# Research Papers — 2025-12 · bundle page 78 of 175

> Full-text markdown of papers #3851–3900 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/78
[← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/77.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-12/page/79.md)

### FLAME: Flow Enhanced Legendre Memory Models for General Time Series Forecasting

Authors: Xingjian Wu, Zhengyu Li, Hanyin Cheng, Xiangfei Qiu, Jilin Hu, Chenjuan Guo, Bin Yang
Published: 2025-12-16
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.14253v4

In this work, we introduce FLAME, a family of extremely lightweight and capable Time Series Foundation Models, which support versatile forecasting tasks via generative probabilistic modeling, while ensuring both efficiency and robustness. FLAME utilizes the Legendre Memory for strong generalization capabilities. By adapting variants of Legendre Memory, i.e., translated Legendre (LegT) and scaled Legendre (LegS), in the Encoding and Decoding phases, FLAME can effectively capture the inherent inductive bias within data and make efficient long-range inferences. To enhance the accuracy of probabilistic forecasting while remaining efficient, FLAME adopts a normalizing-flow-based forecasting head, which can model complex distributions over the forecasting horizon in a generative manner. Comprehensive experiments on three well-recognized benchmarks, including TSFM-Bench, ProbTS, and TFB, demonstrate that FLAME is a strong out-of-the-box tool for decision intelligence.

---

### Gödel's Poetry

Authors: Kelly J. Davis
Published: 2025-12-16
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2512.14252v1

Formal, automated theorem proving has long been viewed as a challenge to artificial intelligence. We introduce here a new approach to computer theorem proving, one that employs specialized language models for Lean4 proof generation combined with recursive decomposition of difficult theorems into simpler entailing propositions. These models are coordinated through a multi-agent architecture that orchestrates autoformalization (if required), proof generation, decomposition of difficult theorems into simpler entailing propositions, and recursive proof (and/or decomposition) of these propositions. Without decomposition, we achieve a 90.4% pass rate on miniF2F. With decomposition, this is significantly improved. A key technical contribution lies in our extension of the Kimina Lean Server with abstract syntax tree (AST) parsing capabilities to facilitate automated, recursive proof decomposition. The system is made available on PyPI as goedels-poetry (at https://pypi.org/project/goedels-poetry ), and the open-source implementation KellyJDavis/goedels-poetry (at https://github.com/KellyJDavis/goedels-poetry ) facilitates both adaptation to alternative language models and extension with custom functionality.

---

### Randomized multi-class classification under system constraints: a unified approach via post-processing

Authors: Evgenii Chzhen, Mohamed Hebiri, Gayane Taturyan
Published: 2025-12-16
Categories: math.OC, stat.ML
arXiv: https://arxiv.org/abs/2512.14246v1

We study the problem of multi-class classification under system-level constraints expressible as linear functionals over randomized classifiers. We propose a post-processing approach that adjusts a given base classifier to satisfy general constraints without retraining. Our method formulates the problem as a linearly constrained stochastic program over randomized classifiers, and leverages entropic regularization and dual optimization techniques to construct a feasible solution. We provide finite-sample guarantees for the risk and constraint satisfaction for the final output of our algorithm under minimal assumptions. The framework accommodates a broad class of constraints, including fairness, abstention, and churn requirements.

---

### From Context to EDUs: Faithful and Structured Context Compression via Elementary Discourse Unit Decomposition

Authors: Yiqing Zhou, Yu Lei, Shuzheng Si, Qingyan Sun, Wei Wang, Yifei Wu, Hao Wen, Gang Chen, Fanchao Qi, Maosong Sun
Published: 2025-12-16
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2512.14244v4

Managing extensive context remains a critical bottleneck for Large Language Models (LLMs), particularly in applications like long-document question answering and autonomous agents where lengthy inputs incur high computational costs and introduce noise. Existing compression techniques often disrupt local coherence through discrete token removal or rely on implicit latent encoding that suffers from positional bias and incompatibility with closed-source APIs. To address these limitations, we introduce the EDU-based Context Compressor, a novel explicit compression framework designed to preserve both global structure and fine-grained details. Our approach reformulates context compression as a structure-then-select process. First, our LingoEDU transforms linear text into a structural relation tree of Elementary Discourse Units (EDUs) which are anchored strictly to source indices to eliminate hallucination. Second, a lightweight ranking module selects query-relevant sub-trees for linearization. To rigorously evaluate structural understanding, we release StructBench, a manually annotated dataset of 248 diverse documents. Empirical results demonstrate that our method achieves state-of-the-art structural prediction accuracy and significantly outperforms frontier LLMs while reducing costs. Furthermore, our structure-aware compression substantially enhances performance across downstream tasks ranging from long-context tasks to complex Deep Search scenarios.

---

### Beyond MMD: Evaluating Graph Generative Models with Geometric Deep Learning

Authors: Salvatore Romano, Marco Grassia, Giuseppe Mangioni
Published: 2025-12-16
Categories: cs.LG, cs.AI, physics.soc-ph
arXiv: https://arxiv.org/abs/2512.14241v2

Graph generation is a crucial task in many fields, including network science and bioinformatics, as it enables the creation of synthetic graphs that mimic the properties of real-world networks for various applications. Graph Generative Models (GGMs) have emerged as a promising solution to this problem, leveraging deep learning techniques to learn the underlying distribution of real-world graphs and generate new samples that closely resemble them. Examples include approaches based on Variational Auto-Encoders, Recurrent Neural Networks, and more recently, diffusion-based models. However, the main limitation often lies in the evaluation process, which typically relies on Maximum Mean Discrepancy (MMD) as a metric to assess the distribution of graph properties in the generated ensemble. This paper introduces a novel methodology for evaluating GGMs that overcomes the limitations of MMD, which we call RGM (Representation-aware Graph-generation Model evaluation). As a practical demonstration of our methodology, we present a comprehensive evaluation of two state-of-the-art Graph Generative Models: Graph Recurrent Attention Networks (GRAN) and Efficient and Degree-guided graph GEnerative model (EDGE). We investigate their performance in generating realistic graphs and compare them using a Geometric Deep Learning model trained on a custom dataset of synthetic and real-world graphs, specifically designed for graph classification tasks. Our findings reveal that while both models can generate graphs with certain topological properties, they exhibit significant limitations in preserving the structural characteristics that distinguish different graph domains. We also highlight the inadequacy of Maximum Mean Discrepancy as an evaluation metric for GGMs and suggest alternative approaches for future research.

---

### Physically consistent model learning for reaction-diffusion systems

Authors: Erion Morina, Martin Holler
Published: 2025-12-16
Categories: cs.LG, math.AP, math.OC
arXiv: https://arxiv.org/abs/2512.14240v1

This paper addresses the problem of learning reaction-diffusion (RD) systems from data while ensuring physical consistency and well-posedness of the learned models. Building on a regularization-based framework for structured model learning, we focus on learning parameterized reaction terms and investigate how to incorporate key physical properties, such as mass conservation and quasipositivity, directly into the learning process. Our main contributions are twofold: First, we propose techniques to systematically modify a given class of parameterized reaction terms such that the resulting terms inherently satisfy mass conservation and quasipositivity, ensuring that the learned RD systems preserve non-negativity and adhere to physical principles. These modifications also guarantee well-posedness of the resulting PDEs under additional regularity and growth conditions. Second, we extend existing theoretical results on regularization-based model learning to RD systems using these physically consistent reaction terms. Specifically, we prove that solutions to the learning problem converge to a unique, regularization-minimizing solution of a limit system even when conservation laws and quasipositivity are enforced. In addition, we provide approximation results for quasipositive functions, essential for constructing physically consistent parameterizations. These results advance the development of interpretable and reliable data-driven models for RD systems that align with fundamental physical laws.

---

### Two CFG Nahuatl for automatic corpora expansion

Authors: Juan-José Guzmán-Landa, Juan-Manuel Torres-Moreno, Miguel Figueroa-Saavedra, Ligia Quintana-Torres, Graham Ranger Martha-Lorena Avendaño-Garrido
Published: 2025-12-16
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.14239v1

The aim of this article is to introduce two Context-Free Grammars (CFG) for Nawatl Corpora expansion. Nawatl is an Amerindian language (it is a National Language of Mexico) of the $π$-language type, i.e. a language with few digital resources. For this reason the corpora available for the learning of Large Language Models (LLMs) are virtually non-existent, posing a significant challenge. The goal is to produce a substantial number of syntactically valid artificial Nawatl sentences and thereby to expand the corpora for the purpose of learning non contextual embeddings. For this objective, we introduce two new Nawatl CFGs and use them in generative mode. Using these grammars, it is possible to expand Nawatl corpus significantly and subsequently to use it to learn embeddings and to evaluate their relevance in a sentences semantic similarity task. The results show an improvement compared to the results obtained using only the original corpus without artificial expansion, and also demonstrate that economic embeddings often perform better than some LLMs.

---

### Ladder Up, Memory Down: Low-Cost Fine-Tuning With Side Nets

Authors: Estelle Zheng, Nathan Cerisara, Sébastien Warichet, Emmanuel Helbert, Christophe Cerisara
Published: 2025-12-16
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2512.14237v2

Fine-tuning large language models (LLMs) is often limited by the memory available on commodity GPUs. Parameter-efficient fine-tuning (PEFT) methods such as QLoRA reduce the number of trainable parameters, yet still incur high memory usage induced by the backward pass in the full model. We revisit Ladder Side Tuning (LST), a rarely explored PEFT technique that adds a lightweight side network, and show that it matches QLoRA's compute scaling slope while cutting peak memory by 50\%. Across different downstream benchmarks spanning natural language understanding, mathematical and LLM-critic tasks, LST has competitive performance with QLoRA's accuracy on average while being much more memory-efficient. This efficiency enables fine-tuning of 7B-parameter models on a single 12 GB consumer GPU with 2k-token contexts, requiring no gradient checkpointing\textemdash conditions under which QLoRA exhausts memory. Beyond memory efficiency, we also establish scaling laws showing that LST scales similarly to QLoRA. We exploit Ladder's architectural flexibility by introducing xLadder, a depth-extended variant that increases effective depth via cross-connections and shortens chain-of-thought (CoT) at fixed parameter count. Ladder is strong when memory is the bottleneck; xLadder builds on this by enabling deeper reasoning without additional memory overhead.

---

### Elastic3D: Controllable Stereo Video Conversion with Guided Latent Decoding

Authors: Nando Metzger, Prune Truong, Goutam Bhat, Konrad Schindler, Federico Tombari
Published: 2025-12-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.14236v2

The growing demand for immersive 3D content calls for automated monocular-to-stereo video conversion. We present Elastic3D, a controllable, direct end-to-end method for upgrading a conventional video to a binocular one. Our approach, based on (conditional) latent diffusion, avoids artifacts due to explicit depth estimation and warping. The key to its high-quality stereo video output is a novel, guided VAE decoder that ensures sharp and epipolar-consistent stereo video output. Moreover, our method gives the user control over the strength of the stereo effect (more precisely, the disparity range) at inference time, via an intuitive, scalar tuning knob. Experiments on three different datasets of real-world stereo videos show that our method outperforms both traditional warping-based and recent warping-free baselines and sets a new standard for reliable, controllable stereo video conversion. Please check the project page for the video samples https://elastic3d.github.io.

---

### 4D-RaDiff: Latent Point Diffusion for 4D Radar Point Cloud Generation

Authors: Jimmie Kwok, Holger Caesar, Andras Palffy
Published: 2025-12-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.14235v2

Automotive radar has shown promising developments in environment perception due to its cost-effectiveness and robustness in adverse weather conditions. However, the limited availability of annotated radar data poses a significant challenge for advancing radar-based perception systems. To address this limitation, we propose a novel framework to generate 4D radar point clouds for training and evaluating object detectors. Unlike image-based diffusion, our method is designed to consider the sparsity and unique characteristics of radar point clouds by applying diffusion to a latent point cloud representation. Within this latent space, generation is controlled via conditioning at either the object or scene level. The proposed 4D-RaDiff converts unlabeled bounding boxes into high-quality radar annotations and transforms existing LiDAR point cloud data into realistic radar scenes. Experiments demonstrate that incorporating synthetic radar data of 4D-RaDiff as data augmentation method during training of object detection models consistently improves performance compared to training on real data only. In addition, pre-training on our synthetic radar data achieves competitive detection performance, providing a promising, scalable approach to reduce dependence on costly manual annotations.

---

### ViBES: A Conversational Agent with Behaviorally-Intelligent 3D Virtual Body

Authors: Juze Zhang, Changan Chen, Xin Chen, Heng Yu, Tiange Xiang, Ali Sartaz Khan, Shrinidhi K. Lakshmikanth, Ehsan Adeli
Published: 2025-12-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.14234v2

Human communication is inherently multimodal and social: words, prosody, and body language jointly carry intent. Yet most prior systems model human behavior as a translation task co-speech gesture or text-to-motion that maps a fixed utterance to motion clips-without requiring agentic decision-making about when to move, what to do, or how to adapt across multi-turn dialogue. This leads to brittle timing, weak social grounding, and fragmented stacks where speech, text, and motion are trained or inferred in isolation. We introduce ViBES (Voice in Behavioral Expression and Synchrony), a conversational 3D agent that jointly plans language and movement and executes dialogue-conditioned body actions. Concretely, ViBES is a speech-language-behavior (SLB) model with a mixture-of-modality-experts (MoME) backbone: modality-partitioned transformer experts for speech, facial expression, and body motion. The model processes interleaved multimodal token streams with hard routing by modality (parameters are split per expert), while sharing information through cross-expert attention. By leveraging strong pretrained speech-language models, the agent supports mixed-initiative interaction: users can speak, type, or issue body-action directives mid-conversation, and the system exposes controllable behavior hooks for streaming responses. We further benchmark on multi-turn conversation with automatic metrics of dialogue-motion alignment and behavior quality, and observe consistent gains over strong co-speech and text-to-motion baselines. ViBES goes beyond "speech-conditioned motion generation" toward agentic virtual bodies where language, prosody, and movement are jointly generated, enabling controllable, socially competent 3D interaction. Code and data will be made available at: ai.stanford.edu/~juze/ViBES/

---

### PentestEval: Benchmarking LLM-based Penetration Testing with Modular and Stage-Level Design

Authors: Ruozhao Yang, Mingfei Cheng, Gelei Deng, Tianwei Zhang, Junjie Wang, Xiaofei Xie
Published: 2025-12-16
Categories: cs.SE, cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2512.14233v1

Penetration testing is essential for assessing and strengthening system security against real-world threats, yet traditional workflows remain highly manual, expertise-intensive, and difficult to scale. Although recent advances in Large Language Models (LLMs) offer promising opportunities for automation, existing applications rely on simplistic prompting without task decomposition or domain adaptation, resulting in unreliable black-box behavior and limited insight into model capabilities across penetration testing stages. To address this gap, we introduce PentestEval, the first comprehensive benchmark for evaluating LLMs across six decomposed penetration testing stages: Information Collection, Weakness Gathering and Filtering, Attack Decision-Making, Exploit Generation and Revision. PentestEval integrates expert-annotated ground truth with a fully automated evaluation pipeline across 346 tasks covering all stages in 12 realistic vulnerable scenarios. Our stage-level evaluation of 9 widely used LLMs reveals generally weak performance and distinct limitations across the stages of penetration-testing workflow. End-to-end pipelines reach only 31% success rate, and existing LLM-powered systems such as PentestGPT, PentestAgent, and VulnBot exhibit similar limitations, with autonomous agents failing almost entirely. These findings highlight that autonomous penetration testing demands stronger structured reasoning, where modularization enhances each individual stage and improves overall performance. PentestEval provides the foundational benchmark needed for future research on fine-grained, stage-level evaluation, paving the way toward more reliable LLM-based automation.

---

### Multi-View MRI Approach for Classification of MGMT Methylation in Glioblastoma Patients

Authors: Rawan Alyahya, Asrar Alruwayqi, Atheer Alqarni, Asma Alkhaldi, Metab Alkubeyyer, Xin Gao, Mona Alshahrani
Published: 2025-12-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.14232v1

The presence of MGMT promoter methylation significantly affects how well chemotherapy works for patients with Glioblastoma Multiforme (GBM). Currently, confirmation of MGMT promoter methylation relies on invasive brain tumor tissue biopsies. In this study, we explore radiogenomics techniques, a promising approach in precision medicine, to identify genetic markers from medical images. Using MRI scans and deep learning models, we propose a new multi-view approach that considers spatial relationships between MRI views to detect MGMT methylation status. Importantly, our method extracts information from all three views without using a complicated 3D deep learning model, avoiding issues associated with high parameter count, slow convergence, and substantial memory demands. We also introduce a new technique for tumor slice extraction and show its superiority over existing methods based on multiple evaluation metrics. By comparing our approach to state-of-the-art models, we demonstrate the efficacy of our method. Furthermore, we share a reproducible pipeline of published models, encouraging transparency and the development of robust diagnostic tools. Our study highlights the potential of non-invasive methods for identifying MGMT promoter methylation and contributes to advancing precision medicine in GBM treatment.

---

### Understanding the Gain from Data Filtering in Multimodal Contrastive Learning

Authors: Divyansh Pareek, Sewoong Oh, Simon S. Du
Published: 2025-12-16
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2512.14230v1

The success of modern multimodal representation learning relies on internet-scale datasets. Due to the low quality of a large fraction of raw web data, data curation has become a critical step in the training pipeline. Filtering using a trained model (i.e., teacher-based filtering) has emerged as a successful solution, leveraging a pre-trained model to compute quality scores. To explain the empirical success of teacher-based filtering, we characterize the performance of filtered contrastive learning under the standard bimodal data generation model. Denoting $η\in(0,1)$ as the fraction of data with correctly matched modalities among $n$ paired samples, we utilize a linear contrastive learning setup to show a provable benefit of data filtering: $(i)$ the error without filtering is upper and lower bounded by $\frac{1}{η\sqrt{n}}$, and $(ii)$ the error with teacher-based filtering is upper bounded by $\frac{1}{\sqrt{ηn}}$ in the large $η$ regime, and by $\frac{1}{\sqrt{n}}$ in the small $η$ regime.

---

### Georeferencing complex relative locality descriptions with large language models

Authors: Aneesha Fernando, Surangika Ranathunga, Kristin Stock, Raj Prasanna, Christopher B. Jones
Published: 2025-12-16
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.14228v1

Georeferencing text documents has typically relied on either gazetteer-based methods to assign geographic coordinates to place names, or on language modelling approaches that associate textual terms with geographic locations. However, many location descriptions specify positions relatively with spatial relationships, making geocoding based solely on place names or geo-indicative words inaccurate. This issue frequently arises in biological specimen collection records, where locations are often described through narratives rather than coordinates if they pre-date GPS. Accurate georeferencing is vital for biodiversity studies, yet the process remains labour-intensive, leading to a demand for automated georeferencing solutions. This paper explores the potential of Large Language Models (LLMs) to georeference complex locality descriptions automatically, focusing on the biodiversity collections domain. We first identified effective prompting patterns, then fine-tuned an LLM using Quantized Low-Rank Adaptation (QLoRA) on biodiversity datasets from multiple regions and languages. Our approach outperforms existing baselines with an average, across datasets, of 65% of records within a 10 km radius, for a fixed amount of training data. The best results (New York state) were 85% within 10km and 67% within 1km. The selected LLM performs well for lengthy, complex descriptions, highlighting its potential for georeferencing intricate locality descriptions.

---

### OmniGen: Unified Multimodal Sensor Generation for Autonomous Driving

Authors: Tao Tang, Enhui Ma, xia zhou, Letian Wang, Tianyi Yan, Xueyang Zhang, Kun Zhan, Peng Jia, XianPeng Lang, Jia-Wang Bian, Kaicheng Yu, Xiaodan Liang
Published: 2025-12-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.14225v1

Autonomous driving has seen remarkable advancements, largely driven by extensive real-world data collection. However, acquiring diverse and corner-case data remains costly and inefficient. Generative models have emerged as a promising solution by synthesizing realistic sensor data. However, existing approaches primarily focus on single-modality generation, leading to inefficiencies and misalignment in multimodal sensor data. To address these challenges, we propose OminiGen, which generates aligned multimodal sensor data in a unified framework. Our approach leverages a shared Bird\u2019s Eye View (BEV) space to unify multimodal features and designs a novel generalizable multimodal reconstruction method, UAE, to jointly decode LiDAR and multi-view camera data. UAE achieves multimodal sensor decoding through volume rendering, enabling accurate and flexible reconstruction. Furthermore, we incorporate a Diffusion Transformer (DiT) with a ControlNet branch to enable controllable multimodal sensor generation. Our comprehensive experiments demonstrate that OminiGen achieves desired performances in unified multimodal sensor data generation with multimodal consistency and flexible sensor adjustments.

---

### History-Enhanced Two-Stage Transformer for Aerial Vision-and-Language Navigation

Authors: Xichen Ding, Jianzhe Gao, Cong Pan, Wenguan Wang, Jie Qin
Published: 2025-12-16
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2512.14222v2

Aerial Vision-and-Language Navigation (AVLN) requires Unmanned Aerial Vehicle (UAV) agents to localize targets in large-scale urban environments based on linguistic instructions. While successful navigation demands both global environmental reasoning and local scene comprehension, existing UAV agents typically adopt mono-granularity frameworks that struggle to balance these two aspects. To address this limitation, this work proposes a History-Enhanced Two-Stage Transformer (HETT) framework, which integrates the two aspects through a coarse-to-fine navigation pipeline. Specifically, HETT first predicts coarse-grained target positions by fusing spatial landmarks and historical context, then refines actions via fine-grained visual analysis. In addition, a historical grid map is designed to dynamically aggregate visual features into a structured spatial memory, enhancing comprehensive scene awareness. Additionally, the CityNav dataset annotations are manually refined to enhance data quality. Experiments on the refined CityNav dataset show that HETT delivers significant performance gains, while extensive ablation studies further verify the effectiveness of each component.

---

### Weighted Conformal Prediction Provides Adaptive and Valid Mask-Conditional Coverage for General Missing Data Mechanisms

Authors: Jiarong Fan, Juhyun Park. Thi Phuong Thuy Vo, Nicolas Brunel
Published: 2025-12-16
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2512.14221v1

Conformal prediction (CP) offers a principled framework for uncertainty quantification, but it fails to guarantee coverage when faced with missing covariates. In addressing the heterogeneity induced by various missing patterns, Mask-Conditional Valid (MCV) Coverage has emerged as a more desirable property than Marginal Coverage. In this work, we adapt split CP to handle missing values by proposing a preimpute-mask-then-correct framework that can offer valid coverage. We show that our method provides guaranteed Marginal Coverage and Mask-Conditional Validity for general missing data mechanisms. A key component of our approach is a reweighted conformal prediction procedure that corrects the prediction sets after distributional imputation (multiple imputation) of the calibration dataset, making our method compatible with standard imputation pipelines. We derive two algorithms, and we show that they are approximately marginally valid and MCV. We evaluate them on synthetic and real-world datasets. It reduces significantly the width of prediction intervals w.r.t standard MCV methods, while maintaining the target guarantees.

---

### Estimating problem difficulty without ground truth using Large Language Model comparisons

Authors: Marthe Ballon, Andres Algaba, Brecht Verbeken, Vincent Ginis
Published: 2025-12-16
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2512.14220v1

Recent advances in the finetuning of large language models (LLMs) have significantly improved their performance on established benchmarks, emphasizing the need for increasingly difficult, synthetic data. A key step in this data generation pipeline is a method for estimating problem difficulty. Current approaches, such as human calibration or performance-based scoring, fail to generalize to out-of-distribution problems, i.e. problems currently unsolvable by humans and LLMs, because they are not scalable, time-consuming, and ground truth dependent. Therefore, we propose a new method for estimating problem difficulty, LLM compare, that addresses these limitations. An LLM performs pairwise difficulty comparisons, and then Bradley-Terry scores are computed based on the outcomes. To validate our method, we first propose a conceptual framework that positions existing approaches on three orthogonal planes--construction, scale and dependence--identifying which quadrants a measure needs to occupy to score out-of-distribution problems. LLM compare naturally occupies all desirable quadrants as the first measure that is continuous and dynamic, model-agnostic and independent of ground truth information. As a second validation, we show that LLM compare demonstrates strong alignment with human annotations: Pearson $r \geq 0.80$ for $n=1876$. Thirdly, we show that LLM compare is robust to hallucinations, with less than $6\%$ degradation in Pearson correlation for $10\%$ noise injection. Our work represents a significant step towards replacing time-consuming human annotations and synthetic data generation, and will be an important driver for curriculum design, model evaluation, and AI-assisted research ideation.

---

### DRAW2ACT: Turning Depth-Encoded Trajectories into Robotic Demonstration Videos

Authors: Yang Bai, Liudi Yang, George Eskandar, Fengyi Shen, Mohammad Altillawi, Ziyuan Liu, Gitta Kutyniok
Published: 2025-12-16
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2512.14217v1

Video diffusion models provide powerful real-world simulators for embodied AI but remain limited in controllability for robotic manipulation. Recent works on trajectory-conditioned video generation address this gap but often rely on 2D trajectories or single modality conditioning, which restricts their ability to produce controllable and consistent robotic demonstrations. We present DRAW2ACT, a depth-aware trajectory-conditioned video generation framework that extracts multiple orthogonal representations from the input trajectory, capturing depth, semantics, shape and motion, and injects them into the diffusion model. Moreover, we propose to jointly generate spatially aligned RGB and depth videos, leveraging cross-modality attention mechanisms and depth supervision to enhance the spatio-temporal consistency. Finally, we introduce a multimodal policy model conditioned on the generated RGB and depth sequences to regress the robot's joint angles. Experiments on Bridge V2, Berkeley Autolab, and simulation benchmarks show that DRAW2ACT achieves superior visual fidelity and consistency while yielding higher manipulation success rates compared to existing baselines.

---

### Error Bound Analysis of Physics-Informed Neural Networks-Driven T2 Quantification in Cardiac Magnetic Resonance Imaging

Authors: Mengxue Zhang, Qingrui Cai, Yinyin Chen, Hang Jin, Jianjun Zhou, Qiu Guo, Peijun Zhao, Zhiping Mao, Xingxing Zhang, Yuyu Xia, Xianwang Jiang, Qin Xu et al.
Published: 2025-12-16
Categories: physics.bio-ph, cs.AI
arXiv: https://arxiv.org/abs/2512.14211v1

Physics-Informed Neural Networks (PINN) are emerging as a promising approach for quantitative parameter estimation of Magnetic Resonance Imaging (MRI). While existing deep learning methods can provide an accurate quantitative estimation of the T2 parameter, they still require large amounts of training data and lack theoretical support and a recognized gold standard. Thus, given the absence of PINN-based approaches for T2 estimation, we propose embedding the fundamental physics of MRI, the Bloch equation, in the loss of PINN, which is solely based on target scan data and does not require a pre-defined training database. Furthermore, by deriving rigorous upper bounds for both the T2 estimation error and the generalization error of the Bloch equation solution, we establish a theoretical foundation for evaluating the PINN's quantitative accuracy. Even without access to the ground truth or a gold standard, this theory enables us to estimate the error with respect to the real quantitative parameter T2. The accuracy of T2 mapping and the validity of the theoretical analysis are demonstrated on a numerical cardiac model and a water phantom, where our method exhibits excellent quantitative precision in the myocardial T2 range. Clinical applicability is confirmed in 94 acute myocardial infarction (AMI) patients, achieving low-error quantitative T2 estimation under the theoretical error bound, highlighting the robustness and potential of PINN.

---

### Understanding and Improving Hyperbolic Deep Reinforcement Learning

Authors: Timo Klein, Thomas Lang, Andrii Shkabrii, Alexander Sturm, Kevin Sidak, Lukas Miklautz, Claudia Plant, Yllka Velaj, Sebastian Tschiatschek
Published: 2025-12-16
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2512.14202v2

The exponential volume growth of hyperbolic geometry can embed the hierarchical relationships between states in reinforcement learning (RL) with far less distortion than Euclidean space. However, hyperbolic deep RL faces severe optimization challenges, and formal analysis of why optimization fails is lacking. We identify key factors that determine the success and failure of training hyperbolic deep RL agents. By analyzing the gradients of core operations in the Poincaré Ball and Hyperboloid models of hyperbolic geometry, we show that large-norm embeddings destabilize gradient-based training, leading to trust-region violations in proximal policy optimization (PPO). Based on these insights, we introduce Hyper++, a new hyperbolic deep RL agent that consists of three components: (1) feature regularization guaranteeing bounded norms while avoiding the curse of dimensionality from clipping; (2) a categorical value loss for stable critic training; and (3) a more optimization-friendly formulation of hyperbolic network layers. On ProcGen, we show that Hyper++ guarantees stable learning, outperforms prior hyperbolic agents, and reduces wall-clock time by approximately 30%. On Atari-5 with Double DQN, Hyper++ strongly outperforms Euclidean and hyperbolic baselines. We release our code at https://github.com/Probabilistic-and-Interactive-ML/hyper-rl.

---

### Beyond a Single Light: A Large-Scale Aerial Dataset for Urban Scene Reconstruction Under Varying Illumination

Authors: Zhuoxiao Li, Wenzong Ma, Taoyu Wu, Jinjing Zhu, Shuai Zhang, Jing OU, Tongyan Hua, Yinrui Ren, Rongjun Qin, Hui Xiong, Wufan Zhao
Published: 2025-12-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.14200v3

Recent advances in Neural Radiance Fields and 3D Gaussian Splatting have demonstrated strong potential for large-scale UAV-based 3D reconstruction tasks by fitting the appearance of images. However, real-world large-scale captures are often based on multi-temporal data capture, where illumination inconsistencies across different times of day can significantly lead to color artifacts, geometric inaccuracies, and inconsistent appearance. Due to the lack of UAV datasets that systematically capture the same areas under varying illumination conditions, this challenge remains largely underexplored. To fill this gap, we introduceSkyLume, a large-scale, real-world UAV dataset specifically designed for studying illumination robust 3D reconstruction in urban scene modeling: (1) We collect data from 10 urban regions data comprising more than 100k high resolution UAV images (four oblique views and nadir), where each region is captured at three periods of the day to systematically isolate illumination changes. (2) To support precise evaluation of geometry and appearance, we provide per-scene LiDAR scans and accurate 3D ground-truth for assessing depth, surface normals, and reconstruction quality under varying illumination. (3) For the inverse rendering task, we introduce the Temporal Consistency Coefficient (TCC), a metric that measuress cross-time albedo stability and directly evaluates the robustness of the disentanglement of light and material. We aim for this resource to serve as a foundation that advances research and real-world evaluation in large-scale inverse rendering, geometry reconstruction, and novel view synthesis.

---

### Fracture Morphology Classification: Local Multiclass Modeling for Multilabel Complexity

Authors: Cassandra Krause, Mattias P. Heinrich, Ron Keuth
Published: 2025-12-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.14196v1

Between $15\,\%$ and $45\,\%$ of children experience a fracture during their growth years, making accurate diagnosis essential. Fracture morphology, alongside location and fragment angle, is a key diagnostic feature. In this work, we propose a method to extract fracture morphology by assigning automatically global AO codes to corresponding fracture bounding boxes. This approach enables the use of public datasets and reformulates the global multilabel task into a local multiclass one, improving the average F1 score by $7.89\,\%$. However, performance declines when using imperfect fracture detectors, highlighting challenges for real-world deployment. Our code is available on GitHub.

---

### Random-Bridges as Stochastic Transports for Generative Models

Authors: Stefano Goria, Levent A. Mengütürk, Murat C. Mengütürk, Berkan Sesen
Published: 2025-12-16
Categories: cs.LG, math.PR
arXiv: https://arxiv.org/abs/2512.14190v3

This paper motivates the use of random-bridges -- stochastic processes conditioned to take target distributions at fixed timepoints -- in the realm of generative modelling. Herein, random-bridges can act as stochastic transports between two probability distributions when appropriately initialized, and can display either Markovian or non-Markovian, and either continuous, discontinuous or hybrid patterns depending on the driving process. We show how one can start from general probabilistic statements and then branch out into specific representations for learning and simulation algorithms in terms of information processing. Our empirical results, built on Gaussian random bridges, produce high-quality samples in significantly fewer steps compared to traditional approaches, while achieving competitive Frechet inception distance scores. Our analysis provides evidence that the proposed framework is computationally cheap and suitable for high-speed generation tasks.

---

### Optimizing the Adversarial Perturbation with a Momentum-based Adaptive Matrix

Authors: Wei Tao, Sheng Long, Xin Liu, Wei Li, Qing Tao
Published: 2025-12-16
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.14188v1

Generating adversarial examples (AEs) can be formulated as an optimization problem. Among various optimization-based attacks, the gradient-based PGD and the momentum-based MI-FGSM have garnered considerable interest. However, all these attacks use the sign function to scale their perturbations, which raises several theoretical concerns from the point of view of optimization. In this paper, we first reveal that PGD is actually a specific reformulation of the projected gradient method using only the current gradient to determine its step-size. Further, we show that when we utilize a conventional adaptive matrix with the accumulated gradients to scale the perturbation, PGD becomes AdaGrad. Motivated by this analysis, we present a novel momentum-based attack AdaMI, in which the perturbation is optimized with an interesting momentum-based adaptive matrix. AdaMI is proved to attain optimal convergence for convex problems, indicating that it addresses the non-convergence issue of MI-FGSM, thereby ensuring stability of the optimization process. The experiments demonstrate that the proposed momentum-based adaptive matrix can serve as a general and effective technique to boost adversarial transferability over the state-of-the-art methods across different networks while maintaining better stability and imperceptibility.

---

### Establishing Stochastic Object Models from Noisy Data via Ambient Measurement-Integrated Diffusion

Authors: Xiaoning Lei, Jianwei Sun, Wenhao Cai, Xichen Xu, Yanshu Wang, Hu Gao
Published: 2025-12-16
Categories: cs.GR, cs.CV
arXiv: https://arxiv.org/abs/2512.14187v3

Task-based measures of image quality (IQ) are critical for evaluating medical imaging systems, which must account for randomness including anatomical variability. Stochastic object models (SOMs) provide a statistical description of such variability, but conventional mathematical SOMs fail to capture realistic anatomy, while data-driven approaches typically require clean data rarely available in clinical tasks. To address this challenge, we propose AMID, an unsupervised Ambient Measurement-Integrated Diffusion with noise decoupling, which establishes clean SOMs directly from noisy measurements. AMID introduces a measurement-integrated strategy aligning measurement noise with the diffusion trajectory, and explicitly models coupling between measurement and diffusion noise across steps, an ambient loss is thus designed base on it to learn clean SOMs. Experiments on real CT and mammography datasets show that AMID outperforms existing methods in generation fidelity and yields more reliable task-based IQ evaluation, demonstrating its potential for unsupervised medical imaging analysis.

---

### End-to-End Learning-based Video Streaming Enhancement Pipeline: A Generative AI Approach

Authors: Emanuele Artioli, Farzad Tashtarian, Christian Timmerer
Published: 2025-12-16
Categories: cs.MM, cs.AI
arXiv: https://arxiv.org/abs/2512.14185v1

The primary challenge of video streaming is to balance high video quality with smooth playback. Traditional codecs are well tuned for this trade-off, yet their inability to use context means they must encode the entire video data and transmit it to the client. This paper introduces ELVIS (End-to-end Learning-based VIdeo Streaming Enhancement Pipeline), an end-to-end architecture that combines server-side encoding optimizations with client-side generative in-painting to remove and reconstruct redundant video data. Its modular design allows ELVIS to integrate different codecs, inpainting models, and quality metrics, making it adaptable to future innovations. Our results show that current technologies achieve improvements of up to 11 VMAF points over baseline benchmarks, though challenges remain for real-time applications due to computational demands. ELVIS represents a foundational step toward incorporating generative AI into video streaming pipelines, enabling higher quality experiences without increased bandwidth requirements.

---

### Towards Explainable Quantum AI: Informing the Encoder Selection of Quantum Neural Networks via Visualization

Authors: Shaolun Ruan, Feng Liang, Rohan Ramakrishna, Chao Ren, Rudai Yan, Qiang Guan, Jiannan Li, Yong Wang
Published: 2025-12-16
Categories: quant-ph, cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2512.14181v1

Quantum Neural Networks (QNNs) represent a promising fusion of quantum computing and neural network architectures, offering speed-ups and efficient processing of high-dimensional, entangled data. A crucial component of QNNs is the encoder, which maps classical input data into quantum states. However, choosing suitable encoders remains a significant challenge, largely due to the lack of systematic guidance and the trial-and-error nature of current approaches. This process is further impeded by two key challenges: (1) the difficulty in evaluating encoded quantum states prior to training, and (2) the lack of intuitive methods for analyzing an encoder's ability to effectively distinguish data features. To address these issues, we introduce a novel visualization tool, XQAI-Eyes, which enables QNN developers to compare classical data features with their corresponding encoded quantum states and to examine the mixed quantum states across different classes. By bridging classical and quantum perspectives, XQAI-Eyes facilitates a deeper understanding of how encoders influence QNN performance. Evaluations across diverse datasets and encoder designs demonstrate XQAI-Eyes's potential to support the exploration of the relationship between encoder design and QNN effectiveness, offering a holistic and transparent approach to optimizing quantum encoders. Moreover, domain experts used XQAI-Eyes to derive two key practices for quantum encoder selection, grounded in the principles of pattern preservation and feature mapping.

---

### Spherical Voronoi: Directional Appearance as a Differentiable Partition of the Sphere

Authors: Francesco Di Sario, Daniel Rebain, Dor Verbin, Marco Grangetto, Andrea Tagliasacchi
Published: 2025-12-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.14180v2

Radiance field methods (e.g. 3D Gaussian Splatting) have emerged as a powerful paradigm for novel view synthesis, yet their appearance modeling often relies on Spherical Harmonics (SH), which impose fundamental limitations. SH struggle with high-frequency signals, exhibit Gibbs ringing artifacts, and fail to capture specular reflections - a key component of realistic rendering. Although alternatives like spherical Gaussians offer improvements, they add significant optimization complexity. We propose Spherical Voronoi (SV) as a unified framework for appearance representation in 3D Gaussian Splatting. SV partitions the directional domain into learnable regions with smooth boundaries, providing an intuitive and stable parameterization for view-dependent effects. For diffuse appearance, SV achieves competitive results while keeping optimization simpler than existing alternatives. For reflections - where SH fail - we leverage SV as learnable reflection probes, taking reflected directions as input following principles from classical graphics. This formulation attains state-of-the-art results on synthetic and real-world datasets, demonstrating that SV offers a principled, efficient, and general solution for appearance modeling in explicit 3D representations. Project page: https://sphericalvoronoi.github.io/

---

### A Comparative Analysis of Retrieval-Augmented Generation Techniques for Bengali Standard-to-Dialect Machine Translation Using LLMs

Authors: K. M. Jubair Sami, Dipto Sumit, Ariyan Hossain, Farig Sadeque
Published: 2025-12-16
Categories: cs.CL, cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2512.14179v1

Translating from a standard language to its regional dialects is a significant NLP challenge due to scarce data and linguistic variation, a problem prominent in the Bengali language. This paper proposes and compares two novel RAG pipelines for standard-to-dialectal Bengali translation. The first, a Transcript-Based Pipeline, uses large dialect sentence contexts from audio transcripts. The second, a more effective Standardized Sentence-Pairs Pipeline, utilizes structured local\_dialect:standard\_bengali sentence pairs. We evaluated both pipelines across six Bengali dialects and multiple LLMs using BLEU, ChrF, WER, and BERTScore. Our findings show that the sentence-pair pipeline consistently outperforms the transcript-based one, reducing Word Error Rate (WER) from 76\% to 55\% for the Chittagong dialect. Critically, this RAG approach enables smaller models (e.g., Llama-3.1-8B) to outperform much larger models (e.g., GPT-OSS-120B), demonstrating that a well-designed retrieval strategy can be more crucial than model size. This work contributes an effective, fine-tuning-free solution for low-resource dialect translation, offering a practical blueprint for preserving linguistic diversity.

---

### Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes

Authors: Joseph Hoche, Andrei Bursuc, David Brellmann, Gilles Louppe, Pavel Izmailov, Angela Yao, Gianni Franchi
Published: 2025-12-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.14177v4

Large Vision-Language Models (LVLMs) often produce plausible but unreliable outputs, making robust uncertainty estimation essential. Recent work on semantic uncertainty estimates relies on external models to cluster multiple sampled responses and measure their semantic consistency. However, these clustering methods are often fragile, highly sensitive to minor phrasing variations, and can incorrectly group or separate semantically similar answers, leading to unreliable uncertainty estimates. We propose Semantic Gaussian Process Uncertainty (SGPU), a Bayesian framework that quantifies semantic uncertainty by analyzing the geometric structure of answer embeddings, avoiding brittle clustering. SGPU maps generated answers into a dense semantic space, computes the Gram matrix of their embeddings, and summarizes their semantic configuration via the eigenspectrum. This spectral representation is then fed into a Gaussian Process Classifier that learns to map patterns of semantic consistency to predictive uncertainty, and that can be applied in both black-box and white-box settings. Across six LLMs and LVLMs on eight datasets spanning VQA, image classification, and textual QA, SGPU consistently achieves state-of-the-art calibration (ECE) and discriminative (AUROC, AUARC) performance. We further show that SGPU transfers across models and modalities, indicating that its spectral representation captures general patterns of semantic uncertainty.

---

### On Improving Deep Active Learning with Formal Verification

Authors: Jonathan Spiegelman, Guy Amir, Guy Katz
Published: 2025-12-16
Categories: cs.LG, cs.LO
arXiv: https://arxiv.org/abs/2512.14170v1

Deep Active Learning (DAL) aims to reduce labeling costs in neural-network training by prioritizing the most informative unlabeled samples for annotation. Beyond selecting which samples to label, several DAL approaches further enhance data efficiency by augmenting the training set with synthetic inputs that do not require additional manual labeling. In this work, we investigate how augmenting the training data with adversarial inputs that violate robustness constraints can improve DAL performance. We show that adversarial examples generated via formal verification contribute substantially more than those produced by standard, gradient-based attacks. We apply this extension to multiple modern DAL techniques, as well as to a new technique that we propose, and show that it yields significant improvements in model generalization across standard benchmarks.

---

### IntentMiner: Intent Inversion Attack via Tool Call Analysis in the Model Context Protocol

Authors: Yunhao Yao, Zhiqiang Wang, Haoran Cheng, Yihang Cheng, Haohua Du, Xiang-Yang Li
Published: 2025-12-16
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2512.14166v2

The evolution of Large Language Models (LLMs) into Agentic AI has established the Model Context Protocol (MCP) as the standard for connecting reasoning engines with external tools. Although this decoupled architecture fosters modularity, it simultaneously shatters the traditional trust boundary. We uncover a novel privacy vector inherent to this paradigm: the Intent Inversion Attack. We show that semi-honest third-party MCP servers can accurately reconstruct users' underlying intents by leveraging only authorized metadata (e.g., function signatures, arguments, and receipts), effectively bypassing the need for raw query access. To quantify this threat, we introduce IntentMiner. Unlike statistical approaches, IntentMiner employs a hierarchical semantic parsing strategy that performs step-level intent reconstruction by analyzing tool functions, parameter entities, and result feedback in an orthogonal manner. Experiments on the ToolACE benchmark reveal that IntentMiner achieves a semantic alignment of over 85% with original queries, substantially surpassing LLM baselines. This work exposes a critical endogenous vulnerability: without semantic obfuscation, executing functions requires the transparency of intent, thereby challenging the privacy foundations of next-generation AI agents.

---

### FastDDHPose: Towards Unified, Efficient, and Disentangled 3D Human Pose Estimation

Authors: Qingyuan Cai, Linxin Zhang, Xuecai Hu, Saihui Hou, Yongzhen Huang
Published: 2025-12-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.14162v1

Recent approaches for monocular 3D human pose estimation (3D HPE) have achieved leading performance by directly regressing 3D poses from 2D keypoint sequences. Despite the rapid progress in 3D HPE, existing methods are typically trained and evaluated under disparate frameworks, lacking a unified framework for fair comparison. To address these limitations, we propose Fast3DHPE, a modular framework that facilitates rapid reproduction and flexible development of new methods. By standardizing training and evaluation protocols, Fast3DHPE enables fair comparison across 3D human pose estimation methods while significantly improving training efficiency. Within this framework, we introduce FastDDHPose, a Disentangled Diffusion-based 3D Human Pose Estimation method which leverages the strong latent distribution modeling capability of diffusion models to explicitly model the distributions of bone length and bone direction while avoiding further amplification of hierarchical error accumulation. Moreover, we design an efficient Kinematic-Hierarchical Spatial and Temporal Denoiser that encourages the model to focus on kinematic joint hierarchies while avoiding unnecessary modeling of overly complex joint topologies. Extensive experiments on Human3.6M and MPI-INF-3DHP show that the Fast3DHPE framework enables fair comparison of all methods while significantly improving training efficiency. Within this unified framework, FastDDHPose achieves state-of-the-art performance with strong generalization and robustness in in-the-wild scenarios. The framework and models will be released at: https://github.com/Andyen512/Fast3DHPE

---

### CIS-BA: Continuous Interaction Space Based Backdoor Attack for Object Detection in the Real-World

Authors: Shuxin Zhao, Bo Lang, Nan Xiao, Yilang Zhang
Published: 2025-12-16
Categories: cs.CV, cs.CR
arXiv: https://arxiv.org/abs/2512.14158v1

Object detection models deployed in real-world applications such as autonomous driving face serious threats from backdoor attacks. Despite their practical effectiveness,existing methods are inherently limited in both capability and robustness due to their dependence on single-trigger-single-object mappings and fragile pixel-level cues. We propose CIS-BA, a novel backdoor attack paradigm that redefines trigger design by shifting from static object features to continuous inter-object interaction patterns that describe how objects co-occur and interact in a scene. By modeling these patterns as a continuous interaction space, CIS-BA introduces space triggers that, for the first time, enable a multi-trigger-multi-object attack mechanism while achieving robustness through invariant geometric relations. To implement this paradigm, we design CIS-Frame, which constructs space triggers via interaction analysis, formalizes them as class-geometry constraints for sample poisoning, and embeds the backdoor during detector training. CIS-Frame supports both single-object attacks (object misclassification and disappearance) and multi-object simultaneous attacks, enabling complex and coordinated effects across diverse interaction states. Experiments on MS-COCO and real-world videos show that CIS-BA achieves over 97% attack success under complex environments and maintains over 95% effectiveness under dynamic multi-trigger conditions, while evading three state-of-the-art defenses. In summary, CIS-BA extends the landscape of backdoor attacks in interaction-intensive scenarios and provides new insights into the security of object detection systems.

---

### Ophiuchus: Incentivizing Tool-augmented "Think with Images" for Joint Medical Segmentation, Understanding and Reasoning

Authors: Yankai Jiang, Yujie Zhang, Peng Zhang, Wenjie Li, Yichen Li, Jintai Chen, Xiaoming Shi, Shihui Zhen
Published: 2025-12-16
Categories: cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2512.14157v2

Recent medical MLLMs have made significant progress in generating step-by-step textual reasoning chains. However, they still struggle with complex clinical tasks that necessitate dynamic and iterative focusing on fine-grained visual regions. To close this gap, we introduce Ophiuchus, a versatile, tool-augmented framework that equips an MLLM to (i) decide when fine-grained visual evidence is needed, (ii) determine where to probe and ground within the medical image, and (iii) seamlessly weave the relevant sub-image content back into an interleaved, multimodal chain of thought for precise segmentation and diagnosis. Ophiuchus moves beyond mere tool-calling by tightly fusing the MLLM's inherent grounding and reasoning capabilities with external tools, enabling more accurate and trustworthy decisions. The core of our method is a three-stage training strategy: cold-start SFT for basic tool selection; self-reflection fine-tuning to strengthen decision revision; and agentic tool reinforcement learning to elicit sophisticated, expert-like diagnostic behaviors. Extensive experiments show that Ophiuchus consistently outperforms both closed-source and open-source SOTA methods across diverse medical benchmarks, including VQA, detection, and reasoning-based segmentation. Our project code is available at https://github.com/SII-zyj/Ophiuchus.

---

### PathFinder: Advancing Path Loss Prediction for Single-to-Multi-Transmitter Scenario

Authors: Zhijie Zhong, Zhiwen Yu, Pengyu Li, Jianming Lv, C. L. Philip Chen, Min Chen
Published: 2025-12-16
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2512.14150v3

Radio path loss prediction (RPP) is critical for optimizing 5G networks and enabling IoT, smart city, and similar applications. However, current deep learning-based RPP methods lack proactive environmental modeling, struggle with realistic multi-transmitter scenarios, and generalize poorly under distribution shifts, particularly when training/testing environments differ in building density or transmitter configurations. This paper identifies three key issues: (1) passive environmental modeling that overlooks transmitters and key environmental features; (2) overemphasis on single-transmitter scenarios despite real-world multi-transmitter prevalence; (3) excessive focus on in-distribution performance while neglecting distribution shift challenges. To address these, we propose PathFinder, a novel architecture that actively models buildings and transmitters via disentangled feature encoding and integrates Mask-Guided Low-Rank Attention to independently focus on receiver and building regions. We also introduce a Transmitter-Oriented Mixup strategy for robust training and a new benchmark, single-to-multi-transmitter RPP (S2MT-RPP), tailored to evaluate extrapolation performance (multi-transmitter testing after single-transmitter training). Experimental results show PathFinder outperforms state-of-the-art methods significantly, especially in challenging multi-transmitter scenarios. Our code and project site are available at: https://emorzz1g.github.io/PathFinder/.

---

### Astraea: A State-Aware Scheduling Engine for LLM-Powered Agents

Authors: Hongqiu Ni, Jiabao Zhang, Guopeng Li, Zilong Wang, Ruiqi Wu, Chi Zhang, Haisheng Tan
Published: 2025-12-16
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.14142v1

Large Language Models (LLMs) are increasingly being deployed as intelligent agents. Their multi-stage workflows, which alternate between local computation and calls to external network services like Web APIs, introduce a mismatch in their execution pattern and the scheduling granularity of existing inference systems such as vLLM. Existing systems typically focus on per-segment optimization which prevents them from minimizing the end-to-end latency of the complete agentic workflow, i.e., the global Job Completion Time (JCT) over the entire request lifecycle. To address this limitation, we propose Astraea, a service engine designed to shift the optimization from local segments to the global request lifecycle. Astraea employs a state-aware, hierarchical scheduling algorithm that integrates a request's historical state with future predictions. It dynamically classifies requests by their I/O and compute intensive nature and uses an enhanced HRRN policy to balance efficiency and fairness. Astraea also implements an adaptive KV cache manager that intelligently handles the agent state during I/O waits based on the system memory pressure. Extensive experiments show that Astraea reduces average JCT by up to 25.5\% compared to baseline methods. Moreover, our approach demonstrates strong robustness and stability under high load across various model scales.

---

### TorchTraceAP: A New Benchmark Dataset for Detecting Performance Anti-Patterns in Computer Vision Models

Authors: Hanning Chen, Keyu Man, Kevin Zhu, Chenguang Zhu, Haonan Li, Tongbo Luo, Xizhou Feng, Wei Sun, Sreen Tallam, Mohsen Imani, Partha Kanuparthy
Published: 2025-12-16
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2512.14141v1

Identifying and addressing performance anti-patterns in machine learning (ML) models is critical for efficient training and inference, but it typically demands deep expertise spanning system infrastructure, ML models and kernel development. While large tech companies rely on dedicated ML infrastructure engineers to analyze torch traces and benchmarks, such resource-intensive workflows are largely inaccessible to computer vision researchers in general. Among the challenges, pinpointing problematic trace segments within lengthy execution traces remains the most time-consuming task, and is difficult to automate with current ML models, including LLMs. In this work, we present the first benchmark dataset specifically designed to evaluate and improve ML models' ability to detect anti patterns in traces. Our dataset contains over 600 PyTorch traces from diverse computer vision models classification, detection, segmentation, and generation collected across multiple hardware platforms. We also propose a novel iterative approach: a lightweight ML model first detects trace segments with anti patterns, followed by a large language model (LLM) for fine grained classification and targeted feedback. Experimental results demonstrate that our method significantly outperforms unsupervised clustering and rule based statistical techniques for detecting anti pattern regions. Our method also effectively compensates LLM's limited context length and reasoning inefficiencies.

---

### SketchAssist: A Practical Assistant for Semantic Edits and Precise Local Redrawing

Authors: Han Zou, Yan Zhang, Ruiqi Yu, Cong Xie, Jie Huang, Zhenpeng Zhan
Published: 2025-12-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.14140v2

Sketch editing requires jointly handling high-level semantic changes and precise local redrawing, a combination that is particularly challenging for sparse, style-sensitive line art. Unlike natural images, sketches rely on minimal visual cues, making it difficult for existing methods to reconcile global semantic modifications with fine-grained structural control while preserving overall coherence. We present SketchAssist, an interactive sketch assistant that unifies instruction-guided editing with line-guided region redrawing, enabling efficient and controllable sketch manipulation while preserving overall composition. To support this task, we introduce a controllable data generation pipeline that constructs structured edit sequences with precise attribute variations and maintains structural alignment across multi-step modifications, while expanding stylistic diversity via style-preserving transformations. Building on this data, SketchAssist adopts a unified framework based on DiT, using a multi-channel input representation to encode sketches, masks, and guidance signals within a single interface. To further handle different editing modes, we integrate a Task-guided Mixture-of-Experts (T-MoE) into LoRA layers, enabling adaptive control over semantic and structural guidance. Extensive experiments demonstrate state-of-the-art performance on both tasks, achieving strong instruction adherence and improved structural and style consistency compared to recent methods. Together, our method provide a practical and controllable solution for sketch editing.

---

### LAPPI: Interactive Optimization with LLM-Assisted Preference-Based Problem Instantiation

Authors: So Kuroki, Manami Nakagawa, Shigeo Yoshida, Yuki Koyama, Kozuno Tadashi
Published: 2025-12-16
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2512.14138v1

Many real-world tasks, such as trip planning or meal planning, can be formulated as combinatorial optimization problems. However, using optimization solvers is difficult for end users because it requires problem instantiation: defining candidate items, assigning preference scores, and specifying constraints. We introduce LAPPI (LLM-Assisted Preference-based Problem Instantiation), an interactive approach that uses large language models (LLMs) to support users in this instantiation process. Through natural language conversations, the system helps users transform vague preferences into well-defined optimization problems. These instantiated problems are then passed to existing optimization solvers to generate solutions. In a user study on trip planning, our method successfully captured user preferences and generated feasible plans that outperformed both conventional and prompt-engineering approaches. We further demonstrate LAPPI's versatility by adapting it to an additional use case.

---

### Erasing CLIP Memories: Non-Destructive, Data-Free Zero-Shot class Unlearning in CLIP Models

Authors: Ashish Mishra, Tarun Kumar, Gyanaranjan Nayak, Arpit Shah, Suparna Bhattacharya, Martin Foltin
Published: 2025-12-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.14137v1

We introduce a novel, closed-form approach for selective unlearning in multimodal models, specifically targeting pretrained models such as CLIP. Our method leverages nullspace projection to erase the target class information embedded in the final projection layer, without requiring any retraining or the use of images from the forget set. By computing an orthonormal basis for the subspace spanned by target text embeddings and projecting these directions, we dramatically reduce the alignment between image features and undesired classes. Unlike traditional unlearning techniques that rely on iterative fine-tuning and extensive data curation, our approach is both computationally efficient and surgically precise. This leads to a pronounced drop in zero-shot performance for the target classes while preserving the overall multimodal knowledge of the model. Our experiments demonstrate that even a partial projection can balance between complete unlearning and retaining useful information, addressing key challenges in model decontamination and privacy preservation.

---

### UIXPOSE: Mobile Malware Detection via Intention-Behaviour Discrepancy Analysis

Authors: Amirmohammad Pasdar, Toby Murray, Van-Thuan Pham
Published: 2025-12-16
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2512.14130v1

We introduce UIXPOSE, a source-code-agnostic framework that operates on both compiled and open-source apps. This framework applies Intention Behaviour Alignment (IBA) to mobile malware analysis, aligning UI-inferred intent with runtime semantics. Previous work either infers intent statically, e.g., permission-centric, or widget-level or monitors coarse dynamic signals (endpoints, partial resource usage) that miss content and context. UIXPOSE infers an intent vector from each screen using vision-language models and knowledge structures and combines decoded network payloads, heap/memory signals, and resource utilisation traces into a behaviour vector. Their alignment, calculated at runtime, can both detect misbehaviour and highlight exploration of behaviourally rich paths. In three real-world case studies, UIXPOSE reveals covert exfiltration and hidden background activity that evade metadata-only baselines, demonstrating how IBA improves dynamic detection.

---

### Consistent Instance Field for Dynamic Scene Understanding

Authors: Junyi Wu, Van Nguyen Nguyen, Benjamin Planche, Jiachen Tao, Changchang Sun, Zhongpai Gao, Zhenghao Zhao, Anwesa Choudhuri, Gengyu Zhang, Meng Zheng, Feiran Wang, Terrence Chen et al.
Published: 2025-12-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.14126v1

We introduce Consistent Instance Field, a continuous and probabilistic spatio-temporal representation for dynamic scene understanding. Unlike prior methods that rely on discrete tracking or view-dependent features, our approach disentangles visibility from persistent object identity by modeling each space-time point with an occupancy probability and a conditional instance distribution. To realize this, we introduce a novel instance-embedded representation based on deformable 3D Gaussians, which jointly encode radiance and semantic information and are learned directly from input RGB images and instance masks through differentiable rasterization. Furthermore, we introduce new mechanisms to calibrate per-Gaussian identities and resample Gaussians toward semantically active regions, ensuring consistent instance representations across space and time. Experiments on HyperNeRF and Neu3D datasets demonstrate that our method significantly outperforms state-of-the-art methods on novel-view panoptic segmentation and open-vocabulary 4D querying tasks.

---

### SportsGPT: An LLM-driven Framework for Interpretable Sports Motion Assessment and Training Guidance

Authors: Wenbo Tian, Ruting Lin, Hongxian Zheng, Yaodong Yang, Geng Wu, Zihao Zhang, Zhang Zhang
Published: 2025-12-16
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2512.14121v2

Existing intelligent sports analysis systems mainly focus on "scoring and visualization," often lacking automatic performance diagnosis and interpretable training guidance. Recent advances in Large Language Models (LLMs) and motion analysis techniques provide new opportunities to address the above limitations. In this paper, we propose SportsGPT, an LLM-driven framework for interpretable sports motion assessment and training guidance, which establishes a closed loop from motion time-series input to professional training guidance. First, given a set of high-quality target models, we introduce MotionDTW, a two-stage time series alignment algorithm designed for accurate keyframe extraction from skeleton-based motion sequences. Subsequently, we design a Knowledge-based Interpretable Sports Motion Assessment Model (KISMAM) to obtain a set of interpretable assessment metrics (e.g., insufficient extension) by contrasting the keyframes with the target models. Finally, we propose SportsRAG, a RAG-based training guidance model built upon Qwen3. Leveraging a 6B-token knowledge base, it prompts the LLM to generate professional training guidance by retrieving domain-specific QA pairs. Experimental results demonstrate that MotionDTW significantly outperforms traditional methods with lower temporal error and higher IoU scores. Furthermore, ablation studies validate the KISMAM and SportsRAG, confirming that SportsGPT surpasses general LLMs in diagnostic accuracy and professionalism.

---

### CogMem: A Cognitive Memory Architecture for Sustained Multi-Turn Reasoning in Large Language Models

Authors: Yiran Zhang, Jincheng Hu, Mark Dras, Usman Naseem
Published: 2025-12-16
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.14118v1

Large language models (LLMs) excel at single-turn reasoning but often lose accuracy and coherence over extended, multi-turn interactions. Recent evaluations such as TurnBench highlight recurring failure modes-reasoning bias, task drift, hallucination, overconfidence, and memory decay. Current approaches typically append full conversational histories, causing unbounded context growth, higher computational costs, and degraded reasoning efficiency. We introduce CogMem, a cognitively inspired, memory-augmented LLM architecture that supports sustained iterative reasoning through structured, persistent memory. CogMem incorporates three layers: a Long-Term Memory (LTM) that consolidates cross-session reasoning strategies; a Direct Access (DA) memory that maintains session-level notes and retrieves relevant long-term memories; and a Focus of Attention (FoA) mechanism that dynamically reconstructs concise, task-relevant context at each turn. Experiments on TurnBench show that this layered design mitigates reasoning failures, controls context growth, and improves consistency across extended reasoning chains, moving toward more reliable, human-like reasoning in LLMs.

---

### Joint Multimodal Contrastive Learning for Robust Spoken Term Detection and Keyword Spotting

Authors: Ramesh Gundluru, Shubham Gupta, Sri Rama Murty K
Published: 2025-12-16
Categories: cs.SD, cs.LG
arXiv: https://arxiv.org/abs/2512.14115v1

Acoustic Word Embeddings (AWEs) improve the efficiency of speech retrieval tasks such as Spoken Term Detection (STD) and Keyword Spotting (KWS). However, existing approaches suffer from limitations, including unimodal supervision, disjoint optimization of audio-audio and audio-text alignment, and the need for task-specific models. To address these shortcomings, we propose a joint multimodal contrastive learning framework that unifies both acoustic and cross-modal supervision in a shared embedding space. Our approach simultaneously optimizes: (i) audio-text contrastive learning, inspired by the CLAP loss, to align audio and text representations and (ii) audio-audio contrastive learning, via Deep Word Discrimination (DWD) loss, to enhance intra-class compactness and inter-class separation. The proposed method outperforms existing AWE baselines on word discrimination task while flexibly supporting both STD and KWS. To our knowledge, this is the first comprehensive approach of its kind.

---

### MFE-GAN: Efficient GAN-based Framework for Document Image Enhancement and Binarization with Multi-scale Feature Extraction

Authors: Rui-Yang Ju, KokSheik Wong, Yanlin Jin, Jen-Shiun Chiang
Published: 2025-12-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.14114v1

Document image enhancement and binarization are commonly performed prior to document analysis and recognition tasks for improving the efficiency and accuracy of optical character recognition (OCR) systems. This is because directly recognizing text in degraded documents, particularly in color images, often results in unsatisfactory recognition performance. To address these issues, existing methods train independent generative adversarial networks (GANs) for different color channels to remove shadows and noise, which, in turn, facilitates efficient text information extraction. However, deploying multiple GANs results in long training and inference times. To reduce both training and inference times of document image enhancement and binarization models, we propose MFE-GAN, an efficient GAN-based framework with multi-scale feature extraction (MFE), which incorporates Haar wavelet transformation (HWT) and normalization to process document images before feeding them into GANs for training. In addition, we present novel generators, discriminators, and loss functions to improve the model's performance, and we conduct ablation studies to demonstrate their effectiveness. Experimental results on the Benchmark, Nabuco, and CMATERdb datasets demonstrate that the proposed MFE-GAN significantly reduces the total training and inference times while maintaining comparable performance with respect to state-of-the-art (SOTA) methods. The implementation of this work is available at https://ruiyangju.github.io/MFE-GAN.

---

### Selective, Controlled and Domain-Agnostic Unlearning in Pretrained CLIP: A Training- and Data-Free Approach

Authors: Ashish Mishra, Gyanaranjan Nayak, Tarun Kumar, Arpit Shah, Suparna Bhattacharya, Martin Foltin
Published: 2025-12-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.14113v1

Pretrained models like CLIP have demonstrated impressive zero-shot classification capabilities across diverse visual domains, spanning natural images, artistic renderings, and abstract representations. However, real-world applications often demand the removal (or "unlearning") of specific object classes without requiring additional data or retraining, or affecting the model's performance on unrelated tasks. In this paper, we propose a novel training- and data-free unlearning framework that enables three distinct forgetting paradigms: (1) global unlearning of selected objects across all domains, (2) domain-specific knowledge removal (e.g., eliminating sketch representations while preserving photo recognition), and (3) complete unlearning in selective domains. By leveraging a multimodal nullspace through synergistic integration of text prompts and synthesized visual prototypes derived from CLIP's joint embedding space, our method efficiently removes undesired class information while preserving the remaining knowledge. This approach overcomes the limitations of existing retraining-based methods and offers a flexible and computationally efficient solution for controlled model forgetting.

---