# Research Papers — 2025-10 · bundle page 36 of 217

> Full-text markdown of papers #1751–1800 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/36
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/35.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/37.md)

### MAP4TS: A Multi-Aspect Prompting Framework for Time-Series Forecasting with Large Language Models

Authors: Suchan Lee, Jihoon Choi, Sohyeon Lee, Minseok Song, Bong-Gyu Jang, Hwanjo Yu, Soyeon Caren Han
Published: 2025-10-27
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.23090v2

Recent advances have investigated the use of pretrained large language models (LLMs) for time-series forecasting by aligning numerical inputs with LLM embedding spaces. However, existing multimodal approaches often overlook the distinct statistical properties and temporal dependencies that are fundamental to time-series data. To bridge this gap, we propose MAP4TS, a novel Multi-Aspect Prompting Framework that explicitly incorporates classical time-series analysis into the prompt design. Our framework introduces four specialized prompt components: a Global Domain Prompt that conveys dataset-level context, a Local Domain Prompt that encodes recent trends and series-specific behaviors, and a pair of Statistical and Temporal Prompts that embed handcrafted insights derived from autocorrelation (ACF), partial autocorrelation (PACF), and Fourier analysis. Multi-Aspect Prompts are combined with raw time-series embeddings and passed through a cross-modality alignment module to produce unified representations, which are then processed by an LLM and projected for final forecasting. Extensive experiments across eight diverse datasets show that MAP4TS consistently outperforms state-of-the-art LLM-based methods. Our ablation studies further reveal that prompt-aware designs significantly enhance performance stability and that GPT-2 backbones, when paired with structured prompts, outperform larger models like LLaMA in long-term forecasting tasks.

---

### EndoWave: 4D Gaussian Splatting with Rational Wavelet for Endoscopic Reconstruction

Authors: Taoyu Wu, Yiyi Miao, Jiaxin Guo, Ziyan Chen, Sihang Zhao, Zhuoxiao Li, Zhe Tang, Baoru Huang, Limin Yu
Published: 2025-10-27
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2510.23087v2

In robot-assisted minimally invasive surgery, accurate 3D reconstruction from endoscopic video is vital for downstream tasks and improved outcomes. However, endoscopic scenarios present unique challenges, including photometric inconsistencies, non-rigid tissue motion, and view-dependent highlights. Most 3DGS-based methods that rely solely on appearance constraints for optimizing 3DGS are often insufficient in this context, as these dynamic visual artifacts can mislead the optimization process and lead to inaccurate reconstructions. To address these limitations, we present EndoWave, a unified spatio-temporal Gaussian Splatting framework by incorporating an optical flow-based geometric constraint and a multi-resolution rational wavelet supervision. First, we adopt a unified spatio-temporal Gaussian representation that directly optimizes primitives in a 4D domain. Second, we propose a geometric constraint derived from optical flow to enhance temporal coherence and effectively constrain the 3D structure of the scene. Third, we propose a multi-resolution rational orthogonal wavelet as a constraint, which can effectively separate the details of the endoscope and enhance the rendering performance. Extensive evaluations on two real surgical datasets, EndoNeRF and StereoMIS, demonstrate that our method EndoWave achieves state-of-the-art reconstruction quality and visual accuracy compared to the baseline method.

---

### Smaller Models, Smarter Rewards: A Two-Sided Approach to Process and Outcome Rewards

Authors: Jan Niklas Groeneveld, Xi Qin, Alexander Schaefer, Yaad Oren
Published: 2025-10-27
Categories: cs.AI, cs.LG, cs.SE
arXiv: https://arxiv.org/abs/2510.23083v3

Generating high-quality code remains a challenge for Large Language Models (LLMs). For the evolution of reasoning models on this task, reward models are a necessary intermediate step. These models judge outcomes or intermediate steps. Decoder-only transformer models can be turned into reward models by introducing a regression layer and supervised fine-tuning. While it is known that reflection capabilities generally increase with the size of a model, we want to investigate whether state-of-the-art small language models like the Phi-4 family can be turned into usable reward models blending the consideration of process rewards and outcome rewards. Targeting this goal, we construct a dataset of code samples with correctness labels derived from the APPS coding challenge benchmark. We then train a value-head model to estimate the success probability of intermediate outputs. Our evaluation shows that small LLMs are capable of serving as effective reward models or code evaluation critics, successfully identifying correct solutions among multiple candidates. Using this critic, we achieve over a 20% improvement in the search capability of the most accurate code out of multiple generations.

---

### A Survey on LLM Mid-Training

Authors: Chengying Tu, Xuemiao Zhang, Rongxiang Weng, Rumei Li, Chen Zhang, Yang Bai, Hongfei Yan, Jingang Wang, Xunliang Cai
Published: 2025-10-27
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.23081v2

Recent advances in foundation models have highlighted the significant benefits of multi-stage training, with a particular emphasis on the emergence of mid-training as a vital stage that bridges pre-training and post-training. Mid-training is distinguished by its use of intermediate data and computational resources, systematically enhancing specified capabilities such as mathematics, coding, reasoning, and long-context extension, while maintaining foundational competencies. This survey provides a formal definition of mid-training for large language models (LLMs) and investigates optimization frameworks that encompass data curation, training strategies, and model architecture optimization. We analyze mainstream model implementations in the context of objective-driven interventions, illustrating how mid-training serves as a distinct and critical stage in the progressive development of LLM capabilities. By clarifying the unique contributions of mid-training, this survey offers a comprehensive taxonomy and actionable insights, supporting future research and innovation in the advancement of LLMs.

---

### Strategies for Robust Deep Learning Based Deformable Registration

Authors: Joel Honkamaa, Pekka Marttinen
Published: 2025-10-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.23079v1

Deep learning based deformable registration methods have become popular in recent years. However, their ability to generalize beyond training data distribution can be poor, significantly hindering their usability. LUMIR brain registration challenge for Learn2Reg 2025 aims to advance the field by evaluating the performance of the registration on contrasts and modalities different from those included in the training set. Here we describe our submission to the challenge, which proposes a very simple idea for significantly improving robustness by transforming the images into MIND feature space before feeding them into the model. In addition, a special ensembling strategy is proposed that shows a small but consistent improvement.

---

### Think before Recommendation: Autonomous Reasoning-enhanced Recommender

Authors: Xiaoyu Kong, Junguang Jiang, Bin Liu, Ziru Xu, Han Zhu, Jian Xu, Bo Zheng, Jiancan Wu, Xiang Wang
Published: 2025-10-27
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2510.23077v1

The core task of recommender systems is to learn user preferences from historical user-item interactions. With the rapid development of large language models (LLMs), recent research has explored leveraging the reasoning capabilities of LLMs to enhance rating prediction tasks. However, existing distillation-based methods suffer from limitations such as the teacher model's insufficient recommendation capability, costly and static supervision, and superficial transfer of reasoning ability. To address these issues, this paper proposes RecZero, a reinforcement learning (RL)-based recommendation paradigm that abandons the traditional multi-model and multi-stage distillation approach. Instead, RecZero trains a single LLM through pure RL to autonomously develop reasoning capabilities for rating prediction. RecZero consists of two key components: (1) "Think-before-Recommendation" prompt construction, which employs a structured reasoning template to guide the model in step-wise analysis of user interests, item features, and user-item compatibility; and (2) rule-based reward modeling, which adopts group relative policy optimization (GRPO) to compute rewards for reasoning trajectories and optimize the LLM. Additionally, the paper explores a hybrid paradigm, RecOne, which combines supervised fine-tuning with RL, initializing the model with cold-start reasoning samples and further optimizing it with RL. Experimental results demonstrate that RecZero and RecOne significantly outperform existing baseline methods on multiple benchmark datasets, validating the superiority of the RL paradigm in achieving autonomous reasoning-enhanced recommender systems.

---

### Fast-MIA: Efficient and Scalable Membership Inference for LLMs

Authors: Hiromu Takahashi, Shotaro Ishihara
Published: 2025-10-27
Categories: cs.CR, cs.CL
arXiv: https://arxiv.org/abs/2510.23074v2

We propose Fast-MIA (https://github.com/Nikkei/fast-mia), a Python library for efficiently evaluating membership inference attacks (MIA) against large language models (LLMs). MIA has emerged as a crucial technique for auditing privacy risks and copyright infringement in LLMs. However, computational demands have grown substantially: recent methods rely on repeated inference, while practical auditing requires large-scale evaluation. Progress is further hindered by existing implementations that execute methods independently, redundantly computing shared intermediate results such as log-probabilities. To address these challenges, Fast-MIA combines two strategies: (1) high-throughput batch inference via vLLM, achieving approximately 5$\times$ speedup, and (2) a cross-method caching architecture that computes intermediate results once and shares them across methods. The library includes representative MIA methods under a unified framework, integrates with established benchmarks, and supports flexible YAML configuration. We release Fast-MIA under the Apache License 2.0 to support scalable and reproducible MIA research.

---

### Quality-Aware Translation Tagging in Multilingual RAG system

Authors: Hoyeon Moon, Byeolhee Kim, Nikhil Verma
Published: 2025-10-27
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.23070v1

Multilingual Retrieval-Augmented Generation (mRAG) often retrieves English documents and translates them into the query language for low-resource settings. However, poor translation quality degrades response generation performance. Existing approaches either assume sufficient translation quality or utilize the rewriting method, which introduces factual distortion and hallucinations. To mitigate these problems, we propose Quality-Aware Translation Tagging in mRAG (QTT-RAG), which explicitly evaluates translation quality along three dimensions-semantic equivalence, grammatical accuracy, and naturalness&fluency-and attach these scores as metadata without altering the original content. We evaluate QTT-RAG against CrossRAG and DKM-RAG as baselines in two open-domain QA benchmarks (XORQA, MKQA) using six instruction-tuned LLMs ranging from 2.4B to 14B parameters, covering two low-resource languages (Korean and Finnish) and one high-resource language (Chinese). QTT-RAG outperforms the baselines by preserving factual integrity while enabling generator models to make informed decisions based on translation reliability. This approach allows for effective usage of cross-lingual documents in low-resource settings with limited native language documents, offering a practical and robust solution across multilingual domains.

---

### TLCD: A Deep Transfer Learning Framework for Cross-Disciplinary Cognitive Diagnosis

Authors: Zhifeng Wang, Meixin Su, Yang Yang, Chunyan Zeng, Lizhi Ye
Published: 2025-10-27
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.23062v1

Driven by the dual principles of smart education and artificial intelligence technology, the online education model has rapidly emerged as an important component of the education industry. Cognitive diagnostic technology can utilize students' learning data and feedback information in educational evaluation to accurately assess their ability level at the knowledge level. However, while massive amounts of information provide abundant data resources, they also bring about complexity in feature extraction and scarcity of disciplinary data. In cross-disciplinary fields, traditional cognitive diagnostic methods still face many challenges. Given the differences in knowledge systems, cognitive structures, and data characteristics between different disciplines, this paper conducts in-depth research on neural network cognitive diagnosis and knowledge association neural network cognitive diagnosis, and proposes an innovative cross-disciplinary cognitive diagnosis method (TLCD). This method combines deep learning techniques and transfer learning strategies to enhance the performance of the model in the target discipline by utilizing the common features of the main discipline. The experimental results show that the cross-disciplinary cognitive diagnosis model based on deep learning performs better than the basic model in cross-disciplinary cognitive diagnosis tasks, and can more accurately evaluate students' learning situation.

---

### Seq-DeepIPC: Sequential Sensing for End-to-End Control in Legged Robot Navigation

Authors: Oskar Natan, Jun Miura
Published: 2025-10-27
Categories: cs.RO, cs.CV, eess.IV, eess.SY
arXiv: https://arxiv.org/abs/2510.23057v2

We present Seq-DeepIPC, a sequential end-to-end perception-to-control model for legged robot navigation in real-world environments. Seq-DeepIPC advances intelligent sensing for autonomous legged navigation by tightly integrating multi-modal perception (RGB-D + GNSS) with temporal fusion and control. The model jointly predicts semantic segmentation and depth estimation, giving richer spatial features for planning and control. For efficient deployment on edge devices, we use a lightweight model as the encoder, reducing computation while maintaining accuracy. Heading estimation is simplified by removing the noisy IMU and instead deriving global heading via differential analysis of sequential GNSS coordinates. We collected a larger and more diverse dataset that includes both road and grass terrains, and validated Seq-DeepIPC on a robot dog. Comparative and ablation studies show that sequential inputs improve perception and control in our models, while other baselines do not benefit. Seq-DeepIPC achieves competitive or better results with reasonable model size; although GNSS-only heading is less reliable near tall buildings, it is robust in open areas. Overall, Seq-DeepIPC extends end-to-end navigation beyond wheeled robots to more versatile and temporally-aware systems. To support future research, we will release the codes to our GitHub repo at https://github.com/oskarnatan/Seq-DeepIPC.

---

### AirFed: A Federated Graph-Enhanced Multi-Agent Reinforcement Learning Framework for Multi-UAV Cooperative Mobile Edge Computing

Authors: Zhiyu Wang, Suman Raj, Rajkumar Buyya
Published: 2025-10-27
Categories: cs.LG, cs.DC
arXiv: https://arxiv.org/abs/2510.23053v2

Multiple Unmanned Aerial Vehicles (UAVs) cooperative Mobile Edge Computing (MEC) systems face critical challenges in coordinating trajectory planning, task offloading, and resource allocation while ensuring Quality of Service (QoS) under dynamic and uncertain environments. Existing approaches suffer from limited scalability, slow convergence, and inefficient knowledge sharing among UAVs, particularly when handling large-scale IoT device deployments with stringent deadline constraints. This paper proposes AirFed, a novel federated graph-enhanced multi-agent reinforcement learning framework that addresses these challenges through three key innovations. First, we design dual-layer dynamic Graph Attention Networks (GATs) that explicitly model spatial-temporal dependencies among UAVs and IoT devices, capturing both service relationships and collaborative interactions within the network topology. Second, we develop a dual-Actor single-Critic architecture that jointly optimizes continuous trajectory control and discrete task offloading decisions. Third, we propose a reputation-based decentralized federated learning mechanism with gradient-sensitive adaptive quantization, enabling efficient and robust knowledge sharing across heterogeneous UAVs. Extensive experiments demonstrate that AirFed achieves 42.9% reduction in weighted cost compared to state-of-the-art baselines, attains over 99% deadline satisfaction and 94.2% IoT device coverage rate, and reduces communication overhead by 54.5%. Scalability analysis confirms robust performance across varying UAV numbers, IoT device densities, and system scales, validating AirFed's practical applicability for large-scale UAV-MEC deployments.

---

### Knocking-Heads Attention

Authors: Zhanchao Zhou, Xiaodong Chen, Haoxing Chen, Zhenzhong Lan, Jianguo Li
Published: 2025-10-27
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.23052v1

Multi-head attention (MHA) has become the cornerstone of modern large language models, enhancing representational capacity through parallel attention heads. However, increasing the number of heads inherently weakens individual head capacity, and existing attention mechanisms - whether standard MHA or its variants like grouped-query attention (GQA) and grouped-tied attention (GTA) - simply concatenate outputs from isolated heads without strong interaction. To address this limitation, we propose knocking-heads attention (KHA), which enables attention heads to "knock" on each other - facilitating cross-head feature-level interactions before the scaled dot-product attention. This is achieved by applying a shared, diagonally-initialized projection matrix across all heads. The diagonal initialization preserves head-specific specialization at the start of training while allowing the model to progressively learn integrated cross-head representations. KHA adds only minimal parameters and FLOPs and can be seamlessly integrated into MHA, GQA, GTA, and other attention variants. We validate KHA by training a 6.1B parameter MoE model (1.01B activated) on 1T high-quality tokens. Compared to baseline attention mechanisms, KHA brings superior and more stable training dynamics, achieving better performance across downstream tasks.

---

### SwiftTS: A Swift Selection Framework for Time Series Pre-trained Models via Multi-task Meta-Learning

Authors: Tengxue Zhang, Biao Ouyang, Yang Shu, Xinyang Chen, Chenjuan Guo, Bin Yang
Published: 2025-10-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.23051v2

Pre-trained models exhibit strong generalization to various downstream tasks. However, given the numerous models available in the model hub, identifying the most suitable one by individually fine-tuning is time-consuming. In this paper, we propose \textbf{SwiftTS}, a swift selection framework for time series pre-trained models. To avoid expensive forward propagation through all candidates, SwiftTS adopts a learning-guided approach that leverages historical dataset-model performance pairs across diverse horizons to predict model performance on unseen datasets. It employs a lightweight dual-encoder architecture that embeds time series and candidate models with rich characteristics, computing patchwise compatibility scores between data and model embeddings for efficient selection. To further enhance the generalization across datasets and horizons, we introduce a horizon-adaptive expert composition module that dynamically adjusts expert weights, and the transferable cross-task learning with cross-dataset and cross-horizon task sampling to enhance out-of-distribution (OOD) robustness. Extensive experiments on 14 downstream datasets and 8 pre-trained models demonstrate that SwiftTS achieves state-of-the-art performance in time series pre-trained model selection.

---

### Advantage Shaping as Surrogate Reward Maximization: Unifying Pass@K Policy Gradients

Authors: Christos Thrampoulidis, Sadegh Mahdavi, Wenlong Deng
Published: 2025-10-27
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.23049v3

This note reconciles two seemingly distinct approaches to policy gradient optimization for the Pass@K objective in reinforcement learning with verifiable rewards: (1) direct REINFORCE-style methods, and (2) advantage-shaping techniques that directly modify GRPO. We show that these are two sides of the same coin. By reverse-engineering existing advantage-shaping algorithms, we reveal that they implicitly optimize surrogate rewards. We specifically interpret practical "hard-example up-weighting" modifications to GRPO as reward-level regularization. Conversely, starting from surrogate reward objectives, we provide a simple recipe for deriving both existing and new advantage-shaping methods. This perspective provides a lens for RLVR policy gradient optimization beyond our original motivation of Pass@K.

---

### A Survey of AI Scientists

Authors: Guiyao Tie, Pan Zhou, Lichao Sun
Published: 2025-10-27
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.23045v5

Artificial intelligence is undergoing a profound transition from a computational instrument to an autonomous originator of scientific knowledge. This emerging paradigm, the AI scientist, is architected to emulate the complete scientific workflow-from initial hypothesis generation to the final synthesis of publishable findings-thereby promising to fundamentally reshape the pace and scale of discovery. However, the rapid and unstructured proliferation of these systems has created a fragmented research landscape, obscuring overarching methodological principles and developmental trends. This survey provides a systematic and comprehensive synthesis of this domain by introducing a unified, six-stage methodological framework that deconstructs the end-to-end scientific process into: Literature Review, Idea Generation, Experimental Preparation, Experimental Execution, Scientific Writing, and Paper Generation. Through this analytical lens, we chart the field's evolution from early Foundational Modules (2022-2023) to integrated Closed-Loop Systems (2024), and finally to the current frontier of Scalability, Impact, and Human-AI Collaboration (2025-present). By rigorously synthesizing these developments, this survey not only clarifies the current state of autonomous science but also provides a critical roadmap for overcoming remaining challenges in robustness and governance, ultimately guiding the next generation of systems toward becoming trustworthy and indispensable partners in human scientific inquiry.

---

### HieraMamba: Video Temporal Grounding via Hierarchical Anchor-Mamba Pooling

Authors: Joungbin An, Kristen Grauman
Published: 2025-10-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.23043v2

Video temporal grounding, the task of localizing the start and end times of a natural language query in untrimmed video, requires capturing both global context and fine-grained temporal detail. This challenge is particularly pronounced in long videos, where existing methods often compromise temporal fidelity by over-downsampling or relying on fixed windows. We present HieraMamba, a hierarchical architecture that preserves temporal structure and semantic richness across scales. At its core are Anchor-MambaPooling (AMP) blocks, which utilize Mamba's selective scanning to produce compact anchor tokens that summarize video content at multiple granularities. Two complementary objectives, anchor-conditioned and segment-pooled contrastive losses, encourage anchors to retain local detail while remaining globally discriminative. HieraMamba sets a new state-of-the-art on Ego4D-NLQ, MAD, and TACoS, demonstrating precise, temporally faithful localization in long, untrimmed videos.

---

### LLM Meets Diffusion: A Hybrid Framework for Crystal Material Generation

Authors: Subhojyoti Khastagir, Kishalay Das, Pawan Goyal, Seung-Cheol Lee, Satadeep Bhattacharjee, Niloy Ganguly
Published: 2025-10-27
Categories: cs.LG, cond-mat.mtrl-sci, cs.AI
arXiv: https://arxiv.org/abs/2510.23040v1

Recent advances in generative modeling have shown significant promise in designing novel periodic crystal structures. Existing approaches typically rely on either large language models (LLMs) or equivariant denoising models, each with complementary strengths: LLMs excel at handling discrete atomic types but often struggle with continuous features such as atomic positions and lattice parameters, while denoising models are effective at modeling continuous variables but encounter difficulties in generating accurate atomic compositions. To bridge this gap, we propose CrysLLMGen, a hybrid framework that integrates an LLM with a diffusion model to leverage their complementary strengths for crystal material generation. During sampling, CrysLLMGen first employs a fine-tuned LLM to produce an intermediate representation of atom types, atomic coordinates, and lattice structure. While retaining the predicted atom types, it passes the atomic coordinates and lattice structure to a pre-trained equivariant diffusion model for refinement. Our framework outperforms state-of-the-art generative models across several benchmark tasks and datasets. Specifically, CrysLLMGen not only achieves a balanced performance in terms of structural and compositional validity but also generates more stable and novel materials compared to LLM-based and denoisingbased models Furthermore, CrysLLMGen exhibits strong conditional generation capabilities, effectively producing materials that satisfy user-defined constraints. Code is available at https://github.com/kdmsit/crysllmgen

---

### Sublinear Sketches for Approximate Nearest Neighbor and Kernel Density Estimation

Authors: Ved Danait, Srijan Das, Sujoy Bhore
Published: 2025-10-27
Categories: cs.LG, cs.DS, stat.ML
arXiv: https://arxiv.org/abs/2510.23039v2

Approximate Nearest Neighbor (ANN) search and Approximate Kernel Density Estimation (A-KDE) are fundamental problems at the core of modern machine learning, with broad applications in data analysis, information systems, and large-scale decision making. In massive and dynamic data streams, a central challenge is to design compact sketches that preserve essential structural properties of the data while enabling efficient queries. In this work, we develop new sketching algorithms that achieve sublinear space and query time guarantees for both ANN and A-KDE for a dynamic stream of data. For ANN in the streaming model, under natural assumptions, we design a sublinear sketch that requires only $\mathcal{O}(n^{(1-η)(1+ρ)})$ memory by storing only a sublinear ($n^{-η}$) fraction of the total inputs, where $ρ$ is a parameter of the LSH family, and $0<η<1$. Our method supports sublinear query time, batch queries, and extends to the more general Turnstile model. While earlier works have focused on Exact NN, this is the first result on ANN that achieves near-optimal trade-offs between memory size and approximation error. Next, for A-KDE in the Sliding-Window model, we propose a sketch of size $\mathcal{O}\left(LW \cdot \frac{1}{\sqrt{1+ε} - 1} \log^2 N\right)$, where $L$ is the number of sketch rows, $W$ is the LSH range, $N$ is the window size, and $ε$ is the approximation error. This, to the best of our knowledge, is the first theoretical sublinear sketch guarantee for A-KDE in the Sliding-Window model. We complement our theoretical results with experiments on various real-world datasets, which show that the proposed sketches are lightweight and achieve consistently low error in practice.

---

### Incentivizing Agentic Reasoning in LLM Judges via Tool-Integrated Reinforcement Learning

Authors: Ran Xu, Jingjing Chen, Jiayu Ye, Yu Wu, Jun Yan, Carl Yang, Hongkun Yu
Published: 2025-10-27
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.23038v2

Large Language Models (LLMs) are widely used as judges to evaluate response quality, providing a scalable alternative to human evaluation. However, most LLM judges operate solely on intrinsic text-based reasoning, limiting their ability to verify complex constraints or perform accurate computation. Motivated by the success of tool-integrated reasoning (TIR) in numerous tasks, we propose TIR-Judge, an end-to-end RL framework for training LLM judges that integrates a code executor for precise evaluation. TIR-Judge is built on three principles: (i) diverse training across verifiable and non-verifiable domains, (ii) flexible judgment formats (pointwise, pairwise, listwise), and (iii) iterative RL that bootstraps directly from the initial model without distillation. On seven public benchmarks, TIR-Judge surpasses strong reasoning-based judges by up to 6.4% (pointwise) and 7.7% (pairwise), and achieves listwise performance comparable to Claude-Opus-4 despite having only 8B parameters. Remarkably, TIR-Judge-Zero - trained entirely without distilled judge trajectories, matches the performance of distilled variants, demonstrating that tool-augmented judges can self-evolve through iterative reinforcement learning.

---

### A high-capacity linguistic steganography based on entropy-driven rank-token mapping

Authors: Jun Jiang, Weiming Zhang, Nenghai Yu, Kejiang Chen
Published: 2025-10-27
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2510.23035v1

Linguistic steganography enables covert communication through embedding secret messages into innocuous texts; however, current methods face critical limitations in payload capacity and security. Traditional modification-based methods introduce detectable anomalies, while retrieval-based strategies suffer from low embedding capacity. Modern generative steganography leverages language models to generate natural stego text but struggles with limited entropy in token predictions, further constraining capacity. To address these issues, we propose an entropy-driven framework called RTMStega that integrates rank-based adaptive coding and context-aware decompression with normalized entropy. By mapping secret messages to token probability ranks and dynamically adjusting sampling via context-aware entropy-based adjustments, RTMStega achieves a balance between payload capacity and imperceptibility. Experiments across diverse datasets and models demonstrate that RTMStega triples the payload capacity of mainstream generative steganography, reduces processing time by over 50%, and maintains high text quality, offering a trustworthy solution for secure and efficient covert communication.

---

### Efficient and Encrypted Inference using Binarized Neural Networks within In-Memory Computing Architectures

Authors: Gokulnath Rajendran, Suman Deb, Anupam Chattopadhyay
Published: 2025-10-27
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2510.23034v1

Binarized Neural Networks (BNNs) are a class of deep neural networks designed to utilize minimal computational resources, which drives their popularity across various applications. Recent studies highlight the potential of mapping BNN model parameters onto emerging non-volatile memory technologies, specifically using crossbar architectures, resulting in improved inference performance compared to traditional CMOS implementations. However, the common practice of protecting model parameters from theft attacks by storing them in an encrypted format and decrypting them at runtime introduces significant computational overhead, thus undermining the core principles of in-memory computing, which aim to integrate computation and storage. This paper presents a robust strategy for protecting BNN model parameters, particularly within in-memory computing frameworks. Our method utilizes a secret key derived from a physical unclonable function to transform model parameters prior to storage in the crossbar. Subsequently, the inference operations are performed on the encrypted weights, achieving a very special case of Fully Homomorphic Encryption (FHE) with minimal runtime overhead. Our analysis reveals that inference conducted without the secret key results in drastically diminished performance, with accuracy falling below 15%. These results validate the effectiveness of our protection strategy in securing BNNs within in-memory computing architectures while preserving computational efficiency.

---

### Nested AutoRegressive Models

Authors: Hongyu Wu, Xuhui Fan, Zhangkai Wu, Longbing Cao
Published: 2025-10-27
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.23028v1

AutoRegressive (AR) models have demonstrated competitive performance in image generation, achieving results comparable to those of diffusion models. However, their token-by-token image generation mechanism remains computationally intensive and existing solutions such as VAR often lead to limited sample diversity. In this work, we propose a Nested AutoRegressive~(NestAR) model, which proposes nested AutoRegressive architectures in generating images. NestAR designs multi-scale modules in a hierarchical order. These different scaled modules are constructed in an AR architecture, where one larger-scale module is conditioned on outputs from its previous smaller-scale module. Within each module, NestAR uses another AR structure to generate ``patches'' of tokens. The proposed nested AR architecture reduces the overall complexity from $\mathcal{O}(n)$ to $\mathcal{O}(\log n)$ in generating $n$ image tokens, as well as increases image diversities. NestAR further incorporates flow matching loss to use continuous tokens, and develops objectives to coordinate these multi-scale modules in model training. NestAR achieves competitive image generation performance while significantly lowering computational cost.

---

### Towards Stable and Effective Reinforcement Learning for Mixture-of-Experts

Authors: Di Zhang, Xun Wu, Shaohan Huang, Lingjie Jiang, Yaru Hao, Li Dong, Zewen Chi, Zhifang Sui, Furu Wei
Published: 2025-10-27
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2510.23027v2

Recent advances in reinforcement learning (RL) have substantially improved the training of large-scale language models, leading to significant gains in generation quality and reasoning ability. However, most existing research focuses on dense models, while RL training for Mixture-of-Experts (MoE) architectures remains underexplored. To address the instability commonly observed in MoE training, we propose a novel router-aware approach to optimize importance sampling (IS) weights in off-policy RL. Specifically, we design a rescaling strategy guided by router logits, which effectively reduces gradient variance and mitigates training divergence. Experimental results demonstrate that our method significantly improves both the convergence stability and the final performance of MoE models, highlighting the potential of RL algorithmic innovations tailored to MoE architectures and providing a promising direction for efficient training of large-scale expert models.

---

### Mixed-Density Diffuser: Efficient Planning with Non-Uniform Temporal Resolution

Authors: Crimson Stambaugh, Rajesh P. N. Rao
Published: 2025-10-27
Categories: cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2510.23026v5

Recent studies demonstrate that diffusion planners benefit from sparse-step planning over single-step planning. Training models to skip steps in their trajectories helps capture long-term dependencies without additional memory or computational cost. However, predicting excessively sparse plans degrades performance. We hypothesize this temporal density threshold is non-uniform across a planning horizon and that certain parts of a predicted trajectory should be more densely generated. We propose Mixed-Density Diffuser (MDD), a diffusion planner where the densities throughout the horizon are tunable hyperparameters. We show that MDD surpasses the SOTA Diffusion Veteran (DV) framework across the Maze2D, Franka Kitchen, and Antmaze Datasets for Deep Data-Driven Reinforcement Learning (D4RL) task domains, achieving a new SOTA on the D4RL benchmark.

---

### UniAIDet: A Unified and Universal Benchmark for AI-Generated Image Content Detection and Localization

Authors: Huixuan Zhang, Xiaojun Wan
Published: 2025-10-27
Categories: cs.CV, cs.CL
arXiv: https://arxiv.org/abs/2510.23023v1

With the rapid proliferation of image generative models, the authenticity of digital images has become a significant concern. While existing studies have proposed various methods for detecting AI-generated content, current benchmarks are limited in their coverage of diverse generative models and image categories, often overlooking end-to-end image editing and artistic images. To address these limitations, we introduce UniAIDet, a unified and comprehensive benchmark that includes both photographic and artistic images. UniAIDet covers a wide range of generative models, including text-to-image, image-to-image, image inpainting, image editing, and deepfake models. Using UniAIDet, we conduct a comprehensive evaluation of various detection methods and answer three key research questions regarding generalization capability and the relation between detection and localization. Our benchmark and analysis provide a robust foundation for future research.

---

### M$^{3}$T2IBench: A Large-Scale Multi-Category, Multi-Instance, Multi-Relation Text-to-Image Benchmark

Authors: Huixuan Zhang, Xiaojun Wan
Published: 2025-10-27
Categories: cs.CV, cs.CL
arXiv: https://arxiv.org/abs/2510.23020v1

Text-to-image models are known to struggle with generating images that perfectly align with textual prompts. Several previous studies have focused on evaluating image-text alignment in text-to-image generation. However, these evaluations either address overly simple scenarios, especially overlooking the difficulty of prompts with multiple different instances belonging to the same category, or they introduce metrics that do not correlate well with human evaluation. In this study, we introduce M$^3$T2IBench, a large-scale, multi-category, multi-instance, multi-relation along with an object-detection-based evaluation metric, $AlignScore$, which aligns closely with human evaluation. Our findings reveal that current open-source text-to-image models perform poorly on this challenging benchmark. Additionally, we propose the Revise-Then-Enforce approach to enhance image-text alignment. This training-free post-editing method demonstrates improvements in image-text alignment across a broad range of diffusion models. \footnote{Our code and data has been released in supplementary material and will be made publicly available after the paper is accepted.}

---

### Sentinel: Dynamic Knowledge Distillation for Personalized Federated Intrusion Detection in Heterogeneous IoT Networks

Authors: Gurpreet Singh, Keshav Sood, P. Rajalakshmi, Yong Xiang
Published: 2025-10-27
Categories: cs.LG, cs.DC
arXiv: https://arxiv.org/abs/2510.23019v1

Federated learning (FL) offers a privacy-preserving paradigm for machine learning, but its application in intrusion detection systems (IDS) within IoT networks is challenged by severe class imbalance, non-IID data, and high communication overhead.These challenges severely degrade the performance of conventional FL methods in real-world network traffic classification. To overcome these limitations, we propose Sentinel, a personalized federated IDS (pFed-IDS) framework that incorporates a dual-model architecture on each client, consisting of a personalized teacher and a lightweight shared student model. This design effectively balances deep local adaptation with efficient global model consensus while preserving client privacy by transmitting only the compact student model, thus reducing communication costs. Sentinel integrates three key mechanisms to ensure robust performance: bidirectional knowledge distillation with adaptive temperature scaling, multi-faceted feature alignment, and class-balanced loss functions. Furthermore, the server employs normalized gradient aggregation with equal client weighting to enhance fairness and mitigate client drift. Extensive experiments on the IoTID20 and 5GNIDD benchmark datasets demonstrate that Sentinel significantly outperforms state-of-the-art federated methods, establishing a new performance benchmark, especially under extreme data heterogeneity, while maintaining communication efficiency.

---

### Coupled Flow Matching

Authors: Wenxi Cai, Yuheng Wang, Naichen Shi
Published: 2025-10-27
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2510.23015v1

We introduce Coupled Flow Matching (CPFM), a framework that integrates controllable dimensionality reduction and high-fidelity reconstruction. CPFM learns coupled continuous flows for both the high-dimensional data x and the low-dimensional embedding y, which enables sampling p(y|x) via a latent-space flow and p(x|y) via a data-space flow. Unlike classical dimension-reduction methods, where information discarded during compression is often difficult to recover, CPFM preserves the knowledge of residual information within the weights of a flow network. This design provides bespoke controllability: users may decide which semantic factors to retain explicitly in the latent space, while the complementary information remains recoverable through the flow network. Coupled flow matching builds on two components: (i) an extended Gromov-Wasserstein optimal transport objective that establishes a probabilistic correspondence between data and embeddings, and (ii) a dual-conditional flow-matching network that extrapolates the correspondence to the underlying space. Experiments on multiple benchmarks show that CPFM yields semantically rich embeddings and reconstructs data with higher fidelity than existing baselines.

---

### MoEMeta: Mixture-of-Experts Meta Learning for Few-Shot Relational Learning

Authors: Han Wu, Jie Yin
Published: 2025-10-27
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.23013v4

Few-shot knowledge graph relational learning seeks to perform reasoning over relations given only a limited number of training examples. While existing approaches largely adopt a meta-learning framework for enabling fast adaptation to new relations, they suffer from two key pitfalls. First, they learn relation meta-knowledge in isolation, failing to capture common relational patterns shared across tasks. Second, they struggle to effectively incorporate local, task-specific contexts crucial for rapid adaptation. To address these limitations, we propose MoEMeta, a novel meta-learning framework that disentangles globally shared knowledge from task-specific contexts to enable both effective model generalization and rapid adaptation. MoEMeta introduces two key innovations: (i) a mixture-of-experts (MoE) model that learns globally shared relational prototypes to enhance generalization, and (ii) a task-tailored adaptation mechanism that captures local contexts for fast task-specific adaptation. By balancing global generalization with local adaptability, MoEMeta significantly advances few-shot relational learning. Extensive experiments and analyses on three KG benchmarks show that MoEMeta consistently outperforms existing baselines, achieving state-of-the-art performance.

---

### Softmax is $1/2$-Lipschitz: A tight bound across all $\ell_p$ norms

Authors: Pravin Nair
Published: 2025-10-27
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.23012v1

The softmax function is a basic operator in machine learning and optimization, used in classification, attention mechanisms, reinforcement learning, game theory, and problems involving log-sum-exp terms. Existing robustness guarantees of learning models and convergence analysis of optimization algorithms typically consider the softmax operator to have a Lipschitz constant of $1$ with respect to the $\ell_2$ norm. In this work, we prove that the softmax function is contractive with the Lipschitz constant $1/2$, uniformly across all $\ell_p$ norms with $p \ge 1$. We also show that the local Lipschitz constant of softmax attains $1/2$ for $p = 1$ and $p = \infty$, and for $p \in (1,\infty)$, the constant remains strictly below $1/2$ and the supremum $1/2$ is achieved only in the limit. To our knowledge, this is the first comprehensive norm-uniform analysis of softmax Lipschitz continuity. We demonstrate how the sharper constant directly improves a range of existing theoretical results on robustness and convergence. We further validate the sharpness of the $1/2$ Lipschitz constant of the softmax operator through empirical studies on attention-based architectures (ViT, GPT-2, Qwen3-8B) and on stochastic policies in reinforcement learning.

---

### LangLingual: A Personalised, Exercise-oriented English Language Learning Tool Leveraging Large Language Models

Authors: Sammriddh Gupta, Sonit Singh, Aditya Joshi, Mira Kim
Published: 2025-10-27
Categories: cs.CL, cs.CY
arXiv: https://arxiv.org/abs/2510.23011v1

Language educators strive to create a rich experience for learners, while they may be restricted in the extend of feedback and practice they can provide. We present the design and development of LangLingual, a conversational agent built using the LangChain framework and powered by Large Language Models. The system is specifically designed to provide real-time, grammar-focused feedback, generate context-aware language exercises and track learner proficiency over time. The paper discusses the architecture, implementation and evaluation of LangLingual in detail. The results indicate strong usability, positive learning outcomes and encouraging learner engagement.

---

### UGAE: Unified Geometry and Attribute Enhancement for G-PCC Compressed Point Clouds

Authors: Pan Zhao, Hui Yuan, Chongzhen Tian, Tian Guo, Raouf Hamzaoui, Zhigeng Pan
Published: 2025-10-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.23009v1

Lossy compression of point clouds reduces storage and transmission costs; however, it inevitably leads to irreversible distortion in geometry structure and attribute information. To address these issues, we propose a unified geometry and attribute enhancement (UGAE) framework, which consists of three core components: post-geometry enhancement (PoGE), pre-attribute enhancement (PAE), and post-attribute enhancement (PoAE). In PoGE, a Transformer-based sparse convolutional U-Net is used to reconstruct the geometry structure with high precision by predicting voxel occupancy probabilities. Building on the refined geometry structure, PAE introduces an innovative enhanced geometry-guided recoloring strategy, which uses a detail-aware K-Nearest Neighbors (DA-KNN) method to achieve accurate recoloring and effectively preserve high-frequency details before attribute compression. Finally, at the decoder side, PoAE uses an attribute residual prediction network with a weighted mean squared error (W-MSE) loss to enhance the quality of high-frequency regions while maintaining the fidelity of low-frequency regions. UGAE significantly outperformed existing methods on three benchmark datasets: 8iVFB, Owlii, and MVUB. Compared to the latest G-PCC test model (TMC13v29), UGAE achieved an average BD-PSNR gain of 9.98 dB and 90.98% BD-bitrate savings for geometry under the D1 metric, as well as a 3.67 dB BD-PSNR improvement with 56.88% BD-bitrate savings for attributes on the Y component. Additionally, it improved perceptual quality significantly.

---

### From Prompt Optimization to Multi-Dimensional Credibility Evaluation: Enhancing Trustworthiness of Chinese LLM-Generated Liver MRI Reports -- with Preliminary Extension to Lung Cancer

Authors: Qiuli Wang, Xinhuang Sun, Yonglin Chen, Jie Cheng, Yongxu Liu, Xingpeng Zhang, Xiaoming Li, Wei Chen
Published: 2025-10-27
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.23008v3

Large language models (LLMs) have demonstrated promising performance in generating diagnostic conclusions from imaging findings, thereby supporting radiology reporting, trainee education, and quality control. However, systematic guidance on how to optimize prompt design across different clinical contexts remains underexplored. Moreover, a comprehensive and standardized framework for assessing the trustworthiness of LLM-generated radiology reports is yet to be established. This study aims to enhance the trustworthiness of LLM-generated liver MRI reports by introducing a Multi-Dimensional Credibility Assessment (MDCA) framework and providing guidance on institution-specific prompt optimization. The proposed framework is applied to evaluate and compare the performance of several advanced LLMs, including Kimi-K2-Instruct-0905, Qwen3-235B-A22B-Instruct-2507, DeepSeek-V3, and ByteDance-Seed-OSS-36B-Instruct, using the SiliconFlow platform.

---

### CoMo: Compositional Motion Customization for Text-to-Video Generation

Authors: Youcan Xu, Zhen Wang, Jiaxin Shi, Kexin Li, Feifei Shao, Jun Xiao, Yi Yang, Jun Yu, Long Chen
Published: 2025-10-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.23007v1

While recent text-to-video models excel at generating diverse scenes, they struggle with precise motion control, particularly for complex, multi-subject motions. Although methods for single-motion customization have been developed to address this gap, they fail in compositional scenarios due to two primary challenges: motion-appearance entanglement and ineffective multi-motion blending. This paper introduces CoMo, a novel framework for $\textbf{compositional motion customization}$ in text-to-video generation, enabling the synthesis of multiple, distinct motions within a single video. CoMo addresses these issues through a two-phase approach. First, in the single-motion learning phase, a static-dynamic decoupled tuning paradigm disentangles motion from appearance to learn a motion-specific module. Second, in the multi-motion composition phase, a plug-and-play divide-and-merge strategy composes these learned motions without additional training by spatially isolating their influence during the denoising process. To facilitate research in this new domain, we also introduce a new benchmark and a novel evaluation metric designed to assess multi-motion fidelity and blending. Extensive experiments demonstrate that CoMo achieves state-of-the-art performance, significantly advancing the capabilities of controllable video generation. Our project page is at https://como6.github.io/.

---

### Understanding In-Context Learning Beyond Transformers: An Investigation of State Space and Hybrid Architectures

Authors: Shenran Wang, Timothy Tin-Long Tse, Jian Zhu
Published: 2025-10-27
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.23006v2

We perform in-depth evaluations of in-context learning (ICL) on state-of-the-art transformer, state-space, and hybrid large language models over two categories of knowledge-based ICL tasks. Using a combination of behavioral probing and intervention-based methods, we have discovered that, while LLMs of different architectures can behave similarly in task performance, their internals could remain different. We discover that function vectors (FVs) responsible for ICL are primarily located in the self-attention and Mamba layers, and speculate that Mamba2 uses a different mechanism from FVs to perform ICL. FVs are more important for ICL involving parametric knowledge retrieval, but not for contextual knowledge understanding. Our work contributes to a more nuanced understanding across architectures and task types. Methodologically, our approach also highlights the importance of combining both behavioural and mechanistic analyses to investigate LLM capabilities.

---

### An Intelligent Water-Saving Irrigation System Based on Multi-Sensor Fusion and Visual Servoing Control

Authors: ZhengKai Huang, YiKun Wang, ChenYu Hui, XiaoCheng
Published: 2025-10-27
Categories: cs.RO, cs.CV, eess.SY
arXiv: https://arxiv.org/abs/2510.23003v1

This paper introduces an intelligent water-saving irrigation system designed to address critical challenges in precision agriculture, such as inefficient water use and poor terrain adaptability. The system integrates advanced computer vision, robotic control, and real-time stabilization technologies via a multi-sensor fusion approach. A lightweight YOLO model, deployed on an embedded vision processor (K210), enables real-time plant container detection with over 96% accuracy under varying lighting conditions. A simplified hand-eye calibration algorithm-designed for 'handheld camera' robot arm configurations-ensures that the end effector can be precisely positioned, with a success rate exceeding 90%. The active leveling system, driven by the STM32F103ZET6 main control chip and JY901S inertial measurement data, can stabilize the irrigation platform on slopes up to 10 degrees, with a response time of 1.8 seconds. Experimental results across three simulated agricultural environments (standard greenhouse, hilly terrain, complex lighting) demonstrate a 30-50% reduction in water consumption compared to conventional flood irrigation, with water use efficiency exceeding 92% in all test cases.

---

### ProfileXAI: User-Adaptive Explainable AI

Authors: Gilber A. Corrales, Carlos Andrés Ferro Sánchez, Reinel Tabares-Soto, Jesús Alfonso López Sotelo, Gonzalo A. Ruz, Johan Sebastian Piña Durán
Published: 2025-10-27
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.22998v1

ProfileXAI is a model- and domain-agnostic framework that couples post-hoc explainers (SHAP, LIME, Anchor) with retrieval - augmented LLMs to produce explanations for different types of users. The system indexes a multimodal knowledge base, selects an explainer per instance via quantitative criteria, and generates grounded narratives with chat-enabled prompting. On Heart Disease and Thyroid Cancer datasets, we evaluate fidelity, robustness, parsimony, token use, and perceived quality. No explainer dominates: LIME achieves the best fidelity-robustness trade-off (Infidelity $\le 0.30$, $L<0.7$ on Heart Disease); Anchor yields the sparsest, low-token rules; SHAP attains the highest satisfaction ($\bar{x}=4.1$). Profile conditioning stabilizes tokens ($σ\le 13\%$) and maintains positive ratings across profiles ($\bar{x}\ge 3.7$, with domain experts at $3.77$), enabling efficient and trustworthy explanations.

---

### LoMix: Learnable Weighted Multi-Scale Logits Mixing for Medical Image Segmentation

Authors: Md Mostafijur Rahman, Radu Marculescu
Published: 2025-10-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.22995v1

U-shaped networks output logits at multiple spatial scales, each capturing a different blend of coarse context and fine detail. Yet, training still treats these logits in isolation - either supervising only the final, highest-resolution logits or applying deep supervision with identical loss weights at every scale - without exploring mixed-scale combinations. Consequently, the decoder output misses the complementary cues that arise only when coarse and fine predictions are fused. To address this issue, we introduce LoMix (Logits Mixing), a NAS-inspired, differentiable plug-and-play module that generates new mixed-scale outputs and learns how exactly each of them should guide the training process. More precisely, LoMix mixes the multi-scale decoder logits with four lightweight fusion operators: addition, multiplication, concatenation, and attention-based weighted fusion, yielding a rich set of synthetic mutant maps. Every original or mutant map is given a softplus loss weight that is co-optimized with network parameters, mimicking a one-step architecture search that automatically discovers the most useful scales, mixtures, and operators. Plugging LoMix into recent U-shaped architectures (i.e., PVT-V2-B2 backbone with EMCAD decoder) on Synapse 8-organ dataset improves DICE by +4.2% over single-output supervision, +2.2% over deep supervision, and +1.5% over equally weighted additive fusion, all with zero inference overhead. When training data are scarce (e.g., one or two labeled scans), the advantage grows to +9.23%, underscoring LoMix's data efficiency. Across four benchmarks and diverse U-shaped networks, LoMiX improves DICE by up to +13.5% over single-output supervision, confirming that learnable weighted mixed-scale fusion generalizes broadly while remaining data efficient, fully interpretable, and overhead-free at inference. Our code is available at https://github.com/SLDGroup/LoMix.

---

### SceneDecorator: Towards Scene-Oriented Story Generation with Scene Planning and Scene Consistency

Authors: Quanjian Song, Donghao Zhou, Jingyu Lin, Fei Shen, Jiaze Wang, Xiaowei Hu, Cunjian Chen, Pheng-Ann Heng
Published: 2025-10-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.22994v1

Recent text-to-image models have revolutionized image generation, but they still struggle with maintaining concept consistency across generated images. While existing works focus on character consistency, they often overlook the crucial role of scenes in storytelling, which restricts their creativity in practice. This paper introduces scene-oriented story generation, addressing two key challenges: (i) scene planning, where current methods fail to ensure scene-level narrative coherence by relying solely on text descriptions, and (ii) scene consistency, which remains largely unexplored in terms of maintaining scene consistency across multiple stories. We propose SceneDecorator, a training-free framework that employs VLM-Guided Scene Planning to ensure narrative coherence across different scenes in a ``global-to-local'' manner, and Long-Term Scene-Sharing Attention to maintain long-term scene consistency and subject diversity across generated stories. Extensive experiments demonstrate the superior performance of SceneDecorator, highlighting its potential to unleash creativity in the fields of arts, films, and games.

---

### Can Language Models Compose Skills In-Context?

Authors: Zidong Liu, Zhuoyan Xu, Zhenmei Shi, Yingyu Liang
Published: 2025-10-27
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2510.22993v1

Composing basic skills from simple tasks to accomplish composite tasks is crucial for modern intelligent systems. We investigate the in-context composition ability of language models to perform composite tasks that combine basic skills demonstrated in in-context examples. This is more challenging than the standard setting, where skills and their composition can be learned in training. We conduct systematic experiments on various representative open-source language models, utilizing linguistic and logical tasks designed to probe composition abilities. The results reveal that simple task examples can have a surprising negative impact on the performance, because the models generally struggle to recognize and assemble the skills correctly, even with Chain-of-Thought examples. Theoretical analysis further shows that it is crucial to align examples with the corresponding steps in the composition. This inspires a method for the probing tasks, whose improved performance provides positive support for our insights.

---

### Adaptive Forests For Classification

Authors: Dimitris Bertsimas, Yubing Cui
Published: 2025-10-27
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.22991v1

Random Forests (RF) and Extreme Gradient Boosting (XGBoost) are two of the most widely used and highly performing classification and regression models. They aggregate equally weighted CART trees, generated randomly in RF or sequentially in XGBoost. In this paper, we propose Adaptive Forests (AF), a novel approach that adaptively selects the weights of the underlying CART models. AF combines (a) the Optimal Predictive-Policy Trees (OP2T) framework to prescribe tailored, input-dependent unequal weights to trees and (b) Mixed Integer Optimization (MIO) to refine weight candidates dynamically, enhancing overall performance. We demonstrate that AF consistently outperforms RF, XGBoost, and other weighted RF in binary and multi-class classification problems over 20+ real-world datasets.

---

### USF-MAE: Ultrasound Self-Supervised Foundation Model with Masked Autoencoding

Authors: Youssef Megahed, Robin Ducharme, Aylin Erman, Mark Walker, Steven Hawken, Adrian D. C. Chan
Published: 2025-10-27
Categories: eess.IV, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2510.22990v2

Ultrasound imaging is one of the most widely used diagnostic modalities, offering real-time, radiation-free assessment across diverse clinical domains. However, interpretation of ultrasound images remains challenging due to high noise levels, operator dependence, and limited field of view, resulting in substantial inter-observer variability. Current Deep Learning approaches are hindered by the scarcity of large labeled datasets and the domain gap between general and sonographic images, which limits the transferability of models pretrained on non-medical data. To address these challenges, we introduce the Ultrasound Self-Supervised Foundation Model with Masked Autoencoding (USF-MAE), the first large-scale self-supervised MAE framework pretrained exclusively on ultrasound data. The model was pre-trained on 370,000 2D and 3D ultrasound images curated from 46 open-source datasets, collectively termed OpenUS-46, spanning over twenty anatomical regions. This curated dataset has been made publicly available to facilitate further research and reproducibility. Using a Vision Transformer encoder-decoder architecture, USF-MAE reconstructs masked image patches, enabling it to learn rich, modality-specific representations directly from unlabeled data. The pretrained encoder was fine-tuned on three public downstream classification benchmarks: BUS-BRA (breast cancer), MMOTU-2D (ovarian tumors), and GIST514-DB (gastrointestinal stromal tumors). Across all tasks, USF-MAE consistently outperformed conventional CNN and ViT baselines, achieving F1-scores of 81.6%, 79.6%, and 82.4%, respectively. Despite not using labels during pretraining, USF-MAE approached the performance of the supervised foundation model UltraSam on breast cancer classification and surpassed it on the other tasks, demonstrating strong cross-anatomical generalization.

---

### Equivariant Neural Networks for General Linear Symmetries on Lie Algebras

Authors: Chankyo Kim, Sicheng Zhao, Minghan Zhu, Tzu-Yuan Lin, Maani Ghaffari
Published: 2025-10-27
Categories: cs.LG, cs.NE
arXiv: https://arxiv.org/abs/2510.22984v2

Many scientific and geometric problems exhibit general linear symmetries, yet most equivariant neural networks are built for compact groups or simple vector features, limiting their reuse on matrix-valued data such as covariances, inertias, or shape tensors. We introduce Reductive Lie Neurons (ReLNs), an exactly GL(n)-equivariant architecture that natively supports matrix-valued and Lie-algebraic features. ReLNs resolve a central stability issue for reductive Lie algebras by introducing a non-degenerate adjoint (conjugation)-invariant bilinear form, enabling principled nonlinear interactions and invariant feature construction in a single architecture that transfers across subgroups without redesign. We demonstrate ReLNs on algebraic tasks with sl(3) and sp(4) symmetries, Lorentz-equivariant particle physics, uncertainty-aware drone state estimation via joint velocity-covariance processing, learning from 3D Gaussian-splat representations, and EMLP double-pendulum benchmark spanning multiple symmetry groups. ReLNs consistently match or outperform strong equivariant and self-supervised baselines while using substantially fewer parameters and compute, improving the accuracy-efficiency trade-off and providing a practical, reusable backbone for learning with broad linear symmetries. Project page: https://reductive-lie-neuron.github.io/

---

### QoSGMAA: A Robust Multi-Order Graph Attention and Adversarial Framework for Sparse QoS Prediction

Authors: Guanchen Du, Jianlong Xu, Mingtong Li, Ruiqi Wang, Qianqing Guo, Caiyi Chen, Qingcao Dai, Yuxiang Zeng
Published: 2025-10-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.22982v1

With the rapid advancement of internet technologies, network services have become critical for delivering diverse and reliable applications to users. However, the exponential growth in the number of available services has resulted in many similar offerings, posing significant challenges in selecting optimal services. Predicting Quality of Service (QoS) accurately thus becomes a fundamental prerequisite for ensuring reliability and user satisfaction. However, existing QoS prediction methods often fail to capture rich contextual information and exhibit poor performance under extreme data sparsity and structural noise. To bridge this gap, we propose a novel architecture, QoSMGAA, specifically designed to enhance prediction accuracy in complex and noisy network service environments. QoSMGAA integrates a multi-order attention mechanism to aggregate extensive contextual data and predict missing QoS values effectively. Additionally, our method incorporates adversarial neural networks to perform autoregressive supervised learning based on transformed interaction matrices. To capture complex, higher-order interactions among users and services, we employ a discrete sampling technique leveraging the Gumbel-Softmax method to generate informative negative samples. Comprehensive experimental validation conducted on large-scale real-world datasets demonstrates that our proposed model significantly outperforms existing baseline methods, highlighting its strong potential for practical deployment in service selection and recommendation scenarios.

---

### Exploring Semantic-constrained Adversarial Example with Instruction Uncertainty Reduction

Authors: Jin Hu, Jiakai Wang, Linna Jing, Haolin Li, Haodong Liu, Haotong Qin, Aishan Liu, Ke Xu, Xianglong Liu
Published: 2025-10-27
Categories: cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2510.22981v1

Recently, semantically constrained adversarial examples (SemanticAE), which are directly generated from natural language instructions, have become a promising avenue for future research due to their flexible attacking forms. To generate SemanticAEs, current methods fall short of satisfactory attacking ability as the key underlying factors of semantic uncertainty in human instructions, such as referring diversity, descriptive incompleteness, and boundary ambiguity, have not been fully investigated. To tackle the issues, this paper develops a multi-dimensional instruction uncertainty reduction (InSUR) framework to generate more satisfactory SemanticAE, i.e., transferable, adaptive, and effective. Specifically, in the dimension of the sampling method, we propose the residual-driven attacking direction stabilization to alleviate the unstable adversarial optimization caused by the diversity of language references. By coarsely predicting the language-guided sampling process, the optimization process will be stabilized by the designed ResAdv-DDIM sampler, therefore releasing the transferable and robust adversarial capability of multi-step diffusion models. In task modeling, we propose the context-encoded attacking scenario constraint to supplement the missing knowledge from incomplete human instructions. Guidance masking and renderer integration are proposed to regulate the constraints of 2D/3D SemanticAE, activating stronger scenario-adapted attacks. Moreover, in the dimension of generator evaluation, we propose the semantic-abstracted attacking evaluation enhancement by clarifying the evaluation boundary, facilitating the development of more effective SemanticAE generators. Extensive experiments demonstrate the superiority of the transfer attack performance of InSUR. Moreover, we realize the reference-free generation of semantically constrained 3D adversarial examples for the first time.

---

### How Muon's Spectral Design Benefits Generalization: A Study on Imbalanced Data

Authors: Bhavya Vasudeva, Puneesh Deora, Yize Zhao, Vatsal Sharan, Christos Thrampoulidis
Published: 2025-10-27
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.22980v3

The growing adoption of spectrum-aware matrix-valued optimizers such as Muon and Shampoo in deep learning motivates a systematic study of their generalization properties and, in particular, when they might outperform competitive algorithms. We approach this question by introducing appropriate simplifying abstractions as follows: First, we use imbalanced data as a testbed. Second, we study the canonical form of such optimizers, which is Spectral Gradient Descent (SpecGD) -- each update step is $UV^T$ where $UΣV^T$ is the truncated SVD of the gradient. Third, within this framework we identify a canonical setting for which we precisely quantify when SpecGD outperforms vanilla Euclidean GD. For a Gaussian mixture data model and both linear and bilinear models, we show that unlike GD, which prioritizes learning dominant principal components of the data first, SpecGD learns all principal components of the data at equal rates. We demonstrate how this translates to a growing gap in class balanced loss favoring SpecGD early in training and further show that the gap remains consistent even when the GD counterpart uses adaptive step-sizes via normalization. By extending the analysis to deep linear models, we show that depth amplifies these effects. We empirically verify our theoretical findings on a variety of imbalanced datasets. Our experiments compare practical variants of spectral methods, like Muon and Shampoo, against their Euclidean counterparts and Adam. The results validate our findings that these spectral optimizers achieve superior generalization by promoting a more balanced learning of the data's underlying components.

---

### The Reasoning Trap: How Enhancing LLM Reasoning Amplifies Tool Hallucination

Authors: Chenlong Yin, Zeyang Sha, Shiwen Cui, Changhua Meng, Zechao Li
Published: 2025-10-27
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.22977v2

Enhancing the reasoning capabilities of Large Language Models (LLMs) is a key strategy for building Agents that "think then act." However, recent observations, like OpenAI's o3, suggest a paradox: stronger reasoning often coincides with increased hallucination, yet no prior work has systematically examined whether reasoning enhancement itself causes tool hallucination. To address this gap, we pose the central question: Does strengthening reasoning increase tool hallucination? To answer this, we introduce SimpleToolHalluBench, a diagnostic benchmark measuring tool hallucination in two failure modes: (i) no tool available, and (ii) only distractor tools available. Through controlled experiments, we establish three key findings. First, we demonstrate a causal relationship: progressively enhancing reasoning through RL increases tool hallucination proportionally with task performance gains. Second, this effect transcends overfitting - training on non-tool tasks (e.g., mathematics) still amplifies subsequent tool hallucination. Third, the effect is method-agnostic, appearing when reasoning is instilled via supervised fine-tuning and when it is merely elicited at inference by switching from direct answers to step-by-step thinking. We also evaluate mitigation strategies including Prompt Engineering and Direct Preference Optimization (DPO), revealing a fundamental reliability-capability trade-off: reducing hallucination consistently degrades utility. Mechanistically, Reasoning RL disproportionately collapses tool-reliability-related representations, and hallucinations surface as amplified divergences concentrated in late-layer residual streams. These findings reveal that current reasoning enhancement methods inherently amplify tool hallucination, highlighting the need for new training objectives that jointly optimize for capability and reliability.

---

### Analysis of accuracy and efficiency of neural networks to simulate Navier-Stokes fluid flows with obstacles

Authors: Rui Hespanha, Elliot McGuire, João Hespanha
Published: 2025-10-27
Categories: physics.flu-dyn, cs.LG
arXiv: https://arxiv.org/abs/2510.22976v1

Conventional fluid simulations can be time consuming and energy intensive. We researched the viability of a neural network for simulating incompressible fluids in a randomized obstacle-heavy environment, as an alternative to the numerical simulation of the Navier-Stokes equation. We hypothesized that the neural network predictions would have a relatively low error for simulations over a small number of time steps, but errors would eventually accumulate to the point that the output would become very noisy. Over a rich set of obstacle configurations, we achieved a root mean square error of 0.32% on our training dataset and 0.36% on a testing dataset. These errors only grew to 1.45% and 2.34% at t = 10 and, 2.11% and 4.16% at timestep t = 20. We also found that our selected neural network was approximately 8,800 times faster at predicting the flow than a conventional simulation. Our findings indicate neural networks can be extremely useful at simulating fluids in obstacle-heavy environments. Useful applications include modeling forest fire smoke, pipe fluid flow, and underwater/flood currents.

---

### VoMP: Predicting Volumetric Mechanical Property Fields

Authors: Rishit Dagli, Donglai Xiang, Vismay Modi, Charles Loop, Clement Fuji Tsang, Anka He Chen, Anita Hu, Gavriel State, David I. W. Levin, Maria Shugrina
Published: 2025-10-27
Categories: cs.CV, cs.GR, cs.LG
arXiv: https://arxiv.org/abs/2510.22975v2

Physical simulation relies on spatially-varying mechanical properties, often laboriously hand-crafted. VoMP is a feed-forward method trained to predict Young's modulus ($E$), Poisson's ratio ($ν$), and density ($ρ$) throughout the volume of 3D objects, in any representation that can be rendered and voxelized. VoMP aggregates per-voxel multi-view features and passes them to our trained Geometry Transformer to predict per-voxel material latent codes. These latents reside on a manifold of physically plausible materials, which we learn from a real-world dataset, guaranteeing the validity of decoded per-voxel materials. To obtain object-level training data, we propose an annotation pipeline combining knowledge from segmented 3D datasets, material databases, and a vision-language model, along with a new benchmark. Experiments show that VoMP estimates accurate volumetric properties, far outperforming prior art in accuracy and speed.

---

### Scaling Up Occupancy-centric Driving Scene Generation: Dataset and Method

Authors: Bohan Li, Xin Jin, Hu Zhu, Hongsi Liu, Ruikai Li, Jiazhe Guo, Kaiwen Cai, Chao Ma, Yueming Jin, Hao Zhao, Xiaokang Yang, Wenjun Zeng
Published: 2025-10-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.22973v2

Driving scene generation is a critical domain for autonomous driving, enabling downstream applications, including perception and planning evaluation. Occupancy-centric methods have recently achieved state-of-the-art results by offering consistent conditioning across frames and modalities; however, their performance heavily depends on annotated occupancy data, which still remains scarce. To overcome this limitation, we curate Nuplan-Occ, the largest semantic occupancy dataset to date, constructed from the widely used Nuplan benchmark. Its scale and diversity facilitate not only large-scale generative modeling but also autonomous driving downstream applications. Based on this dataset, we develop a unified framework that jointly synthesizes high-quality semantic occupancy, multi-view videos, and LiDAR point clouds. Our approach incorporates a spatio-temporal disentangled architecture to support high-fidelity spatial expansion and temporal forecasting of 4D dynamic occupancy. To bridge modal gaps, we further propose two novel techniques: a Gaussian splatting-based sparse point map rendering strategy that enhances multi-view video generation, and a sensor-aware embedding strategy that explicitly models LiDAR sensor properties for realistic multi-LiDAR simulation. Extensive experiments demonstrate that our method achieves superior generation fidelity and scalability compared to existing approaches, and validates its practical value in downstream tasks. Repo: https://github.com/Arlo0o/UniScene-Unified-Occupancy-centric-Driving-Scene-Generation/tree/v2

---