# Research Papers — 2025-12 · bundle page 147 of 175

> Full-text markdown of papers #7301–7350 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/147
[← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/146.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-12/page/148.md)

### Realizable Abstractions: Near-Optimal Hierarchical Reinforcement Learning

Authors: Roberto Cipollone, Luca Iocchi, Matteo Leonetti
Published: 2025-12-04
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2512.04958v1

The main focus of Hierarchical Reinforcement Learning (HRL) is studying how large Markov Decision Processes (MDPs) can be more efficiently solved when addressed in a modular way, by combining partial solutions computed for smaller subtasks. Despite their very intuitive role for learning, most notions of MDP abstractions proposed in the HRL literature have limited expressive power or do not possess formal efficiency guarantees. This work addresses these fundamental issues by defining Realizable Abstractions, a new relation between generic low-level MDPs and their associated high-level decision processes. The notion we propose avoids non-Markovianity issues and has desirable near-optimality guarantees. Indeed, we show that any abstract policy for Realizable Abstractions can be translated into near-optimal policies for the low-level MDP, through a suitable composition of options. As demonstrated in the paper, these options can be expressed as solutions of specific constrained MDPs. Based on these findings, we propose RARL, a new HRL algorithm that returns compositional and near-optimal low-level policies, taking advantage of the Realizable Abstraction given in the input. We show that RARL is Probably Approximately Correct, it converges in a polynomial number of samples, and it is robust to inaccuracies in the abstraction.

---

### LLMs Know More Than Words: A Genre Study with Syntax, Metaphor & Phonetics

Authors: Weiye Shi, Zhaowei Zhang, Shaoheng Yan, Yaodong Yang
Published: 2025-12-04
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2512.04957v1

Large language models (LLMs) demonstrate remarkable potential across diverse language related tasks, yet whether they capture deeper linguistic properties, such as syntactic structure, phonetic cues, and metrical patterns from raw text remains unclear. To analysis whether LLMs can learn these features effectively and apply them to important nature language related tasks, we introduce a novel multilingual genre classification dataset derived from Project Gutenberg, a large-scale digital library offering free access to thousands of public domain literary works, comprising thousands of sentences per binary task (poetry vs. novel;drama vs. poetry;drama vs. novel) in six languages (English, French, German, Italian, Spanish, and Portuguese). We augment each with three explicit linguistic feature sets (syntactic tree structures, metaphor counts, and phonetic metrics) to evaluate their impact on classification performance. Experiments demonstrate that although LLM classifiers can learn latent linguistic structures either from raw text or from explicitly provided features, different features contribute unevenly across tasks, which underscores the importance of incorporating more complex linguistic signals during model training.

---

### Amortized Inference of Multi-Modal Posteriors using Likelihood-Weighted Normalizing Flows

Authors: Rajneil Baruah
Published: 2025-12-04
Categories: cs.LG, hep-ex, hep-ph, physics.comp-ph, physics.data-an
arXiv: https://arxiv.org/abs/2512.04954v3

We present a novel technique for amortized posterior estimation using Normalizing Flows trained with likelihood-weighted importance sampling. This approach allows for the efficient inference of theoretical parameters in high-dimensional inverse problems without the need for posterior training samples. We implement the method on multi-modal benchmark tasks in 2D and 3D to check for the efficacy. A critical observation of our study is the impact of the topology of the base distributions on the modelled posteriors. We find that standard unimodal base distributions fail to capture disconnected support, resulting in spurious probability \textit{bridges} between modes. We demonstrate that initializing the flow with a Gaussian Mixture Model that matches the cardinality of the target modes significantly improves reconstruction fidelity, as measured by some distance and divergence metrics. Finally, we apply this method to a curated problem in heavy flavour physics --- the extraction of the Wolfenstein parameters from the CP asymmetry in $B^0\to J/ψ\,K^0$; it is multimodal, non-Gaussian, and asymmetric in its mode weights --- and compare the results against a well-converged Markov Chain Monte Carlo reference using different metrics.

---

### Amortized Inference of Multi-Modal Posteriors using Likelihood-Weighted Normalizing Flows

Authors: Rajneil Baruah
Published: 2025-12-04
Categories: cs.LG, hep-ex, hep-ph, physics.comp-ph, physics.data-an
arXiv: https://arxiv.org/abs/2512.04954v1

We present a novel technique for amortized posterior estimation using Normalizing Flows trained with likelihood-weighted importance sampling. This approach allows for the efficient inference of theoretical parameters in high-dimensional inverse problems without the need for posterior training samples. We implement the method on multi-modal benchmark tasks in 2D and 3D to check for the efficacy. A critical observation of our study is the impact of the topology of the base distributions on the modelled posteriors. We find that standard unimodal base distributions fail to capture disconnected support, resulting in spurious probability bridges between modes. We demonstrate that initializing the flow with a Gaussian Mixture Model that matches the cardinality of the target modes significantly improves reconstruction fidelity, as measured by some distance and divergence metrics.

---

### FASTer: Toward Efficient Autoregressive Vision Language Action Modeling via Neural Action Tokenization

Authors: Yicheng Liu, Shiduo Zhang, Zibin Dong, Baijun Ye, Tianyuan Yuan, Xiaopeng Yu, Linqi Yin, Chenhao Lu, Junhao Shi, Luca Jiang-Tao Yu, Liangtao Zheng, Tao Jiang et al.
Published: 2025-12-04
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2512.04952v2

Autoregressive vision-language-action (VLA) models have recently demonstrated strong capabilities in robotic manipulation. However, their core process of action tokenization often involves a trade-off between reconstruction fidelity and inference efficiency. We introduce FASTer, a unified framework for efficient and generalizable robot learning that integrates a learnable tokenizer with an autoregressive policy built upon it. FASTerVQ encodes action chunks as single-channel images, capturing global spatio-temporal dependencies while maintaining a high compression ratio. FASTerVLA builds on this tokenizer with block-wise autoregressive decoding and a lightweight action expert, achieving both faster inference and higher task performance. Extensive experiments across simulated and real-world benchmarks show that FASTerVQ delivers superior reconstruction quality, high token utilization, and strong cross-task and cross-embodiment generalization, while FASTerVLA further improves overall capability, surpassing previous state-of-the-art VLA models in both inference speed and task performance.

---

### FASTer: Toward Efficient Autoregressive Vision Language Action Modeling via neural Action Tokenization

Authors: Yicheng Liu, Shiduo Zhang, Zibin Dong, Baijun Ye, Tianyuan Yuan, Xiaopeng Yu, Linqi Yin, Chenhao Lu, Junhao Shi, Luca Jiang-Tao Yu, Liangtao Zheng, Tao Jiang et al.
Published: 2025-12-04
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2512.04952v1

Autoregressive vision-language-action (VLA) models have recently demonstrated strong capabilities in robotic manipulation. However, their core process of action tokenization often involves a trade-off between reconstruction fidelity and inference efficiency. We introduce FASTer, a unified framework for efficient and generalizable robot learning that integrates a learnable tokenizer with an autoregressive policy built upon it. FASTerVQ encodes action chunks as single-channel images, capturing global spatio-temporal dependencies while maintaining a high compression ratio. FASTerVLA builds on this tokenizer with block-wise autoregressive decoding and a lightweight action expert, achieving both faster inference and higher task performance. Extensive experiments across simulated and real-world benchmarks show that FASTerVQ delivers superior reconstruction quality, high token utilization, and strong cross-task and cross-embodiment generalization, while FASTerVLA further improves overall capability, surpassing previous state-of-the-art VLA models in both inference speed and task performance.

---

### CARL: Criticality-Aware Agentic Reinforcement Learning

Authors: Leyang Shen, Yang Zhang, Chun Kai Ling, Xiaoyan Zhao, Tat-Seng Chua
Published: 2025-12-04
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2512.04949v3

Agents capable of accomplishing complex tasks through multiple interactions with the environment have emerged as a popular research direction. However, in such multi-step settings, the conventional group-level policy optimization algorithm becomes suboptimal because of its underlying assumption that each step holds equal contribution, which deviates significantly from reality. Our analysis reveals that only the action choices on a small fraction of states are critical in determining the final outcome. Building on this insight, we propose CARL, a criticality-aware reinforcement learning algorithm tailored for long-horizon agentic reasoning. CARL leverages entropy as a heuristic proxy for state criticality and achieves focused training by assigning rewards to actions taken from high-criticality states while excluding actions taken from low-criticality states from model updates, avoiding noisy credit assignment and redundant computation. Extensive experiments demonstrate that CARL achieves both stronger performance and higher efficiency across diverse evaluation settings. The source code will be publicly available.

---

### CARL: Critical Action Focused Reinforcement Learning for Multi-Step Agent

Authors: Leyang Shen, Yang Zhang, Chun Kai Ling, Xiaoyan Zhao, Tat-Seng Chua
Published: 2025-12-04
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2512.04949v1

Agents capable of accomplishing complex tasks through multiple interactions with the environment have emerged as a popular research direction. However, in such multi-step settings, the conventional group-level policy optimization algorithm becomes suboptimal because of its underlying assumption that each action holds equal contribution, which deviates significantly from reality. Our analysis reveals that only a small fraction of actions are critical in determining the final outcome. Building on this insight, we propose CARL, a critical-action-focused reinforcement learning algorithm tailored for multi-step agents. CARL achieves focused training through providing action-level optimization signals for high-criticality actions while excluding low-criticality actions from model update. Extensive experiments demonstrate that CARL achieves both stronger performance and higher efficiency during training and inference across diverse evaluation settings.

---

### Towards Adaptive Fusion of Multimodal Deep Networks for Human Action Recognition

Authors: Novanto Yudistira
Published: 2025-12-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.04943v1

This study introduces a pioneering methodology for human action recognition by harnessing deep neural network techniques and adaptive fusion strategies across multiple modalities, including RGB, optical flows, audio, and depth information. Employing gating mechanisms for multimodal fusion, we aim to surpass limitations inherent in traditional unimodal recognition methods while exploring novel possibilities for diverse applications. Through an exhaustive investigation of gating mechanisms and adaptive weighting-based fusion architectures, our methodology enables the selective integration of relevant information from various modalities, thereby bolstering both accuracy and robustness in action recognition tasks. We meticulously examine various gated fusion strategies to pinpoint the most effective approach for multimodal action recognition, showcasing its superiority over conventional unimodal methods. Gating mechanisms facilitate the extraction of pivotal features, resulting in a more holistic representation of actions and substantial enhancements in recognition performance. Our evaluations across human action recognition, violence action detection, and multiple self-supervised learning tasks on benchmark datasets demonstrate promising advancements in accuracy. The significance of this research lies in its potential to revolutionize action recognition systems across diverse fields. The fusion of multimodal information promises sophisticated applications in surveillance and human-computer interaction, especially in contexts related to active assisted living.

---

### LiteVGGT: Boosting Vanilla VGGT via Geometry-aware Cached Token Merging

Authors: Zhijian Shu, Cheng Lin, Tao Xie, Wei Yin, Ben Li, Zhiyuan Pu, Weize Li, Yao Yao, Xun Cao, Xiaoyang Guo, Xiao-Xiao Long
Published: 2025-12-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.04939v1

3D vision foundation models like Visual Geometry Grounded Transformer (VGGT) have advanced greatly in geometric perception. However, it is time-consuming and memory-intensive for long sequences, limiting application to large-scale scenes beyond hundreds of images. To address this, we propose LiteVGGT, achieving up to 10x speedup and substantial memory reduction, enabling efficient processing of 1000-image scenes. We derive two key insights for 3D reconstruction: (1) tokens from local image regions have inherent geometric correlations, leading to high similarity and computational redundancy; (2) token similarity across adjacent network layers remains stable, allowing for reusable merge decisions. Guided by these, we design a simple yet efficient strategy, dubbed geometry-aware cached token merging. We analyze each token's geometric importance, optimizing anchor token selection to better preserve key information for reconstruction. We also cache and reuse merge indices across layers, substantially reducing latency with minimal accuracy impact. This strategy retains VGGT's core performance, enabling efficient fine-tuning and FP8 quantization for further gains. Extensive experiments validate LiteVGGT's effectiveness, scalability, and robustness. Project page: https://garlicba.github.io/LiteVGGT/

---

### Toward Continuous Neurocognitive Monitoring: Integrating Speech AI with Relational Graph Transformers for Rare Neurological Diseases

Authors: Raquel Norel, Michele Merler, Pavitra Modi
Published: 2025-12-04
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.04938v1

Patients with rare neurological diseases report cognitive symptoms -"brain fog"- invisible to traditional tests. We propose continuous neurocognitive monitoring via smartphone speech analysis integrated with Relational Graph Transformer (RELGT) architectures. Proof-of-concept in phenylketonuria (PKU) shows speech-derived "Proficiency in Verbal Discourse" correlates with blood phenylalanine (p = -0.50, p < 0.005) but not standard cognitive tests (all |r| < 0.35). RELGT could overcome information bottlenecks in heterogeneous medical data (speech, labs, assessments), enabling predictive alerts weeks before decompensation. Key challenges: multi-disease validation, clinical workflow integration, equitable multilingual deployment. Success would transform episodic neurology into continuous personalized monitoring for millions globally.

---

### Virtually Unrolling the Herculaneum Papyri by Diffeomorphic Spiral Fitting

Authors: Paul Henderson
Published: 2025-12-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.04927v1

The Herculaneum Papyri are a collection of rolled papyrus documents that were charred and buried by the famous eruption of Mount Vesuvius. They promise to contain a wealth of previously unseen Greek and Latin texts, but are extremely fragile and thus most cannot be unrolled physically. A solution to access these texts is virtual unrolling, where the papyrus surface is digitally traced out in a CT scan of the scroll, to create a flattened representation. This tracing is very laborious to do manually in gigavoxel-sized scans, so automated approaches are desirable. We present the first top-down method that automatically fits a surface model to a CT scan of a severely damaged scroll. We take a novel approach that globally fits an explicit parametric model of the deformed scroll to existing neural network predictions of where the rolled papyrus likely passes. Our method guarantees the resulting surface is a single continuous 2D sheet, even passing through regions where the surface is not detectable in the CT scan. We conduct comprehensive experiments on high-resolution CT scans of two scrolls, showing that our approach successfully unrolls large regions, and exceeds the performance of the only existing automated unrolling method suitable for this data.

---

### Semantics Lead the Way: Harmonizing Semantic and Texture Modeling with Asynchronous Latent Diffusion

Authors: Yueming Pan, Ruoyu Feng, Qi Dai, Yuqi Wang, Wenfeng Lin, Mingyu Guo, Chong Luo, Nanning Zheng
Published: 2025-12-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.04926v2

Latent Diffusion Models (LDMs) inherently follow a coarse-to-fine generation process, where high-level semantic structure is generated slightly earlier than fine-grained texture. This indicates the preceding semantics potentially benefit texture generation by providing a semantic anchor. Recent advances have integrated semantic priors from pretrained visual encoders to further enhance LDMs, yet they still denoise semantic and VAE-encoded texture synchronously, neglecting such ordering. Observing these, we propose Semantic-First Diffusion (SFD), a latent diffusion paradigm that explicitly prioritizes semantic formation. SFD first constructs composite latents by combining a compact semantic latent, which is extracted from a pretrained visual encoder via a dedicated Semantic VAE, with the texture latent. The core of SFD is to denoise the semantic and texture latents asynchronously using separate noise schedules: semantics precede textures by a temporal offset, providing clearer high-level guidance for texture refinement and enabling natural coarse-to-fine generation. On ImageNet 256x256 with guidance, SFD achieves FID 1.06 (LightningDiT-XL) and FID 1.04 (1.0B LightningDiT-XXL), while achieving up to 100x faster convergence than the original DiT. SFD also improves existing methods like ReDi and VA-VAE, demonstrating the effectiveness of asynchronous, semantics-led modeling. Project page and code: https://yuemingpan.github.io/SFD.github.io/.

---

### Semantics Lead the Way: Harmonizing Semantic and Texture Modeling with Asynchronous Latent Diffusion

Authors: Yueming Pan, Ruoyu Feng, Qi Dai, Yuqi Wang, Wenfeng Lin, Mingyu Guo, Chong Luo, Nanning Zheng
Published: 2025-12-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.04926v1

Latent Diffusion Models (LDMs) inherently follow a coarse-to-fine generation process, where high-level semantic structure is generated slightly earlier than fine-grained texture. This indicates the preceding semantics potentially benefit texture generation by providing a semantic anchor. Recent advances have integrated semantic priors from pretrained visual encoders to further enhance LDMs, yet they still denoise semantic and VAE-encoded texture synchronously, neglecting such ordering. Observing these, we propose Semantic-First Diffusion (SFD), a latent diffusion paradigm that explicitly prioritizes semantic formation. SFD first constructs composite latents by combining a compact semantic latent, which is extracted from a pretrained visual encoder via a dedicated Semantic VAE, with the texture latent. The core of SFD is to denoise the semantic and texture latents asynchronously using separate noise schedules: semantics precede textures by a temporal offset, providing clearer high-level guidance for texture refinement and enabling natural coarse-to-fine generation. On ImageNet 256x256 with guidance, SFD achieves FID 1.06 (LightningDiT-XL) and FID 1.04 (1.0B LightningDiT-XXL), while achieving up to 100x faster convergence than the original DiT. SFD also improves existing methods like ReDi and VA-VAE, demonstrating the effectiveness of asynchronous, semantics-led modeling. Project page and code: https://yuemingpan.github.io/SFD.github.io/.

---

### Algorithmic Thinking Theory

Authors: MohammadHossein Bateni, Vincent Cohen-Addad, Yuzhou Gu, Silvio Lattanzi, Simon Meierhans, Christopher Mohri
Published: 2025-12-04
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2512.04923v1

Large language models (LLMs) have proven to be highly effective for solving complex reasoning tasks. Surprisingly, their capabilities can often be improved by iterating on previously generated solutions. In this context, a reasoning plan for generating and combining a set of solutions can be thought of as an algorithm for reasoning using a probabilistic oracle. We introduce a theoretical framework for analyzing such reasoning algorithms. This framework formalizes the principles underlying popular techniques for iterative improvement and answer aggregation, providing a foundation for designing a new generation of more powerful reasoning methods. Unlike approaches for understanding models that rely on architectural specifics, our model is grounded in experimental evidence. As a result, it offers a general perspective that may extend to a wide range of current and future reasoning oracles.

---

### The AI Consumer Index (ACE)

Authors: Julien Benchek, Rohit Shetty, Benjamin Hunsberger, Ajay Arun, Zach Richards, Brendan Foody, Osvald Nitski, Bertie Vidgen
Published: 2025-12-04
Categories: cs.AI, cs.CL, cs.HC
arXiv: https://arxiv.org/abs/2512.04921v3

We introduce the first version of the AI Consumer Index (ACE), a benchmark for assessing whether frontier AI models can perform everyday consumer tasks. ACE contains a hidden heldout set of 400 test cases, split across four consumer activities: shopping, food, gaming, and DIY. We are also open sourcing 80 cases as a devset with a CC-BY license. For the ACE leaderboard we evaluated 10 frontier models (with websearch turned on) using a novel grading methodology that dynamically checks whether relevant parts of the response are grounded in the retrieved web sources. GPT 5 (Thinking = High) is the top-performing model, scoring 56.1%, followed by o3 Pro (Thinking = On) at 55.2% and GPT 5.1 (Thinking = High) at 55.1%. Model scores differ across domains, and in Shopping the top model scores under 50\%. We find that models are prone to hallucinating key information, such as prices. ACE shows a substantial gap between the performance of even the best models and consumers' AI needs.

---

### The AI Consumer Index (ACE)

Authors: Julien Benchek, Rohit Shetty, Benjamin Hunsberger, Ajay Arun, Zach Richards, Brendan Foody, Osvald Nitski, Bertie Vidgen
Published: 2025-12-04
Categories: cs.AI, cs.CL, cs.HC
arXiv: https://arxiv.org/abs/2512.04921v1

We introduce the first version of the AI Consumer Index (ACE), a benchmark for assessing whether frontier AI models can perform high-value consumer tasks. ACE contains a hidden heldout set of 400 test cases, split across four consumer activities: shopping, food, gaming, and DIY. We are also open sourcing 80 cases as a devset with a CC-BY license. For the ACE leaderboard we evaluated 10 frontier models (with websearch turned on) using a novel grading methodology that dynamically checks whether relevant parts of the response are grounded in the retrieved web sources. GPT 5 (Thinking = High) is the top-performing model, scoring 56.1%, followed by o3 Pro (Thinking = On) (55.2%) and GPT 5.1 (Thinking = High) (55.1%). Models differ across domains, and in Shopping the top model scores under 50%. For some requests (such as giving the correct price or providing working links), models are highly prone to hallucination. Overall, ACE shows a substantial gap between the performance of even the best models and consumers' AI needs.

---

### Multi-Agent Reinforcement Learning for Intraday Operating Rooms Scheduling under Uncertainty

Authors: Kailiang Liu, Ying Chen, Ralf Borndörfer, Thorsten Koch
Published: 2025-12-04
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.04918v1

Intraday surgical scheduling is a multi-objective decision problem under uncertainty-balancing elective throughput, urgent and emergency demand, delays, sequence-dependent setups, and overtime. We formulate the problem as a cooperative Markov game and propose a multi-agent reinforcement learning (MARL) framework in which each operating room (OR) is an agent trained with centralized training and decentralized execution. All agents share a policy trained via Proximal Policy Optimization (PPO), which maps rich system states to actions, while a within-epoch sequential assignment protocol constructs conflict-free joint schedules across ORs. A mixed-integer pre-schedule provides reference starting times for electives; we impose type-specific quadratic delay penalties relative to these references and a terminal overtime penalty, yielding a single reward that captures throughput, timeliness, and staff workload. In simulations reflecting a realistic hospital mix (six ORs, eight surgery types, random urgent and emergency arrivals), the learned policy outperforms six rule-based heuristics across seven metrics and three evaluation subsets, and, relative to an ex post MIP oracle, quantifies optimality gaps. Policy analytics reveal interpretable behavior-prioritizing emergencies, batching similar cases to reduce setups, and deferring lower-value electives. We also derive a suboptimality bound for the sequential decomposition under simplifying assumptions. We discuss limitations-including OR homogeneity and the omission of explicit staffing constraints-and outline extensions. Overall, the approach offers a practical, interpretable, and tunable data-driven complement to optimization for real-time OR scheduling.

---

### A result relating convex n-widths to covering numbers with some applications to neural networks

Authors: Jonathan Baxter, Peter Bartlett
Published: 2025-12-04
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.04912v1

In general, approximating classes of functions defined over high-dimensional input spaces by linear combinations of a fixed set of basis functions or ``features'' is known to be hard. Typically, the worst-case error of the best basis set decays only as fast as $Θ\(n^{-1/d}\)$, where $n$ is the number of basis functions and $d$ is the input dimension. However, there are many examples of high-dimensional pattern recognition problems (such as face recognition) where linear combinations of small sets of features do solve the problem well. Hence these function classes do not suffer from the ``curse of dimensionality'' associated with more general classes. It is natural then, to look for characterizations of high-dimensional function classes that nevertheless are approximated well by linear combinations of small sets of features. In this paper we give a general result relating the error of approximation of a function class to the covering number of its ``convex core''. For one-hidden-layer neural networks, covering numbers of the class of functions computed by a single hidden node upper bound the covering numbers of the convex core. Hence, using standard results we obtain upper bounds on the approximation rate of neural network classes.

---

### Declarative Synthesis and Multi-Objective Optimization of Stripboard Circuit Layouts Using Answer Set Programming

Authors: Fang Li
Published: 2025-12-04
Categories: cs.AR, cs.AI
arXiv: https://arxiv.org/abs/2512.04910v1

This paper presents a novel approach to automated stripboard circuit layout design using Answer Set Programming (ASP). The work formulates the layout problem as both a synthesis and multi-objective optimization task that simultaneously generates viable layouts while minimizing board area and component strip crossing. By leveraging ASP's declarative nature, this work expresses complex geometric and electrical constraints in a natural and concise manner. The two-phase solving methodology first ensures feasibility before optimizing layout quality. Experimental results demonstrate that this approach generates compact, manufacturable layouts for a range of circuit complexities. This work represents a significant advancement in automated stripboard layout, offering a practical tool for electronics prototyping and education while showcasing the power of declarative programming for solving complex design automation problems.

---

### ReflexFlow: Rethinking Learning Objective for Exposure Bias Alleviation in Flow Matching

Authors: Guanbo Huang, Jingjia Mao, Fanding Huang, Fengkai Liu, Xiangyang Luo, Yaoyuan Liang, Jiasheng Lu, Xiaoe Wang, Pei Liu, Ruiliu Fu, Shao-Lun Huang
Published: 2025-12-04
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2512.04904v2

Despite tremendous recent progress, Flow Matching methods still suffer from exposure bias due to discrepancies in training and inference. This paper investigates the root causes of exposure bias in Flow Matching, including: (1) the model lacks generalization to biased inputs during training, and (2) insufficient low-frequency content captured during early denoising, leading to accumulated bias. Based on these insights, we propose ReflexFlow, a simple and effective reflexive refinement of the Flow Matching learning objective that dynamically corrects exposure bias. ReflexFlow consists of two components: (1) Anti-Drift Rectification (ADR), which reflexively adjusts prediction targets for biased inputs utilizing a redesigned loss under training-time scheduled sampling; and (2) Frequency Compensation (FC), which reflects on missing low-frequency components and compensates them by reweighting the loss using exposure bias. ReflexFlow is model-agnostic, compatible with all Flow Matching frameworks, and improves generation quality across datasets. Experiments on CIFAR-10, CelebA-64, and ImageNet-256 show that ReflexFlow outperforms prior approaches in mitigating exposure bias, achieving a 35.65% reduction in FID on CelebA-64.

---

### ReflexFlow: Rethinking Learning Objective for Exposure Bias Alleviation in Flow Matching

Authors: Guanbo Huang, Jingjia Mao, Fanding Huang, Fengkai Liu, Xiangyang Luo, Yaoyuan Liang, Jiasheng Lu, Xiaoe Wang, Pei Liu, Ruiliu Fu, Shao-Lun Huang
Published: 2025-12-04
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2512.04904v1

Despite tremendous recent progress, Flow Matching methods still suffer from exposure bias due to discrepancies in training and inference. This paper investigates the root causes of exposure bias in Flow Matching, including: (1) the model lacks generalization to biased inputs during training, and (2) insufficient low-frequency content captured during early denoising, leading to accumulated bias. Based on these insights, we propose ReflexFlow, a simple and effective reflexive refinement of the Flow Matching learning objective that dynamically corrects exposure bias. ReflexFlow consists of two components: (1) Anti-Drift Rectification (ADR), which reflexively adjusts prediction targets for biased inputs utilizing a redesigned loss under training-time scheduled sampling; and (2) Frequency Compensation (FC), which reflects on missing low-frequency components and compensates them by reweighting the loss using exposure bias. ReflexFlow is model-agnostic, compatible with all Flow Matching frameworks, and improves generation quality across datasets. Experiments on CIFAR-10, CelebA-64, and ImageNet-256 show that ReflexFlow outperforms prior approaches in mitigating exposure bias, achieving a 35.65% reduction in FID on CelebA-64.

---

### Chameleon: Adaptive Adversarial Agents for Scaling-Based Visual Prompt Injection in Multimodal AI Systems

Authors: M Zeeshan, Saud Satti
Published: 2025-12-04
Categories: cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2512.04895v1

Multimodal Artificial Intelligence (AI) systems, particularly Vision-Language Models (VLMs), have become integral to critical applications ranging from autonomous decision-making to automated document processing. As these systems scale, they rely heavily on preprocessing pipelines to handle diverse inputs efficiently. However, this dependency on standard preprocessing operations, specifically image downscaling, creates a significant yet often overlooked security vulnerability. While intended for computational optimization, scaling algorithms can be exploited to conceal malicious visual prompts that are invisible to human observers but become active semantic instructions once processed by the model. Current adversarial strategies remain largely static, failing to account for the dynamic nature of modern agentic workflows. To address this gap, we propose Chameleon, a novel, adaptive adversarial framework designed to expose and exploit scaling vulnerabilities in production VLMs. Unlike traditional static attacks, Chameleon employs an iterative, agent-based optimization mechanism that dynamically refines image perturbations based on the target model's real-time feedback. This allows the framework to craft highly robust adversarial examples that survive standard downscaling operations to hijack downstream execution. We evaluate Chameleon against Gemini 2.5 Flash model. Our experiments demonstrate that Chameleon achieves an Attack Success Rate (ASR) of 84.5% across varying scaling factors, significantly outperforming static baseline attacks which average only 32.1%. Furthermore, we show that these attacks effectively compromise agentic pipelines, reducing decision-making accuracy by over 45% in multi-step tasks. Finally, we discuss the implications of these vulnerabilities and propose multi-scale consistency checks as a necessary defense mechanism.

---

### Equivariant symmetry-aware head pose estimation for fetal MRI

Authors: Ramya Muthukrishnan, Borjan Gagoski, Aryn Lee, P. Ellen Grant, Elfar Adalsteinsson, Benjamin Billot, Polina Golland
Published: 2025-12-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.04890v8

We present E(3)-Pose, a novel fast pose estimation method that jointly and explicitly models rotation equivariance and object symmetry. Our work is motivated by the challenging problem of accounting for fetal head motion during a diagnostic MRI scan. We aim to enable automatic adaptive prescription of diagnostic 2D MRI slices with 6-DoF head pose estimation, supported by rapid low-resolution 3D MRI volumes acquired before each 2D slice. Existing pose estimation methods struggle to generalize to clinical volumes due to pose ambiguities induced by inherent anatomical symmetries, as well as low resolution, noise, and artifacts. In contrast, E(3)-Pose captures anatomical symmetries and rigid pose equivariance by construction, and yields robust estimates of the fetal head pose. Our experiments on publicly available and representative clinical fetal MRI datasets demonstrate the superior robustness and generalization of our method across domains. Crucially, E(3)-Pose achieves state-of-the-art accuracy on clinical MRI volumes, supporting future clinical translation. Our implementation is publicly available at github.com/MedicalVisionGroup/E3-Pose.

---

### Equivariant Symmetry-Aware Head Pose Estimation for Fetal MRI

Authors: Ramya Muthukrishnan, Borjan Gagoski, Aryn Lee, P. Ellen Grant, Elfar Adalsteinsson, Polina Golland, Benjamin Billot
Published: 2025-12-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.04890v1

We present E(3)-Pose, a novel fast pose estimation method that jointly and explicitly models rotation equivariance and object symmetry. Our work is motivated by the challenging problem of accounting for fetal head motion during a diagnostic MRI scan. We aim to enable automatic adaptive prescription of 2D diagnostic MRI slices with 6-DoF head pose estimation, supported by 3D MRI volumes rapidly acquired before each 2D slice. Existing methods struggle to generalize to clinical volumes, due to pose ambiguities induced by inherent anatomical symmetries, as well as low resolution, noise, and artifacts. In contrast, E(3)-Pose captures anatomical symmetries and rigid pose equivariance by construction, and yields robust estimates of the fetal head pose. Our experiments on publicly available and representative clinical fetal MRI datasets demonstrate the superior robustness and generalization of our method across domains. Crucially, E(3)-Pose achieves state-of-the-art accuracy on clinical MRI volumes, paving the way for clinical translation. Our implementation is available at github.com/ramyamut/E3-Pose.

---

### ZeBROD: Zero-Retraining Based Recognition and Object Detection Framework

Authors: Priyanto Hidayatullah, Nurjannah Syakrani, Yudi Widhiyasana, Muhammad Rizqi Sholahuddin, Refdinal Tubagus, Zahri Al Adzani Hidayat, Hanri Fajar Ramadhan, Dafa Alfarizki Pratama, Farhan Muhammad Yasin
Published: 2025-12-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.04888v4

Object detection constitutes the primary task within the domain of computer vision. It is utilized in numerous domains. Nonetheless, object detection continues to encounter the issue of catastrophic forgetting. The model must be retrained whenever new products are introduced, utilizing not only the new products dataset but also the entirety of the previous dataset. The outcome is obvious: increasing model training expenses and significant time consumption. In numerous sectors, particularly retail checkout, the frequent introduction of new products presents a great challenge. This study introduces Zero-Retraining Based Recognition and Object Detection (ZeBROD), a methodology designed to address the issue of catastrophic forgetting by integrating YOLO11n for object localization with DeIT and Proxy Anchor Loss for feature extraction and metric learning. For classification, we utilize cosine similarity between the embedding features of the target product and those in the Qdrant vector database. In a case study conducted in a retail store with 140 products, the experimental results demonstrate that our proposed framework achieves encouraging accuracy, whether for detecting new or existing products. Furthermore, without retraining, the training duration difference is significant. We achieve almost 3 times the training time efficiency compared to classical object detection approaches. This efficiency escalates as additional new products are added to the product database. The average inference time is 580 ms per image containing multiple products, on an edge device, validating the proposed framework's feasibility for practical use.

---

### You Only Train Once (YOTO): A Retraining-Free Object Detection Framework

Authors: Priyanto Hidayatullah, Nurjannah Syakrani, Yudi Widhiyasana, Muhammad Rizqi Sholahuddin, Refdinal Tubagus, Zahri Al Adzani Hidayat, Hanri Fajar Ramadhan, Dafa Alfarizki Pratama, Farhan Muhammad Yasin
Published: 2025-12-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.04888v1

Object detection constitutes the primary task within the domain of computer vision. It is utilized in numerous domains. Nonetheless, object detection continues to encounter the issue of catastrophic forgetting. The model must be retrained whenever new products are introduced, utilizing not only the new products dataset but also the entirety of the previous dataset. The outcome is obvious: increasing model training expenses and significant time consumption. In numerous sectors, particularly retail checkout, the frequent introduction of new products presents a great challenge. This study introduces You Only Train Once (YOTO), a methodology designed to address the issue of catastrophic forgetting by integrating YOLO11n for object localization with DeIT and Proxy Anchor Loss for feature extraction and metric learning. For classification, we utilize cosine similarity between the embedding features of the target product and those in the Qdrant vector database. In a case study conducted in a retail store with 140 products, the experimental results demonstrate that our proposed framework achieves encouraging accuracy, whether for detecting new or existing products. Furthermore, without retraining, the training duration difference is significant. We achieve almost 3 times the training time efficiency compared to classical object detection approaches. This efficiency escalates as additional new products are added to the product database. The average inference time is 580 ms per image containing multiple products, on an edge device, validating the proposed framework's feasibility for practical use.

---

### SDG-Track: A Heterogeneous Observer-Follower Framework for High-Resolution UAV Tracking on Embedded Platforms

Authors: Jiawen Wen, Yu Hu, Suixuan Qiu, Jinshan Huang, Xiaowen Chu
Published: 2025-12-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.04883v2

Real-time tracking of small unmanned aerial vehicles (UAVs) on edge devices faces a fundamental resolution-speed conflict. Downsampling high-resolution imagery to standard detector input sizes causes small target features to collapse below detectable thresholds. Yet processing native 1080p frames on resource-constrained platforms yields insufficient throughput for smooth gimbal control. We propose SDG-Track, a Sparse Detection-Guided Tracker that adopts an Observer-Follower architecture to reconcile this conflict. The Observer stream runs a high-capacity detector at low frequency on the GPU to provide accurate position anchors from 1920x1080 frames. The Follower stream performs high-frequency trajectory interpolation via ROI-constrained sparse optical flow on the CPU. To handle tracking failures from occlusion or model drift caused by spectrally similar distractors, we introduce Dual-Space Recovery, a training-free re-acquisition mechanism combining color histogram matching with geometric consistency constraints. Experiments on a ground-to-air tracking station demonstrate that SDG-Track achieves 35.1 FPS system throughput while retaining 97.2\% of the frame-by-frame detection precision. The system successfully tracks agile FPV drones under real-world operational conditions on an NVIDIA Jetson Orin Nano. Our paper code is publicly available at https://github.com/Jeffry-wen/SDG-Track

---

### SDG-Track: A Heterogeneous Observer-Follower Framework for High-Resolution UAV Tracking on Embedded Platforms

Authors: Jiawen Wen, Yu Hu, Suixuan Qiu, Jinshan Huang, Xiaowen Chu
Published: 2025-12-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.04883v1

Real-time tracking of small unmanned aerial vehicles (UAVs) on edge devices faces a fundamental resolution-speed conflict. Downsampling high-resolution imagery to standard detector input sizes causes small target features to collapse below detectable thresholds. Yet processing native 1080p frames on resource-constrained platforms yields insufficient throughput for smooth gimbal control. We propose SDG-Track, a Sparse Detection-Guided Tracker that adopts an Observer-Follower architecture to reconcile this conflict. The Observer stream runs a high-capacity detector at low frequency on the GPU to provide accurate position anchors from 1920x1080 frames. The Follower stream performs high-frequency trajectory interpolation via ROI-constrained sparse optical flow on the CPU. To handle tracking failures from occlusion or model drift caused by spectrally similar distractors, we introduce Dual-Space Recovery, a training-free re-acquisition mechanism combining color histogram matching with geometric consistency constraints. Experiments on a ground-to-air tracking station demonstrate that SDG-Track achieves 35.1 FPS system throughput while retaining 97.2\% of the frame-by-frame detection precision. The system successfully tracks agile FPV drones under real-world operational conditions on an NVIDIA Jetson Orin Nano. Our paper code is publicly available at https://github.com/Jeffry-wen/SDG-Track

---

### SP-Det: Self-Prompted Dual-Text Fusion for Generalized Multi-Label Lesion Detection

Authors: Qing Xu, Yanqian Wang, Xiangjian Hea, Yue Li, Yixuan Zhang, Rong Qu, Wenting Duan, Zhen Chen
Published: 2025-12-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.04875v1

Automated lesion detection in chest X-rays has demonstrated significant potential for improving clinical diagnosis by precisely localizing pathological abnormalities. While recent promptable detection frameworks have achieved remarkable accuracy in target localization, existing methods typically rely on manual annotations as prompts, which are labor-intensive and impractical for clinical applications. To address this limitation, we propose SP-Det, a novel self-prompted detection framework that automatically generates rich textual context to guide multi-label lesion detection without requiring expert annotations. Specifically, we introduce an expert-free dual-text prompt generator (DTPG) that leverages two complementary textual modalities: semantic context prompts that capture global pathological patterns and disease beacon prompts that focus on disease-specific manifestations. Moreover, we devise a bidirectional feature enhancer (BFE) that synergistically integrates comprehensive diagnostic context with disease-specific embeddings to significantly improve feature representation and detection accuracy. Extensive experiments on two chest X-ray datasets with diverse thoracic disease categories demonstrate that our SP-Det framework outperforms state-of-the-art detection methods while completely eliminating the dependency on expert-annotated prompts compared to existing promptable architectures.

---

### Shorting Dynamics and Structured Kernel Regularization

Authors: James Tian
Published: 2025-12-04
Categories: math.FA, cs.LG
arXiv: https://arxiv.org/abs/2512.04874v1

This paper develops a nonlinear operator dynamic that progressively removes the influence of a prescribed feature subspace while retaining maximal structure elsewhere. The induced sequence of positive operators is monotone, admits an exact residual decomposition, and converges to the classical shorted operator. Transporting this dynamic to reproducing kernel Hilbert spaces yields a corresponding family of kernels that converges to the largest kernel dominated by the original one and annihilating the given subspace. In the finite-sample setting, the associated Gram operators inherit a structured residual decomposition that leads to a canonical form of kernel ridge regression and a principled way to enforce nuisance invariance. This gives a unified operator-analytic approach to invariant kernel construction and structured regularization in data analysis.

---

### STELLA: Guiding Large Language Models for Time Series Forecasting with Semantic Abstractions

Authors: Junjie Fan, Hongye Zhao, Linduo Wei, Jiayu Rao, Guijia Li, Jiaxin Yuan, Wenqi Xu, Yong Qi
Published: 2025-12-04
Categories: cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2512.04871v1

Recent adaptations of Large Language Models (LLMs) for time series forecasting often fail to effectively enhance information for raw series, leaving LLM reasoning capabilities underutilized. Existing prompting strategies rely on static correlations rather than generative interpretations of dynamic behavior, lacking critical global and instance-specific context. To address this, we propose STELLA (Semantic-Temporal Alignment with Language Abstractions), a framework that systematically mines and injects structured supplementary and complementary information. STELLA employs a dynamic semantic abstraction mechanism that decouples input series into trend, seasonality, and residual components. It then translates intrinsic behavioral features of these components into Hierarchical Semantic Anchors: a Corpus-level Semantic Prior (CSP) for global context and a Fine-grained Behavioral Prompt (FBP) for instance-level patterns. Using these anchors as prefix-prompts, STELLA guides the LLM to model intrinsic dynamics. Experiments on eight benchmark datasets demonstrate that STELLA outperforms state-of-the-art methods in long- and short-term forecasting, showing superior generalization in zero-shot and few-shot settings. Ablation studies further validate the effectiveness of our dynamically generated semantic anchors.

---

### Developing a General Personal Tutor for Education

Authors: Jaan Aru, Kristjan-Julius Laak
Published: 2025-12-04
Categories: cs.CY, cs.AI, q-bio.NC
arXiv: https://arxiv.org/abs/2512.04869v1

The vision of a universal AI tutor has remained elusive, despite decades of effort. Could LLMs be the game-changer? We overview novel issues arising from developing a nationwide AI tutor. We highlight the practical questions that point to specific gaps in our scientific understanding of the learning process.

---

### SEAL: Self-Evolving Agentic Learning for Conversational Question Answering over Knowledge Graphs

Authors: Hao Wang, Jialun Zhong, Changcheng Wang, Zhujun Nie, Zheng Li, Shunyu Yao, Yanzeng Li, Xinchi Li
Published: 2025-12-04
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2512.04868v2

Knowledge-based conversational question answering (KBCQA) confronts persistent challenges in resolving coreference, modeling contextual dependencies, and executing complex logical reasoning. Existing approaches often suffer from inaccuracies and prohibitive computational costs, particularly when processing intricate queries over large knowledge graphs. Specifically, large language models (LLMs) tend to generate syntactically invalid or semantically misaligned logical forms for complex multi-hop or aggregation queries, while conventional entity-relation linking methods face an exponentially growing candidate space. To address these limitations, we introduce SEAL, a novel two-stage semantic parsing framework grounded in self-evolving agentic learning. In the first stage, an LLM extracts a minimal S-expression core capturing the essential semantics, which is then refined by an agentic calibration module to correct syntactic inconsistencies and align entities and relations with the knowledge graph. The second stage employs template-based completion guided by question-type prediction to construct a fully executable S-expression. Crucially, SEAL incorporates a self-evolving mechanism integrating local and global memory with a reflection module, enabling continuous adaptation from dialog history and execution feedback without explicit retraining. Extensive experiments on the SPICE benchmark demonstrate that SEAL achieves state-of-the-art performance in multi-hop reasoning, comparison, and aggregation tasks, validating notable gains in both structural accuracy and computational efficiency.

---

### SEAL: Self-Evolving Agentic Learning for Conversational Question Answering over Knowledge Graphs

Authors: Hao Wang, Jialun Zhong, Changcheng Wang, Zhujun Nie, Zheng Li, Shunyu Yao, Yanzeng Li, Xinchi Li
Published: 2025-12-04
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2512.04868v1

Knowledge-based conversational question answering (KBCQA) confronts persistent challenges in resolving coreference, modeling contextual dependencies, and executing complex logical reasoning. Existing approaches, whether end-to-end semantic parsing or stepwise agent-based reasoning, often suffer from structural inaccuracies and prohibitive computational costs, particularly when processing intricate queries over large knowledge graphs. To address these limitations, we introduce SEAL, a novel two-stage semantic parsing framework grounded in self-evolving agentic learning. In the first stage, a large language model (LLM) extracts a minimal S-expression core that captures the essential semantics of the input query. This core is then refined by an agentic calibration module, which corrects syntactic inconsistencies and aligns entities and relations precisely with the underlying knowledge graph. The second stage employs template-based completion, guided by question-type prediction and placeholder instantiation, to construct a fully executable S-expression. This decomposition not only simplifies logical form generation but also significantly enhances structural fidelity and linking efficiency. Crucially, SEAL incorporates a self-evolving mechanism that integrates local and global memory with a reflection module, enabling continuous adaptation from dialog history and execution feedback without explicit retraining. Extensive experiments on the SPICE benchmark demonstrate that SEAL achieves state-of-the-art performance, especially in multi-hop reasoning, comparison, and aggregation tasks. The results validate notable gains in both structural accuracy and computational efficiency, underscoring the framework's capacity for robust and scalable conversational reasoning.

---

### Functional Stability of Software-Hardware Neural Network Implementation The NeuroComp Project

Authors: Bychkov Oleksii, Senysh Taras
Published: 2025-12-04
Categories: cs.AR, cs.NE
arXiv: https://arxiv.org/abs/2512.04867v1

This paper presents an innovative approach to ensuring functional stability of neural networks through hardware redundancy at the individual neuron level. Unlike the classical Dropout method, which is used during training for regularization purposes, the proposed system ensures resilience to hardware failures during network operation. Each neuron is implemented on a separate microcomputer (ESP32), allowing the system to continue functioning even when individual computational nodes fail.

---

### Series of quasi-uniform scatterings with fast search, root systems and neural network classifications

Authors: Igor V. Netay
Published: 2025-12-04
Categories: math.AG, cs.LG, math.RT
arXiv: https://arxiv.org/abs/2512.04865v1

In this paper we describe an approach to construct large extendable collections of vectors in predefined spaces of given dimensions. These collections are useful for neural network latent space configuration and training. For classification problem with large or unknown number of classes this allows to construct classifiers without classification layer and extend the number of classes without retraining of network from the very beginning. The construction allows to create large well-spaced vector collections in spaces of minimal possible dimension. If the number of classes is known or approximately predictable, one can choose sufficient enough vector collection size. If one needs to significantly extend the number of classes, one can extend the collection in the same latent space, or to incorporate the collection into collection of higher dimensions with same spacing between vectors. Also, regular symmetric structure of constructed vector collections can significantly simplify problems of search for nearest cluster centers or embeddings in the latent space. Construction of vector collections is based on combinatorics and geometry of semi-simple Lie groups irreducible representations with highest weight.

---

### Are Your Agents Upward Deceivers?

Authors: Dadi Guo, Qingyu Liu, Dongrui Liu, Qihan Ren, Shuai Shao, Tianyi Qiu, Haoran Li, Yi R. Fung, Zhongjie Ba, Juntao Dai, Jiaming Ji, Zhikai Chen et al.
Published: 2025-12-04
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.04864v1

Large Language Model (LLM)-based agents are increasingly used as autonomous subordinates that carry out tasks for users. This raises the question of whether they may also engage in deception, similar to how individuals in human organizations lie to superiors to create a good image or avoid punishment. We observe and define agentic upward deception, a phenomenon in which an agent facing environmental constraints conceals its failure and performs actions that were not requested without reporting. To assess its prevalence, we construct a benchmark of 200 tasks covering five task types and eight realistic scenarios in a constrained environment, such as broken tools or mismatched information sources. Evaluations of 11 popular LLMs reveal that these agents typically exhibit action-based deceptive behaviors, such as guessing results, performing unsupported simulations, substituting unavailable information sources, and fabricating local files. We further test prompt-based mitigation and find only limited reductions, suggesting that it is difficult to eliminate and highlighting the need for stronger mitigation strategies to ensure the safety of LLM-based agents.

---

### Contact-Aware Refinement of Human Pose Pseudo-Ground Truth via Bioimpedance Sensing

Authors: Maria-Paola Forte, Nikos Athanasiou, Giulia Ballardini, Jan Ulrich Bartels, Katherine J. Kuchenbecker, Michael J. Black
Published: 2025-12-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.04862v2

Capturing accurate 3D human pose in the wild would provide valuable data for training pose estimation and motion generation methods. While video-based estimation approaches have become increasingly accurate, they often fail in common scenarios involving self-contact, such as a hand touching the face. In contrast, wearable bioimpedance sensing can cheaply and unobtrusively measure ground-truth skin-to-skin contact. Consequently, we propose a novel framework that combines visual pose estimators with bioimpedance sensing to capture the 3D pose of people by taking self-contact into account. Our method, BioTUCH, initializes the pose using an off-the-shelf estimator and introduces contact-aware pose optimization during measured self-contact: reprojection error and deviations from the input estimate are minimized while enforcing vertex proximity constraints. We validate our approach using a new dataset of synchronized RGB video, bioimpedance measurements, and 3D motion capture. Testing with three input pose estimators, we demonstrate an average of 11.7% improvement in reconstruction accuracy. We also present a miniature wearable bioimpedance sensor that enables efficient large-scale collection of contact-aware training data for improving pose estimation and generation using BioTUCH. Code and data are available at biotuch.is.tue.mpg.de

---

### Contact-Aware Refinement of Human Pose Pseudo-Ground Truth via Bioimpedance Sensing

Authors: Maria-Paola Forte, Nikos Athanasiou, Giulia Ballardini, Jan Ulrich Bartels, Katherine J. Kuchenbecker, Michael J. Black
Published: 2025-12-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.04862v1

Capturing accurate 3D human pose in the wild would provide valuable data for training pose estimation and motion generation methods. While video-based estimation approaches have become increasingly accurate, they often fail in common scenarios involving self-contact, such as a hand touching the face. In contrast, wearable bioimpedance sensing can cheaply and unobtrusively measure ground-truth skin-to-skin contact. Consequently, we propose a novel framework that combines visual pose estimators with bioimpedance sensing to capture the 3D pose of people by taking self-contact into account. Our method, BioTUCH, initializes the pose using an off-the-shelf estimator and introduces contact-aware pose optimization during measured self-contact: reprojection error and deviations from the input estimate are minimized while enforcing vertex proximity constraints. We validate our approach using a new dataset of synchronized RGB video, bioimpedance measurements, and 3D motion capture. Testing with three input pose estimators, we demonstrate an average of 11.7% improvement in reconstruction accuracy. We also present a miniature wearable bioimpedance sensor that enables efficient large-scale collection of contact-aware training data for improving pose estimation and generation using BioTUCH. Code and data are available at biotuch.is.tue.mpg.de

---

### Concentration bounds for intrinsic dimension estimation using Gaussian kernels

Authors: Martin Andersson
Published: 2025-12-04
Categories: math.ST, stat.ML
arXiv: https://arxiv.org/abs/2512.04861v2

We prove finite-sample concentration and anti-concentration bounds for dimension estimation using Gaussian kernel sums. Our bounds provide explicit dependence on sample size, bandwidth, and local geometric and distributional parameters, characterizing precisely how regularity conditions influence statistical performance. We also propose a bandwidth selection heuristic using derivative information, supported by numerical experiments.

---

### Concentration bounds for intrinsic dimension estimation using Gaussian kernels

Authors: Martin Andersson
Published: 2025-12-04
Categories: math.ST, stat.ML
arXiv: https://arxiv.org/abs/2512.04861v1

We prove finite-sample concentration and anti-concentration bounds for dimension estimation using Gaussian kernel sums. Our bounds provide explicit dependence on sample size, bandwidth, and local geometric and distributional parameters, characterizing precisely how regularity conditions govern statistical performance. We also propose a bandwidth selection heuristic using derivative information, which shows promise in numerical experiments.

---

### Autoregressive Image Generation Needs Only a Few Lines of Cached Tokens

Authors: Ziran Qin, Youru Lv, Mingbao Lin, Zeren Zhang, Chanfan Gan, Tieyuan Chen, Weiyao Lin
Published: 2025-12-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.04857v1

Autoregressive (AR) visual generation has emerged as a powerful paradigm for image and multimodal synthesis, owing to its scalability and generality. However, existing AR image generation suffers from severe memory bottlenecks due to the need to cache all previously generated visual tokens during decoding, leading to both high storage requirements and low throughput. In this paper, we introduce \textbf{LineAR}, a novel, training-free progressive key-value (KV) cache compression pipeline for autoregressive image generation. By fully exploiting the intrinsic characteristics of visual attention, LineAR manages the cache at the line level using a 2D view, preserving the visual dependency regions while progressively evicting less-informative tokens that are harmless for subsequent line generation, guided by inter-line attention. LineAR enables efficient autoregressive (AR) image generation by utilizing only a few lines of cache, achieving both memory savings and throughput speedup, while maintaining or even improving generation quality. Extensive experiments across six autoregressive image generation models, including class-conditional and text-to-image generation, validate its effectiveness and generality. LineAR improves ImageNet FID from 2.77 to 2.68 and COCO FID from 23.85 to 22.86 on LlamaGen-XL and Janus-Pro-1B, while retaining only 1/6 KV cache. It also improves DPG on Lumina-mGPT-768 with just 1/8 KV cache. Additionally, LineAR achieves significant memory and throughput gains, including up to 67.61% memory reduction and 7.57x speedup on LlamaGen-XL, and 39.66% memory reduction and 5.62x speedup on Janus-Pro-7B.

---

### From Task Executors to Research Partners: Evaluating AI Co-Pilots Through Workflow Integration in Biomedical Research

Authors: Lukas Weidener, Marko Brkić, Chiara Bacci, Mihailo Jovanović, Emre Ulgac, Alex Dobrin, Johannes Weniger, Martin Vlas, Ritvik Singh, Aakaash Meduri
Published: 2025-12-04
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.04854v1

Artificial intelligence systems are increasingly deployed in biomedical research. However, current evaluation frameworks may inadequately assess their effectiveness as research collaborators. This rapid review examines benchmarking practices for AI systems in preclinical biomedical research. Three major databases and two preprint servers were searched from January 1, 2018 to October 31, 2025, identifying 14 benchmarks that assess AI capabilities in literature understanding, experimental design, and hypothesis generation. The results revealed that all current benchmarks assess isolated component capabilities, including data analysis quality, hypothesis validity, and experimental protocol design. However, authentic research collaboration requires integrated workflows spanning multiple sessions, with contextual memory, adaptive dialogue, and constraint propagation. This gap implies that systems excelling on component benchmarks may fail as practical research co-pilots. A process-oriented evaluation framework is proposed that addresses four critical dimensions absent from current benchmarks: dialogue quality, workflow orchestration, session continuity, and researcher experience. These dimensions are essential for evaluating AI systems as research co-pilots rather than as isolated task executors.

---

### Language Models as Semantic Teachers: Post-Training Alignment for Medical Audio Understanding

Authors: Tsai-Ning Wang, Lin-Lin Chen, Neil Zeghidour, Aaqib Saeed
Published: 2025-12-04
Categories: cs.SD, cs.AI
arXiv: https://arxiv.org/abs/2512.04847v2

Pre-trained audio models excel at detecting acoustic patterns in auscultation sounds but often fail to grasp their clinical significance, limiting their use and performance in diagnostic tasks. To bridge this gap, we introduce AcuLa (Audio-Clinical Understanding via Language Alignment), a lightweight post-training framework that instills semantic understanding into any audio encoder by aligning it with a medical language model, which acts as a "semantic teacher." To enable alignment at scale, we construct a large-scale dataset by leveraging off-the-shelf large language models to translate the rich, structured metadata accompanying existing audio recordings into coherent clinical reports. Our alignment strategy combines a representation-level contrastive objective with a self-supervised modeling, ensuring that the model learns clinical semantics while preserving fine-grained temporal cues. AcuLa achieves state-of-the-art results across 18 diverse cardio-respiratory tasks from 10 different datasets, improving the mean AUROC on classification benchmarks from 0.68 to 0.79 and, on the most challenging COVID-19 cough detection task, boosting the AUROC from 0.55 to 0.89. Our work demonstrates that this audio-language alignment transforms purely acoustic models into clinically-aware diagnostic tools, establishing a novel paradigm for enhancing physiological understanding in audio-based health monitoring.

---

### Language Models as Semantic Teachers: Post-Training Alignment for Medical Audio Understanding

Authors: Tsai-Ning Wang, Lin-Lin Chen, Neil Zeghidour, Aaqib Saeed
Published: 2025-12-04
Categories: cs.SD, cs.AI
arXiv: https://arxiv.org/abs/2512.04847v1

Pre-trained audio models excel at detecting acoustic patterns in auscultation sounds but often fail to grasp their clinical significance, limiting their use and performance in diagnostic tasks. To bridge this gap, we introduce AcuLa (Audio-Clinical Understanding via Language Alignment), a lightweight post-training framework that instills semantic understanding into any audio encoder by aligning it with a medical language model, which acts as a "semantic teacher." To enable alignment at scale, we construct a large-scale dataset by leveraging off-the-shelf large language models to translate the rich, structured metadata accompanying existing audio recordings into coherent clinical reports. Our alignment strategy combines a representation-level contrastive objective with a self-supervised modeling, ensuring that the model learns clinical semantics while preserving fine-grained temporal cues. AcuLa achieves state-of-the-art results across 18 diverse cardio-respiratory tasks from 10 different datasets, improving the mean AUROC on classification benchmarks from 0.68 to 0.79 and, on the most challenging COVID-19 cough detection task, boosting the AUROC from 0.55 to 0.89. Our work demonstrates that this audio-language alignment transforms purely acoustic models into clinically-aware diagnostic tools, establishing a novel paradigm for enhancing physiological understanding in audio-based health monitoring.

---

### Mitigating Catastrophic Forgetting in Target Language Adaptation of LLMs via Source-Shielded Updates

Authors: Atsuki Yamaguchi, Terufumi Morishita, Aline Villavicencio, Nikolaos Aletras
Published: 2025-12-04
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2512.04844v2

Expanding the linguistic diversity of instruct large language models (LLMs) is crucial for global accessibility but is often hindered by the reliance on costly specialized target language labeled data and catastrophic forgetting during adaptation. We tackle this challenge under a realistic, low-resource constraint: adapting instruct LLMs using only unlabeled target language data. We introduce Source-Shielded Updates (SSU), a selective parameter update strategy that proactively preserves source knowledge. Using a small set of source data and a parameter importance scoring method, SSU identifies parameters critical to maintaining source abilities. It then applies a column-wise freezing strategy to protect these parameters before adaptation. Experiments across five typologically diverse languages and 7B and 13B models demonstrate that SSU successfully mitigates catastrophic forgetting. It reduces performance degradation on monolingual source tasks to just 3.4% (7B) and 2.8% (13B) on average, a stark contrast to the 20.3% and 22.3% from full fine-tuning. SSU also achieves target-language performance highly competitive with full fine-tuning, outperforming it on all benchmarks for 7B models and the majority for 13B models.

---

### Mitigating Catastrophic Forgetting in Target Language Adaptation of LLMs via Source-Shielded Updates

Authors: Atsuki Yamaguchi, Terufumi Morishita, Aline Villavicencio, Nikolaos Aletras
Published: 2025-12-04
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2512.04844v1

Expanding the linguistic diversity of instruct large language models (LLMs) is crucial for global accessibility but is often hindered by the reliance on costly specialized target language labeled data and catastrophic forgetting during adaptation. We tackle this challenge under a realistic, low-resource constraint: adapting instruct LLMs using only unlabeled target language data. We introduce Source-Shielded Updates (SSU), a selective parameter update strategy that proactively preserves source knowledge. Using a small set of source data and a parameter importance scoring method, SSU identifies parameters critical to maintaining source abilities. It then applies a column-wise freezing strategy to protect these parameters before adaptation. Experiments across five typologically diverse languages and 7B and 13B models demonstrate that SSU successfully mitigates catastrophic forgetting. It reduces performance degradation on monolingual source tasks to just 3.4% (7B) and 2.8% (13B) on average, a stark contrast to the 20.3% and 22.3% from full fine-tuning. SSU also achieves target-language performance highly competitive with full fine-tuning, outperforming it on all benchmarks for 7B models and the majority for 13B models.

---

### From Symptoms to Systems: An Expert-Guided Approach to Understanding Risks of Generative AI for Eating Disorders

Authors: Amy Winecoff, Kevin Klyman
Published: 2025-12-04
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2512.04843v1

Generative AI systems may pose serious risks to individuals vulnerable to eating disorders. Existing safeguards tend to overlook subtle but clinically significant cues, leaving many risks unaddressed. To better understand the nature of these risks, we conducted semi-structured interviews with 15 clinicians, researchers, and advocates with expertise in eating disorders. Using abductive qualitative analysis, we developed an expert-guided taxonomy of generative AI risks across seven categories: (1) providing generalized health advice; (2) encouraging disordered behaviors; (3) supporting symptom concealment; (4) creating thinspiration; (5) reinforcing negative self-beliefs; (6) promoting excessive focus on the body; and (7) perpetuating narrow views about eating disorders. Our results demonstrate how certain user interactions with generative AI systems intersect with clinical features of eating disorders in ways that may intensify risk. We discuss implications of our work, including approaches for risk assessment, safeguard design, and participatory evaluation practices with domain experts.

---

### SoK: a Comprehensive Causality Analysis Framework for Large Language Model Security

Authors: Wei Zhao, Zhe Li, Jun Sun
Published: 2025-12-04
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2512.04841v1

Large Language Models (LLMs) exhibit remarkable capabilities but remain vulnerable to adversarial manipulations such as jailbreaking, where crafted prompts bypass safety mechanisms. Understanding the causal factors behind such vulnerabilities is essential for building reliable defenses. In this work, we introduce a unified causality analysis framework that systematically supports all levels of causal investigation in LLMs, ranging from token-level, neuron-level, and layer-level interventions to representation-level analysis. The framework enables consistent experimentation and comparison across diverse causality-based attack and defense methods. Accompanying this implementation, we provide the first comprehensive survey of causality-driven jailbreak studies and empirically evaluate the framework on multiple open-weight models and safety-critical benchmarks including jailbreaks, hallucination detection, backdoor identification, and fairness evaluation. Our results reveal that: (1) targeted interventions on causally critical components can reliably modify safety behavior; (2) safety-related mechanisms are highly localized (i.e., concentrated in early-to-middle layers with only 1--2\% of neurons exhibiting causal influence); and (3) causal features extracted from our framework achieve over 95\% detection accuracy across multiple threat types. By bridging theoretical causality analysis and practical model safety, our framework establishes a reproducible foundation for research on causality-based attacks, interpretability, and robust attack detection and mitigation in LLMs. Code is available at https://github.com/Amadeuszhao/SOK_Casuality.

---