the original 3D information critically undermines 2D-3D feature fusion, posing a primary obstacle for coherent information fusion and leading to poor feature discriminability. This work proposes DAGLFNet, a pseudo-image-based semantic segmentation framework designed to extract discriminative features. It incorporates three key components: first, a Global-Local Feature Fusion Encoding (GL-FFE) module to enhance intra-set local feature correlation and capture global contextual information; second, a Multi-Branch Feature Extraction (MB-FE) network to capture richer neighborhood information and improve the discriminability of contour features; and third, a Feature Fusion via Deep Feature-guided Attention (FFDFA) mechanism to refine cross-channel feature fusion precision. Experimental evaluations demonstrate that DAGLFNet achieves mean Intersection-over-Union (mIoU) scores of 69.9% and 78.7% on the validation sets of SemanticKITTI and nuScenes, respectively. The method achieves an excellent balance between accuracy and efficiency.

---

### AnyBCQ: Hardware Efficient Flexible Binary-Coded Quantization for Multi-Precision LLMs

Authors: Gunho Park, Jeongin Bae, Beomseok Kwon, Byeongwook Kim, Se Jung Kwon, Dongsoo Lee
Published: 2025-10-12
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.10467v2

The deployment of large language models (LLMs) is increasingly constrained by memory and latency bottlenecks, motivating the need for quantization techniques that flexibly balance accuracy and efficiency. Recent work has introduced multi-precision models, which enable inference at multiple precisions within a single model depending on runtime constraints. To support such flexibility, quantized weights are often stored as bit-planes, where hardware efficiency improves when the compute operates directly at the bit-plane level and activates only the precision required by each request. In this work, we present AnyBCQ, a hardware-friendly multi-precision extension of Binary-Coded Quantization (BCQ) that supports direct bit-plane operations. By representing weights as binary bit-planes with corresponding scale factors, AnyBCQ enables bit-plane-level computation and maps naturally to accelerator-friendly, bit-parallel arithmetic. Our progressive precision expansion mechanism incrementally refines scaling factors while reusing previously assigned binary codes, yielding monotonic improvements in accuracy as additional bits are enabled. We further co-design a specialized kernel that exploits the BCQ structure to support dynamic per-request precision selection with negligible overhead. Experiments on recent LLMs demonstrate that AnyBCQ significantly narrows the accuracy drop in the low-bit regime (e.g. 2-bit), remains competitive at higher precision, and achieves throughput gains of up to 3.0x over half precision and 1.2x over state-of-the-art multi-precision methods. By aligning algorithmic flexibility with hardware efficiency, AnyBCQ provides a practical foundation for multi-precision LLM deployment across diverse service-level objectives.

---

### When Images Speak Louder: Mitigating Language Bias-induced Hallucinations in VLMs through Cross-Modal Guidance

Authors: Jinjin Cao, Zhiyang Chen, Zijun Wang, Liyuan Ma, Weijian Luo, Guojun Qi
Published: 2025-10-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.10466v1

Vision-Language Models (VLMs) have shown solid ability for multimodal understanding of both visual and language contexts. However, existing VLMs often face severe challenges of hallucinations, meaning that VLMs tend to generate responses that are only fluent in the language but irrelevant to images in previous contexts. To address this issue, we analyze how language bias contributes to hallucinations and then introduce Cross-Modal Guidance(CMG), a training-free decoding method that addresses the hallucinations by leveraging the difference between the output distributions of the original model and the one with degraded visual-language attention. In practice, we adaptively mask the attention weight of the most influential image tokens in selected transformer layers to corrupt the visual-language perception as a concrete type of degradation. Such a degradation-induced decoding emphasizes the perception of visual contexts and therefore significantly reduces language bias without harming the ability of VLMs. In experiment sections, we conduct comprehensive studies. All results demonstrate the superior advantages of CMG with neither additional conditions nor training costs. We also quantitatively show CMG can improve different VLM's performance on hallucination-specific benchmarks and generalize effectively.

---

### LightSAE: Parameter-Efficient and Heterogeneity-Aware Embedding for IoT Multivariate Time Series Forecasting

Authors: Yi Ren, Xinjie Yu
Published: 2025-10-12
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.10465v1

Modern Internet of Things (IoT) systems generate massive, heterogeneous multivariate time series data. Accurate Multivariate Time Series Forecasting (MTSF) of such data is critical for numerous applications. However, existing methods almost universally employ a shared embedding layer that processes all channels identically, creating a representational bottleneck that obscures valuable channel-specific information. To address this challenge, we introduce a Shared-Auxiliary Embedding (SAE) framework that decomposes the embedding into a shared base component capturing common patterns and channel-specific auxiliary components modeling unique deviations. Within this decomposition, we \rev{empirically observe} that the auxiliary components tend to exhibit low-rank and clustering characteristics, a structural pattern that is significantly less apparent when using purely independent embeddings. Consequently, we design LightSAE, a parameter-efficient embedding module that operationalizes these observed characteristics through low-rank factorization and a shared, gated component pool. Extensive experiments across 9 IoT-related datasets and 4 backbone architectures demonstrate LightSAE's effectiveness, achieving MSE improvements of up to 22.8\% with only 4.0\% parameter increase.

---

### Post-TIPS Prediction via Multimodal Interaction: A Multi-Center Dataset and Framework for Survival, Complication, and Portal Pressure Assessment

Authors: Junhao Dong, Dejia Liu, Ruiqi Ding, Zongxing Chen, Yingjie Huang, Zhu Meng, Jianbo Zhao, Zhicheng Zhao, Fei Su
Published: 2025-10-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.10464v1

Transjugular intrahepatic portosystemic shunt (TIPS) is an established procedure for portal hypertension, but provides variable survival outcomes and frequent overt hepatic encephalopathy (OHE), indicating the necessity of accurate preoperative prognostic modeling. Current studies typically build machine learning models from preoperative CT images or clinical characteristics, but face three key challenges: (1) labor-intensive region-of-interest (ROI) annotation, (2) poor reliability and generalizability of unimodal methods, and (3) incomplete assessment from single-endpoint prediction. Moreover, the lack of publicly accessible datasets constrains research in this field. Therefore, we present MultiTIPS, the first public multi-center dataset for TIPS prognosis, and propose a novel multimodal prognostic framework based on it. The framework comprises three core modules: (1) dual-option segmentation, which integrates semi-supervised and foundation model-based pipelines to achieve robust ROI segmentation with limited annotations and facilitate subsequent feature extraction; (2) multimodal interaction, where three techniques, multi-grained radiomics attention (MGRA), progressive orthogonal disentanglement (POD), and clinically guided prognostic enhancement (CGPE), are introduced to enable cross-modal feature interaction and complementary representation integration, thus improving model accuracy and robustness; and (3) multi-task prediction, where a staged training strategy is used to perform stable optimization of survival, portal pressure gradient (PPG), and OHE prediction for comprehensive prognostic assessment. Extensive experiments on MultiTIPS demonstrate the superiority of the proposed method over state-of-the-art approaches, along with strong cross-domain generalization and interpretability, indicating its promise for clinical application. The dataset and code are available.

---

### Learning from Disagreement: A Group Decision Simulation Framework for Robust Medical Image Segmentation

Authors: Chen Zhong, Yuxuan Yang, Xinyue Zhang, Ruohan Ma, Yong Guo, Gang Li, Jupeng Li
Published: 2025-10-12
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.10462v1

Medical image segmentation annotation suffers from inter-rater variability (IRV) due to differences in annotators' expertise and the inherent blurriness of medical images. Standard approaches that simply average expert labels are flawed, as they discard the valuable clinical uncertainty revealed in disagreements. We introduce a fundamentally new approach with our group decision simulation framework, which works by mimicking the collaborative decision-making process of a clinical panel. Under this framework, an Expert Signature Generator (ESG) learns to represent individual annotator styles in a unique latent space. A Simulated Consultation Module (SCM) then intelligently generates the final segmentation by sampling from this space. This method achieved state-of-the-art results on challenging CBCT and MRI datasets (92.11% and 90.72% Dice scores). By treating expert disagreement as a useful signal instead of noise, our work provides a clear path toward more robust and trustworthy AI systems for healthcare.

---

### MedCoAct: Confidence-Aware Multi-Agent Collaboration for Complete Clinical Decision

Authors: Hongjie Zheng, Zesheng Shi, Ping Yi
Published: 2025-10-12
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.10461v1

Autonomous agents utilizing Large Language Models (LLMs) have demonstrated remarkable capabilities in isolated medical tasks like diagnosis and image analysis, but struggle with integrated clinical workflows that connect diagnostic reasoning and medication decisions. We identify a core limitation: existing medical AI systems process tasks in isolation without the cross-validation and knowledge integration found in clinical teams, reducing their effectiveness in real-world healthcare scenarios. To transform the isolation paradigm into a collaborative approach, we propose MedCoAct, a confidence-aware multi-agent framework that simulates clinical collaboration by integrating specialized doctor and pharmacist agents, and present a benchmark, DrugCareQA, to evaluate medical AI capabilities in integrated diagnosis and treatment workflows. Our results demonstrate that MedCoAct achieves 67.58\% diagnostic accuracy and 67.58\% medication recommendation accuracy, outperforming single agent framework by 7.04\% and 7.08\% respectively. This collaborative approach generalizes well across diverse medical domains, proving especially effective for telemedicine consultations and routine clinical scenarios, while providing interpretable decision-making pathways.

---

### Understanding and Bridging the Planner-Coder Gap: A Systematic Study on the Robustness of Multi-Agent Systems for Code Generation

Authors: Zongyi Lyu, Songqiang Chen, Zhenlan Ji, Liwen Wang, Shuai Wang, Daoyuan Wu, Wenxuan Wang, Shing-Chi Cheung
Published: 2025-10-12
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2510.10460v2

Multi-agent systems (MASs) have emerged as a promising paradigm for automated code generation, demonstrating impressive performance on established benchmarks. Despite their prosperous development, the fundamental mechanisms underlying their robustness remain poorly understood, raising critical concerns for real-world deployment. This paper conducts a systematic empirical study to uncover the internal robustness flaws of MASs using a mutation-based methodology. By designing a testing pipeline incorporating semantic-preserving mutation operators and a novel fitness function, we assess mainstream MASs across multiple datasets and LLMs. Our findings reveal substantial robustness flaws: semantically equivalent inputs cause drastic performance drops, with MASs failing to solve 7.9\%--83.3\% of problems they initially resolved successfully. Through comprehensive failure analysis, we discover a fundamental cause underlying these robustness issues: the \textit{planner-coder gap}, which accounts for 75.3\% of failures. This gap arises from information loss in the multi-stage transformation process where planning agents decompose requirements into underspecified plans, and coding agents subsequently misinterpret intricate logic during code generation. Based on this formulated information transformation process, we propose a \textit{repairing method} that mitigates information loss through multi-prompt generation and introduces a monitor agent to bridge the planner-coder gap. Evaluation shows that our repairing method effectively enhances the robustness of MASs by solving 40.0\%--88.9\% of identified failures. Our work uncovers critical robustness flaws in MASs and provides effective mitigation strategies, contributing essential insights for developing more reliable MASs for code generation.

---

### NIM: Neuro-symbolic Ideographic Metalanguage for Inclusive Communication

Authors: Prawaal Sharma, Poonam Goyal, Navneet Goyal, Vidisha Sharma
Published: 2025-10-12
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.10459v1

Digital communication has become the cornerstone of modern interaction, enabling rapid, accessible, and interactive exchanges. However, individuals with lower academic literacy often face significant barriers, exacerbating the "digital divide". In this work, we introduce a novel, universal ideographic metalanguage designed as an innovative communication framework that transcends academic, linguistic, and cultural boundaries. Our approach leverages principles of Neuro-symbolic AI, combining neural-based large language models (LLMs) enriched with world knowledge and symbolic knowledge heuristics grounded in the linguistic theory of Natural Semantic Metalanguage (NSM). This enables the semantic decomposition of complex ideas into simpler, atomic concepts. Adopting a human-centric, collaborative methodology, we engaged over 200 semi-literate participants in defining the problem, selecting ideographs, and validating the system. With over 80\% semantic comprehensibility, an accessible learning curve, and universal adaptability, our system effectively serves underprivileged populations with limited formal education.

---

### Rethinking LLM Evaluation: Can We Evaluate LLMs with 200x Less Data?

Authors: Shaobo Wang, Cong Wang, Wenjie Fu, Yue Min, Mingquan Feng, Isabel Guan, Xuming Hu, Conghui He, Cunxiang Wang, Kexin Yang, Xingzhang Ren, Fei Huang et al.
Published: 2025-10-12
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2510.10457v1

As the demand for comprehensive evaluations of diverse model capabilities steadily increases, benchmark suites have correspondingly grown significantly in scale. Despite notable advances in redundancy reduction and subset-level performance prediction, a systematic framework that effectively integrates these methods to ensure both prediction accuracy and ranking consistency is still largely elusive. In this paper, we first perform a sample-level analysis of benchmark redundancy and identify several highly similar samples that can be eliminated. Besides, we frame benchmark compression as an optimization problem with the aim of score reconstruction. Building on these, we then propose EssenceBench, a coarse-to-fine framework utilizing an iterative Genetic Algorithm (GA), which takes the advantages of fitness-based subset search and attribution-based sample search. Compared to previous methods, our approach yields superior compression results with lower reconstruction error and markedly higher efficiency. In particular, on the HellaSwag benchmark (10K samples), our method preserves the ranking of all models shifting within 5% using 25x fewer samples, and achieves 95% ranking preservation shifting within 5% using only 200x fewer samples.

---

### On the Problem of Consistent Anomalies in Zero-Shot Industrial Anomaly Detection

Authors: Tai Le-Gia, Ahn Jaehyun
Published: 2025-10-12
Categories: cs.CV, stat.AP
arXiv: https://arxiv.org/abs/2510.10456v1

Zero-shot image anomaly classification (AC) and segmentation (AS) are vital for industrial quality control, detecting defects without prior training data. Existing representation-based methods compare patch features with nearest neighbors in unlabeled test images but struggle with consistent anomalies -- similar defects recurring across multiple images -- resulting in poor AC/AS performance. We introduce Consistent-Anomaly Detection Graph (CoDeGraph), a novel algorithm that identifies and filters consistent anomalies from similarity computations. Our key insight is that normal patches in industrial images show stable, gradually increasing similarity to other test images, while consistent-anomaly patches exhibit abrupt similarity spikes after exhausting a limited set of similar matches, a phenomenon we term ``neighbor-burnout.'' CoDeGraph constructs an image-level graph, with images as nodes and edges connecting those with shared consistent-anomaly patterns, using community detection to filter these anomalies. We provide a theoretical foundation using Extreme Value Theory to explain the effectiveness of our approach. Experiments on MVTec AD with the ViT-L-14-336 backbone achieve 98.3% AUROC for AC and AS performance of 66.8% (+4.2%) F1 and 68.1% (+5.4%) AP over state-of-the-art zero-shot methods. Using the DINOv2 backbone further improves segmentation, yielding 69.1% (+6.5%) F1 and 71.9% (+9.2%) AP, demonstrating robustness across architectures.

---

### Traj-CoA: Patient Trajectory Modeling via Chain-of-Agents for Lung Cancer Risk Prediction

Authors: Sihang Zeng, Yujuan Fu, Sitong Zhou, Zixuan Yu, Lucas Jing Liu, Jun Wen, Matthew Thompson, Ruth Etzioni, Meliha Yetisgen
Published: 2025-10-12
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.10454v2

Large language models (LLMs) offer a generalizable approach for modeling patient trajectories, but suffer from the long and noisy nature of electronic health records (EHR) data in temporal reasoning. To address these challenges, we introduce Traj-CoA, a multi-agent system involving chain-of-agents for patient trajectory modeling. Traj-CoA employs a chain of worker agents to process EHR data in manageable chunks sequentially, distilling critical events into a shared long-term memory module, EHRMem, to reduce noise and preserve a comprehensive timeline. A final manager agent synthesizes the worker agents' summary and the extracted timeline in EHRMem to make predictions. In a zero-shot one-year lung cancer risk prediction task based on five-year EHR data, Traj-CoA outperforms baselines of four categories. Analysis reveals that Traj-CoA exhibits clinically aligned temporal reasoning, establishing it as a promisingly robust and generalizable approach for modeling complex patient trajectories. Implementation of Traj-CoA is available on https://github.com/zengsihang/Traj-CoA.

---

### End-to-end Speech Recognition with similar length speech and text

Authors: Peng Fan, Wenping Wang, Fei Deng
Published: 2025-10-12
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.10453v1

The mismatch of speech length and text length poses a challenge in automatic speech recognition (ASR). In previous research, various approaches have been employed to align text with speech, including the utilization of Connectionist Temporal Classification (CTC). In earlier work, a key frame mechanism (KFDS) was introduced, utilizing intermediate CTC outputs to guide downsampling and preserve keyframes, but traditional methods (CTC) failed to align speech and text appropriately when downsampling speech to a text-similar length. In this paper, we focus on speech recognition in those cases where the length of speech aligns closely with that of the corresponding text. To address this issue, we introduce two methods for alignment: a) Time Independence Loss (TIL) and b) Aligned Cross Entropy (AXE) Loss, which is based on edit distance. To enhance the information on keyframes, we incorporate frame fusion by applying weights and summing the keyframe with its context 2 frames. Experimental results on AISHELL-1 and AISHELL-2 dataset subsets show that the proposed methods outperform the previous work and achieve a reduction of at least 86\% in the number of frames.

---

### Steering Over-refusals Towards Safety in Retrieval Augmented Generation

Authors: Utsav Maskey, Mark Dras, Usman Naseem
Published: 2025-10-12
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.10452v1

Safety alignment in large language models (LLMs) induces over-refusals -- where LLMs decline benign requests due to aggressive safety filters. We analyze this phenomenon in retrieval-augmented generation (RAG), where both the query intent and retrieved context properties influence refusal behavior. We construct RagRefuse, a domain-stratified benchmark spanning medical, chemical, and open domains, pairing benign and harmful queries with controlled context contamination patterns and sizes. Our analysis shows that context arrangement / contamination, domain of query and context, and harmful-text density trigger refusals even on benign queries, with effects depending on model-specific alignment choices. To mitigate over-refusals, we introduce \textsc{SafeRAG-Steering}, a model-centric embedding intervention that steers the embedding regions towards the confirmed safe, non-refusing output regions at inference time. This reduces over-refusals in contaminated RAG pipelines while preserving legitimate refusals.

---

### Data-driven simulator of multi-animal behavior with unknown dynamics via offline and online reinforcement learning

Authors: Keisuke Fujii, Kazushi Tsutsui, Yu Teshima, Makoto Itoh, Naoya Takeishi, Nozomi Nishiumi, Ryoya Tanaka, Shunsuke Shigaki, Yoshinobu Kawahara
Published: 2025-10-12
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.10451v1

Simulators of animal movements play a valuable role in studying behavior. Advances in imitation learning for robotics have expanded possibilities for reproducing human and animal movements. A key challenge for realistic multi-animal simulation in biology is bridging the gap between unknown real-world transition models and their simulated counterparts. Because locomotion dynamics are seldom known, relying solely on mathematical models is insufficient; constructing a simulator that both reproduces real trajectories and supports reward-driven optimization remains an open problem. We introduce a data-driven simulator for multi-animal behavior based on deep reinforcement learning and counterfactual simulation. We address the ill-posed nature of the problem caused by high degrees of freedom in locomotion by estimating movement variables of an incomplete transition model as actions within an RL framework. We also employ a distance-based pseudo-reward to align and compare states between cyber and physical spaces. Validated on artificial agents, flies, newts, and silkmoth, our approach achieves higher reproducibility of species-specific behaviors and improved reward acquisition compared with standard imitation and RL methods. Moreover, it enables counterfactual behavior prediction in novel experimental settings and supports multi-individual modeling for flexible what-if trajectory generation, suggesting its potential to simulate and elucidate complex multi-animal behaviors.

---

### RECON: Reasoning with Condensation for Efficient Retrieval-Augmented Generation

Authors: Zhichao Xu, Minheng Wang, Yawei Wang, Wenqian Ye, Yuntao Du, Yunpu Ma, Yijun Tian
Published: 2025-10-12
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.10448v2

Search agents trained with reinforcement learning (RL) interleave reasoning with tool calls in a multi-turn, tool-integrated reasoning (TIR) loop, where each tool invocation returns an environment observation that is appended to the agent's context. As the rollout proceeds, these raw observations accumulate, inflating token cost and diluting the signal available for downstream reasoning. Unlike single-pass retrieve-then-read pipelines, where context compression is a one-time postprocessing step, the multi-turn RL setting requires compression that runs at every observation step while remaining decoupled from policy optimization. We introduce RECON (REasoning with CONdensation), a framework that addresses this challenge by inserting a dedicated observation compressor into the reasoning loop. The compressor is trained via a two-stage curriculum: relevance pretraining on QA datasets followed by multi-aspect distillation from proprietary LLMs, and remains frozen during RL training to preserve policy stability. Integrated into the Search-R1 search-agent pipeline, RECON reduces total context length by 35%, improves training speed by 5.4% and inference latency by 30.9%, while boosting average exact-match by 14.5% on the 3B agent and 3.0% on the 7B agent, with particular strength in multi-hop QA. These results establish learned observation compression as a key component for building practical, scalable RL-trained search agents.

---

### Reverse Supervision at Scale: Exponential Search Meets the Economics of Annotation

Authors: Masoud Makrehchi
Published: 2025-10-12
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.10446v2

We analyze a reversed-supervision strategy that searches over labelings of a large unlabeled set \(B\) to minimize error on a small labeled set \(A\). The search space is \(2^n\), and the resulting complexity remains exponential even under large constant-factor speedups (e.g., quantum or massively parallel hardware). Consequently, arbitrarily fast -- but not exponentially faster -- computation does not obviate the need for informative labels or priors. In practice, the machine learning pipeline still requires an initial human contribution: specifying the objective, defining classes, and providing a seed set of representative annotations that inject inductive bias and align models with task semantics. Synthetic labels from generative AI can partially substitute provided their quality is human-grade and anchored by a human-specified objective, seed supervision, and validation. In this view, generative models function as \emph{label amplifiers}, leveraging small human-curated cores via active, semi-supervised, and self-training loops, while humans retain oversight for calibration, drift detection, and failure auditing. Thus, extreme computational speed reduces wall-clock time but not the fundamental supervision needs of learning; initial human (or human-grade) input remains necessary to ground the system in the intended task.

---

### Do Audio LLMs Really LISTEN, or Just Transcribe? Measuring Lexical vs. Acoustic Emotion Cues Reliance

Authors: Jingyi Chen, Zhimeng Guo, Jiyun Chun, Pichao Wang, Andrew Perrault, Micha Elsner
Published: 2025-10-12
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.10444v2

Understanding emotion from speech requires sensitivity to both lexical and acoustic cues. However, it remains unclear whether large audio language models (LALMs) genuinely process acoustic information or rely primarily on lexical content. We present LISTEN (Lexical vs. Acoustic Speech Test for Emotion in Narratives), a controlled benchmark designed to disentangle lexical reliance from acoustic sensitivity in emotion understanding. Across evaluations of six state-of-the-art LALMs, we observe a consistent lexical dominance. Models predict "neutral" when lexical cues are neutral or absent, show limited gains under cue alignment, and fail to classify distinct emotions under cue conflict. In paralinguistic settings, performance approaches chance. These results indicate that current LALMs largely "transcribe" rather than "listen," relying heavily on lexical semantics while underutilizing acoustic cues. LISTEN offers a principled framework for assessing emotion understanding in multimodal models.

---

### Does Weighting Improve Matrix Factorization for Recommender Systems?

Authors: Alex Ayoub, Samuel Robertson, Dawen Liang, Harald Steck, Nathan Kallus
Published: 2025-10-12
Categories: cs.IR, cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.10440v1

Matrix factorization is a widely used approach for top-N recommendation and collaborative filtering. When implemented on implicit feedback data (such as clicks), a common heuristic is to upweight the observed interactions. This strategy has been shown to improve performance for certain algorithms. In this paper, we conduct a systematic study of various weighting schemes and matrix factorization algorithms. Somewhat surprisingly, we find that training with unweighted data can perform comparably to, and sometimes outperform, training with weighted data, especially for large models. This observation challenges the conventional wisdom. Nevertheless, we identify cases where weighting can be beneficial, particularly for models with lower capacity and specific regularization schemes. We also derive efficient algorithms for exactly minimizing several weighted objectives that were previously considered computationally intractable. Our work provides a comprehensive analysis of the interplay between weighting, regularization, and model capacity in matrix factorization for recommender systems.

---

### MonoSE(3)-Diffusion: A Monocular SE(3) Diffusion Framework for Robust Camera-to-Robot Pose Estimation

Authors: Kangjian Zhu, Haobo Jiang, Yigong Zhang, Jianjun Qian, Jian Yang, Jin Xie
Published: 2025-10-12
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2510.10434v1

We propose MonoSE(3)-Diffusion, a monocular SE(3) diffusion framework that formulates markerless, image-based robot pose estimation as a conditional denoising diffusion process. The framework consists of two processes: a visibility-constrained diffusion process for diverse pose augmentation and a timestep-aware reverse process for progressive pose refinement. The diffusion process progressively perturbs ground-truth poses to noisy transformations for training a pose denoising network. Importantly, we integrate visibility constraints into the process, ensuring the transformations remain within the camera field of view. Compared to the fixed-scale perturbations used in current methods, the diffusion process generates in-view and diverse training poses, thereby improving the network generalization capability. Furthermore, the reverse process iteratively predicts the poses by the denoising network and refines pose estimates by sampling from the diffusion posterior of current timestep, following a scheduled coarse-to-fine procedure. Moreover, the timestep indicates the transformation scales, which guide the denoising network to achieve more accurate pose predictions. The reverse process demonstrates higher robustness than direct prediction, benefiting from its timestep-aware refinement scheme. Our approach demonstrates improvements across two benchmarks (DREAM and RoboKeyGen), achieving a notable AUC of 66.75 on the most challenging dataset, representing a 32.3% gain over the state-of-the-art.

---

### Multi-Task Learning with Feature-Similarity Laplacian Graphs for Predicting Alzheimer's Disease Progression

Authors: Zixiang Xu, Menghui Zhou, Jun Qi, Xuanhan Fan, Yun Yang, Po Yang
Published: 2025-10-12
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.10433v1

Alzheimer's Disease (AD) is the most prevalent neurodegenerative disorder in aging populations, posing a significant and escalating burden on global healthcare systems. While Multi-Tusk Learning (MTL) has emerged as a powerful computational paradigm for modeling longitudinal AD data, existing frameworks do not account for the time-varying nature of feature correlations. To address this limitation, we propose a novel MTL framework, named Feature Similarity Laplacian graph Multi-Task Learning (MTL-FSL). Our framework introduces a novel Feature Similarity Laplacian (FSL) penalty that explicitly models the time-varying relationships between features. By simultaneously considering temporal smoothness among tasks and the dynamic correlations among features, our model enhances both predictive accuracy and biological interpretability. To solve the non-smooth optimization problem arising from our proposed penalty terms, we adopt the Alternating Direction Method of Multipliers (ADMM) algorithm. Experiments conducted on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset demonstrate that our proposed MTL-FSL framework achieves state-of-the-art performance, outperforming various baseline methods. The implementation source can be found at https://github.com/huatxxx/MTL-FSL.

---

### Hierarchical LoRA MoE for Efficient CTR Model Scaling

Authors: Zhichen Zeng, Mengyue Hang, Xiaolong Liu, Xiaoyi Liu, Xiao Lin, Ruizhong Qiu, Tianxin Wei, Zhining Liu, Siyang Yuan, Chaofei Yang, Yiqun Liu, Hang Yin et al.
Published: 2025-10-12
Categories: cs.LG, cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2510.10432v1

Deep models have driven significant advances in click-through rate (CTR) prediction. While vertical scaling via layer stacking improves model expressiveness, the layer-by-layer sequential computation poses challenges to efficient scaling. Conversely, horizontal scaling through Mixture of Experts (MoE) achieves efficient scaling by activating a small subset of experts in parallel, but flat MoE layers may struggle to capture the hierarchical structure inherent in recommendation tasks. To push the Return-On-Investment (ROI) boundary, we explore the complementary strengths of both directions and propose HiLoMoE, a hierarchical LoRA MoE framework that enables holistic scaling in a parameter-efficient manner. Specifically, HiLoMoE employs lightweight rank-1 experts for parameter-efficient horizontal scaling, and stacks multiple MoE layers with hierarchical routing to enable combinatorially diverse expert compositions. Unlike conventional stacking, HiLoMoE routes based on prior layer scores rather than outputs, allowing all layers to execute in parallel. A principled three-stage training framework ensures stable optimization and expert diversity. Experiments on four public datasets show that HiLoMoE achieving better performance-efficiency tradeoff, achieving an average AUC improvement of 0.20\% in AUC and 18.5\% reduction in FLOPs compared to the non-MoE baseline.

---