# Research Papers — 2025-12 · bundle page 75 of 175 > Full-text markdown of papers #3701–3750 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/75 [← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/74.md) [Next bundle →](https://aipod.dev/papers/archive/2025-12/page/76.md) ### Visual-textual Dermatoglyphic Animal Biometrics: A First Case Study on Panthera tigris Authors: Wenshuo Li, Majid Mirmehdi, Tilo Burghardt Published: 2025-12-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.14878v1 Biologists have long combined visuals with textual field notes to re-identify (Re-ID) animals. Contemporary AI tools automate this for species with distinctive morphological features but remain largely image-based. Here, we extend Re-ID methodologies by incorporating precise dermatoglyphic textual descriptors-an approach used in forensics but new to ecology. We demonstrate that these specialist semantics abstract and encode animal coat topology using human-interpretable language tags. Drawing on 84,264 manually labelled minutiae across 3,355 images of 185 tigers (Panthera tigris), we evaluate this visual-textual methodology, revealing novel capabilities for cross-modal identity retrieval. To optimise performance, we developed a text-image co-synthesis pipeline to generate 'virtual individuals', each comprising dozens of life-like visuals paired with dermatoglyphic text. Benchmarking against real-world scenarios shows this augmentation significantly boosts AI accuracy in cross-modal retrieval while alleviating data scarcity. We conclude that dermatoglyphic language-guided biometrics can overcome vision-only limitations, enabling textual-to-visual identity recovery underpinned by human-verifiable matchings. This represents a significant advance towards explainability in Re-ID and a language-driven unification of descriptive modalities in ecological monitoring. --- ### Isolated Sign Language Recognition with Segmentation and Pose Estimation Authors: Daniel Perkins, Davis Hunter, Dhrumil Patel, Galen Flanagan Published: 2025-12-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.14876v1 The recent surge in large language models has automated translations of spoken and written languages. However, these advances remain largely inaccessible to American Sign Language (ASL) users, whose language relies on complex visual cues. Isolated sign language recognition (ISLR) - the task of classifying videos of individual signs - can help bridge this gap but is currently limited by scarce per-sign data, high signer variability, and substantial computational costs. We propose a model for ISLR that reduces computational requirements while maintaining robustness to signer variation. Our approach integrates (i) a pose estimation pipeline to extract hand and face joint coordinates, (ii) a segmentation module that isolates relevant information, and (iii) a ResNet-Transformer backbone to jointly model spatial and temporal dependencies. --- ### How Does Fourier Analysis Network Work? A Mechanism Analysis and a New Dual-Activation Layer Proposal Authors: Sam Jeong, Hae Yong Kim Published: 2025-12-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.14873v3 Fourier Analysis Network (FAN) was recently proposed as a simple way to improve neural network performance by replacing part of Rectified Linear Unit (ReLU) activations with sine and cosine functions. Although several studies have reported small but consistent gains across tasks, the underlying mechanism behind these improvements has remained unclear. In this work, we show that only the sine activation contributes positively to performance, whereas the cosine activation tends to be detrimental. Our analysis reveals that the improvement is not a consequence of the sine function's periodic nature; instead, it stems from the function's local behavior near x = 0, where its non-zero derivative mitigates the vanishing-gradient problem. We further show that FAN primarily alleviates the dying-ReLU problem, in which a neuron consistently receives negative inputs, produces zero gradients, and stops learning. Although modern ReLU-like activations, such as Leaky ReLU, GELU, and Swish, reduce ReLU's zero-gradient region, they still contain input domains where gradients remain significantly diminished, contributing to slower optimization and hindering rapid convergence. FAN addresses this limitation by introducing a more stable gradient pathway. This analysis shifts the understanding of FAN's benefits from a spectral interpretation to a concrete analysis of training dynamics, leading to the development of the Dual-Activation Layer (DAL), a more efficient convergence accelerator. We evaluate DAL on three tasks: classification of noisy sinusoidal signals versus pure noise, MNIST digit classification, and Electrocardiogram (ECG)-based biometric recognition. In all cases, DAL models converge faster and achieve equal or higher validation accuracy compared to models with conventional activations. --- ### HERBench: A Benchmark for Multi-Evidence Integration in Video Question Answering Authors: Dan Ben-Ami, Gabriele Serussi, Kobi Cohen, Chaim Baskin Published: 2025-12-16 Categories: cs.CV, eess.IV arXiv: https://arxiv.org/abs/2512.14870v2 Video Large Language Models (Video-LLMs) are improving rapidly, yet current Video Question Answering (VideoQA) benchmarks often admit single-cue shortcuts, under-testing reasoning that must integrate evidence across time. We introduce HERBench, a benchmark designed to make multi-evidence integration unavoidable: each question requires at least three non-overlapping cues drawn from distinct video segments. HERBench contains 26,806 five-way multiple-choice questions across 12 compositional tasks. To make evidential demand measurable, we introduce the Minimum Required Frame-Set (MRFS), the smallest number of frames a model must fuse to answer correctly, and show that HERBench imposes higher evidential demand than prior benchmarks. Evaluating 13 state-of-the-art Video-LLMs yields only 31-42% accuracy, only modestly above the 20\% random-guess baseline. We disentangle this failure into two critical bottlenecks: (1) a retrieval deficit, where frame selectors overlook key evidence, and (2) a fusion deficit, where models fail to integrate information even when all necessary evidence is provided. HERBench thus provides a principled benchmark for studying robust multi-evidence video understanding. --- ### Autonomous Learning of Attractors for Neuromorphic Computing with Wien Bridge Oscillator Networks Authors: Riley Acker, Aman Desai, Garrett Kenyon, Frank Barrows Published: 2025-12-16 Categories: cs.NE, cs.ET, nlin.AO arXiv: https://arxiv.org/abs/2512.14869v1 We present an oscillatory neuromorphic primitive implemented with networks of coupled Wien bridge oscillators and tunable resistive couplings. Phase relationships between oscillators encode patterns, and a local Hebbian learning rule continuously adapts the couplings, allowing learning and recall to emerge from the same ongoing analog dynamics rather than from separate training and inference phases. Using a Kuramoto-style phase model with an effective energy function, we show that learned phase patterns form attractor states and validate this behavior in simulation and hardware. We further realize a 2-4-2 architecture with a hidden layer of oscillators, whose bipartite visible-hidden coupling allows multiple internal configurations to produce the same visible phase states. When inputs are switched, transient spikes in energy followed by relaxation indicate how the network can reduce surprise by reshaping its energy landscape. These results support coupled oscillator circuits as a hardware platform for energy-based neuromorphic computing with autonomous, continuous learning. --- ### Audio MultiChallenge: A Multi-Turn Evaluation of Spoken Dialogue Systems on Natural Human Interaction Authors: Advait Gosai, Tyler Vuong, Utkarsh Tyagi, Steven Li, Wenjia You, Miheer Bavare, Arda Uçar, Zhongwang Fang, Brian Jang, Bing Liu, Yunzhong He Published: 2025-12-16 Categories: cs.SD, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2512.14865v1 End-to-end (E2E) spoken dialogue systems are increasingly replacing cascaded pipelines for voice-based human-AI interaction, processing raw audio directly without intermediate transcription. Existing benchmarks primarily evaluate these models on synthetic speech and single-turn tasks, leaving realistic multi-turn conversational ability underexplored. We introduce Audio MultiChallenge, an open-source benchmark to evaluate E2E spoken dialogue systems under natural multi-turn interaction patterns. Building on the text-based MultiChallenge framework, which evaluates Inference Memory, Instruction Retention, and Self Coherence, we introduce a new axis Voice Editing that tests robustness to mid-utterance speech repairs and backtracking. We further augment each axis to the audio modality, such as introducing Audio-Cue challenges for Inference Memory that require recalling ambient sounds and paralinguistic signals beyond semantic content. We curate 452 conversations from 47 speakers with 1,712 instance-specific rubrics through a hybrid audio-native agentic and human-in-the-loop pipeline that exposes model failures at scale while preserving natural disfluencies found in unscripted human speech. Our evaluation of proprietary and open-source models reveals that even frontier models struggle on our benchmark, with Gemini 3 Pro Preview (Thinking), our highest-performing model achieving a 54.65% pass rate. Error analysis shows that models fail most often on our new axes and that Self Coherence degrades with longer audio context. These failures reflect difficulty of tracking edits, audio cues, and long-range context in natural spoken dialogue. Audio MultiChallenge provides a reproducible testbed to quantify them and drive improvements in audio-native multi-turn interaction capability. --- ### Penetration Testing of Agentic AI: A Comparative Security Analysis Across Models and Frameworks Authors: Viet K. Nguyen, Mohammad I. Husain Published: 2025-12-16 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2512.14860v1 Agentic AI introduces security vulnerabilities that traditional LLM safeguards fail to address. Although recent work by Unit 42 at Palo Alto Networks demonstrated that ChatGPT-4o successfully executes attacks as an agent that it refuses in chat mode, there is no comparative analysis in multiple models and frameworks. We conducted the first systematic penetration testing and comparative evaluation of agentic AI systems, testing five prominent models (Claude 3.5 Sonnet, Gemini 2.5 Flash, GPT-4o, Grok 2, and Nova Pro) across two agentic AI frameworks (AutoGen and CrewAI) using a seven-agent architecture that mimics the functionality of a university information management system and 13 distinct attack scenarios that span prompt injection, Server Side Request Forgery (SSRF), SQL injection, and tool misuse. Our 130 total test cases reveal significant security disparities: AutoGen demonstrates a 52.3% refusal rate versus CrewAI's 30.8%, while model performance ranges from Nova Pro's 46.2% to Claude and Grok 2's 38.5%. Most critically, Grok 2 on CrewAI rejected only 2 of 13 attacks (15.4% refusal rate), and the overall refusal rate of 41.5% across all configurations indicates that more than half of malicious prompts succeeded despite enterprise-grade safety mechanisms. We identify six distinct defensive behavior patterns including a novel "hallucinated compliance" strategy where models fabricate outputs rather than executing or refusing attacks, and provide actionable recommendations for secure agent deployment. Complete attack prompts are also included in the Appendix to enable reproducibility. --- ### T5Gemma 2: Seeing, Reading, and Understanding Longer Authors: Biao Zhang, Paul Suganthan, Gaël Liu, Ilya Philippov, Sahil Dua, Ben Hora, Kat Black, Gus Martins, Omar Sanseviero, Shreya Pathak, Cassidy Hardin, Francesco Visin et al. Published: 2025-12-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.14856v2 We introduce T5Gemma 2, the next generation of the T5Gemma family of lightweight open encoder-decoder models, featuring strong multilingual, multimodal and long-context capabilities. T5Gemma 2 follows the adaptation recipe (via UL2) in T5Gemma -- adapting a pretrained decoder-only model into an encoder-decoder model, and extends it from text-only regime to multimodal based on the Gemma 3 models. We further propose two methods to improve the efficiency: tied word embedding that shares all embeddings across encoder and decoder, and merged attention that unifies decoder self- and cross-attention into a single joint module. Experiments demonstrate the generality of the adaptation strategy over architectures and modalities as well as the unique strength of the encoder-decoder architecture on long context modeling. Similar to T5Gemma, T5Gemma 2 yields comparable or better pretraining performance and significantly improved post-training performance than its Gemma 3 counterpart. We release the pretrained models (270M-270M, 1B-1B and 4B-4B) to the community for future research. --- ### A Roadmap for Applying Graph Neural Networks to Numerical Data: Insights from Cementitious Materials Authors: Mahmuda Sharmin, Taihao Han, Jie Huang, Narayanan Neithalath, Gaurav Sant, Aditya Kumar Published: 2025-12-16 Categories: cs.CE, cs.AI arXiv: https://arxiv.org/abs/2512.14855v1 Machine learning (ML) has been increasingly applied in concrete research to optimize performance and mixture design. However, one major challenge in applying ML to cementitious materials is the limited size and diversity of available databases. A promising solution is the development of multi-modal databases that integrate both numerical and graphical data. Conventional ML frameworks in cement research are typically restricted to a single data modality. Graph neural network (GNN) represents a new generation of neural architectures capable of learning from data structured as graphs, capturing relationships through irregular or topology-dependent connections rather than fixed spatial coordinates. While GNN is inherently designed for graphical data, they can be adapted to extract correlations from numerical datasets and potentially embed physical laws directly into their architecture, enabling explainable and physics-informed predictions. This work is among the first few studies to implement GNNs to design concrete, with a particular emphasis on establishing a clear and reproducible pathway for converting tabular data into graph representations using the k-nearest neighbor (K-NN) approach. Model hyperparameters and feature selection are systematically optimized to enhance prediction performance. The GNN shows performance comparable to the benchmark random forest, which has been demonstrated by many studies to yield reliable predictions for cementitious materials. Overall, this study provides a foundational roadmap for transitioning from traditional ML to advanced AI architectures. The proposed framework establishes a strong foundation for future multi-modal and physics-informed GNN models capable of capturing complex material behaviors and accelerating the design and optimization of cementitious materials. --- ### Unreliable Uncertainty Estimates with Monte Carlo Dropout Authors: Aslak Djupskås, Alexander Johannes Stasik, Signe Riemer-Sørensen Published: 2025-12-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.14851v1 Reliable uncertainty estimation is crucial for machine learning models, especially in safety-critical domains. While exact Bayesian inference offers a principled approach, it is often computationally infeasible for deep neural networks. Monte Carlo dropout (MCD) was proposed as an efficient approximation to Bayesian inference in deep learning by applying neuron dropout at inference time \citep{gal2016dropout}. Hence, the method generates multiple sub-models yielding a distribution of predictions to estimate uncertainty. We empirically investigate its ability to capture true uncertainty and compare to Gaussian Processes (GP) and Bayesian Neural Networks (BNN). We find that MCD struggles to accurately reflect the underlying true uncertainty, particularly failing to capture increased uncertainty in extrapolation and interpolation regions as observed in Bayesian models. The findings suggest that uncertainty estimates from MCD, as implemented and evaluated in these experiments, is not as reliable as those from traditional Bayesian approaches for capturing epistemic and aleatoric uncertainty. --- ### MALCDF: A Distributed Multi-Agent LLM Framework for Real-Time Cyber Authors: Arth Bhardwaj, Sia Godika, Yuvam Loonker Published: 2025-12-16 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2512.14846v1 Traditional, centralized security tools often miss adaptive, multi-vector attacks. We present the Multi-Agent LLM Cyber Defense Framework (MALCDF), a practical setup where four large language model (LLM) agents-Detection, Intelligence, Response, and Analysis-work together in real time. Agents communicate over a Secure Communication Layer (SCL) with encrypted, ontology-aligned messages, and produce audit-friendly outputs (e.g., MITRE ATT&CK mappings). For evaluation, we keep the test simple and consistent: all reported metrics come from the same 50-record live stream derived from the CICIDS2017 feature schema. CICIDS2017 is used for configuration (fields/schema) and to train a practical ML baseline. The ML-IDS baseline is a Lightweight Random Forest IDS (LRF-IDS) trained on a subset of CICIDS2017 and tested on the 50-record stream, with no overlap between training and test records. In experiments, MALCDF reaches 90.0% detection accuracy, 85.7% F1-score, and 9.1% false-positive rate, with 6.8s average per-event latency. It outperforms the lightweight ML-IDS baseline and a single-LLM setup on accuracy while keeping end-to-end outputs consistent. Overall, this hands-on build suggests that coordinating simple LLM agents with secure, ontology-aligned messaging can improve practical, real-time cyber defense. --- ### Let the Barbarians In: How AI Can Accelerate Systems Performance Research Authors: Audrey Cheng, Shu Liu, Melissa Pan, Zhifei Li, Shubham Agarwal, Mert Cemri, Bowen Wang, Alexander Krentsel, Tian Xia, Jongseok Park, Shuo Yang, Jeff Chen et al. Published: 2025-12-16 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2512.14806v4 Artificial Intelligence (AI) is beginning to transform the research process by automating the discovery of new solutions. This shift depends on the availability of reliable verifiers, which AI-driven approaches require to validate candidate solutions. Research focused on improving systems performance is especially well-suited to this paradigm because system performance problems naturally admit such verifiers: candidates can be implemented in real systems or simulators and evaluated against predefined workloads. We term this iterative cycle of generation, evaluation, and refinement AI-Driven Research for Systems (ADRS). Using several open-source ADRS instances (i.e., OpenEvolve, GEPA, and ShinkaEvolve), we demonstrate across ten case studies (e.g., multi-region cloud scheduling, mixture-of-experts load balancing, LLM-based SQL, transaction scheduling) that ADRS-generated solutions can match or even outperform human state-of-the-art designs. Based on these findings, we outline best practices (e.g., level of prompt specification, amount of feedback, robust evaluation) for effectively using ADRS, and we discuss future research directions and their implications. Although we do not yet have a universal recipe for applying ADRS across all of systems research, we hope our preliminary findings, together with the challenges we identify, offer meaningful guidance for future work as researcher effort shifts increasingly toward problem formulation and strategic oversight. Note: This paper is an extension of our prior work (14). It adds extensive evaluation across multiple ADRS frameworks and provides deeper analysis and insights into best practices. --- ### Sharing State Between Prompts and Programs Authors: Ellie Y. Cheng, Logan Weber, Tian Jin, Michael Carbin Published: 2025-12-16 Categories: cs.PL, cs.AI arXiv: https://arxiv.org/abs/2512.14805v2 The rise of large language models (LLMs) has introduced a new type of programming: natural language programming. Users write prompts, which are instructions in natural language, to direct LLMs to perform tasks such as natural language processing, code generation, reasoning, etc. An emerging area of research enables interoperability between prompts and programs. We present a novel programming abstraction, shared program state, that removes the manual work required to enable interoperability between prompts and program states. With shared program state, programmers can write prompts that directly access program variables, compute with program objects, and implement control flow in the program. We present a schema for specifying natural function interfaces that extend programming systems to support programs with prompts and leverage this schema to specify shared program state as a natural function interface. We implement shared program state in the Nightjar programming system. Nightjar enables programmers to write Python programs containing prompts that share the Python program state. We show that Nightjar programs achieve comparable or higher task accuracy than manually written implementations (+4-19%), while decreasing the lines of code by 39.6% on average. The tradeoff is that Nightjar may incur runtime overhead (0.4-4.3x manual implementations). --- ### Incentives or Ontology? A Structural Rebuttal to OpenAI's Hallucination Thesis Authors: Richard Ackermann, Simeon Emanuilov Published: 2025-12-16 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.14801v1 OpenAI has recently argued that hallucinations in large language models result primarily from misaligned evaluation incentives that reward confident guessing rather than epistemic humility. On this view, hallucination is a contingent behavioral artifact, remediable through improved benchmarks and reward structures. In this paper, we challenge that interpretation. Drawing on previous work on structural hallucination and empirical experiments using a Licensing Oracle, we argue that hallucination is not an optimization failure but an architectural inevitability of the transformer model. Transformers do not represent the world; they model statistical associations among tokens. Their embedding spaces form a pseudo-ontology derived from linguistic co-occurrence rather than world-referential structure. At ontological boundary conditions - regions where training data is sparse or incoherent - the model necessarily interpolates fictional continuations in order to preserve coherence. No incentive mechanism can modify this structural dependence on pattern completion. Our empirical results demonstrate that hallucination can only be eliminated through external truth-validation and abstention modules, not through changes to incentives, prompting, or fine-tuning. The Licensing Oracle achieves perfect abstention precision across domains precisely because it supplies grounding that the transformer lacks. We conclude that hallucination is a structural property of generative architectures and that reliable AI requires hybrid systems that distinguish linguistic fluency from epistemic responsibility. --- ### Artificial Intelligence for the Assessment of Peritoneal Carcinosis during Diagnostic Laparoscopy for Advanced Ovarian Cancer Authors: Riccardo Oliva, Farahdiba Zarin, Alice Zampolini Faustini, Armine Vardazaryan, Andrea Rosati, Vinkle Srivastav, Nunzia Del Villano, Jacques Marescaux, Giovanni Scambia, Pietro Mascagni, Nicolas Padoy, Anna Fagotti Published: 2025-12-16 Categories: eess.IV, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2512.14797v1 Advanced Ovarian Cancer (AOC) is often diagnosed at an advanced stage with peritoneal carcinosis (PC). Fagotti score (FS) assessment at diagnostic laparoscopy (DL) guides treatment planning by estimating surgical resectability, but its subjective and operator-dependent nature limits reproducibility and widespread use. Videos of patients undergoing DL with concomitant FS assessments at a referral center were retrospectively collected and divided into a development dataset, for data annotation, AI training and evaluation, and an independent test dataset, for internal validation. In the development dataset, FS-relevant frames were manually annotated for anatomical structures and PC. Deep learning models were trained to automatically identify FS-relevant frames, segment structures and PC, and predict video-level FS and indication to surgery (ItS). AI performance was evaluated using Dice score for segmentation, F1-scores for anatomical stations (AS) and ItS prediction, and root mean square error (RMSE) for final FS estimation. In the development dataset, the segmentation model trained on 7,311 frames, achieved Dice scores of 70$\pm$3% for anatomical structures and 56$\pm$3% for PC. Video-level AS classification achieved F1-scores of 74$\pm$3% and 73$\pm$4%, FS prediction showed normalized RMSE values of 1.39$\pm$0.18 and 1.15$\pm$0.08, and ItS reached F1-scores of 80$\pm$8% and 80$\pm$2% in the development (n=101) and independent test datasets (n=50), respectively. This is the first AI model to predict the feasibility of cytoreductive surgery providing automated FS estimation from DL videos. Its reproducible and reliable performance across datasets suggests that AI can support surgeons through standardized intraoperative tumor burden assessment and clinical decision-making in AOC. --- ### Magnification-Aware Distillation (MAD): A Self-Supervised Framework for Unified Representation Learning in Gigapixel Whole-Slide Images Authors: Mahmut S. Gokmen, Mitchell A. Klusty, Peter T. Nelson, Allison M. Neltner, Sen-Ching Samson Cheung, Thomas M. Pearce, David A Gutman, Brittany N. Dugger, Devavrat S. Bisht, Margaret E. Flanagan, V. K. Cody Bumgardner Published: 2025-12-16 Categories: eess.IV, cs.AI, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2512.14796v1 Whole-slide images (WSIs) contain tissue information distributed across multiple magnification levels, yet most self-supervised methods treat these scales as independent views. This separation prevents models from learning representations that remain stable when resolution changes, a key requirement for practical neuropathology workflows. This study introduces Magnification-Aware Distillation (MAD), a self-supervised strategy that links low-magnification context with spatially aligned high-magnification detail, enabling the model to learn how coarse tissue structure relates to fine cellular patterns. The resulting foundation model, MAD-NP, is trained entirely through this cross-scale correspondence without annotations. A linear classifier trained only on 10x embeddings maintains 96.7% of its performance when applied to unseen 40x tiles, demonstrating strong resolution-invariant representation learning. Segmentation outputs remain consistent across magnifications, preserving anatomical boundaries and minimizing noise. These results highlight the feasibility of scalable, magnification-robust WSI analysis using a unified embedding space --- ### IaC Generation with LLMs: An Error Taxonomy and A Study on Configuration Knowledge Injection Authors: Roman Nekrasov, Stefano Fossati, Indika Kumara, Damian Andrew Tamburri, Willem-Jan van den Heuvel Published: 2025-12-16 Categories: cs.AI, cs.SE arXiv: https://arxiv.org/abs/2512.14792v1 Large Language Models (LLMs) currently exhibit low success rates in generating correct and intent-aligned Infrastructure as Code (IaC). This research investigated methods to improve LLM-based IaC generation, specifically for Terraform, by systematically injecting structured configuration knowledge. To facilitate this, an existing IaC-Eval benchmark was significantly enhanced with cloud emulation and automated error analysis. Additionally, a novel error taxonomy for LLM-assisted IaC code generation was developed. A series of knowledge injection techniques was implemented and evaluated, progressing from Naive Retrieval-Augmented Generation (RAG) to more sophisticated Graph RAG approaches. These included semantic enrichment of graph components and modeling inter-resource dependencies. Experimental results demonstrated that while baseline LLM performance was poor (27.1% overall success), injecting structured configuration knowledge increased technical validation success to 75.3% and overall success to 62.6%. Despite these gains in technical correctness, intent alignment plateaued, revealing a "Correctness-Congruence Gap" where LLMs can become proficient "coders" but remain limited "architects" in fulfilling nuanced user intent. --- ### Forecast Skill Is Not Decision Skill: Evidence from Weather-Dependent Decision Tasks Authors: Kornelius Raeth, Nicole Ludwig Published: 2025-12-16 Categories: cs.LG, stat.AP arXiv: https://arxiv.org/abs/2512.14779v2 Standard weather forecast evaluations focus on the forecaster's perspective and on a statistical assessment comparing forecasts and observations. In practice, however, forecasts are used to make decisions, so it seems natural to take the decision-maker's perspective and quantify the value of a forecast by its ability to improve decision-making. Decision calibration provides a novel framework for evaluating probabilistic forecast performance at the decision level rather than the forecast level. We evaluate decision calibration to compare a Machine Learning and a classical numerical weather prediction model on various weather-dependent decision tasks, though the framework is applicable to any set of forecast models. We find that model performance at the forecast level does not reliably translate to performance in downstream decision-making: some performance differences only become apparent at the decision level, and even among seemingly similar decision tasks, model rankings can change. Our results confirm that typical forecast evaluations are insufficient for selecting the optimal forecast model for a specific decision task. --- ### Improving VQA Reliability: A Dual-Assessment Approach with Self-Reflection and Cross-Model Verification Authors: Xixian Wu, Yang Ou, Pengchao Tian, Zian Yang, Jielei Zhang, Peiyi Li, Longwen Gao Published: 2025-12-16 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.14770v1 Vision-language models (VLMs) have demonstrated significant potential in Visual Question Answering (VQA). However, the susceptibility of VLMs to hallucinations can lead to overconfident yet incorrect answers, severely undermining answer reliability. To address this, we propose Dual-Assessment for VLM Reliability (DAVR), a novel framework that integrates Self-Reflection and Cross-Model Verification for comprehensive uncertainty estimation. The DAVR framework features a dual-pathway architecture: one pathway leverages dual selector modules to assess response reliability by fusing VLM latent features with QA embeddings, while the other deploys external reference models for factual cross-checking to mitigate hallucinations. Evaluated in the Reliable VQA Challenge at ICCV-CLVL 2025, DAVR achieves a leading $Φ_{100}$ score of 39.64 and a 100-AUC of 97.22, securing first place and demonstrating its effectiveness in enhancing the trustworthiness of VLM responses. --- ### Privacy-Preserving Feature Valuation in Vertical Federated Learning Using Shapley-CMI and PSI Permutation Authors: Unai Laskurain, Aitor Aguirre-Ortuzar, Urko Zurutuza Published: 2025-12-16 Categories: cs.CR, cs.AI, cs.DC arXiv: https://arxiv.org/abs/2512.14767v1 Federated Learning (FL) is an emerging machine learning paradigm that enables multiple parties to collaboratively train models without sharing raw data, ensuring data privacy. In Vertical FL (VFL), where each party holds different features for the same users, a key challenge is to evaluate the feature contribution of each party before any model is trained, particularly in the early stages when no model exists. To address this, the Shapley-CMI method was recently proposed as a model-free, information-theoretic approach to feature valuation using Conditional Mutual Information (CMI). However, its original formulation did not provide a practical implementation capable of computing the required permutations and intersections securely. This paper presents a novel privacy-preserving implementation of Shapley-CMI for VFL. Our system introduces a private set intersection (PSI) server that performs all necessary feature permutations and computes encrypted intersection sizes across discretized and encrypted ID groups, without the need for raw data exchange. Each party then uses these intersection results to compute Shapley-CMI values, computing the marginal utility of their features. Initial experiments confirm the correctness and privacy of the proposed system, demonstrating its viability for secure and efficient feature contribution estimation in VFL. This approach ensures data confidentiality, scales across multiple parties, and enables fair data valuation without requiring the sharing of raw data or training models. --- ### GR-Agent: Adaptive Graph Reasoning Agent under Incomplete Knowledge Authors: Dongzhuoran Zhou, Yuqicheng Zhu, Xiaxia Wang, Hongkuan Zhou, Jiaoyan Chen, Steffen Staab, Yuan He, Evgeny Kharlamov Published: 2025-12-16 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.14766v1 Large language models (LLMs) achieve strong results on knowledge graph question answering (KGQA), but most benchmarks assume complete knowledge graphs (KGs) where direct supporting triples exist. This reduces evaluation to shallow retrieval and overlooks the reality of incomplete KGs, where many facts are missing and answers must be inferred from existing facts. We bridge this gap by proposing a methodology for constructing benchmarks under KG incompleteness, which removes direct supporting triples while ensuring that alternative reasoning paths required to infer the answer remain. Experiments on benchmarks constructed using our methodology show that existing methods suffer consistent performance degradation under incompleteness, highlighting their limited reasoning ability. To overcome this limitation, we present the Adaptive Graph Reasoning Agent (GR-Agent). It first constructs an interactive environment from the KG, and then formalizes KGQA as agent environment interaction within this environment. GR-Agent operates over an action space comprising graph reasoning tools and maintains a memory of potential supporting reasoning evidence, including relevant relations and reasoning paths. Extensive experiments demonstrate that GR-Agent outperforms non-training baselines and performs comparably to training-based methods under both complete and incomplete settings. --- ### Guided Discrete Diffusion for Constraint Satisfaction Problems Authors: Justin Jung Published: 2025-12-16 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.14765v1 We propose discrete diffusion guidance for constraint satisfaction problems (CSPs) and demonstrate its ability to solve Sudoku puzzles without supervision. --- ### Scaling Causal Mediation for Complex Systems: A Framework for Root Cause Analysis Authors: Alessandro Casadei, Sreyoshi Bhaduri, Rohit Malshe, Pavan Mullapudi, Raj Ratan, Ankush Pole, Arkajit Rakshit Published: 2025-12-16 Categories: stat.ME, cs.AI, econ.EM arXiv: https://arxiv.org/abs/2512.14764v1 Modern operational systems ranging from logistics and cloud infrastructure to industrial IoT, are governed by complex, interdependent processes. Understanding how interventions propagate through such systems requires causal inference methods that go beyond direct effects to quantify mediated pathways. Traditional mediation analysis, while effective in simple settings, fails to scale to the high-dimensional directed acyclic graphs (DAGs) encountered in practice, particularly when multiple treatments and mediators interact. In this paper, we propose a scalable mediation analysis framework tailored for large causal DAGs involving multiple treatments and mediators. Our approach systematically decomposes total effects into interpretable direct and indirect components. We demonstrate its practical utility through applied case studies in fulfillment center logistics, where complex dependencies and non-controllable factors often obscure root causes. --- ### MemFlow: Flowing Adaptive Memory for Consistent and Efficient Long Video Narratives Authors: Sihui Ji, Xi Chen, Shuai Yang, Xin Tao, Pengfei Wan, Hengshuang Zhao Published: 2025-12-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.14699v1 The core challenge for streaming video generation is maintaining the content consistency in long context, which poses high requirement for the memory design. Most existing solutions maintain the memory by compressing historical frames with predefined strategies. However, different to-generate video chunks should refer to different historical cues, which is hard to satisfy with fixed strategies. In this work, we propose MemFlow to address this problem. Specifically, before generating the coming chunk, we dynamically update the memory bank by retrieving the most relevant historical frames with the text prompt of this chunk. This design enables narrative coherence even if new event happens or scenario switches in future frames. In addition, during generation, we only activate the most relevant tokens in the memory bank for each query in the attention layers, which effectively guarantees the generation efficiency. In this way, MemFlow achieves outstanding long-context consistency with negligible computation burden (7.9% speed reduction compared with the memory-free baseline) and keeps the compatibility with any streaming video generation model with KV cache. --- ### TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs Authors: Jun Zhang, Teng Wang, Yuying Ge, Yixiao Ge, Xinhao Li, Ying Shan, Limin Wang Published: 2025-12-16 Categories: cs.CV, cs.AI, cs.CL, cs.MM arXiv: https://arxiv.org/abs/2512.14698v2 This paper does not introduce a novel method but instead establishes a straightforward, incremental, yet essential baseline for video temporal grounding (VTG), a core capability in video understanding. While multimodal large language models (MLLMs) excel at various video understanding tasks, the recipes for optimizing them for VTG remain under-explored. In this paper, we present TimeLens, a systematic investigation into building MLLMs with strong VTG ability, along two primary dimensions: data quality and algorithmic design. We first expose critical quality issues in existing VTG benchmarks and introduce TimeLens-Bench, comprising meticulously re-annotated versions of three popular benchmarks with strict quality criteria. Our analysis reveals dramatic model re-rankings compared to legacy benchmarks, confirming the unreliability of prior evaluation standards. We also address noisy training data through an automated re-annotation pipeline, yielding TimeLens-100K, a large-scale, high-quality training dataset. Building on our data foundation, we conduct in-depth explorations of algorithmic design principles, yielding a series of meaningful insights and effective yet efficient practices. These include interleaved textual encoding for time representation, a thinking-free reinforcement learning with verifiable rewards (RLVR) approach as the training paradigm, and carefully designed recipes for RLVR training. These efforts culminate in TimeLens models, a family of MLLMs with state-of-the-art VTG performance among open-source models and even surpass proprietary models such as GPT-5 and Gemini-2.5-Flash. All codes, data, and models will be released to facilitate future research. --- ### Spherical Leech Quantization for Visual Tokenization and Generation Authors: Yue Zhao, Hanwen Jiang, Zhenlin Xu, Chutong Yang, Ehsan Adeli, Philipp Krähenbühl Published: 2025-12-16 Categories: cs.CV, cs.AI, cs.LG, eess.SP arXiv: https://arxiv.org/abs/2512.14697v1 Non-parametric quantization has received much attention due to its efficiency on parameters and scalability to a large codebook. In this paper, we present a unified formulation of different non-parametric quantization methods through the lens of lattice coding. The geometry of lattice codes explains the necessity of auxiliary loss terms when training auto-encoders with certain existing lookup-free quantization variants such as BSQ. As a step forward, we explore a few possible candidates, including random lattices, generalized Fibonacci lattices, and densest sphere packing lattices. Among all, we find the Leech lattice-based quantization method, which is dubbed as Spherical Leech Quantization ($Λ_{24}$-SQ), leads to both a simplified training recipe and an improved reconstruction-compression tradeoff thanks to its high symmetry and even distribution on the hypersphere. In image tokenization and compression tasks, this quantization approach achieves better reconstruction quality across all metrics than BSQ, the best prior art, while consuming slightly fewer bits. The improvement also extends to state-of-the-art auto-regressive image generation frameworks. --- ### CRISP: Contact-Guided Real2Sim from Monocular Video with Planar Scene Primitives Authors: Zihan Wang, Jiashun Wang, Jeff Tan, Yiwen Zhao, Jessica Hodgins, Shubham Tulsiani, Deva Ramanan Published: 2025-12-16 Categories: cs.CV, cs.GR, cs.RO arXiv: https://arxiv.org/abs/2512.14696v3 We introduce CRISP, a method that recovers simulatable human motion and scene geometry from monocular video. Prior work on joint human-scene reconstruction relies on data-driven priors and joint optimization with no physics in the loop, or recovers noisy geometry with artifacts that cause motion tracking policies with scene interactions to fail. In contrast, our key insight is to recover convex, clean, and simulation-ready geometry by fitting planar primitives to a point cloud reconstruction of the scene, via a simple clustering pipeline over depth, normals, and flow. To reconstruct scene geometry that might be occluded during interactions, we make use of human-scene contact modeling (e.g., we use human posture to reconstruct the occluded seat of a chair). Finally, we ensure that human and scene reconstructions are physically-plausible by using them to drive a humanoid controller via reinforcement learning. Our approach reduces motion tracking failure rates from 55.2\% to 6.9\% on human-centric video benchmarks (EMDB, PROX), while delivering a 43\% faster RL simulation throughput. We further validate it on in-the-wild videos including casually-captured videos, Internet videos, and even Sora-generated videos. This demonstrates CRISP's ability to generate physically-valid human motion and interaction environments at scale, greatly advancing real-to-sim applications for robotics and AR/VR. --- ### Universal Reasoning Model Authors: Zitian Gao, Lynx Chen, Yihao Xiao, He Xing, Ran Tao, Haoming Luo, Joey Zhou, Bryan Dai Published: 2025-12-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.14693v3 Universal transformers (UTs) have been widely used for complex reasoning tasks such as ARC-AGI and Sudoku, yet the specific sources of their performance gains remain underexplored. In this work, we systematically analyze UTs variants and show that improvements on ARC-AGI primarily arise from the recurrent inductive bias and strong nonlinear components of Transformer, rather than from elaborate architectural designs. Motivated by this finding, we propose the Universal Reasoning Model (URM), which enhances the UT with short convolution and truncated backpropagation. Our approach substantially improves reasoning performance, achieving state-of-the-art 53.8% pass@1 on ARC-AGI 1 and 16.0% pass@1 on ARC-AGI 2. Our code is avaliable at https://github.com/UbiquantAI/URM. --- ### Native and Compact Structured Latents for 3D Generation Authors: Jianfeng Xiang, Xiaoxue Chen, Sicheng Xu, Ruicheng Wang, Zelong Lv, Yu Deng, Hongyuan Zhu, Yue Dong, Hao Zhao, Nicholas Jing Yuan, Jiaolong Yang Published: 2025-12-16 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.14692v1 Recent advancements in 3D generative modeling have significantly improved the generation realism, yet the field is still hampered by existing representations, which struggle to capture assets with complex topologies and detailed appearance. This paper present an approach for learning a structured latent representation from native 3D data to address this challenge. At its core is a new sparse voxel structure called O-Voxel, an omni-voxel representation that encodes both geometry and appearance. O-Voxel can robustly model arbitrary topology, including open, non-manifold, and fully-enclosed surfaces, while capturing comprehensive surface attributes beyond texture color, such as physically-based rendering parameters. Based on O-Voxel, we design a Sparse Compression VAE which provides a high spatial compression rate and a compact latent space. We train large-scale flow-matching models comprising 4B parameters for 3D generation using diverse public 3D asset datasets. Despite their scale, inference remains highly efficient. Meanwhile, the geometry and material quality of our generated assets far exceed those of existing models. We believe our approach offers a significant advancement in 3D generative modeling. --- ### MMGR: Multi-Modal Generative Reasoning Benchmark and Evaluation Authors: Zefan Cai, Haoyi Qiu, Tianyi Ma, Haozhe Zhao, Gengze Zhou, Tingting Liao, Xinyan Velocity Yu, Kung-Hsiang Huang, Ke Wan, Shawn Lin, Parisa Kordjamshidi, Minjia Zhang et al. Published: 2025-12-16 Categories: cs.CL, cs.CV arXiv: https://arxiv.org/abs/2512.14691v3 Modern multimodal generative models can synthesize visually compelling images and videos, but it remains unclear whether this visual fluency reflects genuine reasoning: when prompted to generate a solution, can a model preserve the physical, logical, spatial, and temporal constraints a task requires, or does it merely produce plausible-looking media? To answer this question, we introduce MMGR (Multi-Modal Generative Reasoning Benchmark and Evaluation), a benchmark for evaluating generative reasoning across video, image, and language-based systems. MMGR covers 10 tasks from three domains (Abstract Reasoning, Embodied Navigation, and Physical Commonsense) and probes five reasoning abilities: Physical, Logical, 2D Spatial, 3D Spatial, and Temporal. Its evaluation emphasizes answer-verifiable tasks and, for video generation, process-aware chain-of-frame reasoning, where intermediate frames must form valid steps toward the target outcome rather than visually smooth but incorrect transitions. Evaluating state-of-the-art video generators, image generators, and LLM/VLM baselines reveals a sharp gap between visual quality and reasoning correctness: video models perform best on Physical Commonsense, but remain weak on symbolic tasks such as Sudoku, ARC, and Math, and brittle in cross-view embodied navigation. Image generators often outperform video generators on embodied navigation despite lacking temporal outputs, showing that longer visual generation does not automatically yield stronger reasoning. MMGR reframes evaluation of multimodal generation from whether outputs look realistic to whether they solve the underlying reasoning problem. --- ### CHIP: Adaptive Compliance for Humanoid Control through Hindsight Perturbation Authors: Sirui Chen, Zi-ang Cao, Zhengyi Luo, Fernando Castañeda, Chenran Li, Tingwu Wang, Ye Yuan, Linxi "Jim" Fan, C. Karen Liu, Yuke Zhu Published: 2025-12-16 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2512.14689v2 Recent progress in humanoid robots has unlocked agile locomotion skills, including backflipping, running, and crawling. Yet it remains challenging for a humanoid robot to perform forceful manipulation tasks such as moving objects, wiping, and pushing a cart. We propose adaptive Compliance Humanoid control through hIsight Perturbation (CHIP), a plug-and-play module that enables controllable end-effector stiffness while preserving agile tracking of dynamic reference motions. CHIP is easy to implement and requires neither data augmentation nor additional reward tuning. We show that a generalist motion-tracking controller trained with CHIP can perform a diverse set of forceful manipulation tasks that require different end-effector compliance, such as multi-robot collaboration, wiping, box delivery, and door opening. --- ### Spoken DialogSum: An Emotion-Rich Conversational Dataset for Spoken Dialogue Summarization Authors: Yen-Ju Lu, Kunxiao Gao, Mingrui Liang, Helin Wang, Thomas Thebaud, Laureano Moro-Velazquez, Najim Dehak, Jesus Villalba Published: 2025-12-16 Categories: cs.CL, cs.AI, cs.LG, eess.AS arXiv: https://arxiv.org/abs/2512.14687v2 Recent audio language models can follow long conversations. However, research on emotion-aware or spoken dialogue summarization is constrained by the lack of data that links speech, summaries, and paralinguistic cues. We introduce Spoken DialogSum, the first corpus aligning raw conversational audio with factual summaries, emotion-rich summaries, and utterance-level labels for speaker age, gender, and emotion. The dataset is built in two stages: first, an LLM rewrites DialogSum scripts with Switchboard-style fillers and back-channels, then tags each utterance with emotion, pitch, and speaking rate. Second, an expressive TTS engine synthesizes speech from the tagged scripts, aligned with paralinguistic labels. Spoken DialogSum comprises 13,460 emotion-diverse dialogues, each paired with both a factual and an emotion-focused summary. We release an online demo at https://fatfat-emosum.github.io/EmoDialog-Sum-Audio-Samples/, with plans to release the full dataset in the near future. Baselines show that an Audio-LLM raises emotional-summary ROUGE-L by 28% relative to a cascaded ASR-LLM system, confirming the value of end-to-end speech modeling. --- ### Bias-Variance Trade-off for Clipped Stochastic First-Order Methods: From Bounded Variance to Infinite Mean Authors: Chuan He Published: 2025-12-16 Categories: cs.LG, cs.AI, math.OC, stat.CO, stat.ML arXiv: https://arxiv.org/abs/2512.14686v1 Stochastic optimization is fundamental to modern machine learning. Recent research has extended the study of stochastic first-order methods (SFOMs) from light-tailed to heavy-tailed noise, which frequently arises in practice, with clipping emerging as a key technique for controlling heavy-tailed gradients. Extensive theoretical advances have further shown that the oracle complexity of SFOMs depends on the tail index $α$ of the noise. Nonetheless, existing complexity results often cover only the case $α\in (1,2)$, that is, the regime where the noise has a finite mean, while the complexity bounds tend to infinity as $α$ approaches $1$. This paper tackles the general case of noise with tail index $α\in(0,2)$, covering regimes ranging from noise with bounded variance to noise with an infinite mean, where the latter case has been scarcely studied. Through a novel analysis of the bias-variance trade-off in gradient clipping, we show that when a symmetry measure of the noise tail is controlled, clipped SFOMs achieve improved complexity guarantees in the presence of heavy-tailed noise for any tail index $α\in (0,2)$. Our analysis of the bias-variance trade-off not only yields new unified complexity guarantees for clipped SFOMs across this full range of tail indices, but is also straightforward to apply and can be combined with classical analyses under light-tailed noise to establish oracle complexity guarantees under heavy-tailed noise. Finally, numerical experiments validate our theoretical findings. --- ### Early Warning Index for Patient Deteriorations in Hospitals Authors: Dimitris Bertsimas, Yu Ma, Kimberly Villalobos Carballo, Gagan Singh, Michal Laskowski, Jeff Mather, Dan Kombert, Howard Haronian Published: 2025-12-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.14683v1 Hospitals lack automated systems to harness the growing volume of heterogeneous clinical and operational data to effectively forecast critical events. Early identification of patients at risk for deterioration is essential not only for patient care quality monitoring but also for physician care management. However, translating varied data streams into accurate and interpretable risk assessments poses significant challenges due to inconsistent data formats. We develop a multimodal machine learning framework, the Early Warning Index (EWI), to predict the aggregate risk of ICU admission, emergency response team dispatch, and mortality. Key to EWI's design is a human-in-the-loop process: clinicians help determine alert thresholds and interpret model outputs, which are enhanced by explainable outputs using Shapley Additive exPlanations (SHAP) to highlight clinical and operational factors (e.g., scheduled surgeries, ward census) driving each patient's risk. We deploy EWI in a hospital dashboard that stratifies patients into three risk tiers. Using a dataset of 18,633 unique patients at a large U.S. hospital, our approach automatically extracts features from both structured and unstructured electronic health record (EHR) data and achieves C-statistics of 0.796. It is currently used as a triage tool for proactively managing at-risk patients. The proposed approach saves physicians valuable time by automatically sorting patients of varying risk levels, allowing them to concentrate on patient care rather than sifting through complex EHR data. By further pinpointing specific risk drivers, the proposed model provides data-informed adjustments to caregiver scheduling and allocation of critical resources. As a result, clinicians and administrators can avert downstream complications, including costly procedures or high readmission rates and improve overall patient flow. --- ### Fast and Accurate Causal Parallel Decoding using Jacobi Forcing Authors: Lanxiang Hu, Siqi Kou, Yichao Fu, Samyam Rajbhandari, Tajana Rosing, Yuxiong He, Zhijie Deng, Hao Zhang Published: 2025-12-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.14681v1 Multi-token generation has emerged as a promising paradigm for accelerating transformer-based large model inference. Recent efforts primarily explore diffusion Large Language Models (dLLMs) for parallel decoding to reduce inference latency. To achieve AR-level generation quality, many techniques adapt AR models into dLLMs to enable parallel decoding. However, they suffer from limited speedup compared to AR models due to a pretrain-to-posttrain mismatch. Specifically, the masked data distribution in post-training deviates significantly from the real-world data distribution seen during pretraining, and dLLMs rely on bidirectional attention, which conflicts with the causal prior learned during pretraining and hinders the integration of exact KV cache reuse. To address this, we introduce Jacobi Forcing, a progressive distillation paradigm where models are trained on their own generated parallel decoding trajectories, smoothly shifting AR models into efficient parallel decoders while preserving their pretrained causal inference property. The models trained under this paradigm, Jacobi Forcing Model, achieves 3.8x wall-clock speedup on coding and math benchmarks with minimal loss in performance. Based on Jacobi Forcing Models' trajectory characteristics, we introduce multi-block decoding with rejection recycling, which enables up to 4.5x higher token acceptance count per iteration and nearly 4.0x wall-clock speedup, effectively trading additional compute for lower inference latency. Our code is available at https://github.com/hao-ai-lab/JacobiForcing. --- ### VASA-3D: Lifelike Audio-Driven Gaussian Head Avatars from a Single Image Authors: Sicheng Xu, Guojun Chen, Jiaolong Yang, Yizhong Zhang, Yu Deng, Steve Lin, Baining Guo Published: 2025-12-16 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.14677v1 We propose VASA-3D, an audio-driven, single-shot 3D head avatar generator. This research tackles two major challenges: capturing the subtle expression details present in real human faces, and reconstructing an intricate 3D head avatar from a single portrait image. To accurately model expression details, VASA-3D leverages the motion latent of VASA-1, a method that yields exceptional realism and vividness in 2D talking heads. A critical element of our work is translating this motion latent to 3D, which is accomplished by devising a 3D head model that is conditioned on the motion latent. Customization of this model to a single image is achieved through an optimization framework that employs numerous video frames of the reference head synthesized from the input image. The optimization takes various training losses robust to artifacts and limited pose coverage in the generated training data. Our experiment shows that VASA-3D produces realistic 3D talking heads that cannot be achieved by prior art, and it supports the online generation of 512x512 free-viewpoint videos at up to 75 FPS, facilitating more immersive engagements with lifelike 3D avatars. --- ### Fractal and Chaotic Activation Functions in Echo State Networks: Preprocessing Topology Governs the Echo State Property Authors: Rae Chipera, Jenny Du, Irene Tsapara Published: 2025-12-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.14675v2 Contemporary reservoir computing relies heavily on globally Lipschitz, well-behaved activation functions, limiting applications in defense, disaster response, and pharmaceutical modeling where robust operation under extreme conditions is critical. We systematically investigate non-smooth activation functions, including chaotic, stochastic, and fractal variants, in echo state networks. Through parameter sweeps across 36,610 reservoir configurations, we demonstrate that several non-smooth functions not only maintain behavior consistent with the Echo State Property (ESP) but outperform traditional smooth activations in convergence speed and spectral radius tolerance. Notably, the Cantor function (continuous everywhere, zero derivative almost everywhere) maintains ESP-consistent behavior up to spectral radii of rho = 10, an order of magnitude beyond typical bounds for traditional functions, while achieving 2.6x faster convergence than tanh and ReLU. We introduce a theoretical framework for quantized activation functions, defining a Degenerate Echo State Property (d-ESP) capturing stability for discrete-output functions, and prove that d-ESP implies traditional ESP. We conjecture a critical crowding ratio Q=N/k (reservoir size / quantization levels) predicting failure thresholds for discrete activations. Our analysis reveals that preprocessing topology, rather than continuity, determines stability: monotone, compressive preprocessing maintains ESP across scales, while dispersive or discontinuous preprocessing triggers sharp failures. Our findings challenge assumptions about activation function design in reservoir computing; the exceptional performance of certain fractal functions is only partially explained by the effective-gain analysis presented here, suggesting fundamental gaps in our understanding of how geometric properties of activation functions influence reservoir dynamics. --- ### ART: Articulated Reconstruction Transformer Authors: Zizhang Li, Cheng Zhang, Zhengqin Li, Henry Howard-Jenkins, Zhaoyang Lv, Chen Geng, Jiajun Wu, Richard Newcombe, Jakob Engel, Zhao Dong Published: 2025-12-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.14671v3 We introduce ART, Articulated Reconstruction Transformer -- a category-agnostic, feed-forward model that reconstructs complete 3D articulated objects from only sparse, multi-state RGB images. Previous methods for articulated object reconstruction either rely on slow optimization with fragile cross-state correspondences or use feed-forward models limited to specific object categories. In contrast, ART treats articulated objects as assemblies of rigid parts, formulating reconstruction as part-based prediction. Our newly designed transformer architecture maps sparse image inputs to a set of learnable part slots, from which ART jointly decodes unified representations for individual parts, including their 3D geometry, texture, and explicit articulation parameters. The resulting reconstructions are physically interpretable and readily exportable for simulation. Trained on a large-scale, diverse dataset with per-part supervision, and evaluated across diverse benchmarks, ART achieves significant improvements over existing baselines and establishes a new state of the art for articulated object reconstruction from image inputs. --- ### EVOLVE-VLA: Test-Time Training from Environment Feedback for Vision-Language-Action Models Authors: Zechen Bai, Chen Gao, Mike Zheng Shou Published: 2025-12-16 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2512.14666v1 Achieving truly adaptive embodied intelligence requires agents that learn not just by imitating static demonstrations, but by continuously improving through environmental interaction, which is akin to how humans master skills through practice. Vision-Language-Action (VLA) models have advanced robotic manipulation by leveraging large language models, yet remain fundamentally limited by Supervised Finetuning (SFT): requiring hundreds of demonstrations per task, rigidly memorizing trajectories, and failing to adapt when deployment conditions deviate from training. We introduce EVOLVE-VLA, a test-time training framework enabling VLAs to continuously adapt through environment interaction with minimal or zero task-specific demonstrations. The key technical challenge is replacing oracle reward signals (unavailable at test time) with autonomous feedback. We address this through a learned progress estimator providing dense feedback, and critically, we design our framework to ``tame'' this inherently noisy signal via two mechanisms: (1) an accumulative progress estimation mechanism smoothing noisy point-wise estimates, and (2) a progressive horizon extension strategy enabling gradual policy evolution. EVOLVE-VLA achieves substantial gains: +8.6\% on long-horizon tasks, +22.0\% in 1-shot learning, and enables cross-task generalization -- achieving 20.8\% success on unseen tasks without task-specific demonstrations training (vs. 0\% for pure SFT). Qualitative analysis reveals emergent capabilities absent in demonstrations, including error recovery and novel strategies. This work represents a critical step toward VLAs that truly learn and adapt, moving beyond static imitation toward continuous self-improvements. --- ### Enhancing Visual Sentiment Analysis via Semiotic Isotopy-Guided Dataset Construction Authors: Marco Blanchini, Giovanna Maria Dimitri, Benedetta Tondi, Tarcisio Lancioni, Mauro Barni Published: 2025-12-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.14665v1 Visual Sentiment Analysis (VSA) is a challenging task due to the vast diversity of emotionally salient images and the inherent difficulty of acquiring sufficient data to capture this variability comprehensively. Key obstacles include building large-scale VSA datasets and developing effective methodologies that enable algorithms to identify emotionally significant elements within an image. These challenges are reflected in the limited generalization performance of VSA algorithms and models when trained and tested across different datasets. Starting from a pool of existing data collections, our approach enables the creation of a new larger dataset that not only contains a wider variety of images than the original ones, but also permits training new models with improved capability to focus on emotionally relevant combinations of image elements. This is achieved through the integration of the semiotic isotopy concept within the dataset creation process, providing deeper insights into the emotional content of images. Empirical evaluations show that models trained on a dataset generated with our method consistently outperform those trained on the original data collections, achieving superior generalization across major VSA benchmarks --- ### gridfm-datakit-v1: A Python Library for Scalable and Realistic Power Flow and Optimal Power Flow Data Generation Authors: Alban Puech, Matteo Mazzonelli, Celia Cintas, Tamara R. Govindasamy, Mangaliso Mngomezulu, Jonas Weiss, Matteo Baù, Anna Varbella, François Mirallès, Kibaek Kim, Le Xie, Hendrik F. Hamann et al. Published: 2025-12-16 Categories: cs.LG, cs.AI, eess.SY, math.OC arXiv: https://arxiv.org/abs/2512.14658v1 We introduce gridfm-datakit-v1, a Python library for generating realistic and diverse Power Flow (PF) and Optimal Power Flow (OPF) datasets for training Machine Learning (ML) solvers. Existing datasets and libraries face three main challenges: (1) lack of realistic stochastic load and topology perturbations, limiting scenario diversity; (2) PF datasets are restricted to OPF-feasible points, hindering generalization of ML solvers to cases that violate operating limits (e.g., branch overloads or voltage violations); and (3) OPF datasets use fixed generator cost functions, limiting generalization across varying costs. gridfm-datakit addresses these challenges by: (1) combining global load scaling from real-world profiles with localized noise and supporting arbitrary N-k topology perturbations to create diverse yet realistic datasets; (2) generating PF samples beyond operating limits; and (3) producing OPF data with varying generator costs. It also scales efficiently to large grids (up to 10,000 buses). Comparisons with OPFData, OPF-Learn, PGLearn, and PF$Δ$ are provided. Available on GitHub at https://github.com/gridfm/gridfm-datakit under Apache 2.0 and via `pip install gridfm-datakit`. --- ### WaveSim: A Wavelet-based Multi-scale Similarity Metric for Weather and Climate Fields Authors: Gabriele Accarino, Viviana Acquaviva, Sara Shamekh, Duncan Watson-Parris, David Lawrence Published: 2025-12-16 Categories: physics.ao-ph, cs.CV, physics.data-an arXiv: https://arxiv.org/abs/2512.14656v1 We introduce WaveSim, a multi-scale similarity metric for the evaluation of spatial fields in weather and climate applications. WaveSim exploits wavelet transforms to decompose input fields into scale-specific wavelet coefficients. The metric is built by multiplying three orthogonal components derived from these coefficients: Magnitude, which quantifies similarities in the energy distribution of the coefficients, i.e., the intensity of the field; Displacement, which captures spatial shift by comparing the centers of mass of normalized energy distributions; and Structure, which assesses pattern organization independent of location and amplitude. Each component yields a scale-specific similarity score ranging from 0 (no similarity) to 1 (perfect similarity), which are then combined across scales to produce an overall similarity measure. We first evaluate WaveSim using synthetic test cases, applying controlled spatial and temporal perturbations to systematically assess its sensitivity and expected behavior. We then demonstrate its applicability to physically relevant case studies of key modes of climate variability in Earth System Models. Traditional point-wise metrics lack a mechanism for attributing errors to physical scales or modes of dissimilarity. By operating in the wavelet domain and decomposing the signal along independent axes, WaveSim bypasses these limitations and provides an interpretable and diagnostically rich framework for assessing similarity in complex fields. Additionally, the WaveSim framework allows users to place emphasis on a specific scale or component, and lends itself to user-specific model intercomparison, model evaluation, and calibration and training of forecasting systems. We provide a PyTorch-ready implementation of WaveSim, along with all evaluation scripts, at: https://github.com/gabrieleaccarino/wavesim. --- ### ViRC: Enhancing Visual Interleaved Mathematical CoT with Reason Chunking Authors: Lihong Wang, Liangqi Li, Weiwei Feng, Jiamin Wu, Changtao Miao, Tieru Wu, Rui Ma, Bo Zhang, Zhe Li Published: 2025-12-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.14654v3 CoT has significantly enhanced the reasoning ability of LLMs while it faces challenges when extended to multimodal domains, particularly in mathematical tasks. Existing MLLMs typically perform textual reasoning solely from a single static mathematical image, overlooking dynamic visual acquisition during reasoning. In contrast, humans repeatedly examine visual image and employ step-by-step reasoning to prove intermediate propositions. This strategy of decomposing the problem-solving process into key logical nodes adheres to Miller's Law in cognitive science. Inspired by this insight, we propose a ViRC framework for multimodal mathematical tasks, introducing a Reason Chunking mechanism that structures multimodal mathematical CoT into consecutive Critical Reasoning Units (CRUs) to simulate human expert problem-solving patterns. CRUs ensure intra-unit textual coherence for intermediate proposition verification while integrating visual information across units to generate subsequent propositions and support structured reasoning. To this end, we present CRUX dataset by using three visual tools and four reasoning patterns to provide explicitly annotated CRUs across multiple reasoning paths for each mathematical problem. Leveraging the CRUX dataset, we propose a progressive training strategy inspired by human cognitive learning, which includes Instructional SFT, Practice SFT, and Strategic RL, aimed at further strengthening the Reason Chunking ability of the model. The resulting ViRC-7B model achieves a 18.8% average improvement over baselines across multiple mathematical benchmarks. Code is available at https://github.com/Leon-LihongWang/ViRC. --- ### Segmental Attention Decoding With Long Form Acoustic Encodings Authors: Pawel Swietojanski, Xinwei Li, Mingbin Xu, Takaaki Hori, Dogan Can, Xiaodan Zhuang Published: 2025-12-16 Categories: eess.AS, cs.CL arXiv: https://arxiv.org/abs/2512.14652v1 We address the fundamental incompatibility of attention-based encoder-decoder (AED) models with long-form acoustic encodings. AED models trained on segmented utterances learn to encode absolute frame positions by exploiting limited acoustic context beyond segment boundaries, but fail to generalize when decoding long-form segments where these cues vanish. The model loses ability to order acoustic encodings due to permutation invariance of keys and values in cross-attention. We propose four modifications: (1) injecting explicit absolute positional encodings into cross-attention for each decoded segment, (2) long-form training with extended acoustic context to eliminate implicit absolute position encoding, (3) segment concatenation to cover diverse segmentations needed during training, and (4) semantic segmentation to align AED-decoded segments with training segments. We show these modifications close the accuracy gap between continuous and segmented acoustic encodings, enabling auto-regressive use of the attention decoder. --- ### Adaptable Segmentation Pipeline for Diverse Brain Tumors with Radiomic-Guided Subtyping and Lesion-Wise Model Ensemble Authors: Daniel Capellán-Martín, Abhijeet Parida, Zhifan Jiang, Nishad Kulkarni, Krithika Iyer, Austin Tapp, Syed Muhammad Anwar, María J. Ledesma-Carbayo, Marius George Linguraru Published: 2025-12-16 Categories: cs.CV, eess.IV arXiv: https://arxiv.org/abs/2512.14648v2 Robust and generalizable segmentation of brain tumors on multi-parametric magnetic resonance imaging (MRI) remains difficult because tumor types differ widely. The BraTS 2025 Lighthouse Challenge benchmarks segmentation methods on diverse high-quality datasets of adult and pediatric tumors: multi-consortium international pediatric brain tumor segmentation (PED), preoperative meningioma tumor segmentation (MEN), meningioma radiotherapy segmentation (MEN-RT), and segmentation of pre- and post-treatment brain metastases (MET). We present a flexible, modular, and adaptable pipeline that improves segmentation performance by selecting and combining state-of-the-art models and applying tumor- and lesion-specific processing before and after training. Radiomic features extracted from MRI help detect tumor subtype, ensuring a more balanced training. Custom lesion-level performance metrics determine the influence of each model in the ensemble and optimize post-processing that further refines the predictions, enabling the workflow to tailor every step to each case. On the BraTS testing sets, our pipeline achieved performance comparable to top-ranked algorithms across multiple challenges. These findings confirm that custom lesion-aware processing and model selection yield robust segmentations yet without locking the method to a specific network architecture. Our method has the potential for quantitative tumor measurement in clinical practice, supporting diagnosis and prognosis. --- ### TiME: Tiny Monolingual Encoders for Efficient NLP Pipelines Authors: David Schulmeister, Valentin Hartmann, Lars Klein, Robert West Published: 2025-12-16 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2512.14645v1 Today, a lot of research on language models is focused on large, general-purpose models. However, many NLP pipelines only require models with a well-defined, small set of capabilities. While large models are capable of performing the tasks of those smaller models, they are simply not fast enough to process large amounts of data or offer real-time responses. Furthermore, they often use unnecessarily large amounts of energy, leading to sustainability concerns and problems when deploying them on battery-powered devices. In our work, we show how to train small models for such efficiency-critical applications. As opposed to many off-the-shelf NLP pipelines, our models use modern training techniques such as distillation, and offer support for low-resource languages. We call our models TiME (Tiny Monolingual Encoders) and comprehensively evaluate them on a range of common NLP tasks, observing an improved trade-off between benchmark performance on one hand, and throughput, latency and energy consumption on the other. Along the way, we show that distilling monolingual models from multilingual teachers is possible, and likewise distilling models with absolute positional embeddings from teachers with relative positional embeddings. --- ### A Multicenter Benchmark of Multiple Instance Learning Models for Lymphoma Subtyping from HE-stained Whole Slide Images Authors: Rao Muhammad Umer, Daniel Sens, Jonathan Noll, Sohom Dey, Christian Matek, Lukas Wolfseher, Rainer Spang, Ralf Huss, Johannes Raffler, Sarah Reinke, Ario Sadafi, Wolfram Klapper et al. Published: 2025-12-16 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.14640v3 Timely and accurate lymphoma diagnosis is essential for guiding cancer treatment. Standard diagnostic practice combines hematoxylin and eosin (HE)-stained whole slide images with immunohistochemistry, flow cytometry, and molecular genetic tests to determine lymphoma subtypes, a process requiring costly equipment, and skilled personnel, causing treatment delays. Deep learning methods could assist pathologists by extracting diagnostic information from routinely available HE-stained slides directly, yet comprehensive benchmarks for lymphoma subtyping on multicenter data are lacking. In this work, we present the first multicenter lymphoma benchmark, covering four common lymphoma subtypes and healthy control tissue. We systematically evaluate five publicly available pathology foundation models (H-optimus-1, H0-mini, Virchow2, UNI2, Titan) combined with attention-based (AB-MIL) and transformer-based (TransMIL) multiple instance learning aggregators across three magnifications (10x, 20x, 40x). On in-distribution test sets, models achieve multiclass balanced accuracies exceeding 80% across all magnifications, with foundation models performing similarly, and aggregation methods showing comparable results. The magnification study reveals that 40x resolution is sufficient, with no performance gains from higher resolutions or cross-magnification aggregation. However, on out-of-distribution test sets, performance drops substantially to around 60%, highlighting significant generalization challenges. To advance the field, larger multicenter studies covering additional rare lymphoma subtypes are needed. We provide an automated benchmarking pipeline to facilitate such future research. Our paper codes is publicly available at https://github.com/RaoUmer/LymphomaMIL. --- ### AMD-HookNet++: Evolution of AMD-HookNet with Hybrid CNN-Transformer Feature Enhancement for Glacier Calving Front Segmentation Authors: Fei Wu, Marcel Dreier, Nora Gourmelon, Sebastian Wind, Jianlin Zhang, Thorsten Seehaus, Matthias Braun, Andreas Maier, Vincent Christlein Published: 2025-12-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.14639v1 The dynamics of glaciers and ice shelf fronts significantly impact the mass balance of ice sheets and coastal sea levels. To effectively monitor glacier conditions, it is crucial to consistently estimate positional shifts of glacier calving fronts. AMD-HookNet firstly introduces a pure two-branch convolutional neural network (CNN) for glacier segmentation. Yet, the local nature and translational invariance of convolution operations, while beneficial for capturing low-level details, restricts the model ability to maintain long-range dependencies. In this study, we propose AMD-HookNet++, a novel advanced hybrid CNN-Transformer feature enhancement method for segmenting glaciers and delineating calving fronts in synthetic aperture radar images. Our hybrid structure consists of two branches: a Transformer-based context branch to capture long-range dependencies, which provides global contextual information in a larger view, and a CNN-based target branch to preserve local details. To strengthen the representation of the connected hybrid features, we devise an enhanced spatial-channel attention module to foster interactions between the hybrid CNN-Transformer branches through dynamically adjusting the token relationships from both spatial and channel perspectives. Additionally, we develop a pixel-to-pixel contrastive deep supervision to optimize our hybrid model by integrating pixelwise metric learning into glacier segmentation. Through extensive experiments and comprehensive quantitative and qualitative analyses on the challenging glacier segmentation benchmark dataset CaFFe, we show that AMD-HookNet++ sets a new state of the art with an IoU of 78.2 and a HD95 of 1,318 m, while maintaining a competitive MDE of 367 m. More importantly, our hybrid model produces smoother delineations of calving fronts, resolving the issue of jagged edges typically seen in pure Transformer-based approaches. --- ### Evaluating Music Context Preservation: A Multi-facet Framework for Music Editing Systems Authors: Yash Vishe, Eric Xue, Xunyi Jiang, Zachary Novack, Junda Wu, Julian McAuley, Xin Xu Published: 2025-12-16 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2512.14629v2 Music editing plays a vital role in modern music production, with applications in film, broadcasting, and game development. Recent advances in music editing systems have enabled diverse editing tasks such as timbre transfer, instrument substitution, and genre transformation. However, many existing works overlook evaluating their ability to preserve musical facets that should remain unchanged during editing, which we define as Music Context Preservation (MuseCP). While some studies do consider MuseCP, their evaluation protocols and metrics are not comprehensive. To address this, we introduce the first MuseCP evaluation framework, MuseCPEval, that covers four categories of music facets with fine-grained and well-tailored metrics to capture nuanced changes in music attributes. Objective validation and a human study demonstrate the effectiveness of these metrics. Moreover, the case studies on diverse music editing systems illustrate the practical utility of these metrics as a testbed and diagnostic tool, providing insights into the strengths and limitations of existing systems. We hope our metrics and findings can offer practical guidance for developing more effective and reliable music editing strategies with strong MuseCP capability --- ### Learning the score under shape constraints Authors: Rebecca M. Lewis, Oliver Y. Feng, Henry W. J. Reeve, Min Xu, Richard J. Samworth Published: 2025-12-16 Categories: math.ST, stat.ML arXiv: https://arxiv.org/abs/2512.14624v1 Score estimation has recently emerged as a key modern statistical challenge, due to its pivotal role in generative modelling via diffusion models. Moreover, it is an essential ingredient in a new approach to linear regression via convex $M$-estimation, where the corresponding error densities are projected onto the log-concave class. Motivated by these applications, we study the minimax risk of score estimation with respect to squared $L^2(P_0)$-loss, where $P_0$ denotes an underlying log-concave distribution on $\mathbb{R}$. Such distributions have decreasing score functions, but on its own, this shape constraint is insufficient to guarantee a finite minimax risk. We therefore define subclasses of log-concave densities that capture two fundamental aspects of the estimation problem. First, we establish the crucial impact of tail behaviour on score estimation by determining the minimax rate over a class of log-concave densities whose score function exhibits controlled growth relative to the quantile levels. Second, we explore the interplay between smoothness and log-concavity by considering the class of log-concave densities with a scale restriction and a $(β,L)$-Hölder assumption on the log-density for some $β\in (1,2)$. We show that the minimax risk over this latter class is of order $L^{2/(2β+1)}n^{-β/(2β+1)}$ up to poly-logarithmic factors, where $n$ denotes the sample size. When $β< 2$, this rate is faster than could be obtained under either the shape constraint or the smoothness assumption alone. Our upper bounds are attained by a locally adaptive, multiscale estimator constructed from a uniform confidence band for the score function. This study highlights intriguing differences between the score estimation and density estimation problems over this shape-constrained class. ---