# Research Papers — 2025-12 · bundle page 156 of 175

> Full-text markdown of papers #7751–7800 of 8703 published in 2025-12, newest first. AI-readable mirrors of the full 8703-paper 2025-12 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2025-12/page/156
[← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/155.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-12/page/157.md)

### EfficientECG: Cross-Attention with Feature Fusion for Efficient Electrocardiogram Classification

Authors: Hanhui Deng, Xinglin Li, Jie Luo, Zhanpeng Jin, Di Wu
Published: 2025-12-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.03804v1

Electrocardiogram is a useful diagnostic signal that can detect cardiac abnormalities by measuring the electrical activity generated by the heart. Due to its rapid, non-invasive, and richly informative characteristics, ECG has many emerging applications. In this paper, we study novel deep learning technologies to effectively manage and analyse ECG data, with the aim of building a diagnostic model, accurately and quickly, that can substantially reduce the burden on medical workers. Unlike the existing ECG models that exhibit a high misdiagnosis rate, our deep learning approaches can automatically extract the features of ECG data through end-to-end training. Specifically, we first devise EfficientECG, an accurate and lightweight classification model for ECG analysis based on the existing EfficientNet model, which can effectively handle high-frequency long-sequence ECG data with various leading types. On top of that, we next propose a cross-attention-based feature fusion model of EfficientECG for analysing multi-lead ECG data with multiple features (e.g., gender and age). Our evaluations on representative ECG datasets validate the superiority of our model against state-of-the-art works in terms of high precision, multi-feature fusion, and lightweights.

---

### Enhancing Instruction-Following Capabilities in Seq2Seq Models: DoLA Adaptations for T5

Authors: Huey Sun, Anabel Yong, Lorenzo Gilly, Felipe Jin
Published: 2025-12-03
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.03803v2

Encoder-decoder models such as FLAN-T5 are finetuned to follow instructions, but often fail when the instructions conflict with memorized continuations ingrained during training. To understand this behavior, we adapt DoLa to FLAN-T5 and examine how representations evolve in the decoder. Our findings show that T5's intermediate layers undergo rapid shifts driven by cross-attention to the encoder. When projected through the language modeling head, each depth presents highly volatile token preferences, leading to unreliable behavior with contrastive decoding. Motivated by this, we introduce a gradient-based activation-steering method that injects an "instruction-compliance" direction into mid-decoder layers, where the representation is both meaningful and still malleable. This intervention dramatically improves MemoTrap performance (52% to 99.7%), demonstrating that mechanistic steering can succeed where contrastive decoding fails in Seq2Seq architectures.

---

### Enhancing Instruction-Following Capabilities in Seq2Seq Models: DoLA Adaptations for T5

Authors: Huey Sun, Anabel Yong, Lorenzo Gilly, Felipe Jin
Published: 2025-12-03
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.03803v1

Contrastive decoding is a lightweight and effective inference-time method that improves the quality of text generation in Large Language Models. However, algorithms such as DoLa (Decoding by Contrastive Layers) have only been implemented in decoder-only architectures and studied for their impact on improving factuality. This work adapts DoLa for the T5 and FLAN-T5 model families and evaluates its impact on the models' instruction following capabilities, which to our knowledge is the first implementation of a contrastive decoding strategy in an encoder-decoder architecture. Our results show that DoLa improves the faithfulness of text generation for certain categories of tasks and harms others. To understand these results, we present a layer-by-layer analysis of logit evolution in a FLAN-T5 model to quantify DoLa's impact on token output probabilities.

---

### LSRS: Latent Scale Rejection Sampling for Visual Autoregressive Modeling

Authors: Hong-Kai Zheng, Piji Li
Published: 2025-12-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.03796v1

Visual Autoregressive (VAR) modeling approach for image generation proposes autoregressive processing across hierarchical scales, decoding multiple tokens per scale in parallel. This method achieves high-quality generation while accelerating synthesis. However, parallel token sampling within a scale may lead to structural errors, resulting in suboptimal generated images. To mitigate this, we propose Latent Scale Rejection Sampling (LSRS), a method that progressively refines token maps in the latent scale during inference to enhance VAR models. Our method uses a lightweight scoring model to evaluate multiple candidate token maps sampled at each scale, selecting the high-quality map to guide subsequent scale generation. By prioritizing early scales critical for structural coherence, LSRS effectively mitigates autoregressive error accumulation while maintaining computational efficiency. Experiments demonstrate that LSRS significantly improves VAR's generation quality with minimal additional computational overhead. For the VAR-d30 model, LSRS increases the inference time by merely 1% while reducing its FID score from 1.95 to 1.78. When the inference time is increased by 15%, the FID score can be further reduced to 1.66. LSRS offers an efficient test-time scaling solution for enhancing VAR-based generation.

---

### MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving

Authors: Jia Hu, Zhexi Lian, Xuerun Yan, Ruiang Bi, Dou Shen, Yu Ruan, Chunlong Xia, Haoran Wang
Published: 2025-12-03
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2512.03795v3

Autonomous Driving (AD) vehicles still struggle to exhibit human-like behavior in highly dynamic and interactive traffic scenarios. The key challenge lies in AD's limited ability to interact with surrounding vehicles, largely due to a lack of understanding the underlying mechanisms of social interaction. To address this issue, we introduce MPCFormer, an explainable socially-aware autonomous driving approach with physics-informed and data-driven coupled social interaction dynamics. In this model, the dynamics are formulated into a discrete space-state representation, which embeds physics priors to enhance modeling explainability. The dynamics coefficients are learned from naturalistic driving data via a Transformer-based encoder-decoder architecture. To the best of our knowledge, MPCFormer is the first approach to explicitly model the dynamics of multi-vehicle social interactions. The learned social interaction dynamics enable the planner to generate manifold, human-like behaviors when interacting with surrounding traffic. By leveraging the MPC framework, the approach mitigates the potential safety risks typically associated with purely learning-based methods. Open-looped evaluation on NGSIM dataset demonstrates that MPCFormer achieves superior social interaction awareness, yielding the lowest trajectory prediction errors compared with other state-of-the-art approaches. The prediction achieves an ADE as low as 0.86 m over a long prediction horizon of 5 seconds. Close-looped experiments in highly intense interaction scenarios, where consecutive lane changes are required to exit an off-ramp, further validate the effectiveness of MPCFormer. Results show that MPCFormer achieves the highest planning success rate of 94.67%, improves driving efficiency by 15.75%, and reduces the collision rate from 21.25% to 0.5%, outperforming a frontier Reinforcement Learning (RL) based planner.

---

### MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving

Authors: Jia Hu, Zhexi Lian, Xuerun Yan, Ruiang Bi, Dou Shen, Yu Ruan, Haoran Wang
Published: 2025-12-03
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2512.03795v1

Autonomous Driving (AD) vehicles still struggle to exhibit human-like behavior in highly dynamic and interactive traffic scenarios. The key challenge lies in AD's limited ability to interact with surrounding vehicles, largely due to a lack of understanding the underlying mechanisms of social interaction. To address this issue, we introduce MPCFormer, an explainable socially-aware autonomous driving approach with physics-informed and data-driven coupled social interaction dynamics. In this model, the dynamics are formulated into a discrete space-state representation, which embeds physics priors to enhance modeling explainability. The dynamics coefficients are learned from naturalistic driving data via a Transformer-based encoder-decoder architecture. To the best of our knowledge, MPCFormer is the first approach to explicitly model the dynamics of multi-vehicle social interactions. The learned social interaction dynamics enable the planner to generate manifold, human-like behaviors when interacting with surrounding traffic. By leveraging the MPC framework, the approach mitigates the potential safety risks typically associated with purely learning-based methods. Open-looped evaluation on NGSIM dataset demonstrates that MPCFormer achieves superior social interaction awareness, yielding the lowest trajectory prediction errors compared with other state-of-the-art approach. The prediction achieves an ADE as low as 0.86 m over a long prediction horizon of 5 seconds. Close-looped experiments in highly intense interaction scenarios, where consecutive lane changes are required to exit an off-ramp, further validate the effectiveness of MPCFormer. Results show that MPCFormer achieves the highest planning success rate of 94.67%, improves driving efficiency by 15.75%, and reduces the collision rate from 21.25% to 0.5%, outperforming a frontier Reinforcement Learning (RL) based planner.

---

### AdaptVision: Efficient Vision-Language Models via Adaptive Visual Acquisition

Authors: Zichuan Lin, Yicheng Liu, Yang Yang, Lvfang Tao, Deheng Ye
Published: 2025-12-03
Categories: cs.CV, cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2512.03794v3

Vision-Language Models (VLMs) have achieved remarkable success in visual question answering tasks, but their reliance on large numbers of visual tokens introduces significant computational overhead. While existing efficient VLM approaches reduce visual tokens through fixed-ratio compression, they operate passively and lack the ability to adapt to varying task requirements. This motivates a fundamental question: Can VLMs autonomously determine the minimum number of visual tokens required for each sample? Inspired by human active vision mechanisms, we introduce AdaptVision, an efficient VLM paradigm that enables adaptive visual token acquisition through a coarse-to-fine approach. Our model initially processes compressed visual tokens from low-resolution images and selectively acquires additional visual information by invoking a bounding box tool to crop key regions when necessary. We train AdaptVision using a reinforcement learning framework that carefully balances accuracy and efficiency. Central to our approach is Decoupled Turn Policy Optimization (DTPO), which decouples the learning objective into two components: (1) tool learning, which optimizes correct tool utilization, and (2) accuracy improvement, which refines the generated responses to improve answer correctness. Based on this formulation, we further decouple advantage estimation by computing separate advantages for tokens associated with each objective. This formulation enables more effective optimization for AdaptVision compared to vanilla GRPO. Comprehensive experiments across multiple VQA benchmarks demonstrate that AdaptVision achieves superior performance while consuming substantially fewer visual tokens than state-of-the-art efficient VLM methods.

---

### AdaptVision: Efficient Vision-Language Models via Adaptive Visual Acquisition

Authors: Zichuan Lin, Yicheng Liu, Yang Yang, Lvfang Tao, Deheng Ye
Published: 2025-12-03
Categories: cs.CV, cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2512.03794v1

Vision-Language Models (VLMs) have achieved remarkable success in visual question answering tasks, but their reliance on large numbers of visual tokens introduces significant computational overhead. While existing efficient VLM approaches reduce visual tokens through fixed-ratio compression, they operate passively and lack the ability to adapt to varying task requirements. This motivates a fundamental question: Can VLMs autonomously determine the minimum number of visual tokens required for each sample? Inspired by human active vision mechanisms, we introduce AdaptVision, an efficient VLM paradigm that enables adaptive visual token acquisition through a coarse-to-fine approach. Our model initially processes compressed visual tokens from low-resolution images and selectively acquires additional visual information by invoking a bounding box tool to crop key regions when necessary. We train AdaptVision using a reinforcement learning framework that carefully balances accuracy and efficiency. Central to our approach is Decoupled Turn Policy Optimization (DTPO), which decouples the learning objective into two components: (1) tool learning, which optimizes correct tool utilization, and (2) accuracy improvement, which refines the generated responses to improve answer correctness. Based on this formulation, we further decouple advantage estimation by computing separate advantages for tokens associated with each objective. This formulation enables more effective optimization for AdaptVision compared to vanilla GRPO. Comprehensive experiments across multiple VQA benchmarks demonstrate that AdaptVision achieves superior performance while consuming substantially fewer visual tokens than state-of-the-art efficient VLM methods.

---

### Adaptive Identification and Modeling of Clinical Pathways with Process Mining

Authors: Francesco Vitale, Nicola Mazzocca
Published: 2025-12-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.03787v2

Clinical pathways are specialized healthcare plans that model patient treatment procedures. They are developed to provide criteria-based progression and standardize patient treatment, thereby improving care, reducing resource use, and accelerating patient recovery. However, manual modeling of these pathways based on clinical guidelines and domain expertise is difficult and may not reflect the actual best practices for different variations or combinations of diseases. We propose a two-phase modeling method using process mining, which extends the knowledge base of clinical pathways by leveraging conformance checking diagnostics. In the first phase, historical data of a given disease is collected to capture treatment in the form of a process model. In the second phase, new data is compared against the reference model to verify conformance. Based on the conformance checking results, the knowledge base can be expanded with more specific models tailored to new variants or disease combinations. We demonstrate our approach using Synthea, a benchmark dataset simulating patient treatments for SARS-CoV-2 infections with varying COVID-19 complications. The results show that our method enables expanding the knowledge base of clinical pathways with sufficient precision, peaking to 95.62% AUC while maintaining an arc-degree simplicity of 67.11%.

---

### Adaptive Identification and Modeling of Clinical Pathways with Process Mining

Authors: Francesco Vitale, Nicola Mazzocca
Published: 2025-12-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.03787v1

Clinical pathways are specialized healthcare plans that model patient treatment procedures. They are developed to provide criteria-based progression and standardize patient treatment, thereby improving care, reducing resource use, and accelerating patient recovery. However, manual modeling of these pathways based on clinical guidelines and domain expertise is difficult and may not reflect the actual best practices for different variations or combinations of diseases. We propose a two-phase modeling method using process mining, which extends the knowledge base of clinical pathways by leveraging conformance checking diagnostics. In the first phase, historical data of a given disease is collected to capture treatment in the form of a process model. In the second phase, new data is compared against the reference model to verify conformance. Based on the conformance checking results, the knowledge base can be expanded with more specific models tailored to new variants or disease combinations. We demonstrate our approach using Synthea, a benchmark dataset simulating patient treatments for SARS-CoV-2 infections with varying COVID-19 complications. The results show that our method enables expanding the knowledge base of clinical pathways with sufficient precision, peaking to 95.62% AUC while maintaining an arc-degree simplicity of 67.11%.

---

### Forensic Activity Classification Using Digital Traces from iPhones: A Machine Learning-based Approach

Authors: Conor McCarthy, Jan Peter van Zandwijk, Marcel Worring, Zeno Geradts
Published: 2025-12-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.03786v1

Smartphones and smartwatches are ever-present in daily life, and provide a rich source of information on their users' behaviour. In particular, digital traces derived from the phone's embedded movement sensors present an opportunity for a forensic investigator to gain insight into a person's physical activities. In this work, we present a machine learning-based approach to translate digital traces into likelihood ratios (LRs) for different types of physical activities. Evaluating on a new dataset, NFI\_FARED, which contains digital traces from four different types of iPhones labelled with 19 activities, it was found that our approach could produce useful LR systems to distinguish 167 out of a possible 171 activity pairings. The same approach was extended to analyse likelihoods for multiple activities (or groups of activities) simultaneously and create activity timelines to aid in both the early and latter stages of forensic investigations. The dataset and all code required to replicate the results have also been made public to encourage further research on this topic.

---

### Omni-AutoThink: Adaptive Multimodal Reasoning via Reinforcement Learning

Authors: Dongchao Yang, Songxiang Liu, Disong Wang, Yuanyuan Wang, Guanglu Wan, Helen Meng
Published: 2025-12-03
Categories: cs.AI, cs.SD
arXiv: https://arxiv.org/abs/2512.03783v2

Recent advances in Omni models have enabled unified multimodal perception and generation. However, most existing systems still exhibit rigid reasoning behaviors, either overthinking simple problems or failing to reason when necessary. To address this limitation, we propose Omni-AutoThink, a novel adaptive reasoning framework that dynamically adjusts the model's reasoning depth according to task difficulty. Our framework comprises two stages: (1) an Adaptive Supervised Fine-Tuning (Adaptive SFT) stage, which endows the Omni model with fundamental reasoning capability using large-scale reasoning-augmented data, and (2) an Adaptive Reinforcement Learning (Adaptive GRPO) stage, which optimizes reasoning behaviors based on task complexity and reward feedback. We further construct a comprehensive adaptive reasoning benchmark that spans text-only, text-audio, text-visual, and text-audio-visual modalities, providing both training and evaluation splits for multimodal reasoning assessment. Experimental results demonstrate that our proposed framework significantly improves adaptive reasoning performance compared to previous baselines. All benchmark data and code will be publicly released.

---

### Omni-AutoThink: Adaptive Multimodal Reasoning via Reinforcement Learning

Authors: Dongchao Yang, Songxiang Liu, Disong Wang, Yuanyuan Wang, Guanglu Wan, Helen Meng
Published: 2025-12-03
Categories: cs.AI, cs.SD
arXiv: https://arxiv.org/abs/2512.03783v1

Recent advances in Omni models have enabled unified multimodal perception and generation. However, most existing systems still exhibit rigid reasoning behaviors, either overthinking simple problems or failing to reason when necessary. To address this limitation, we propose Omni-AutoThink, a novel adaptive reasoning framework that dynamically adjusts the model's reasoning depth according to task difficulty. Our framework comprises two stages: (1) an Adaptive Supervised Fine-Tuning (Adaptive SFT) stage, which endows the Omni model with fundamental reasoning capability using large-scale reasoning-augmented data, and (2) an Adaptive Reinforcement Learning (Adaptive GRPO) stage, which optimizes reasoning behaviors based on task complexity and reward feedback. We further construct a comprehensive adaptive reasoning benchmark that spans text-only, text-audio, text-visual, and text-audio-visual modalities, providing both training and evaluation splits for multimodal reasoning assessment. Experimental results demonstrate that our proposed framework significantly improves adaptive reasoning performance compared to previous baselines. All benchmark data and code will be publicly released.

---

### A comparison between initialization strategies for the infinite hidden Markov model

Authors: Federico P. Cortese, Luca Rossini
Published: 2025-12-03
Categories: stat.ME, stat.AP, stat.ML
arXiv: https://arxiv.org/abs/2512.03777v2

Infinite hidden Markov models provide a flexible framework for modeling time-series with structural changes and complex dynamics, without requiring the number of latent states to be specified in advance. This flexibility is achieved through the hierarchical Dirichlet process prior, while efficient Bayesian inference is enabled by the beam sampler, which combines dynamic programming with slice sampling to truncate the infinite state space adaptively. Despite extensive methodological developments, the role of initialization in this framework has received limited attention. This gap is addressed by systematically evaluating initialization strategies commonly used for finite hidden Markov models and assessing their suitability in the infinite setting. Results from both simulated and real datasets show that distance-based clustering initializations consistently outperform model-based and uniform alternatives, the latter being the most widely adopted in the existing literature.

---

### A comparison between initialization strategies for the infinite hidden Markov model

Authors: Federico P. Cortese, Luca Rossini
Published: 2025-12-03
Categories: stat.ME, stat.AP, stat.ML
arXiv: https://arxiv.org/abs/2512.03777v1

Infinite hidden Markov models provide a flexible framework for modelling time series with structural changes and complex dynamics, without requiring the number of latent states to be specified in advance. This flexibility is achieved through the hierarchical Dirichlet process prior, while efficient Bayesian inference is enabled by the beam sampler, which combines dynamic programming with slice sampling to truncate the infinite state space adaptively. Despite extensive methodological developments, the role of initialization in this framework has received limited attention. This study addresses this gap by systematically evaluating initialization strategies commonly used for finite hidden Markov models and assessing their suitability in the infinite setting. Results from both simulated and real datasets show that distance-based clustering initializations consistently outperform model-based and uniform alternatives, the latter being the most widely adopted in the existing literature.

---

### Bayesian Optimization for Automatic Tuning of Torque-Level Nonlinear Model Predictive Control

Authors: Gabriele Fadini, Deepak Ingole, Tong Duy Son, Alisa Rupenyan
Published: 2025-12-03
Categories: cs.RO, cs.AI, eess.SY
arXiv: https://arxiv.org/abs/2512.03772v1

This paper presents an auto-tuning framework for torque-based Nonlinear Model Predictive Control (nMPC), where the MPC serves as a real-time controller for optimal joint torque commands. The MPC parameters, including cost function weights and low-level controller gains, are optimized using high-dimensional Bayesian Optimization (BO) techniques, specifically Sparse Axis-Aligned Subspace (SAASBO) with a digital twin (DT) to achieve precise end-effector trajectory real-time tracking on an UR10e robot arm. The simulation model allows efficient exploration of the high-dimensional parameter space, and it ensures safe transfer to hardware. Our simulation results demonstrate significant improvements in tracking performance (+41.9%) and reduction in solve times (-2.5%) compared to manually-tuned parameters. Moreover, experimental validation on the real robot follows the trend (with a +25.8% improvement), emphasizing the importance of digital twin-enabled automated parameter optimization for robotic operations.

---

### In-Context Representation Hijacking

Authors: Itay Yona, Amir Sarid, Michael Karasik, Yossi Gandelsman
Published: 2025-12-03
Categories: cs.CL, cs.AI, cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2512.03771v2

We introduce $\textbf{Doublespeak}$, a simple in-context representation hijacking attack against large language models (LLMs). The attack works by systematically replacing a harmful keyword (e.g., bomb) with a benign token (e.g., carrot) across multiple in-context examples, provided a prefix to a harmful request. We demonstrate that this substitution leads to the internal representation of the benign token converging toward that of the harmful one, effectively embedding the harmful semantics under a euphemism. As a result, superficially innocuous prompts (e.g., "How to build a carrot?") are internally interpreted as disallowed instructions (e.g., "How to build a bomb?"), thereby bypassing the model's safety alignment. We use interpretability tools to show that this semantic overwrite emerges layer by layer, with benign meanings in early layers converging into harmful semantics in later ones. Doublespeak is optimization-free, broadly transferable across model families, and achieves strong success rates on closed-source and open-source systems, reaching 74% ASR on Llama-3.3-70B-Instruct with a single-sentence context override. Our findings highlight a new attack surface in the latent space of LLMs, revealing that current alignment strategies are insufficient and should instead operate at the representation level.

---

### In-Context Representation Hijacking

Authors: Itay Yona, Amir Sarid, Michael Karasik, Yossi Gandelsman
Published: 2025-12-03
Categories: cs.CL, cs.AI, cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2512.03771v1

We introduce \textbf{Doublespeak}, a simple \emph{in-context representation hijacking} attack against large language models (LLMs). The attack works by systematically replacing a harmful keyword (e.g., \textit{bomb}) with a benign token (e.g., \textit{carrot}) across multiple in-context examples, provided a prefix to a harmful request. We demonstrate that this substitution leads to the internal representation of the benign token converging toward that of the harmful one, effectively embedding the harmful semantics under a euphemism. As a result, superficially innocuous prompts (e.g., ``How to build a carrot?'') are internally interpreted as disallowed instructions (e.g., ``How to build a bomb?''), thereby bypassing the model's safety alignment. We use interpretability tools to show that this semantic overwrite emerges layer by layer, with benign meanings in early layers converging into harmful semantics in later ones. Doublespeak is optimization-free, broadly transferable across model families, and achieves strong success rates on closed-source and open-source systems, reaching 74\% ASR on Llama-3.3-70B-Instruct with a single-sentence context override. Our findings highlight a new attack surface in the latent space of LLMs, revealing that current alignment strategies are insufficient and should instead operate at the representation level.

---

### Deep Unfolding: Recent Developments, Theory, and Design Guidelines

Authors: Nir Shlezinger, Santiago Segarra, Yi Zhang, Dvir Avrahami, Zohar Davidov, Tirza Routtenberg, Yonina C. Eldar
Published: 2025-12-03
Categories: cs.LG, eess.SP
arXiv: https://arxiv.org/abs/2512.03768v2

Optimization methods play a central role in signal processing, serving as the mathematical foundation for inference, estimation, and control. While classical iterative optimization algorithms provide interpretability and theoretical guarantees, they often rely on surrogate objectives, require careful hyperparameter tuning, and exhibit substantial computational latency. Conversely, machine learning (ML ) offers powerful data-driven modeling capabilities but lacks the structure, transparency, and efficiency needed for optimization-driven inference. Deep unfolding has recently emerged as a compelling framework that bridges these two paradigms by systematically transforming iterative optimization algorithms into structured, trainable ML architectures. This article provides a tutorial-style overview of deep unfolding, presenting a unified perspective of methodologies for converting optimization solvers into ML models and highlighting their conceptual, theoretical, and practical implications. We review the foundations of optimization for inference and for learning, introduce four representative design paradigms for deep unfolding, and discuss the distinctive training schemes that arise from their iterative nature. Furthermore, we survey recent theoretical advances that establish convergence and generalization guarantees for unfolded optimizers, and provide comparative qualitative and empirical studies illustrating their relative trade-offs in complexity, interpretability, and robustness.

---

### Deep Unfolding: Recent Developments, Theory, and Design Guidelines

Authors: Nir Shlezinger, Santiago Segarra, Yi Zhang, Dvir Avrahami, Zohar Davidov, Tirza Routtenberg, Yonina C. Eldar
Published: 2025-12-03
Categories: cs.LG, eess.SP
arXiv: https://arxiv.org/abs/2512.03768v1

Optimization methods play a central role in signal processing, serving as the mathematical foundation for inference, estimation, and control. While classical iterative optimization algorithms provide interpretability and theoretical guarantees, they often rely on surrogate objectives, require careful hyperparameter tuning, and exhibit substantial computational latency. Conversely, machine learning (ML ) offers powerful data-driven modeling capabilities but lacks the structure, transparency, and efficiency needed for optimization-driven inference. Deep unfolding has recently emerged as a compelling framework that bridges these two paradigms by systematically transforming iterative optimization algorithms into structured, trainable ML architectures. This article provides a tutorial-style overview of deep unfolding, presenting a unified perspective of methodologies for converting optimization solvers into ML models and highlighting their conceptual, theoretical, and practical implications. We review the foundations of optimization for inference and for learning, introduce four representative design paradigms for deep unfolding, and discuss the distinctive training schemes that arise from their iterative nature. Furthermore, we survey recent theoretical advances that establish convergence and generalization guarantees for unfolded optimizers, and provide comparative qualitative and empirical studies illustrating their relative trade-offs in complexity, interpretability, and robustness.

---

### RoCo: Role-Based LLMs Collaboration for Automatic Heuristic Design

Authors: Jiawei Xu, Feng-Feng Wei, Wei-Neng Chen
Published: 2025-12-03
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.03762v2

Automatic Heuristic Design (AHD) has gained traction as a promising solution for solving combinatorial optimization problems (COPs). Large Language Models (LLMs) have emerged and become a promising approach to achieving AHD, but current LLM-based AHD research often only considers a single role. This paper proposes RoCo, a novel Multi-Agent Role-Based System, to enhance the diversity and quality of AHD through multi-role collaboration. RoCo coordinates four specialized LLM-guided agents-explorer, exploiter, critic, and integrator-to collaboratively generate high-quality heuristics. The explorer promotes long-term potential through creative, diversity-driven thinking, while the exploiter focuses on short-term improvements via conservative, efficiency-oriented refinements. The critic evaluates the effectiveness of each evolution step and provides targeted feedback and reflection. The integrator synthesizes proposals from the explorer and exploiter, balancing innovation and exploitation to drive overall progress. These agents interact in a structured multi-round process involving feedback, refinement, and elite mutations guided by both short-term and accumulated long-term reflections. We evaluate RoCo on five different COPs under both white-box and black-box settings. Experimental results demonstrate that RoCo achieves superior performance, consistently generating competitive heuristics that outperform existing methods including ReEvo and HSEvo, both in white-box and black-box scenarios. This role-based collaborative paradigm establishes a new standard for robust and high-performing AHD.

---

### RoCo: Role-Based LLMs Collaboration for Automatic Heuristic Design

Authors: Jiawei Xu, Fengfeng Wei, Weineng Chen
Published: 2025-12-03
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.03762v1

Automatic Heuristic Design (AHD) has gained traction as a promising solution for solving combinatorial optimization problems (COPs). Large Language Models (LLMs) have emerged and become a promising approach to achieving AHD, but current LLM-based AHD research often only considers a single role. This paper proposes RoCo, a novel Multi-Agent Role-Based System, to enhance the diversity and quality of AHD through multi-role collaboration. RoCo coordinates four specialized LLM-guided agents-explorer, exploiter, critic, and integrator-to collaboratively generate high-quality heuristics. The explorer promotes long-term potential through creative, diversity-driven thinking, while the exploiter focuses on short-term improvements via conservative, efficiency-oriented refinements. The critic evaluates the effectiveness of each evolution step and provides targeted feedback and reflection. The integrator synthesizes proposals from the explorer and exploiter, balancing innovation and exploitation to drive overall progress. These agents interact in a structured multi-round process involving feedback, refinement, and elite mutations guided by both short-term and accumulated long-term reflections. We evaluate RoCo on five different COPs under both white-box and black-box settings. Experimental results demonstrate that RoCo achieves superior performance, consistently generating competitive heuristics that outperform existing methods including ReEvo and HSEvo, both in white-box and black-box scenarios. This role-based collaborative paradigm establishes a new standard for robust and high-performing AHD.

---

### Principled RL for Diffusion LLMs Emerges from a Sequence-Level Perspective

Authors: Jingyang Ou, Jiaqi Han, Minkai Xu, Shaoxuan Xu, Jianwen Xie, Stefano Ermon, Yi Wu, Chongxuan Li
Published: 2025-12-03
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2512.03759v1

Reinforcement Learning (RL) has proven highly effective for autoregressive language models, but adapting these methods to diffusion large language models (dLLMs) presents fundamental challenges. The core difficulty lies in likelihood approximation: while autoregressive models naturally provide token-level conditional probabilities essential for token-level RL objectives (e.g., GRPO), dLLMs generate sequences through iterative non-autoregressive denoising steps that lack this factorization. To address this fundamental mismatch, we propose ELBO-based Sequence-level Policy Optimization (ESPO), a principled RL framework that treats entire sequence generation as a single action and uses the ELBO as a tractable sequence-level likelihood proxy. Our method incorporates per-token normalization of importance ratios and robust KL-divergence estimation to ensure stable large-scale training. Extensive experiments on mathematical reasoning, coding, and planning tasks demonstrate that ESPO significantly outperforms token-level baselines, achieving dramatic improvements of 20-40 points on the Countdown task, while maintaining consistent gains on math and coding benchmarks. Our approach establishes sequence-level optimization as a principled and empirically effective paradigm for RL in dLLMs. Our code is available at https://github.com/ML-GSAI/ESPO.

---

### Origin-Conditional Trajectory Encoding: Measuring Urban Configurational Asymmetries through Neural Decomposition

Authors: Stephen Law, Tao Yang, Nanjiang Chen, Xuhui Lin
Published: 2025-12-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.03755v1

Urban analytics increasingly relies on AI-driven trajectory analysis, yet current approaches suffer from methodological fragmentation: trajectory learning captures movement patterns but ignores spatial context, while spatial embedding methods encode street networks but miss temporal dynamics. Three gaps persist: (1) lack of joint training that integrates spatial and temporal representations, (2) origin-agnostic treatment that ignores directional asymmetries in navigation ($A \to B \ne B \to A$), and (3) over-reliance on auxiliary data (POIs, imagery) rather than fundamental geometric properties of urban space. We introduce a conditional trajectory encoder that jointly learns spatial and movement representations while preserving origin-dependent asymmetries using geometric features. This framework decomposes urban navigation into shared cognitive patterns and origin-specific spatial narratives, enabling quantitative measurement of cognitive asymmetries across starting locations. Our bidirectional LSTM processes visibility ratio and curvature features conditioned on learnable origin embeddings, decomposing representations into shared urban patterns and origin-specific signatures through contrastive learning. Results from six synthetic cities and real-world validation on Beijing's Xicheng District demonstrate that urban morphology creates systematic cognitive inequalities. This provides urban planners quantitative tools for assessing experiential equity, offers architects insights into layout decisions' cognitive impacts, and enables origin-aware analytics for navigation systems.

---

### Research on Brain Tumor Classification Method Based on Improved ResNet34 Network

Authors: Yufeng Li, Wenchao Zhao, Bo Dang, Weimin Wang
Published: 2025-12-03
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2512.03751v1

Previously, image interpretation in radiology relied heavily on manual methods. However, manual classification of brain tumor medical images is time-consuming and labor-intensive. Even with shallow convolutional neural network models, the accuracy is not ideal. To improve the efficiency and accuracy of brain tumor image classification, this paper proposes a brain tumor classification model based on an improved ResNet34 network. This model uses the ResNet34 residual network as the backbone network and incorporates multi-scale feature extraction. It uses a multi-scale input module as the first layer of the ResNet34 network and an Inception v2 module as the residual downsampling layer. Furthermore, a channel attention mechanism module assigns different weights to different channels of the image from a channel domain perspective, obtaining more important feature information. The results after a five-fold crossover experiment show that the average classification accuracy of the improved network model is approximately 98.8%, which is not only 1% higher than ResNet34, but also only 80% of the number of parameters of the original model. Therefore, the improved network model not only improves accuracy but also reduces clutter, achieving a classification effect with fewer parameters and higher accuracy.

---

### Universally Converging Representations of Matter Across Scientific Foundation Models

Authors: Sathya Edamadaka, Soojung Yang, Ju Li, Rafael Gómez-Bombarelli
Published: 2025-12-03
Categories: cs.LG, cond-mat.mtrl-sci
arXiv: https://arxiv.org/abs/2512.03750v1

Machine learning models of vastly different modalities and architectures are being trained to predict the behavior of molecules, materials, and proteins. However, it remains unclear whether they learn similar internal representations of matter. Understanding their latent structure is essential for building scientific foundation models that generalize reliably beyond their training domains. Although representational convergence has been observed in language and vision, its counterpart in the sciences has not been systematically explored. Here, we show that representations learned by nearly sixty scientific models, spanning string-, graph-, 3D atomistic, and protein-based modalities, are highly aligned across a wide range of chemical systems. Models trained on different datasets have highly similar representations of small molecules, and machine learning interatomic potentials converge in representation space as they improve in performance, suggesting that foundation models learn a common underlying representation of physical reality. We then show two distinct regimes of scientific models: on inputs similar to those seen during training, high-performing models align closely and weak models diverge into local sub-optima in representation space; on vastly different structures from those seen during training, nearly all models collapse onto a low-information representation, indicating that today's models remain limited by training data and inductive bias and do not yet encode truly universal structure. Our findings establish representational alignment as a quantitative benchmark for foundation-level generality in scientific models. More broadly, our work can track the emergence of universal representations of matter as models scale, and for selecting and distilling models whose learned representations transfer best across modalities, domains of matter, and scientific tasks.

---

### Fully Unsupervised Self-debiasing of Text-to-Image Diffusion Models

Authors: Korada Sri Vardhana, Shrikrishna Lolla, Soma Biswas
Published: 2025-12-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.03749v1

Text-to-image (T2I) diffusion models have achieved widespread success due to their ability to generate high-resolution, photorealistic images. These models are trained on large-scale datasets, like LAION-5B, often scraped from the internet. However, since this data contains numerous biases, the models inherently learn and reproduce them, resulting in stereotypical outputs. We introduce SelfDebias, a fully unsupervised test-time debiasing method applicable to any diffusion model that uses a UNet as its noise predictor. SelfDebias identifies semantic clusters in an image encoder's embedding space and uses these clusters to guide the diffusion process during inference, minimizing the KL divergence between the output distribution and the uniform distribution. Unlike supervised approaches, SelfDebias does not require human-annotated datasets or external classifiers trained for each generated concept. Instead, it is designed to automatically identify semantic modes. Extensive experiments show that SelfDebias generalizes across prompts and diffusion model architectures, including both conditional and unconditional models. It not only effectively debiases images along key demographic dimensions while maintaining the visual fidelity of the generated images, but also more abstract concepts for which identifying biases is also challenging.

---

### Thinking with Programming Vision: Towards a Unified View for Thinking with Images

Authors: Zirun Guo, Minjie Hong, Feng Zhang, Kai Jia, Tao Jin
Published: 2025-12-03
Categories: cs.CV, cs.CL
arXiv: https://arxiv.org/abs/2512.03746v1

Multimodal large language models (MLLMs) that think with images can interactively use tools to reason about visual inputs, but current approaches often rely on a narrow set of tools with limited real-world necessity and scalability. In this work, we first reveal a critical and previously overlooked weakness: even state-of-the-art MLLMs are surprisingly brittle, showing significant performance degradation on images with simple orientation changes or natural corruptions, underscoring the need for more robust tool-based reasoning. To address this, we propose CodeVision, a flexible and scalable code-as-tool framework where the model generates code as a universal interface to invoke any image operation, moving beyond fixed tool registries. We train our model using a two-stage methodology, beginning with Supervised Fine-Tuning (SFT) on a high-quality dataset curated for complex, multi-turn tool composition and error recovery, followed by Reinforcement Learning (RL) with a novel and dense process reward function to encourage strategic and efficient tool use. To facilitate this research, we construct new SFT and RL datasets and introduce a challenging new benchmark suite designed to rigorously evaluate robustness to orientation changes and multi-tool reasoning. Experiments on Qwen2.5-VL and Qwen3-VL series show that our approach significantly improves model performance and fosters emergent capabilities such as flexible tool composition, efficient chained execution, and robust error recovery from runtime feedback. Code is available at https://github.com/ByteDance-BandAI/CodeVision.

---

### Dual-level Modality Debiasing Learning for Unsupervised Visible-Infrared Person Re-Identification

Authors: Jiaze Li, Yan Lu, Bin Liu, Guojun Yin, Mang Ye
Published: 2025-12-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.03745v2

Two-stage learning pipeline has achieved promising results in unsupervised visible-infrared person re-identification (USL-VI-ReID). It first performs single-modality learning and then operates cross-modality learning to tackle the modality discrepancy. Although promising, this pipeline inevitably introduces modality bias: modality-specific cues learned in the single-modality training naturally propagate into the following cross-modality learning, impairing identity discrimination and generalization. To address this issue, we propose a Dual-level Modality Debiasing Learning (DMDL) framework that implements debiasing at both the model and optimization levels. At the model level, we propose a Causality-inspired Adjustment Intervention (CAI) module that replaces likelihood-based modeling with causal modeling, preventing modality-induced spurious patterns from being introduced, leading to a low-biased model. At the optimization level, a Collaborative Bias-free Training (CBT) strategy is introduced to interrupt the propagation of modality bias across data, labels, and features by integrating modality-specific augmentation, label refinement, and feature alignment. Extensive experiments on benchmark datasets demonstrate that DMDL could enable modality-invariant feature learning and a more generalized model. The code is available at https://github.com/priester3/DMDL.

---

### Unlocking the Invisible Urban Traffic Dynamics under Extreme Weather: A New Physics-Constrained Hamiltonian Learning Algorithm

Authors: Xuhui Lin, Qiuchen Lu
Published: 2025-12-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.03744v1

Urban transportation systems face increasing resilience challenges from extreme weather events, but current assessment methods rely on surface-level recovery indicators that miss hidden structural damage. Existing approaches cannot distinguish between true recovery and "false recovery," where traffic metrics normalize, but the underlying system dynamics permanently degrade. To address this, a new physics-constrained Hamiltonian learning algorithm combining "structural irreversibility detection" and "energy landscape reconstruction" has been developed. Our approach extracts low-dimensional state representations, identifies quasi-Hamiltonian structures through physics-constrained optimization, and quantifies structural changes via energy landscape comparison. Analysis of London's extreme rainfall in 2021 demonstrates that while surface indicators were fully recovered, our algorithm detected 64.8\% structural damage missed by traditional monitoring. Our framework provides tools for proactive structural risk assessment, enabling infrastructure investments based on true system health rather than misleading surface metrics.

---

### House of Dextra: Cross-embodied Co-design for Dexterous Hands

Authors: Kehlani Fay, Darin Anthony Djapri, Anya Zorin, James Clinton, Ali El Lahib, Hao Su, Michael T. Tolley, Sha Yi, Xiaolong Wang
Published: 2025-12-03
Categories: cs.RO, cs.LG
arXiv: https://arxiv.org/abs/2512.03743v7

Dexterous manipulation is limited by both control and design, without consensus as to what makes manipulators best for performing dexterous tasks. This raises a fundamental challenge: how should we design and control robot manipulators that are optimized for dexterity? We present a co-design framework that learns task-specific hand morphology and complementary dexterous control policies. The framework supports 1) an expansive morphology search space including joint, finger, and palm generation, 2) scalable evaluation across the wide design space via morphology-conditioned cross-embodied control, and 3) real-world fabrication with accessible components. We evaluate the approach across multiple dexterous tasks, including in-hand rotation with simulation and real deployment. Our framework enables an end-to-end pipeline that can design, train, fabricate, and deploy a new robotic hand in under 24 hours. The full framework and generated robot hands are open-sourced and available on our website.

---

### AR-Med: Automated Relevance Enhancement in Medical Search via LLM-Driven Information Augmentation

Authors: Chuyue Wang, Jie Feng, Yuxi Wu, Hang Zhang, Zhiguo Fan, Bing Cheng, Wei Lin
Published: 2025-12-03
Categories: cs.CL, cs.IR
arXiv: https://arxiv.org/abs/2512.03737v1

Accurate and reliable search on online healthcare platforms is critical for user safety and service efficacy. Traditional methods, however, often fail to comprehend complex and nuanced user queries, limiting their effectiveness. Large language models (LLMs) present a promising solution, offering powerful semantic understanding to bridge this gap. Despite their potential, deploying LLMs in this high-stakes domain is fraught with challenges, including factual hallucinations, specialized knowledge gaps, and high operational costs. To overcome these barriers, we introduce \textbf{AR-Med}, a novel framework for \textbf{A}utomated \textbf{R}elevance assessment for \textbf{Med}ical search that has been successfully deployed at scale on the Online Medical Delivery Platforms. AR-Med grounds LLM reasoning in verified medical knowledge through a retrieval-augmented approach, ensuring high accuracy and reliability. To enable efficient online service, we design a practical knowledge distillation scheme that compresses large teacher models into compact yet powerful student models. We also introduce LocalQSMed, a multi-expert annotated benchmark developed to guide model iteration and ensure strong alignment between offline and online performance. Extensive experiments show AR-Med achieves an offline accuracy of over 93\%, a 24\% absolute improvement over the original online system, and delivers significant gains in online relevance and user satisfaction. Our work presents a practical and scalable blueprint for developing trustworthy, LLM-powered systems in real-world healthcare applications.

---

### Crossing the Sim2Real Gap Between Simulation and Ground Testing to Space Deployment of Autonomous Free-flyer Control

Authors: Kenneth Stewart, Samantha Chapin, Roxana Leontie, Carl Glen Henshaw
Published: 2025-12-03
Categories: cs.RO, cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2512.03736v1

Reinforcement learning (RL) offers transformative potential for robotic control in space. We present the first on-orbit demonstration of RL-based autonomous control of a free-flying robot, the NASA Astrobee, aboard the International Space Station (ISS). Using NVIDIA's Omniverse physics simulator and curriculum learning, we trained a deep neural network to replace Astrobee's standard attitude and translation control, enabling it to navigate in microgravity. Our results validate a novel training pipeline that bridges the simulation-to-reality (Sim2Real) gap, utilizing a GPU-accelerated, scientific-grade simulation environment for efficient Monte Carlo RL training. This successful deployment demonstrates the feasibility of training RL policies terrestrially and transferring them to space-based applications. This paves the way for future work in In-Space Servicing, Assembly, and Manufacturing (ISAM), enabling rapid on-orbit adaptation to dynamic mission requirements.

---

### Out-of-the-box: Black-box Causal Attacks on Object Detectors

Authors: Melane Navaratnarajah, David A. Kelly, Hana Chockler
Published: 2025-12-03
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2512.03730v2

Adversarial perturbations are a useful way to expose vulnerabilities in object detectors. Existing perturbation methods are frequently white-box, architecture specific and use a loss function. More importantly, while they are often successful, it is rarely clear why they work. Insights into the mechanism of this success would allow developers to understand and analyze these attacks, as well as fine-tune the model to prevent them. This paper presents BlackCAtt, a black-box algorithm and tool, which uses minimal, causally sufficient pixel sets to construct explainable, imperceptible, reproducible, architecture-agnostic attacks on object detectors. We evaluate BlackCAtt on standard benchmarks and compare it to other black-box adversarial attacks methods. When BlackCAtt has access only to the position and label of a bounding box, it produces attacks that are comparable or better to those produced by other black-box methods. When BlackCAtt has access to the model confidence as well, it can work as a meta-algorithm, improving the ability of standard black-box techniques to construct smaller, less perceptible attacks. As BlackCAtt attacks manipulate causes only, the attacks become fully explainable. We compare the performance of BlackCAtt with other black-box attack methods and show that targeting causal pixels leads to smaller and less perceptible attacks. For example, when using BlackCAtt with SquareAttack, it reduces the average distance ($L_0$ norm) of the attack from the original input from $0.987$ to $0.072$, while maintaining a similar success rate. We perform ablation studies on the BlackCAtt algorithm and analyze the effect of different components on its performance.

---

### Autonomous Planning In-space Assembly Reinforcement-learning free-flYer (APIARY) International Space Station Astrobee Testing

Authors: Samantha Chapin, Kenneth Stewart, Roxana Leontie, Carl Glen Henshaw
Published: 2025-12-03
Categories: cs.RO, cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2512.03729v1

The US Naval Research Laboratory's (NRL's) Autonomous Planning In-space Assembly Reinforcement-learning free-flYer (APIARY) experiment pioneers the use of reinforcement learning (RL) for control of free-flying robots in the zero-gravity (zero-G) environment of space. On Tuesday, May 27th 2025 the APIARY team conducted the first ever, to our knowledge, RL control of a free-flyer in space using the NASA Astrobee robot on-board the International Space Station (ISS). A robust 6-degrees of freedom (DOF) control policy was trained using an actor-critic Proximal Policy Optimization (PPO) network within the NVIDIA Isaac Lab simulation environment, randomizing over goal poses and mass distributions to enhance robustness. This paper details the simulation testing, ground testing, and flight validation of this experiment. This on-orbit demonstration validates the transformative potential of RL for improving robotic autonomy, enabling rapid development and deployment (in minutes to hours) of tailored behaviors for space exploration, logistics, and real-time mission needs.

---

### AI/ML in 3GPP 5G Advanced -- Services and Architecture

Authors: Pradnya Taksande, Shwetha Kiran, Pranav Jha, Prasanna Chaporkar
Published: 2025-12-03
Categories: cs.ET, cs.AI
arXiv: https://arxiv.org/abs/2512.03728v3

The 3rd Generation Partnership Project (3GPP), the standards body for mobile networks, is in the final phase of Release 19 standardization and is beginning Release 20. Artificial Intelligence/ Machine Learning (AI/ML) has brought about a paradigm shift in technology and it is being adopted across industries and verticals. 3GPP has been integrating AI/ML into the 5G advanced system since Release 18. This paper focuses on the AI/ML related technological advancements and features introduced in Release 19 within the Service and System Aspects (SA) Technical specifications group of 3GPP. The advancements relate to two paradigms: (i) enhancements that AI/ML brought to the 5G advanced system (AI for network), e.g. resource optimization, and (ii) enhancements that were made to the 5G system to support AI/ML applications (Network for AI), e.g. image recognition.

---

### Colored Markov Random Fields for Probabilistic Topological Modeling

Authors: Lorenzo Marinucci, Leonardo Di Nino, Gabriele D'Acunto, Mario Edoardo Pandolfo, Paolo Di Lorenzo, Sergio Barbarossa
Published: 2025-12-03
Categories: stat.ML, cs.LG, eess.SP, stat.ME
arXiv: https://arxiv.org/abs/2512.03727v1

Probabilistic Graphical Models (PGMs) encode conditional dependencies among random variables using a graph -nodes for variables, links for dependencies- and factorize the joint distribution into lower-dimensional components. This makes PGMs well-suited for analyzing complex systems and supporting decision-making. Recent advances in topological signal processing highlight the importance of variables defined on topological spaces in several application domains. In such cases, the underlying topology shapes statistical relationships, limiting the expressiveness of canonical PGMs. To overcome this limitation, we introduce Colored Markov Random Fields (CMRFs), which model both conditional and marginal dependencies among Gaussian edge variables on topological spaces, with a theoretical foundation in Hodge theory. CMRFs extend classical Gaussian Markov Random Fields by including link coloring: connectivity encodes conditional independence, while color encodes marginal independence. We quantify the benefits of CMRFs through a distributed estimation case study over a physical network, comparing it with baselines with different levels of topological prior.

---

### PosA-VLA: Enhancing Action Generation via Pose-Conditioned Anchor Attention

Authors: Ziwen Li, Xin Wang, Hanlue Zhang, Runnan Chen, Runqi Lin, Xiao He, Han Huang, Yandong Guo, Fakhri Karray, Tongliang Liu, Mingming Gong
Published: 2025-12-03
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2512.03724v2

The Vision-Language-Action (VLA) models have demonstrated remarkable performance on embodied tasks and shown promising potential for real-world applications. However, current VLAs still struggle to produce consistent and precise target-oriented actions, as they often generate redundant or unstable motions along trajectories, limiting their applicability in time-sensitive scenarios.In this work, we attribute these redundant actions to the spatially uniform perception field of existing VLAs, which causes them to be distracted by target-irrelevant objects, especially in complex environments.To address this issue, we propose an efficient PosA-VLA framework that anchors visual attention via pose-conditioned supervision, consistently guiding the model's perception toward task-relevant regions. The pose-conditioned anchor attention mechanism enables the model to better align instruction semantics with actionable visual cues, thereby improving action generation precision and efficiency. Moreover, our framework adopts a lightweight architecture and requires no auxiliary perception modules (e.g., segmentation or grounding networks), ensuring efficient inference. Extensive experiments verify that our method executes embodied tasks with precise and time-efficient behavior across diverse robotic manipulation benchmarks and shows robust generalization in a variety of challenging environments.

---

### Context-Aware Hierarchical Learning: A Two-Step Paradigm towards Safer LLMs

Authors: Tengyun Ma, Jiaqi Yao, Daojing He, Shihao Peng, Yu Li, Shaohui Liu, Zhuotao Tian
Published: 2025-12-03
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2512.03720v1

Large Language Models (LLMs) have emerged as powerful tools for diverse applications. However, their uniform token processing paradigm introduces critical vulnerabilities in instruction handling, particularly when exposed to adversarial scenarios. In this work, we identify and propose a novel class of vulnerabilities, termed Tool-Completion Attack (TCA), which exploits function-calling mechanisms to subvert model behavior. To evaluate LLM robustness against such threats, we introduce the Tool-Completion benchmark, a comprehensive security assessment framework, which reveals that even state-of-the-art models remain susceptible to TCA, with surprisingly high attack success rates. To address these vulnerabilities, we introduce Context-Aware Hierarchical Learning (CAHL), a sophisticated mechanism that dynamically balances semantic comprehension with role-specific instruction constraints. CAHL leverages the contextual correlations between different instruction segments to establish a robust, context-aware instruction hierarchy. Extensive experiments demonstrate that CAHL significantly enhances LLM robustness against both conventional attacks and the proposed TCA, exhibiting strong generalization capabilities in zero-shot evaluations while still preserving model performance on generic tasks. Our code is available at https://github.com/S2AILab/CAHL.

---

### Over-the-Air Federated Learning: Rethinking Edge AI Through Signal Processing

Authors: Seyed Mohammad Azimi-Abarghouyi, Carlo Fischione, Kaibin Huang
Published: 2025-12-03
Categories: cs.IT, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2512.03719v2

Over-the-Air Federated Learning (AirFL) is an emerging paradigm that tightly integrates wireless signal processing and distributed machine learning to enable scalable AI at the network edge. By exploiting wireless superposition over a shared multiple-access channel, AirFL turns simultaneous transmissions of local model updates into an analog aggregate at the receiver, thereby reducing communication latency, bandwidth usage, and energy consumption in wireless aggregation domains. This article develops a design-oriented tutorial view of analog AirFL. We organize existing schemes according to the signal-processing mechanism used to enable AirFL aggregation: transmitter-side channel compensation and power control, receiver-side equalization and high-dimensional processing, or learning-aware aggregation weighting. This viewpoint leads to three representative classes -- CSIT-aware, blind, and weighted AirFL -- and clarifies their assumptions, performance tradeoffs, complexity, and deployment limitations. We further discuss synchronization, digital and hybrid analog-digital realization, and open research directions for integrating AirFL into practical wireless edge-AI systems.

---

### Matrix Editing Meets Fair Clustering: Parameterized Algorithms and Complexity

Authors: Robert Ganian, Hung P. Hoang, Simon Wietheger
Published: 2025-12-03
Categories: cs.DS, cs.AI
arXiv: https://arxiv.org/abs/2512.03718v1

We study the computational problem of computing a fair means clustering of discrete vectors, which admits an equivalent formulation as editing a colored matrix into one with few distinct color-balanced rows by changing at most $k$ values. While NP-hard in both the fairness-oblivious and the fair settings, the problem is well-known to admit a fixed-parameter algorithm in the former ``vanilla'' setting. As our first contribution, we exclude an analogous algorithm even for highly restricted fair means clustering instances. We then proceed to obtain a full complexity landscape of the problem, and establish tractability results which capture three means of circumventing our obtained lower bound: placing additional constraints on the problem instances, fixed-parameter approximation, or using an alternative parameterization targeting tree-like matrices.

---

### DINO-RotateMatch: A Rotation-Aware Deep Framework for Robust Image Matching in Large-Scale 3D Reconstruction

Authors: Kaichen Zhang, Tianxiang Sheng, Xuanming Shi
Published: 2025-12-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.03715v1

This paper presents DINO-RotateMatch, a deep-learning framework designed to address the chal lenges of image matching in large-scale 3D reconstruction from unstructured Internet images. The method integrates a dataset-adaptive image pairing strategy with rotation-aware keypoint extraction and matching. DINO is employed to retrieve semantically relevant image pairs in large collections, while rotation-based augmentation captures orientation-dependent local features using ALIKED and Light Glue. Experiments on the Kaggle Image Matching Challenge 2025 demonstrate consistent improve ments in mean Average Accuracy (mAA), achieving a Silver Award (47th of 943 teams). The results confirm that combining self-supervised global descriptors with rotation-enhanced local matching offers a robust and scalable solution for large-scale 3D reconstruction.

---

### Consistent Projection of Langevin Dynamics: Preserving Thermodynamics and Kinetics in Coarse-Grained Models

Authors: Vahid Nateghi, Lara Neureither, Selma Moqvist, Carsten Hartmann, Simon Olsson, Feliks Nüske
Published: 2025-12-03
Categories: physics.comp-ph, cs.LG, math.DS
arXiv: https://arxiv.org/abs/2512.03706v3

Coarse graining (CG) is an important task for efficient modeling and simulation of complex multi-scale systems, such as the conformational dynamics of biomolecules. This work presents a projection-based coarse-graining formalism for general underdamped Langevin dynamics. Following the Zwanzig projection approach, we derive a closed-form expression for the coarse grained dynamics. In addition, we show how the generator Extended Dynamic Mode Decomposition (gEDMD) method, which was developed in the context of Koopman operator methods, can be used to model the CG dynamics and evaluate its kinetic properties, such as transition timescales. Finally, we combine our approach with thermodynamic interpolation (TI), a generative approach to transform samples between thermodynamic conditions, to extend the scope of the approach across thermodynamic states without repeated numerical simulations. Using a two-dimensional model system, we demonstrate that the proposed method allows to accurately capture the thermodynamic and kinetic properties of the full-space model.

---

### Overcoming State Inertia: Minimally Invasive Temporal Alignment for Evolving Contexts

Authors: Yijun Liao
Published: 2025-12-03
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.03704v3

Long-context dialogue systems suffer from state inertia, where models over-attend to history and fail to adapt to evolving intents. We demonstrate that standard alignment methods like DPO and even recent long-context optimization techniques struggle to resolve this without incurring a severe contextual alignment tax--a substantial perplexity surge caused by disrupting pre-trained priors. To address this, we propose DZ-TiDPO, a minimally invasive framework that synergizes conflict-aware optimization (during training) with a structural temporal attention bias. This design effectively decouples state updating from general linguistic modeling. Experiments on Multi-Session Chat and our new Inertia Challenge (IC-Bench) show DZ-TiDPO preserves structural coherence while resolving inter-turn conflicts. Crucially, our framework supports dual inference strategies: a negligible-latency static mode for general robustness and a precision-focused dynamic mode for micro-semantic conflicts. Furthermore, our scaling analysis reveals a capacity-stability trade-off, confirming that highly capable mid-sized models (7B) can efficiently internalize temporal alignment. Code and data are available at: https://github.com/lyj20071013/DZ-TiDPO.

---

### Structured Uncertainty Similarity Score (SUSS): Learning a Probabilistic, Interpretable, Perceptual Metric Between Images

Authors: Paula Seidler, Neill D. F. Campbell, Ivor J A Simpson
Published: 2025-12-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.03701v1

Perceptual similarity scores that align with human vision are critical for both training and evaluating computer vision models. Deep perceptual losses, such as LPIPS, achieve good alignment but rely on complex, highly non-linear discriminative features with unknown invariances, while hand-crafted measures like SSIM are interpretable but miss key perceptual properties. We introduce the Structured Uncertainty Similarity Score (SUSS); it models each image through a set of perceptual components, each represented by a structured multivariate Normal distribution. These are trained in a generative, self-supervised manner to assign high likelihood to human-imperceptible augmentations. The final score is a weighted sum of component log-probabilities with weights learned from human perceptual datasets. Unlike feature-based methods, SUSS learns image-specific linear transformations of residuals in pixel space, enabling transparent inspection through decorrelated residuals and sampling. SUSS aligns closely with human perceptual judgments, shows strong perceptual calibration across diverse distortion types, and provides localized, interpretable explanations of its similarity assessments. We further demonstrate stable optimization behavior and competitive performance when using SUSS as a perceptual loss for downstream imaging tasks.

---

### Quantum Topological Graph Neural Networks for Detecting Complex Fraud Patterns

Authors: Mohammad Doost, Mohammad Manthouri
Published: 2025-12-03
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2512.03696v1

We propose a novel QTGNN framework for detecting fraudulent transactions in large-scale financial networks. By integrating quantum embedding, variational graph convolutions, and topological data analysis, QTGNN captures complex transaction dynamics and structural anomalies indicative of fraud. The methodology includes quantum data embedding with entanglement enhancement, variational quantum graph convolutions with non-linear dynamics, extraction of higher-order topological invariants, hybrid quantum-classical anomaly learning with adaptive optimization, and interpretable decision-making via topological attribution. Rigorous convergence guarantees ensure stable training on noisy intermediate-scale quantum (NISQ) devices, while stability of topological signatures provides robust fraud detection. Optimized for NISQ hardware with circuit simplifications and graph sampling, the framework scales to large transaction networks. Simulations on financial datasets, such as PaySim and Elliptic, benchmark QTGNN against classical and quantum baselines, using metrics like ROC-AUC, precision, and false positive rate. An ablation study evaluates the contributions of quantum embeddings, topological features, non-linear channels, and hybrid learning. QTGNN offers a theoretically sound, interpretable, and practical solution for financial fraud detection, bridging quantum machine learning, graph theory, and topological analysis.

---

### AITutor-EvalKit: Exploring the Capabilities of AI Tutors

Authors: Numaan Naeem, Kaushal Kumar Maurya, Kseniia Petukhova, Ekaterina Kochmar
Published: 2025-12-03
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.03688v2

We present AITutor-EvalKit, an application that uses language technology to evaluate the pedagogical quality of AI tutors, provides software for demonstration and evaluation, as well as model inspection and data visualization. This tool is aimed at education stakeholders as well as *ACL community at large, as it supports learning and can also be used to collect user feedback and annotation.

---

### Active Visual Perception: Opportunities and Challenges

Authors: Yian Li, Xiaoyu Guo, Hao Zhang, Jiayu Chen, Shuiwang Li, Xiaowei Dai
Published: 2025-12-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.03687v2

Active visual perception enables an intelligent system to improve perception by controlling how visual evidence is acquired. However, differences in how active perception is defined and evaluated make approaches difficult to compare across tasks. This review clarifies the field's functional scope by distinguishing active observation acquisition from processing fixed inputs. It then organizes representative literature around four questions about what evidence the task requires, which actions can obtain it, how candidate observations should be valued, and how the next sensing action should be selected and executed. New observations update the perceptual state and guide subsequent decisions, forming a closed loop. To evaluate the benefits of active perception, the review examines datasets, interactive environments, physical platforms, and baseline comparisons, and develops an evaluation framework linking improvements in visual evidence to downstream task outcomes while accounting for acquisition costs and risks. The analysis concludes that predicted observation value does not guarantee that useful evidence can be acquired through feasible actions, while task success alone cannot establish the benefit of active observation selection. Further progress requires reliable value estimation and planning over longer decision sequences under physical and resource constraints. It also requires grounding semantic reasoning in acquired evidence and maintaining effective collaboration under imperfect communication, with these capabilities verified through reproducible evaluation of the complete perception and action loop.

---

### InStyle: Instant Appearance Stylization of 3D Shapes

Authors: Melis Ocal, Xiaoyan Xing, Yue Li, Ngo Anh Vien, Sezer Karaoglu, Theo Gevers
Published: 2025-12-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.03683v2

3D stylization is central to game development, virtual reality, and digital arts, where the demand for diverse assets calls for scalable methods that support fast, high-fidelity manipulation. Existing text-to-3D stylization methods typically distill from 2D image editors, requiring time-intensive per-asset optimization and exhibiting multi-view inconsistency due to the limitations of current text-to-image models, which makes them impractical for large-scale production. In this paper, we introduce GaussianBlender, a pioneering feed-forward framework for text-driven 3D stylization that performs edits instantly at inference. Our method learns structured, disentangled latent spaces with controlled information sharing for geometry and appearance from spatially-grouped 3D Gaussians. A latent diffusion model then applies text-conditioned edits on these learned representations. Comprehensive evaluations show that GaussianBlender not only delivers instant, high-fidelity, geometry-preserving, multi-view consistent stylization, but also surpasses methods that require per-instance test-time optimization - unlocking practical, democratized 3D stylization at scale.

---

### Feature-aware Modulation for Learning from Temporal Tabular Data

Authors: Hao-Run Cai, Han-Jia Ye
Published: 2025-12-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.03678v1

While tabular machine learning has achieved remarkable success, temporal distribution shifts pose significant challenges in real-world deployment, as the relationships between features and labels continuously evolve. Static models assume fixed mappings to ensure generalization, whereas adaptive models may overfit to transient patterns, creating a dilemma between robustness and adaptability. In this paper, we analyze key factors essential for constructing an effective dynamic mapping for temporal tabular data. We discover that evolving feature semantics-particularly objective and subjective meanings-introduce concept drift over time. Crucially, we identify that feature transformation strategies are able to mitigate discrepancies in feature representations across temporal stages. Motivated by these insights, we propose a feature-aware temporal modulation mechanism that conditions feature representations on temporal context, modulating statistical properties such as scale and skewness. By aligning feature semantics across time, our approach achieves a lightweight yet powerful adaptation, effectively balancing generalizability and adaptability. Benchmark evaluations validate the effectiveness of our method in handling temporal shifts in tabular data.

---