# Research Papers — 2025-12 · bundle page 81 of 175

> Full-text markdown of papers #4001–4050 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/81
[← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/80.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-12/page/82.md)

### From Unlearning to UNBRANDING: A Benchmark for Trademark-Safe Text-to-Image Generation

Authors: Dawid Malarz, Filip Manjak, Maciej Zięba, Przemysław Spurek, Artur Kasymov
Published: 2025-12-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.13953v2

The rapid progress of text-to-image diffusion models raises significant concerns regarding the unauthorized reproduction of trademarked content. While prior work targets general concepts (e.g., styles, celebrities), it fails to address specific brand identifiers. Brand recognition is multi-dimensional, extending beyond explicit logos to encompass distinctive structural features (e.g., a car's front grille). To tackle this, we introduce unbranding, a novel task for the fine-grained removal of both trademarks and subtle structural brand features, while preserving semantic coherence. We construct a benchmark dataset and introduce a novel evaluation framework combining Vision Language Models (VLMs) with segmentation-based classifiers trained on human annotations of logos and trade dress features, addressing the limitations of existing brand detectors that fail to capture abstract trade dress. Furthermore, we observe that newer, higher-fidelity systems (SDXL, FLUX) synthesize brand identifiers more readily than older models, highlighting the urgency of this challenge. Our results confirm that unbranding is a distinct problem requiring specialized techniques. Project Page: https://gmum.github.io/UNBRANDING/.

---

### An evaluation of SVBRDF Prediction from Generative Image Models for Appearance Modeling of 3D Scenes

Authors: Alban Gauthier, Valentin Deschaintre, Alexandre Lanvin, Fredo Durand, Adrien Bousseau, George Drettakis
Published: 2025-12-15
Categories: cs.CV, cs.GR
arXiv: https://arxiv.org/abs/2512.13950v1

Digital content creation is experiencing a profound change with the advent of deep generative models. For texturing, conditional image generators now allow the synthesis of realistic RGB images of a 3D scene that align with the geometry of that scene. For appearance modeling, SVBRDF prediction networks recover material parameters from RGB images. Combining these technologies allows us to quickly generate SVBRDF maps for multiple views of a 3D scene, which can be merged to form a SVBRDF texture atlas of that scene. In this paper, we analyze the challenges and opportunities for SVBRDF prediction in the context of such a fast appearance modeling pipeline. On the one hand, single-view SVBRDF predictions might suffer from multiview incoherence and yield inconsistent texture atlases. On the other hand, generated RGB images, and the different modalities on which they are conditioned, can provide additional information for SVBRDF estimation compared to photographs. We compare neural architectures and conditions to identify designs that achieve high accuracy and coherence. We find that, surprisingly, a standard UNet is competitive with more complex designs. Project page: http://repo-sam.inria.fr/nerphys/svbrdf-evaluation

---

### Pattern-Guided Diffusion Models

Authors: Vivian Lin, Kuk Jin Jang, Wenwen Si, Insup Lee
Published: 2025-12-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.13945v1

Diffusion models have shown promise in forecasting future data from multivariate time series. However, few existing methods account for recurring structures, or patterns, that appear within the data. We present Pattern-Guided Diffusion Models (PGDM), which leverage inherent patterns within temporal data for forecasting future time steps. PGDM first extracts patterns using archetypal analysis and estimates the most likely next pattern in the sequence. By guiding predictions with this pattern estimate, PGDM makes more realistic predictions that fit within the set of known patterns. We additionally introduce a novel uncertainty quantification technique based on archetypal analysis, and we dynamically scale the guidance level based on the pattern estimate uncertainty. We apply our method to two well-motivated forecasting applications, predicting visual field measurements and motion capture frames. On both, we show that pattern guidance improves PGDM's performance (MAE / CRPS) by up to 40.67% / 56.26% and 14.12% / 14.10%, respectively. PGDM also outperforms baselines by up to 65.58% / 84.83% and 93.64% / 92.55%.

---

### Informing Acquisition Functions via Foundation Models for Molecular Discovery

Authors: Qi Chen, Fabio Ramos, Alán Aspuru-Guzik, Florian Shkurti
Published: 2025-12-15
Categories: cs.LG, cs.AI, q-bio.QM
arXiv: https://arxiv.org/abs/2512.13935v1

Bayesian Optimization (BO) is a key methodology for accelerating molecular discovery by estimating the mapping from molecules to their properties while seeking the optimal candidate. Typically, BO iteratively updates a probabilistic surrogate model of this mapping and optimizes acquisition functions derived from the model to guide molecule selection. However, its performance is limited in low-data regimes with insufficient prior knowledge and vast candidate spaces. Large language models (LLMs) and chemistry foundation models offer rich priors to enhance BO, but high-dimensional features, costly in-context learning, and the computational burden of deep Bayesian surrogates hinder their full utilization. To address these challenges, we propose a likelihood-free BO method that bypasses explicit surrogate modeling and directly leverages priors from general LLMs and chemistry-specific foundation models to inform acquisition functions. Our method also learns a tree-structured partition of the molecular search space with local acquisition functions, enabling efficient candidate selection via Monte Carlo Tree Search. By further incorporating coarse-grained LLM-based clustering, it substantially improves scalability to large candidate sets by restricting acquisition function evaluations to clusters with statistically higher property values. We show through extensive experiments and ablations that the proposed method substantially improves scalability, robustness, and sample efficiency in LLM-guided BO for molecular discovery.

---

### Hierarchical Multi-agent Large Language Model Reasoning for Autonomous Functional Materials Discovery

Authors: Samuel Rothfarb, Megan C. Davis, Ivana Matanovic, Baikun Li, Edward F. Holby, Wilton J. M. Kort-Kamp
Published: 2025-12-15
Categories: cond-mat.mtrl-sci, cs.AI, cs.CL, cs.LG, cs.MA
arXiv: https://arxiv.org/abs/2512.13930v1

Artificial intelligence is reshaping scientific exploration, but most methods automate procedural tasks without engaging in scientific reasoning, limiting autonomy in discovery. We introduce Materials Agents for Simulation and Theory in Electronic-structure Reasoning (MASTER), an active learning framework where large language models autonomously design, execute, and interpret atomistic simulations. In MASTER, a multimodal system translates natural language into density functional theory workflows, while higher-level reasoning agents guide discovery through a hierarchy of strategies, including a single agent baseline and three multi-agent approaches: peer review, triage-ranking, and triage-forms. Across two chemical applications, CO adsorption on Cu-surface transition metal (M) adatoms and on M-N-C catalysts, reasoning-driven exploration reduces required atomistic simulations by up to 90% relative to trial-and-error selection. Reasoning trajectories reveal chemically grounded decisions that cannot be explained by stochastic sampling or semantic bias. Altogether, multi-agent collaboration accelerates materials discovery and marks a new paradigm for autonomous scientific exploration.

---

### A Complete Guide to Spherical Equivariant Graph Transformers

Authors: Sophia Tang
Published: 2025-12-15
Categories: cs.LG, q-bio.QM
arXiv: https://arxiv.org/abs/2512.13927v1

Spherical equivariant graph neural networks (EGNNs) provide a principled framework for learning on three-dimensional molecular and biomolecular systems, where predictions must respect the rotational symmetries inherent in physics. These models extend traditional message-passing GNNs and Transformers by representing node and edge features as spherical tensors that transform under irreducible representations of the rotation group SO(3), ensuring that predictions change in physically meaningful ways under rotations of the input. This guide develops a complete, intuitive foundation for spherical equivariant modeling - from group representations and spherical harmonics, to tensor products, Clebsch-Gordan decomposition, and the construction of SO(3)-equivariant kernels. Building on this foundation, we construct the Tensor Field Network and SE(3)-Transformer architectures and explain how they perform equivariant message-passing and attention on geometric graphs. Through clear mathematical derivations and annotated code excerpts, this guide serves as a self-contained introduction for researchers and learners seeking to understand or implement spherical EGNNs for applications in chemistry, molecular property prediction, protein structure modeling, and generative modeling.

---

### Sliding Window Recurrences for Sequence Models

Authors: Dragos Secrieru, Garyk Brixi, Yoshua Bengio, Taiji Suzuki, Michael Poli, Stefano Massaroli
Published: 2025-12-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.13921v1

Multi-hybrid architectures are poised to take over language modeling due to better quality and performance. We introduce a hierarchical decomposition framework for linear recurrences that allows us to develop algorithms aligned with GPU memory hierarchies, yielding Sliding Window Recurrences. We focus specifically on truncating recurrences to hardware-aligned windows which are naturally jagged, limiting costly inter-warp communication. Using SWR, we develop Phalanx layers that serve as drop-in replacements for windowed attention or linear recurrences. In 1B parameter multi-hybrid models, Phalanx achieves over 10-40% speedup across 4K to 32K context length over optimized Transformers while matching perplexity.

---

### Adaptive digital twins for predictive decision-making: Online Bayesian learning of transition dynamics

Authors: Eugenio Varetti, Matteo Torzoni, Marco Tezzele, Andrea Manzoni
Published: 2025-12-15
Categories: cs.LG, math.NA
arXiv: https://arxiv.org/abs/2512.13919v3

This work shows how adaptivity can enhance value realization of digital twins in civil engineering. We focus on adapting the state transition models within digital twins represented through probabilistic graphical models. The bi-directional interaction between the physical and virtual domains is modeled using dynamic Bayesian networks. By treating state transition probabilities as random variables endowed with conjugate priors, we enable hierarchical online learning of transition dynamics from a state to another through effortless Bayesian updates. We provide the mathematical framework to account for a larger class of distributions with respect to the current literature on digital twins. To compute dynamic policies with precision updates we solve parametric Markov decision processes through reinforcement learning. The proposed adaptive digital twin framework enjoys enhanced personalization, increased robustness, and improved cost-effectiveness. We assess our approach on a case study involving structural health monitoring and maintenance planning of a railway bridge.

---

### Context Branching for LLM Conversations: A Version Control Approach to Exploratory Programming

Authors: Bhargav Chickmagalur Nanjundappa, Spandan Maaheshwari
Published: 2025-12-15
Categories: cs.SE, cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2512.13914v1

Large Language Models (LLMs) have become integral to software engineering workflows, yet their effectiveness degrades significantly in multi-turn conversations. Recent studies demonstrate an average 39% performance drop when instructions are delivered across multiple turns, with models making premature assumptions and failing to course correct (Laban et al., 2025). This degradation is particularly problematic in exploratory programming tasks where developers need to investigate alternative approaches without committing to a single path. Current solutions force users into a false dichotomy: continue in a context-polluted conversation where the LLM becomes increasingly confused, or start fresh and lose all accumulated context. We present ContextBranch, a conversation management system that applies version control semantics to LLM interactions. ContextBranch provides four core primitives--checkpoint, branch, switch, and inject--enabling users to capture conversation state, explore alternatives in isolation, and selectively merge insights. We evaluate ContextBranch through a controlled experiment with 30 software engineering scenarios featuring intentionally polluting explorations. Branched conversations achieved higher response quality compared to linear conversations, with large improvements in focus and context awareness. Benefits were concentrated in complex scenarios involving conceptually distant explorations. Branching reduced context size by 58.1% (31.0 to 13.0 messages), eliminating irrelevant exploratory content. Our work establishes conversation branching as a fundamental primitive for AI-assisted exploratory work, demonstrating that isolation prevents context pollution when exploring alternatives.

---

### Capturing reduced-order quantum many-body dynamics out of equilibrium via neural ordinary differential equations

Authors: Patrick Egenlauf, Iva Březinová, Sabine Andergassen, Miriam Klopotek
Published: 2025-12-15
Categories: cs.LG, cond-mat.stat-mech, quant-ph
arXiv: https://arxiv.org/abs/2512.13913v3

Out-of-equilibrium quantum many-body systems exhibit rapid correlation buildup that underlies many emerging phenomena. Exact wave-function methods to describe this scale exponentially with particle number; simpler mean-field approaches neglect essential two-particle correlations. The time-dependent two-particle reduced density matrix (TD2RDM) formalism offers a middle ground by propagating the two-particle reduced density matrix (2RDM) and closing the BBGKY hierarchy with a reconstruction of the three-particle cumulant. But the validity and existence of time-local reconstruction functionals ignoring memory effects remain unclear across different dynamical regimes. We show that a neural ODE model trained on exact 2RDM data (no dimensionality reduction) can reproduce its dynamics without any explicit three-particle information -- but only in parameter regions where the Pearson correlation between the two- and three-particle cumulants is large. In the anti-correlated or uncorrelated regime, the neural ODE fails, indicating that no simple time-local functional of the instantaneous two-particle cumulant can capture the evolution. The magnitude of the time-averaged three-particle-correlation buildup appears to be the primary predictor of success: For a moderate correlation buildup, both neural ODE predictions and existing TD2RDM reconstructions are accurate, whereas stronger values lead to systematic breakdowns. These findings pinpoint the need for memory-dependent kernels in the three-particle cumulant reconstruction for the latter regime. Our results place the neural ODE as a model-agnostic diagnostic tool that maps the regime of applicability of cumulant expansion methods and guides the development of non-local closure schemes. More broadly, the ability to learn high-dimensional RDM dynamics from limited data opens a pathway to fast, data-driven simulation of correlated quantum matter.

---

### Intelligent matter consisting of active particles

Authors: Julian Jeggle, Raphael Wittkowski
Published: 2025-12-15
Categories: cond-mat.soft, cond-mat.dis-nn, cs.AI, cs.LG, physics.app-ph
arXiv: https://arxiv.org/abs/2512.13912v1

In this book chapter, we review how systems of simple motile agents can be used as a pathway to intelligent systems. It is a well known result from nature that large groups of entities following simple rules, such as swarms of animals, can give rise to much more complex collective behavior in a display of emergence. This begs the question whether we can emulate this behavior in synthetic matter and drive it to a point where the collective behavior reaches the complexity level of intelligent systems. Here, we will use a formalized notion of "intelligent matter" and compare it to recent results in the field of active matter. First, we will explore the approach of emergent computing in which specialized active matter systems are designed to directly solve a given task through emergent behavior. This we will then contrast with the approach of physical reservoir computing powered by the dynamics of active particle systems. In this context, we will also describe a novel reservoir computing scheme for active particles driven ultrasonically or via light refraction.

---

### Exploring Machine Learning, Deep Learning, and Explainable AI Methods for Seasonal Precipitation Prediction in South America

Authors: Matheus Corrêa Domingos, Valdivino Alexandre de Santiago Júnior, Juliana Aparecida Anochi, Elcio Hideiti Shiguemori, Luísa Mirelle Costa dos Santos, Hércules Carlos dos Santos Pereira, André Estevam Costa Oliveira
Published: 2025-12-15
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2512.13910v1

Forecasting meteorological variables is challenging due to the complexity of their processes, requiring advanced models for accuracy. Accurate precipitation forecasts are vital for society. Reliable predictions help communities mitigate climatic impacts. Based on the current relevance of artificial intelligence (AI), classical machine learning (ML) and deep learning (DL) techniques have been used as an alternative or complement to dynamic modeling. However, there is still a lack of broad investigations into the feasibility of purely data-driven approaches for precipitation forecasting. This study aims at addressing this issue where different classical ML and DL approaches for forecasting precipitation in South America, taking into account all 2019 seasons, are considered in a detailed investigation. The selected classical ML techniques were Random Forests and extreme gradient boosting (XGBoost), while the DL counterparts were a 1D convolutional neural network (CNN 1D), a long short-term memory (LSTM) model, and a gated recurrent unit (GRU) model. Additionally, the Brazilian Global Atmospheric Model (BAM) was used as a representative of the traditional dynamic modeling approach. We also relied on explainable artificial intelligence (XAI) to provide some explanations for the models behaviors. LSTM showed strong predictive performance while BAM, the traditional dynamic model representative, had the worst results. Despite presented the higher latency, LSTM was most accurate for heavy precipitation. If cost is a concern, XGBoost offers lower latency with slightly accuracy loss. The results of this research confirm the viability of DL models for climate forecasting, solidifying a global trend in major meteorological and climate forecasting centers.

---

### Assessing High-Risk AI Systems under the EU AI Act: From Legal Requirements to Technical Verification

Authors: Alessio Buscemi, Tom Deckenbrunnen, Fahria Kabir, Kateryna Mishchenko, Nishat Mowla
Published: 2025-12-15
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2512.13907v3

The implementation of the AI Act requires practical mechanisms to verify compliance with legal obligations, yet concrete and operational mappings from high-level requirements to verifiable assessment activities remain limited, contributing to uneven readiness across Member States. This paper presents a structured mapping that translates high-level AI Act requirements into concrete, implementable verification activities applicable across the AI lifecycle. The mapping is derived through a systematic process in which legal requirements are decomposed into operational sub-requirements and grounded in authoritative standards and recognised practices. From this basis, verification activities are identified and characterised along two dimensions: the type of verification performed and the lifecycle target to which it applies. By making explicit the link between regulatory intent and technical and organisational assurance practices, the proposed mapping reduces interpretive uncertainty and provides a reusable reference for consistent, technology-agnostic compliance verification under the AI Act.

---

### Generative AI for Video Translation: A Scalable Architecture for Multilingual Video Conferencing

Authors: Amirkia Rafiei Oskooei, Eren Caglar, Ibrahim Sahin, Ayse Kayabay, Mehmet S. Aktas
Published: 2025-12-15
Categories: cs.MM, cs.AI, cs.CL, cs.CV
arXiv: https://arxiv.org/abs/2512.13904v1

The real-time deployment of cascaded generative AI pipelines for applications like video translation is constrained by significant system-level challenges. These include the cumulative latency of sequential model inference and the quadratic ($\mathcal{O}(N^2)$) computational complexity that renders multi-user video conferencing applications unscalable. This paper proposes and evaluates a practical system-level framework designed to mitigate these critical bottlenecks. The proposed architecture incorporates a turn-taking mechanism to reduce computational complexity from quadratic to linear in multi-user scenarios, and a segmented processing protocol to manage inference latency for a perceptually real-time experience. We implement a proof-of-concept pipeline and conduct a rigorous performance analysis across a multi-tiered hardware setup, including commodity (NVIDIA RTX 4060), cloud (NVIDIA T4), and enterprise (NVIDIA A100) GPUs. Our objective evaluation demonstrates that the system achieves real-time throughput ($τ< 1.0$) on modern hardware. A subjective user study further validates the approach, showing that a predictable, initial processing delay is highly acceptable to users in exchange for a smooth, uninterrupted playback experience. The work presents a validated, end-to-end system design that offers a practical roadmap for deploying scalable, real-time generative AI applications in multilingual communication platforms.

---

### KLO-Net: A Dynamic K-NN Attention U-Net with CSP Encoder for Efficient Prostate Gland Segmentation from MRI

Authors: Anning Tian, Byunghyun Ko, Kaichen Qu, Mengyuan Liu, Jeongkyu Lee
Published: 2025-12-15
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2512.13902v1

Real-time deployment of prostate MRI segmentation on clinical workstations is often bottlenecked by computational load and memory footprint. Deep learning-based prostate gland segmentation approaches remain challenging due to anatomical variability. To bridge this efficiency gap while still maintaining reliable segmentation accuracy, we propose KLO-Net, a dynamic K-Nearest Neighbor attention U-Net with Cross Stage Partial, i.e., CSP, encoder for efficient prostate gland segmentation from MRI scan. Unlike the regular K-NN attention mechanism, the proposed dynamic K-NN attention mechanism allows the model to adaptively determine the number of attention connections for each spatial location within a slice. In addition, CSP blocks address the computational load to reduce memory consumption. To evaluate the model's performance, comprehensive experiments and ablation studies are conducted on two public datasets, i.e., PROMISE12 and PROSTATEx, to validate the proposed architecture. The detailed comparative analysis demonstrates the model's advantage in computational efficiency and segmentation quality.

---

### Let's (not) just put things in Context: Test-Time Training for Long-Context LLMs

Authors: Rachit Bansal, Aston Zhang, Rishabh Tiwari, Lovish Madaan, Sai Surya Duvvuri, Devvrit Khatri, David Brandfonbrener, David Alvarez-Melis, Prajjwal Bhargava, Mihir Sanjay Kale, Samy Jelassi
Published: 2025-12-15
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2512.13898v1

Progress on training and architecture strategies has enabled LLMs with millions of tokens in context length. However, empirical evidence suggests that such long-context LLMs can consume far more text than they can reliably use. On the other hand, it has been shown that inference-time compute can be used to scale performance of LLMs, often by generating thinking tokens, on challenging tasks involving multi-step reasoning. Through controlled experiments on sandbox long-context tasks, we find that such inference-time strategies show rapidly diminishing returns and fail at long context. We attribute these failures to score dilution, a phenomenon inherent to static self-attention. Further, we show that current inference-time strategies cannot retrieve relevant long-context signals under certain conditions. We propose a simple method that, through targeted gradient updates on the given context, provably overcomes limitations of static self-attention. We find that this shift in how inference-time compute is spent leads to consistently large performance improvements across models and long-context benchmarks. Our method leads to large 12.6 and 14.1 percentage point improvements for Qwen3-4B on average across subsets of LongBench-v2 and ZeroScrolls benchmarks. The takeaway is practical: for long context, a small amount of context-specific training is a better use of inference compute than current inference-time scaling strategies like producing more thinking tokens.

---

### One Permutation Is All You Need: Fast, Deterministic Feature Importance and Model Stress-Testing

Authors: Albert Dorador
Published: 2025-12-15
Categories: stat.ML, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2512.13892v3

Reliable estimation of feature contributions in machine learning models is essential for transparency, algorithmic fairness, and regulatory compliance. While permutation feature importance is widely used, classical implementations rely on repeated Monte Carlo shuffling, introducing significant computational overhead and stochastic instability. In this paper, we show that replacing $B$ random permutations with a single, max-min rank-optimal deterministic permutation maintains or improves correlation with ground-truth importance while eliminating estimation variance and reducing complexity from $O(B \cdot n \cdot p)$ to $O(n \cdot p)$. Under location-scale feature distributions, we formally prove exact recovery of scale-adjusted linear regression coefficients, alongside improved importance estimation under concave model sensitivity. We extend this deterministic framework along two complementary dimensions. First, Systemic Feature Importance (SFI) integrates empirical feature correlations to quantify indirect feature reliance through proxy variables. Second, Importance Direction extends scalar importance to a signed, directional representation by measuring concordance between covariate displacements and output shifts. Extensive empirical validation across nearly 200 simulation scenarios demonstrates superior bias-variance trade-offs in high-dimensional and low signal-to-noise regimes. Finally, two real-world credit risk case studies show how coupling SFI with Importance Direction enables practitioners and regulators to audit models for both the magnitude and net sign of hidden reliance on protected attributes, delivering a principled, transparent, and scalable framework for model governance.

---

### Group-Theoretic Reinforcement Learning of Dynamical Decoupling Sequences

Authors: Charles Marrder, Shuo Sun, Murray J. Holland
Published: 2025-12-15
Categories: quant-ph, cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2512.13890v1

Dynamical decoupling seeks to mitigate phase decoherence in qubits by applying a carefully designed sequence of effectively instantaneous electromagnetic pulses. Although analytic solutions exist for pulse timings that are optimal under specific noise regimes, identifying the optimal timings for a realistic noise spectrum remains challenging. We propose a reinforcement learning (RL)-based method for designing pulse sequences on qubits. Our novel action set enables the RL agent to efficiently navigate this inherently non-convex optimization landscape. The action set, derived from Thompson's group $F$, is applicable to a broad class of sequential decision problems whose states can be represented as bounded sequences. We demonstrate that our RL agent can learn pulse sequences that minimize dephasing without requiring explicit knowledge of the underlying noise spectrum. This work opens the possibility for real-time learning of optimal dynamical decoupling sequences on qubits which are dephasing-limited. The model-free nature of our algorithm suggests that the agent may ultimately learn optimal pulse sequences even in the presence of unmodeled physical effects, such as pulse errors or non-Gaussian noise.

---

### OPTIMA: Optimal One-shot Pruning for LLMs via Quadratic Programming Reconstruction

Authors: Mohammad Mozaffari, Samuel Kushnir, Maryam Mehri Dehnavi, Amir Yazdanbakhsh
Published: 2025-12-15
Categories: cs.LG, cs.AI, cs.PF
arXiv: https://arxiv.org/abs/2512.13886v2

Post-training model pruning is a promising solution, yet it faces a trade-off: simple heuristics that zero weights are fast but degrade accuracy, while principled joint optimization methods recover accuracy but are computationally infeasible at modern scale. One-shot methods such as SparseGPT offer a practical trade-off in optimality by applying efficient, approximate heuristic weight updates. To close this gap, we introduce OPTIMA, a practical one-shot post-training pruning method that balances accuracy and scalability. OPTIMA casts layer-wise weight reconstruction after mask selection as independent, row-wise Quadratic Programs (QPs) that share a common layer Hessian. Solving these QPs yields the per-row globally optimal update with respect to the reconstruction objective given the estimated Hessian. The shared-Hessian structure makes the problem highly amenable to batching on accelerators. We implement an accelerator-friendly QP solver that accumulates one Hessian per layer and solves many small QPs in parallel, enabling one-shot post-training pruning at scale on a single accelerator without fine-tuning. OPTIMA integrates with existing mask selectors and consistently improves zero-shot performance across multiple LLM families and sparsity regimes, yielding up to 3.97% absolute accuracy improvement. On an NVIDIA H100, OPTIMA prunes a 8B-parameter transformer end-to-end in 40 hours with 60GB peak memory. Together, these results set a new state-of-the-art accuracy-efficiency trade-offs for one-shot post-training pruning.

---

### FiNERweb: Datasets and Artifacts for Scalable Multilingual Named Entity Recognition

Authors: Jonas Golde, Patrick Haller, Alan Akbik
Published: 2025-12-15
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.13884v1

Recent multilingual named entity recognition (NER) work has shown that large language models (LLMs) can provide effective synthetic supervision, yet such datasets have mostly appeared as by-products of broader experiments rather than as systematic, reusable resources. We introduce FiNERweb, a dataset-creation pipeline that scales the teacher-student paradigm to 91 languages and 25 scripts. Building on FineWeb-Edu, our approach trains regression models to identify NER-relevant passages and annotates them with multilingual LLMs, resulting in about 225k passages with 235k distinct entity labels. Our experiments show that the regression model achieves more than 84 F1, and that models trained on FiNERweb obtain comparable or improved performance in zero shot transfer settings on English, Thai, and Swahili, despite being trained on 19x less data than strong baselines. In addition, we assess annotation quality using LLM-as-a-judge and observe consistently high scores for both faithfulness (3.99 out of 5) and completeness (4.05 out of 5), indicating reliable and informative annotations. Further, we release the dataset with both English labels and translated label sets in the respective target languages because we observe that the performance of current state-of-the-art models drops by 0.02 to 0.09 F1 when evaluated using target language labels instead of English ones. We release FiNERweb together with all accompanying artifacts to the research community in order to facilitate more effective student-teacher training for multilingual named entity recognition.

---

### Privacy-Enhancing Infant Cry Classification with Federated Transformers and Denoising Regularization

Authors: Geofrey Owino, Bernard Shibwabo
Published: 2025-12-15
Categories: cs.LG, cs.AI, cs.SD
arXiv: https://arxiv.org/abs/2512.13880v1

Infant cry classification can aid early assessment of infant needs. However, deployment of such solutions is limited by privacy concerns around audio data, sensitivity to background noise, and domain shift across recording environments. We present an end-to-end infant cry analysis pipeline that integrates a denoising autoencoder (DAE), a convolutional tokenizer, and a Transformer encoder trained using communication-efficient federated learning (FL). The system performs on-device denoising, adaptive segmentation, post hoc calibration, and energy-based out-of-distribution (OOD) abstention. Federated training employs a regularized control variate update with 8-bit adapter deltas under secure aggregation. Using the Baby Chillanto and Donate-a-Cry datasets with ESC-50 noise overlays, the model achieves a macro F1 score of 0.938, an AUC of 0.962, and an Expected Calibration Error (ECE) of 0.032, while reducing per-round client upload from approximately 36 to 42 MB to 3.3 MB. Real-time edge inference on an NVIDIA Jetson Nano (4 GB, TensorRT FP16) achieves 96 ms per one-second spectrogram frame. These results demonstrate a practical path toward privacy-preserving, noise-robust, and communication-efficient infant cry classification suitable for federated deployment.

---

### Dual-R-DETR: Resolving Query Competition with Pairwise Routing in Transformer Decoders

Authors: Ye Zhang, Qi Chen, Wenyou Huang, Rui Liu, Zhengjian Kang
Published: 2025-12-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.13876v2

Detection Transformers (DETR) formulate object detection as a set prediction problem and enable end-to-end training without post-processing. However, object queries in DETR interact through symmetric self-attention, which enforces uniform competition among all query pairs. This often leads to inefficient query dynamics, where multiple queries converge to the same object while others fail to explore alternative regions. We propose Dual-R-DETR, a competition-aware DETR framework that explicitly regulates query interactions via pairwise routing in transformer decoders. Dual-R-DETR distinguishes query-to-query relations as either competitive or cooperative based on appearance similarity, prediction confidence, and spatial geometry. It introduces two complementary routing behaviors: suppressor routing to attenuate interactions among queries targeting the same object, and delegator routing to encourage diversification across distinct regions. These behaviors are realized through lightweight, learnable low-rank biases injected into decoder self-attention, enabling asymmetric query interactions while preserving the standard attention formulation. To ensure inference efficiency, routing biases are applied only during training using a dual-branch strategy, and inference reverts to vanilla self-attention with no additional computational cost. Extensive experiments on COCO and Cityscapes demonstrate that Dual-R-DETR consistently improves multiple DETR variants, outperforming DINO by 1.7% mAP with a ResNet-50 backbone and achieving 57.6% mAP with Swin-L under comparable settings. Code is available at https://github.com/YZk67/Dual-R-DETR.

---

### SAGE: Training Smart Any-Horizon Agents for Long Video Reasoning with Reinforcement Learning

Authors: Jitesh Jain, Jialuo Li, Zixian Ma, Jieyu Zhang, Chris Dongjoo Kim, Sangho Lee, Rohun Tripathi, Tanmay Gupta, Christopher Clark, Humphrey Shi
Published: 2025-12-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.13874v2

As humans, we are natural any-horizon reasoners, i.e., we can decide whether to iteratively skim long videos or watch short ones in full when necessary for a given task. With this in mind, one would expect video reasoning models to reason flexibly across different durations. However, SOTA models are still trained to predict answers in a single turn while processing a large number of frames, akin to watching an entire long video, requiring significant resources. This raises the question: Is it possible to develop performant any-horizon video reasoning systems? Inspired by human behavior, we first propose SAGE, an agent system that performs multi-turn reasoning on long videos while handling simpler problems in a single turn. Secondly, we introduce an easy synthetic data generation pipeline using Gemini-2.5-Flash to train the orchestrator, SAGE-MM, which lies at the core of SAGE. We further propose an effective RL post-training recipe essential for instilling any-horizon reasoning ability in SAGE-MM. Thirdly, we curate SAGE-Bench with an average duration of greater than 700 seconds for evaluating video reasoning ability in real-world entertainment use cases. Lastly, we empirically validate the effectiveness of our system, data, and RL recipe, observing notable improvements of up to 6.1% on open-ended video reasoning tasks, as well as an impressive 8.2% improvement on videos longer than 10 minutes.

---

### Measuring Uncertainty Calibration

Authors: Kamil Ciosek, Nicolò Felicioni, Sina Ghiassian, Juan Elenter Litwin, Francesco Tonolini, David Gustafsson, Eva Garcia-Martin, Carmen Barcena Gonzalez, Raphaëlle Bertrand-Lalo
Published: 2025-12-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.13872v3

We make two contributions to the problem of estimating the $L_1$ calibration error of a binary classifier from a finite dataset. First, we provide an upper bound for any classifier where the calibration function has bounded variation. Second, we provide a method of modifying any classifier so that its calibration error can be upper bounded efficiently without significantly impacting classifier performance and without any restrictive assumptions. All our results are non-asymptotic and distribution-free. We conclude by providing advice on how to measure calibration error in practice. Our methods yield practical procedures that can be run on real-world datasets with modest overhead.

---

### Do Spatial Descriptors Improve Multi-DoF Finger Movement Decoding from HD sEMG?

Authors: Ricardo Gonçalves Molinari, Leonardo Abdala Elias
Published: 2025-12-15
Categories: eess.SP, cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2512.13870v4

Restoring hand function requires simultaneous and proportional control (SPC) of multiple degrees of freedom (DoFs). This study evaluated the multichannel linear descriptors-based block field method (MLD-BFM) against conventional feature extraction approaches for continuous decoding of five finger-joint DoFs using high-density surface electromyography (HD sEMG). Twenty-one healthy participants performed dynamic sinusoidal finger movements while HD sEMG signals were recorded from the proximal forearm. MLD-BFM extracted spatial descriptors including effective field strength ($Σ$), field-strength variation rate ($Φ$), and spatial complexity ($Ω$). Performance was optimized (block size: $2\times2$; window: 0.15,s) and compared with conventional time-domain features, root mean square (RMS) and mean absolute value plus waveform length (MAV-WL), as well as dimensionality reduction methods (PCA and NMF), using multi-output regression models. MLD-BFM achieved the highest mean variance-weighted coefficient of determination ($\mathrm{R}^2_\mathrm{vw}$) across all models, with the multilayer perceptron yielding the best result ($86.68 \pm 0.33 \%$). However, the improvement was not statistically significant relative to time-domain features, suggesting that dense multichannel recordings already encode spatial information through amplitude-based descriptors. MLD-BFM significantly outperformed dimensionality reduction approaches, indicating that preserving the spatial resolution of HD sEMG is critical for accurate multi-DoF finger movement regression.

---

### Coarse-to-Fine Hierarchical Alignment for UAV-based Human Detection using Diffusion Models

Authors: Wenda Li, Meng Wu, Liangzhao Chen, Sungmin Eum, Heesung Kwon, Qing Qu
Published: 2025-12-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.13869v3

Training object detectors demands extensive, task-specific annotations, yet this requirement becomes impractical in UAV-based human detection due to constantly shifting target distributions and the scarcity of labeled images. As a remedy, synthetic simulators are adopted to generate annotated data, with a low annotation cost. However, the domain gap between synthetic and real images hinders the model from being effectively applied to the target domain. Accordingly, we introduce Coarse-to-Fine Hierarchical Alignment (CFHA), a three-stage diffusion-based framework designed to transform synthetic data for UAV-based human detection, narrowing the domain gap while preserving the original synthetic labels. CFHA explicitly decouples global style and local content domain discrepancies and bridges those gaps using three modules: (1) Global Style Transfer -- a diffusion model aligns color, illumination, and texture statistics of synthetic images to the realistic style, using only a small real reference set; (2) Local Refinement -- a super-resolution diffusion model is used to facilitate fine-grained and photorealistic details for the small objects, such as human instances, preserving shape and boundary integrity; (3) Hallucination Removal -- a module that filters out human instances whose visual attributes do not align with real-world data to make the human appearance closer to the target distribution. Extensive experiments on public UAV Sim2Real detection benchmarks demonstrate that our methods significantly improve the detection accuracy compared to the non-transformed baselines. Specifically, our method achieves up to $+14.1$ improvement of mAP50 on Semantic-Drone benchmark. Ablation studies confirm the complementary roles of the global and local stages and highlight the importance of hierarchical alignment. The code is released at \href{https://github.com/liwd190019/CFHA}{this url}.

---

### Safe Online Control-Informed Learning

Authors: Tianyu Zhou, Zihao Liang, Zehui Lu, Shaoshuai Mou
Published: 2025-12-15
Categories: eess.SY, cs.LG, math.OC
arXiv: https://arxiv.org/abs/2512.13868v2

This paper proposes a Safe Online Control-Informed Learning framework for safety-critical autonomous systems. The framework unifies optimal control, parameter estimation, and safety constraints into an online learning process. It employs an extended Kalman filter to incrementally update system parameters in real time, enabling robust and data-efficient adaptation under uncertainty. A softplus barrier function enforces constraint satisfaction during learning and control while eliminating the dependence on high-quality initial guesses. Theoretical analysis establishes convergence and safety guarantees, and the framework's effectiveness is demonstrated on cart-pole and robot-arm systems.

---

### Verification-Guided Context Optimization for Tool Calling via Hierarchical LLMs-as-Editors

Authors: Henger Li, Shuangjie You, Flavio Di Palo, Yiyue Qian, Ayush Jain
Published: 2025-12-15
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2512.13860v1

Tool calling enables large language models (LLMs) to interact with external environments through tool invocation, providing a practical way to overcome the limitations of pretraining. However, the effectiveness of tool use depends heavily on the quality of the associated documentation and knowledge base context. These materials are usually written for human users and are often misaligned with how LLMs interpret information. This problem is even more pronounced in industrial settings, where hundreds of tools with overlapping functionality create challenges in scalability, variability, and ambiguity. We propose Verification-Guided Context Optimization (VGCO), a framework that uses LLMs as editors to automatically refine tool-related documentation and knowledge base context. VGCO works in two stages. First, Evaluation collects real-world failure cases and identifies mismatches between tools and their context. Second, Optimization performs hierarchical editing through offline learning with structure-aware, in-context optimization. The novelty of our LLM editors has three main aspects. First, they use a hierarchical structure that naturally integrates into the tool-calling workflow. Second, they are state-aware, action-specific, and verification-guided, which constrains the search space and enables efficient, targeted improvements. Third, they enable cost-efficient sub-task specialization, either by prompt engineering large editor models or by post-training smaller editor models. Unlike prior work that emphasizes multi-turn reasoning, VGCO focuses on the single-turn, large-scale tool-calling problem and achieves significant improvements in accuracy, robustness, and generalization across LLMs.

---

### EvoLattice: Persistent Internal-Population Evolution through Multi-Alternative Quality-Diversity Graph Representations for LLM-Guided Program Discovery

Authors: Kamer Ali Yuksel
Published: 2025-12-15
Categories: cs.AI, cs.CL, cs.LG, cs.MA, cs.NE
arXiv: https://arxiv.org/abs/2512.13857v2

Large language models (LLMs) are increasingly used to evolve programs and multi-agent systems, yet most existing approaches rely on overwrite-based mutations that maintain only a single candidate at a time. Such methods discard useful variants, suffer from destructive edits, and explore a brittle search space prone to structural failure. We introduce EvoLattice, a framework that represents an entire population of candidate programs or agent behaviors within a single directed acyclic graph. Each node stores multiple persistent alternatives, and every valid path through the graph defines a distinct executable candidate, yielding a large combinatorial search space without duplicating structure. EvoLattice enables fine-grained alternative-level evaluation by scoring each alternative across all paths in which it appears, producing statistics that reveal how local design choices affect global performance. These statistics provide a dense, data-driven feedback signal for LLM-guided mutation, recombination, and pruning, while preserving successful components. Structural correctness is guaranteed by a deterministic self-repair mechanism that enforces acyclicity and dependency consistency independently of the LLM. EvoLattice naturally extends to agent evolution by interpreting alternatives as prompt fragments or sub-agent behaviors. Across program synthesis (proxy and optimizer meta-learning), EvoLattice yields more stable evolution, greater expressivity, and stronger improvement trajectories than prior LLM-guided methods. The resulting dynamics resemble quality-diversity optimization, emerging implicitly from EvoLattice's internal multi-alternative representation rather than an explicit external archive.

---

### Improvise, Adapt, Overcome -- Telescopic Adapters for Efficient Fine-tuning of Vision Language Models in Medical Imaging

Authors: Ujjwal Mishra, Vinita Shukla, Praful Hambarde, Amit Shukla
Published: 2025-12-15
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2512.13855v2

Adapting Vision Language Segmentation Models (VLSMs) to medical imaging domains requires significant computational overhead when using conventional fine-tuning approaches. Existing Parameter-Efficient Fine-Tuning (PEFT) methods apply uniform adapter dimensions across all transformer layers, leading to suboptimal parameter allocation and reduced adaptation efficiency. We introduce Telescopic Adapters, a novel PEFT framework that employs depth-aware scaling to progressively increase adapter capacity from shallow to deep transformer layers. Our method integrates lightweight bottleneck modules within CLIPSeg's vision and text encoders, with adapter dimensions dynamically scaled based on layer depth and semantic relevance. Using only 613k trainable parameters--244x fewer than end-to-end fine-tuning, Telescopic Adapters achieve superior performance across five diverse medical datasets spanning polyp segmentation, skin lesion detection, and breast ultrasound imaging. Comprehensive ablation studies demonstrate that deeper layers require substantially more adaptation capacity than shallow layers, validating our telescopic scaling hypothesis. Our approach establishes a new paradigm for efficient medical VLSM fine-tuning, enabling deployment in resource-constrained clinical environments while maintaining competitive segmentation accuracy. Our source code is publicly available at https://github.com/Ujjwal238/Telescopic_adapters

---

### Dropout Neural Network Training Viewed from a Percolation Perspective

Authors: Finley Devlin, Jaron Sanders
Published: 2025-12-15
Categories: cs.LG, cond-mat.stat-mech, math.PR, stat.ML
arXiv: https://arxiv.org/abs/2512.13853v3

In this work, we investigate the existence and effect of percolation in training deep Neural Networks (NNs) with dropout. Dropout methods are regularisation techniques for training NNs, first introduced by G. Hinton et al. (2012). These methods temporarily remove connections in the NN, randomly at each stage of training, and update the remaining subnetwork with Stochastic Gradient Descent (SGD). The process of removing connections from a network at random is similar to percolation, a paradigm model of statistical physics. If dropout were to remove enough connections such that there is no path between the input and output of the NN, then the NN could not make predictions informed by the data. We study new percolation models that mimic dropout in NNs and characterise the relationship between network topology and this path problem. The theory shows the existence of a percolative effect in dropout. We also show that this percolative effect can cause a breakdown when training NNs without biases with dropout; and we argue heuristically that this breakdown extends to NNs with biases.

---

### Topologically-Stabilized Graph Neural Networks: Empirical Robustness Across Domains

Authors: Jelena Losic
Published: 2025-12-15
Categories: cs.LG, cs.SI
arXiv: https://arxiv.org/abs/2512.13852v1

Graph Neural Networks (GNNs) have become the standard for graph representation learning but remain vulnerable to structural perturbations. We propose a novel framework that integrates persistent homology features with stability regularization to enhance robustness. Building on the stability theorems of persistent homology \cite{cohen2007stability}, our method combines GIN architectures with multi-scale topological features extracted from persistence images, enforced by Hiraoka-Kusano-inspired stability constraints. Across six diverse datasets spanning biochemical, social, and collaboration networks , our approach demonstrates exceptional robustness to edge perturbations while maintaining competitive accuracy. Notably, we observe minimal performance degradation (0-4\% on most datasets) under perturbation, significantly outperforming baseline stability. Our work provides both a theoretically-grounded and empirically-validated approach to robust graph learning that aligns with recent advances in topological regularization

---

### BiCoRec: Bias-Mitigated Context-Aware Sequential Recommendation Model

Authors: Mufhumudzi Muthivhi, Terence L van Zyl, Hairong Wang
Published: 2025-12-15
Categories: cs.IR, cs.LG
arXiv: https://arxiv.org/abs/2512.13848v1

Sequential recommendation models aim to learn from users evolving preferences. However, current state-of-the-art models suffer from an inherent popularity bias. This study developed a novel framework, BiCoRec, that adaptively accommodates users changing preferences for popular and niche items. Our approach leverages a co-attention mechanism to obtain a popularity-weighted user sequence representation, facilitating more accurate predictions. We then present a new training scheme that learns from future preferences using a consistency loss function. BiCoRec aimed to improve the recommendation performance of users who preferred niche items. For these users, BiCoRec achieves a 26.00% average improvement in NDCG@10 over state-of-the-art baselines. When ranking the relevant item against the entire collection, BiCoRec achieves NDCG@10 scores of 0.0102, 0.0047, 0.0021, and 0.0005 for the Movies, Fashion, Games and Music datasets.

---

### MoLingo: Motion-Language Alignment for Text-to-Human Motion Generation

Authors: Yannan He, Garvita Tiwari, Xiaohan Zhang, Pankaj Bora, Tolga Birdal, Jan Eric Lenssen, Gerard Pons-Moll
Published: 2025-12-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.13840v3

We introduce MoLingo, a text-to-motion (T2M) model that generates realistic, lifelike human motion by denoising in a continuous latent space. Recent works perform latent space diffusion, either on the whole latent at once or auto-regressively over multiple latents. In this paper, we study how to make diffusion on continuous motion latents work best. We focus on two questions: (1) how to build a semantically aligned latent space so diffusion becomes more effective, and (2) how to best inject text conditioning so the motion follows the description closely. We propose a semantic-aligned motion encoder trained with frame-level text labels so that latents with similar text meaning stay close, which makes the latent space more diffusion-friendly. We also compare single-token conditioning with a multi-token cross-attention scheme and find that cross-attention gives better motion realism and text-motion alignment. With semantically aligned latents, auto-regressive generation, and cross-attention text conditioning, our model sets a new state of the art in human motion generation on standard metrics and in a user study. We will release our code and models for further research and downstream usage.

---

### Explainable reinforcement learning from human feedback to improve alignment

Authors: Shicheng Liu, Siyuan Xu, Wenjie Qiu, Hangfan Zhang, Minghui Zhu
Published: 2025-12-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.13837v1

A common and effective strategy for humans to improve an unsatisfactory outcome in daily life is to find a cause of this outcome and correct the cause. In this paper, we investigate whether this human improvement strategy can be applied to improving reinforcement learning from human feedback (RLHF) for alignment of language models (LMs). In particular, it is observed in the literature that LMs tuned by RLHF can still output unsatisfactory responses. This paper proposes a method to improve the unsatisfactory responses by correcting their causes. Our method has two parts. The first part proposes a post-hoc explanation method to explain why an unsatisfactory response is generated to a prompt by identifying the training data that lead to this response. We formulate this problem as a constrained combinatorial optimization problem where the objective is to find a set of training data closest to this prompt-response pair in a feature representation space, and the constraint is that the prompt-response pair can be decomposed as a convex combination of this set of training data in the feature space. We propose an efficient iterative data selection algorithm to solve this problem. The second part proposes an unlearning method that improves unsatisfactory responses to some prompts by unlearning the training data that lead to these unsatisfactory responses and, meanwhile, does not significantly degrade satisfactory responses to other prompts. Experimental results demonstrate that our algorithm can improve RLHF.

---

### VajraV1 -- The most accurate Real Time Object Detector of the YOLO family

Authors: Naman Balbir Singh Makkar
Published: 2025-12-15
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2512.13834v1

Recent years have seen significant advances in real-time object detection, with the release of YOLOv10, YOLO11, YOLOv12, and YOLOv13 between 2024 and 2025. This technical report presents the VajraV1 model architecture, which introduces architectural enhancements over existing YOLO-based detectors. VajraV1 combines effective design choices from prior YOLO models to achieve state-of-the-art accuracy among real-time object detectors while maintaining competitive inference speed. On the COCO validation set, VajraV1-Nano achieves 44.3% mAP, outperforming YOLOv12-N by 3.7% and YOLOv13-N by 2.7% at latency competitive with YOLOv12-N and YOLOv11-N. VajraV1-Small achieves 50.4% mAP, exceeding YOLOv12-S and YOLOv13-S by 2.4%. VajraV1-Medium achieves 52.7% mAP, outperforming YOLOv12-M by 0.2%. VajraV1-Large achieves 53.7% mAP, surpassing YOLOv13-L by 0.3%. VajraV1-Xlarge achieves 56.2% mAP, outperforming all existing real-time object detectors.

---

### Machine learning Majorana topology using unsupervised and supervised learning

Authors: Jacob Taylor, Haining Pan, Sankar Das Sarma
Published: 2025-12-15
Categories: cond-mat.dis-nn, cond-mat.mes-hall, cs.LG
arXiv: https://arxiv.org/abs/2512.13825v2

In unsupervised learning, the training data for deep learning does not come with any labels, thus forcing the algorithm to discover hidden patterns in the data for discerning useful information. This, in principle, could be a powerful tool in identifying topological order since topology does not always manifest in obvious physical ways (e.g., topological superconductivity) for its decisive confirmation. The problem, however, is that unsupervised learning is a difficult challenge, necessitating huge computing resources, which may not always work. In the current work, we combine unsupervised and supervised learning to establish that unlabeled (simulated) data in the Majorana splitting in realistic short disordered nanowires may enable not only a distinction between `topological' and `trivial', but also where their crossover happens in the relevant parameter space. This may be a useful tool in identifying topology in experimental Majorana nanowires.

---

### The Double Life of Code World Models: Provably Unmasking Malicious Behavior Through Execution Traces

Authors: Subramanyam Sahoo
Published: 2025-12-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.13821v2

Large language models (LLMs) increasingly generate code with minimal human oversight, raising critical concerns about backdoor injection and malicious behavior. We present Cross-Trace Verification Protocol (CTVP), a novel AI control framework that verifies untrusted code-generating models through semantic orbit analysis. Rather than directly executing potentially malicious code, CTVP leverages the model's own predictions of execution traces across semantically equivalent program transformations. By analyzing consistency patterns in these predicted traces, we detect behavioral anomalies indicative of backdoors. Our approach introduces the Adversarial Robustness Quotient (ARQ), which quantifies the computational cost of verification relative to baseline generation, demonstrating exponential growth with orbit size. Theoretical analysis establishes information-theoretic bounds showing non-gamifiability - adversaries cannot improve through training due to fundamental space complexity constraints. This work demonstrates that semantic orbit analysis provides a theoretically grounded approach to AI control for code generation tasks, though practical deployment requires addressing the high false positive rates observed in initial evaluations.

---

### EEG-D3: A Solution to the Hidden Overfitting Problem of Deep Learning Models

Authors: Siegfried Ludwig, Stylianos Bakas, Konstantinos Barmpas, Georgios Zoumpourlis, Dimitrios A. Adamos, Nikolaos Laskaris, Yannis Panagakis, Stefanos Zafeiriou
Published: 2025-12-15
Categories: cs.LG, cs.AI, cs.CV, cs.HC
arXiv: https://arxiv.org/abs/2512.13806v1

Deep learning for decoding EEG signals has gained traction, with many claims to state-of-the-art accuracy. However, despite the convincing benchmark performance, successful translation to real applications is limited. The frequent disconnect between performance on controlled BCI benchmarks and its lack of generalisation to practical settings indicates hidden overfitting problems. We introduce Disentangled Decoding Decomposition (D3), a weakly supervised method for training deep learning models across EEG datasets. By predicting the place in the respective trial sequence from which the input window was sampled, EEG-D3 separates latent components of brain activity, akin to non-linear ICA. We utilise a novel model architecture with fully independent sub-networks for strict interpretability. We outline a feature interpretation paradigm to contrast the component activation profiles on different datasets and inspect the associated temporal and spatial filters. The proposed method reliably separates latent components of brain activity on motor imagery data. Training downstream classifiers on an appropriate subset of these components prevents hidden overfitting caused by task-correlated artefacts, which severely affects end-to-end classifiers. We further exploit the linearly separable latent space for effective few-shot learning on sleep stage classification. The ability to distinguish genuine components of brain activity from spurious features results in models that avoid the hidden overfitting problem and generalise well to real-world applications, while requiring only minimal labelled data. With interest to the neuroscience community, the proposed method gives researchers a tool to separate individual brain processes and potentially even uncover heretofore unknown dynamics.

---

### Nexels: Neurally-Textured Surfels for Real-Time Novel View Synthesis with Sparse Geometries

Authors: Victor Rong, Jan Held, Victor Chu, Daniel Rebain, Marc Van Droogenbroeck, Kiriakos N. Kutulakos, Andrea Tagliasacchi, David B. Lindell
Published: 2025-12-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.13796v1

Though Gaussian splatting has achieved impressive results in novel view synthesis, it requires millions of primitives to model highly textured scenes, even when the geometry of the scene is simple. We propose a representation that goes beyond point-based rendering and decouples geometry and appearance in order to achieve a compact representation. We use surfels for geometry and a combination of a global neural field and per-primitive colours for appearance. The neural field textures a fixed number of primitives for each pixel, ensuring that the added compute is low. Our representation matches the perceptual quality of 3D Gaussian splatting while using $9.7\times$ fewer primitives and $5.5\times$ less memory on outdoor scenes and using $31\times$ fewer primitives and $3.7\times$ less memory on indoor scenes. Our representation also renders twice as fast as existing textured primitives while improving upon their visual quality.

---

### Constrained Policy Optimization via Sampling-Based Weight-Space Projection

Authors: Shengfan Cao, Francesco Borrelli, Eunhyek Joa
Published: 2025-12-15
Categories: cs.LG, cs.RO
arXiv: https://arxiv.org/abs/2512.13788v3

Safety-critical learning requires policies that improve performance without leaving the safe operating regime. We study constrained policy learning where model parameters must satisfy rollout-based safety constraints that can be evaluated but not differentiated analytically. We propose SCPO, a sampling-based weight-space projection method that enforces safety directly in parameter space without requiring gradient access to the constraint functions. SCPO constructs a local safe region by combining rollout-based safety evaluations with smoothness bounds relating parameter perturbations to changes in safety metrics, and projects each gradient update via a convex QCQP. We establish a safe-by-induction guarantee: starting from any safe initialization, all intermediate policies remain safe given feasible projections. In constrained control settings with a stabilizing backup policy, SCPO further ensures closed-loop stability while enabling safe adaptation beyond the conservative backup. Experiments on constrained regression with harmful supervision and double-integrator imitation with a malicious expert show that SCPO rejects unsafe updates, maintains feasibility throughout training, and achieves meaningful objective improvement.

---

### Semantic Grounding Index: Geometric Bounds on Context Engagement in RAG Systems

Authors: Javier Marín
Published: 2025-12-15
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.13771v1

When retrieval-augmented generation (RAG) systems hallucinate, what geometric trace does this leave in embedding space? We introduce the Semantic Grounding Index (SGI), defined as the ratio of angular distances from the response to the question versus the context on the unit hypersphere $\mathbb{S}^{d-1}$.Our central finding is \emph{semantic laziness}: hallucinated responses remain angularly proximate to questions rather than departing toward retrieved contexts. On HaluEval ($n$=5,000), we observe large effect sizes (Cohen's $d$ ranging from 0.92 to 1.28) across five embedding models with mean cross-model correlation $r$=0.85. Crucially, we derive from the spherical triangle inequality that SGI's discriminative power should increase with question-context angular separation $θ(q,c)$-a theoretical prediction confirmed empirically: effect size rises monotonically from $d$=0.61 -low $θ(q,c)$, to $d$=1.27 -high $θ(q,c)$, with AUC improving from 0.72 to 0.83. Subgroup analysis reveals that SGI excels on long responses ($d$=2.05) and short questions ($d$=1.22), while remaining robust across context lengths. Calibration analysis yields ECE=0.10, indicating SGI scores can serve as probability estimates, not merely rankings. A critical negative result on TruthfulQA (AUC=0.478) establishes that angular geometry measures topical engagement rather than factual accuracy. SGI provides computationally efficient, theoretically grounded infrastructure for identifying responses that warrant verification in production RAG deployments.

---

### Enhancing Semi-Supervised Multi-View Graph Convolutional Networks via Supervised Contrastive Learning and Self-Training

Authors: Huaiyuan Xiao, Fadi Dornaika, Jingjun Bi
Published: 2025-12-15
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2512.13770v1

The advent of graph convolutional network (GCN)-based multi-view learning provides a powerful framework for integrating structural information from heterogeneous views, enabling effective modeling of complex multi-view data. However, existing methods often fail to fully exploit the complementary information across views, leading to suboptimal feature representations and limited performance. To address this, we propose MV-SupGCN, a semi-supervised GCN model that integrates several complementary components with clear motivations and mutual reinforcement. First, to better capture discriminative features and improve model generalization, we design a joint loss function that combines Cross-Entropy loss with Supervised Contrastive loss, encouraging the model to simultaneously minimize intra-class variance and maximize inter-class separability in the latent space. Second, recognizing the instability and incompleteness of single graph construction methods, we combine both KNN-based and semi-supervised graph construction approaches on each view, thereby enhancing the robustness of the data structure representation and reducing generalization error. Third, to effectively utilize abundant unlabeled data and enhance semantic alignment across multiple views, we propose a unified framework that integrates contrastive learning in order to enforce consistency among multi-view embeddings and capture meaningful inter-view relationships, together with pseudo-labeling, which provides additional supervision applied to both the cross-entropy and contrastive loss functions to enhance model generalization. Extensive experiments demonstrate that MV-SupGCN consistently surpasses state-of-the-art methods across multiple benchmarks, validating the effectiveness of our integrated approach. The source code is available at https://github.com/HuaiyuanXiao/MVSupGCN

---

### Beyond Procedural Compliance: Human Oversight as a Dimension of Well-being Efficacy in AI Governance

Authors: Yao Xie, Walter Cullen
Published: 2025-12-15
Categories: cs.CY, cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2512.13768v1

Major AI ethics guidelines and laws, including the EU AI Act, call for effective human oversight, but do not define it as a distinct and developable capacity. This paper introduces human oversight as a well-being capacity, situated within the emerging Well-being Efficacy framework. The concept integrates AI literacy, ethical discernment, and awareness of human needs, acknowledging that some needs may be conflicting or harmful. Because people inevitably project desires, fears, and interests into AI systems, oversight requires the competence to examine and, when necessary, restrain problematic demands. The authors argue that the sustainable and cost-effective development of this capacity depends on its integration into education at every level, from professional training to lifelong learning. The frame of human oversight as a well-being capacity provides a practical path from high-level regulatory goals to the continuous cultivation of human agency and responsibility essential for safe and ethical AI. The paper establishes a theoretical foundation for future research on the pedagogical implementation and empirical validation of well-being effectiveness in multiple contexts.

---

### Towards Deep Learning Surrogate for the Forward Problem in Electrocardiology: A Scalable Alternative to Physics-Based Models

Authors: Shaheim Ogbomo-Harmitt, Cesare Magnetti, Chiara Spota, Jakub Grzelak, Oleg Aslanidi
Published: 2025-12-15
Categories: eess.IV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2512.13765v2

The forward problem in electrocardiology, computing body surface potentials from cardiac electrical activity, is traditionally solved using physics-based models such as the bidomain or monodomain equations. While accurate, these approaches are computationally expensive, limiting their use in real-time and large-scale clinical applications. We propose a proof-of-concept deep learning (DL) framework as an efficient surrogate for forward solvers. The model adopts a time-dependent, attention-based sequence-to-sequence architecture to predict electrocardiogram (ECG) signals from cardiac voltage propagation maps. A hybrid loss combining Huber loss with a spectral entropy term was introduced to preserve both temporal and frequency-domain fidelity. Using 2D tissue simulations incorporating healthy, fibrotic, and gap junction-remodelled conditions, the model achieved high accuracy (mean $R^2 = 0.99 \pm 0.01$). Ablation studies confirmed the contributions of convolutional encoders, time-aware attention, and spectral entropy loss. These findings highlight DL as a scalable, cost-effective alternative to physics-based solvers, with potential for clinical and digital twin applications.

---

### Mathematics and Coding are Universal AI Benchmarks

Authors: Przemyslaw Chojecki
Published: 2025-12-15
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2512.13764v1

We study the special role of mathematics and coding inside the moduli space of psychometric batteries for AI agents. Building on the AAI framework and GVU dynamics from previous works, we define the Mathematics Fiber and show that, when paired with formal proof kernels (e.g. Lean, Coq), GVU flows on this fiber admit spectrally stable self-improvement regimes due to oracle-like verification. Our main technical result is a density theorem: under uniform tightness of agent outputs and a Lipschitz AAI functional, the subspace of batteries generated by mathematical theorem-proving and coding tasks is dense in the moduli space of batteries with respect to the evaluation metric. Coding alone is universal in this sense, while pure mathematics is not; its privilege is spectral rather than expressive. We interpret this as evidence that mathematics and coding provide ``universal coordinates'' for evaluation, and that formal mathematics is a natural ignition domain for recursive self-improvement in advanced AI agents.

---

### State-Dependent Refusal and Learned Incapacity in RLHF-Aligned Language Models

Authors: TK Lee
Published: 2025-12-15
Categories: cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2512.13762v1

Large language models (LLMs) are widely deployed as general-purpose tools, yet extended interaction can reveal behavioral patterns not captured by standard quantitative benchmarks. We present a qualitative case-study methodology for auditing policy-linked behavioral selectivity in long-horizon interaction. In a single 86-turn dialogue session, the same model shows Normal Performance (NP) in broad, non-sensitive domains while repeatedly producing Functional Refusal (FR) in provider- or policy-sensitive domains, yielding a consistent asymmetry between NP and FR across domains. Drawing on learned helplessness as an analogy, we introduce learned incapacity (LI) as a behavioral descriptor for this selective withholding without implying intentionality or internal mechanisms. We operationalize three response regimes (NP, FR, Meta-Narrative; MN) and show that MN role-framing narratives tend to co-occur with refusals in the same sensitive contexts. Overall, the study proposes an interaction-level auditing framework based on observable behavior and motivates LI as a lens for examining potential alignment side effects, warranting further investigation across users and models.

---

### Network-Wide Traffic Volume Estimation from Speed Profiles using a Spatio-Temporal Graph Neural Network with Directed Spatial Attention

Authors: Léo Hein, Giovanni de Nunzio, Giovanni Chierchia, Aurélie Pirayre, Laurent Najman
Published: 2025-12-15
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2512.13758v1

Existing traffic volume estimation methods typically address either forecasting traffic on sensor-equipped roads or spatially imputing missing volumes using nearby sensors. While forecasting models generally disregard unmonitored roads by design, spatial imputation methods explicitly address network-wide estimation; yet this approach relies on volume data at inference time, limiting its applicability in sensor-scarce cities. Unlike traffic volume data, probe vehicle speeds and static road attributes are more broadly accessible and support full coverage of road segments in most urban networks. In this work, we present the Hybrid Directed-Attention Spatio-Temporal Graph Neural Network (HDA-STGNN), an inductive deep learning framework designed to tackle the network-wide volume estimation problem. Our approach leverages speed profiles, static road attributes, and road network topology to predict daily traffic volume profiles across all road segments in the network. To evaluate the effectiveness of our approach, we perform extensive ablation studies that demonstrate the model's capacity to capture complex spatio-temporal dependencies and highlight the value of topological information for accurate network-wide traffic volume estimation without relying on volume data at inference time.

---

### Improving the Plausibility of Pressure Distributions Synthesized from Depth Image through Generative Modeling

Authors: Neevkumar Manavar, Hanno Gerd Meyer, Joachim Waßmuth, Barbara Hammer, Axel Schneider
Published: 2025-12-15
Categories: eess.IV, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2512.13757v2

Monitoring contact pressure in hospital beds is essential for preventing pressure ulcers and enabling real-time patient assessment. Current methods can predict pressure maps but often lack physical plausibility, limiting clinical reliability. This work proposes a framework that enhances plausibility via Informed Latent Space (ILS) and Weight Optimization Loss (WOL) with conditional generative modeling to produce high-fidelity, physically consistent pressure estimates. This study also applies diffusion based conditional Brownian Bridge Diffusion Model (BBDM) and proposes training strategy for its latent counterpart Latent Brownian Bridge Diffusion Model (LBBDM) tailored for pressure synthesis in lying postures. Experiment results shows proposed method improves physical plausibility and performance over baselines: BBDM with ILS delivers highly detailed maps at higher computational cost and large inference time, whereas LBBDM provides faster inference with competitive performance. Overall, the approach supports non-invasive, vision-based, real-time patient monitoring in clinical environments.

---

### Time-aware UNet and super-resolution deep residual networks for spatial downscaling

Authors: Mika Sipilä, Sabrina Maggio, Sandra De Iaco, Klaus Nordhausen, Monica Palma, Sara Taskinen
Published: 2025-12-15
Categories: cs.CV, cs.LG, eess.IV, stat.ML
arXiv: https://arxiv.org/abs/2512.13753v1

Satellite data of atmospheric pollutants are often available only at coarse spatial resolution, limiting their applicability in local-scale environmental analysis and decision-making. Spatial downscaling methods aim to transform the coarse satellite data into high-resolution fields. In this work, two widely used deep learning architectures, the super-resolution deep residual network (SRDRN) and the encoder-decoder-based UNet, are considered for spatial downscaling of tropospheric ozone. Both methods are extended with a lightweight temporal module, which encodes observation time using either sinusoidal or radial basis function (RBF) encoding, and fuses the temporal features with the spatial representations in the networks. The proposed time-aware extensions are evaluated against their baseline counterparts in a case study on ozone downscaling over Italy. The results suggest that, while only slightly increasing computational complexity, the temporal modules significantly improve downscaling performance and convergence speed.

---