# Research Papers — 2026-02 · bundle page 121 of 210

> Full-text markdown of papers #6001–6050 of 10493 published in 2026-02, newest first. AI-readable mirrors of the full 10493-paper 2026-02 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-02/page/121
[← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/120.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-02/page/122.md)

### ICODEN: Ordinary Differential Equation Neural Networks for Interval-Censored Data

Authors: Haoling Wang, Lang Zeng, Tao Sun, Youngjoo Cho, Ying Ding
Published: 2026-02-10
Categories: cs.LG, q-bio.QM, stat.ML
arXiv: https://arxiv.org/abs/2602.10303v1

Predicting time-to-event outcomes when event times are interval censored is challenging because the exact event time is unobserved. Many existing survival analysis approaches for interval-censored data rely on strong model assumptions or cannot handle high-dimensional predictors. We develop ICODEN, an ordinary differential equation-based neural network for interval-censored data that models the hazard function through deep neural networks and obtains the cumulative hazard by solving an ordinary differential equation. ICODEN does not require the proportional hazards assumption or a prespecified parametric form for the hazard function, thereby permitting flexible survival modeling. Across simulation settings with proportional or non-proportional hazards and both linear and nonlinear covariate effects, ICODEN consistently achieves satisfactory predictive accuracy and remains stable as the number of predictors increases. Applications to data from multiple phases of the Alzheimer's Disease Neuroimaging Initiative (ADNI) and to two Age-Related Eye Disease Studies (AREDS and AREDS2) for age-related macular degeneration (AMD) demonstrate ICODEN's robust prediction performance. In both applications, predicting time-to-AD or time-to-late AMD, ICODEN effectively uses hundreds to more than 1,000 SNPs and supports data-driven subgroup identification with differential progression risk profiles. These results establish ICODEN as a practical assumption-lean tool for prediction with interval-censored survival data in high-dimensional biomedical settings.

---

### Configuration-to-Performance Scaling Law with Neural Ansatz

Authors: Huaqing Zhang, Kaiyue Wen, Tengyu Ma
Published: 2026-02-10
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.10300v1

Researchers build scaling laws to forecast the training performance of expensive large-scale runs with larger model size N and data size D. These laws assume that other training hyperparameters are optimally chosen, which can require significant effort and, in some cases, be impossible due to external hardware constraints. To improve predictability across a broader set of hyperparameters and enable simpler tuning at scale, we propose learning a \textit{Configuration-to-Performance Scaling Law} (CPL): a mapping from the \textit{full training configuration} to training performance. Because no simple functional form can express this mapping, we parameterize it with a large language model (LLM), and fit it with diverse open-source pretraining logs across multiple sources, yielding a \textit{Neural} Configuration-to-Performance Scaling Law (NCPL). NCPL accurately predicts how training configurations influence the final pretraining loss, achieving 20-40% lower prediction error than the configuration-agnostic Chinchilla law and generalizing to runs using up to 10 x more compute than any run in the training set. It further supports joint tuning of multiple hyperparameters with performance comparable to hyperparameter scaling law baselines. Finally, NCPL naturally and effectively extends to richer prediction targets such as loss-curve prediction.

---

### On Emergent Social World Models -- Evidence for Functional Integration of Theory of Mind and Pragmatic Reasoning in Language Models

Authors: Polina Tsvilodub, Jan-Felix Klumpp, Amir Mohammadpour, Jennifer Hu, Michael Franke
Published: 2026-02-10
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.10298v2

This paper investigates whether LMs recruit shared computational mechanisms for general Theory of Mind (ToM) and language-specific pragmatic reasoning in order to contribute to the general question of whether LMs may be said to have emergent "social world models", i.e., representations of mental states that are repurposed across tasks (the functional integration hypothesis). Using behavioral evaluations and causal-mechanistic experiments via functional localization methods inspired by cognitive neuroscience, we analyze LMs' performance across seven subcategories of ToM abilities (Beaudoin et al., 2020) on a substantially larger localizer dataset than used in prior like-minded work. Results from stringent hypothesis-driven statistical testing offer suggestive evidence for the functional integration hypothesis, indicating that LMs may develop interconnected "social world models" rather than isolated competencies. This work contributes novel ToM localizer data, methodological refinements to functional localization techniques, and empirical insights into the emergence of social cognition in artificial systems.

---

### ECHO: An Open Research Platform for Evaluation of Chat, Human Behavior, and Outcomes

Authors: Jiqun Liu, Nischal Dinesh, Ran Yu
Published: 2026-02-10
Categories: cs.HC, cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2602.10295v1

ECHO (Evaluation of Chat, Human behavior, and Outcomes) is an open research platform designed to support reproducible, mixed-method studies of human interaction with both conversational AI systems and Web search engines. It enables researchers from varying disciplines to orchestrate end-to-end experimental workflows that integrate consent and background surveys, chat-based and search-based information-seeking sessions, writing or judgment tasks, and pre- and post-task evaluations within a unified, low-coding-load framework. ECHO logs fine-grained interaction traces and participant responses, and exports structured datasets for downstream analysis. By supporting both chat and search alongside flexible evaluation instruments, ECHO lowers technical barriers for studying learning, decision making, and user experience across different information access paradigms, empowering researchers from information retrieval, HCI, and the social sciences to conduct scalable and reproducible human-centered AI evaluations.

---

### What Does Preference Learning Recover from Pairwise Comparison Data?

Authors: Rattana Pukdee, Maria-Florina Balcan, Pradeep Ravikumar
Published: 2026-02-10
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.10286v3

Pairwise preference learning is central to machine learning, with recent applications in aligning language models with human preferences. A typical dataset consists of triplets $(x, y^+, y^-)$, where response $y^+$ is preferred over response $y^-$ for context $x$. The Bradley--Terry (BT) model is the predominant approach, modeling preference probabilities as a function of latent score differences. Standard practice assumes data follows this model and learns the latent scores accordingly. However, real data may violate this assumption, and it remains unclear what BT learning recovers in such cases. Starting from triplet comparison data, we formalize the preference information it encodes through the conditional preference distribution (CPRD). We give precise conditions for when BT is appropriate for modeling the CPRD, and identify factors governing sample efficiency -- namely, margin and connectivity. Together, these results offer a data-centric foundation for understanding what preference learning actually recovers.

---

### What Does Preference Learning Recover from Pairwise Comparison Data?

Authors: Rattana Pukdee, Maria-Florina Balcan, Pradeep Ravikumar
Published: 2026-02-10
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.10286v2

Pairwise preference learning is central to machine learning, with recent applications in aligning language models with human preferences. A typical dataset consists of triplets $(x, y^+, y^-)$, where response $y^+$ is preferred over response $y^-$ for context $x$. The Bradley--Terry (BT) model is the predominant approach, modeling preference probabilities as a function of latent score differences. Standard practice assumes data follows this model and learns the latent scores accordingly. However, real data may violate this assumption, and it remains unclear what BT learning recovers in such cases. Starting from triplet comparison data, we formalize the preference information it encodes through the conditional preference distribution (CPRD). We give precise conditions for when BT is appropriate for modeling the CPRD, and identify factors governing sample efficiency -- namely, margin and connectivity. Together, these results offer a data-centric foundation for understanding what preference learning actually recovers.

---

### Linear-LLM-SCM: Benchmarking LLMs for Coefficient Elicitation in Linear-Gaussian Causal Models

Authors: Kanta Yamaoka, Sumantrak Mukherjee, Thomas Gärtner, David Antony Selby, Stefan Konigorski, Eyke Hüllermeier, Viktor Bengs, Sebastian Josef Vollmer
Published: 2026-02-10
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.10282v2

Large language models (LLMs) have shown potential in identifying qualitative causal relations, but their ability to perform quantitative causal reasoning---estimating effect sizes that parametrize functional relationships---remains underexplored in continuous domains. We introduce Linear-LLM-SCM, a plug-and-play framework for evaluating LLMs on Linear Gaussian structural causal model parametrization when a directed acyclic graph (DAG) is given. The framework decomposes a DAG into local parent-child sets and prompts an LLM to produce a regression-style structural equation per node, which is aggregated and compared against available ground-truth parameters. Our experiments with seven real-world DAGs effect ground truth illustrate limitations of LLMs as quantitative causal parameterizers. Across most models, we observe variability in coefficient estimates and sensitivity to structural perturbations. We open-sourced the framework to further encourage the community to work on studies toward the use of LLM for causal effect elicitation in safety-critical domain, e.g., healthcare.

---

### ERGO: Excess-Risk-Guided Optimization for High-Fidelity Monocular 3D Gaussian Splatting

Authors: Zehua Ma, Hanhui Li, Zhenyu Xie, Xiaonan Luo, Michael Kampffmeyer, Feng Gao, Xiaodan Liang
Published: 2026-02-10
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.10278v1

Generating 3D content from a single image remains a fundamentally challenging and ill-posed problem due to the inherent absence of geometric and textural information in occluded regions. While state-of-the-art generative models can synthesize auxiliary views to provide additional supervision, these views inevitably contain geometric inconsistencies and textural misalignments that propagate and amplify artifacts during 3D reconstruction. To effectively harness these imperfect supervisory signals, we propose an adaptive optimization framework guided by excess risk decomposition, termed ERGO. Specifically, ERGO decomposes the optimization losses in 3D Gaussian splatting into two components, i.e., excess risk that quantifies the suboptimality gap between current and optimal parameters, and Bayes error that models the irreducible noise inherent in synthesized views. This decomposition enables ERGO to dynamically estimate the view-specific excess risk and adaptively adjust loss weights during optimization. Furthermore, we introduce geometry-aware and texture-aware objectives that complement the excess-risk-derived weighting mechanism, establishing a synergistic global-local optimization paradigm. Consequently, ERGO demonstrates robustness against supervision noise while consistently enhancing both geometric fidelity and textural quality of the reconstructed 3D content. Extensive experiments on the Google Scanned Objects dataset and the OmniObject3D dataset demonstrate the superiority of ERGO over existing state-of-the-art methods.

---

### Power-SMC: Low-Latency Sequence-Level Power Sampling for Training-Free LLM Reasoning

Authors: Seyedarmin Azizi, Erfan Baghaei Potraghloo, Minoo Ahmadi, Souvik Kundu, Massoud Pedram
Published: 2026-02-10
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2602.10273v2

Many recent reasoning gains in large language models can be explained as distribution sharpening: biasing generation toward high-likelihood trajectories already supported by the pretrained model, rather than modifying its weights. A natural formalization is the sequence-level power distribution $π_α(y\mid x)\propto p_θ(y\mid x)^α$ ($α>1$), which concentrates mass on whole sequences instead of adjusting token-level temperature. Prior work shows that Metropolis--Hastings (MH) sampling from this distribution recovers strong reasoning performance, but at order-of-magnitude inference slowdowns. We introduce Power-SMC, a training-free Sequential Monte Carlo scheme that targets the same objective while remaining close to standard decoding latency. Power-SMC advances a small particle set in parallel, corrects importance weights token-by-token, and resamples when necessary, all within a single GPU-friendly batched decode. We prove that temperature $τ=1/α$ is the unique prefix-only proposal minimizing incremental weight variance, interpret residual instability via prefix-conditioned Rényi entropies, and introduce an exponent-bridging schedule that improves particle stability without altering the target. On MATH500, Power-SMC matches or exceeds MH power sampling while reducing latency from $16$--$28\times$ to $1.4$--$3.3\times$ over baseline decoding. The code is available at https://github.com/ArminAzizi98/Power-SMC.

---

### MLDocRAG: Multimodal Long-Context Document Retrieval Augmented Generation

Authors: Yongyue Zhang, Yaxiong Wu
Published: 2026-02-10
Categories: cs.IR, cs.CL
arXiv: https://arxiv.org/abs/2602.10271v3

Understanding multimodal long-context documents that comprise multimodal chunks such as paragraphs, figures, and tables is challenging due to (1) cross-modal heterogeneity to localize relevant information across modalities, (2) cross-page reasoning to aggregate dispersed evidence across pages. To address these challenges, we are motivated to adopt a query-centric formulation that projects cross-modal and cross-page information into a unified query representation space, with queries acting as abstract semantic surrogates for heterogeneous multimodal content. In this paper, we propose a Multimodal Long-Context Document Retrieval Augmented Generation (MLDocRAG) framework that leverages a Multimodal Chunk-Query Graph (MCQG) to organize multimodal document content around semantically rich, answerable queries. MCQG is constructed via a multimodal document expansion process that generates fine-grained queries from heterogeneous document chunks and links them to their corresponding content across modalities and pages. This graph-based structure enables selective, query-centric retrieval and structured evidence aggregation, thereby enhancing grounding and coherence in multimodal long-context question answering. Experiments on datasets MMLongBench-Doc and LongDocURL demonstrate that MLDocRAG consistently improves retrieval quality and answer accuracy, demonstrating its effectiveness for multimodal long-context understanding.

---

### From Classical to Topological Neural Networks Under Uncertainty

Authors: Sarah Harkins Dayton, Layal Bou Hamdan, Ioannis D. Schizas, David L. Boothe, Vasileios Maroulas
Published: 2026-02-10
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.10266v1

This chapter explores neural networks, topological data analysis, and topological deep learning techniques, alongside statistical Bayesian methods, for processing images, time series, and graphs to maximize the potential of artificial intelligence in the military domain. Throughout the chapter, we highlight practical applications spanning image, video, audio, and time-series recognition, fraud detection, and link prediction for graphical data, illustrating how topology-aware and uncertainty-aware models can enhance robustness, interpretability, and generalization.

---

### Colorimeter-Supervised Skin Tone Estimation from Dermatoscopic Images for Fairness Auditing

Authors: Marin Benčević, Krešimir Romić, Ivana Hartmann Tolić, Irena Galić
Published: 2026-02-10
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.10265v1

Neural-network-based diagnosis from dermatoscopic images is increasingly used for clinical decision support, yet studies report performance disparities across skin tones. Fairness auditing of these models is limited by the lack of reliable skin-tone annotations in public dermatoscopy datasets. We address this gap with neural networks that predict Fitzpatrick skin type via ordinal regression and the Individual Typology Angle (ITA) via color regression, using in-person Fitzpatrick labels and colorimeter measurements as targets. We further leverage extensive pretraining on synthetic and real dermatoscopic and clinical images. The Fitzpatrick model achieves agreement comparable to human crowdsourced annotations, and ITA predictions show high concordance with colorimeter-derived ITA, substantially outperforming pixel-averaging approaches. Applying these estimators to ISIC 2020 and MILK10k, we find that fewer than 1% of subjects belong to Fitzpatrick types V and VI. We release code and pretrained models as an open-source tool for rapid skin-tone annotation and bias auditing. This is, to our knowledge, the first dermatoscopic skin-tone estimation neural network validated against colorimeter measurements, and it supports growing evidence of clinically relevant performance gaps across skin-tone groups.

---

### Kernel-Based Learning of Chest X-ray Images for Predicting ICU Escalation among COVID-19 Patients

Authors: Qiyuan Shi, Jian Kang, Yi Li
Published: 2026-02-10
Categories: cs.LG, stat.AP, stat.ML
arXiv: https://arxiv.org/abs/2602.10261v1

Kernel methods have been extensively utilized in machine learning for classification and prediction tasks due to their ability to capture complex non-linear data patterns. However, single kernel approaches are inherently limited, as they rely on a single type of kernel function (e.g., Gaussian kernel), which may be insufficient to fully represent the heterogeneity or multifaceted nature of real-world data. Multiple kernel learning (MKL) addresses these limitations by constructing composite kernels from simpler ones and integrating information from heterogeneous sources. Despite these advances, traditional MKL methods are primarily designed for continuous outcomes. We extend MKL to accommodate the outcome variable belonging to the exponential family, representing a broader variety of data types, and refer to our proposed method as generalized linear models with integrated multiple additive regression with kernels (GLIMARK). Empirically, we demonstrate that GLIMARK can effectively recover or approximate the true data-generating mechanism. We have applied it to a COVID-19 chest X-ray dataset, predicting binary outcomes of ICU escalation and extracting clinically meaningful features, underscoring the practical utility of this approach in real-world scenarios.

---

### PMMA: The Polytechnique Montreal Mobility Aids Dataset

Authors: Qingwu Liu, Nicolas Saunier, Guillaume-Alexandre Bilodeau
Published: 2026-02-10
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.10259v2

This study introduces a new object detection dataset of pedestrians using mobility aids, named PMMA. The dataset was collected in an outdoor environment, where volunteers used wheelchairs, canes, and walkers, resulting in nine categories of pedestrians: pedestrians, cane users, two types of walker users, whether walking or resting, five types of wheelchair users, including wheelchair users, people pushing empty wheelchairs, and three types of users pushing occupied wheelchairs, including the entire pushing group, the pusher and the person seated on the wheelchair. To establish a benchmark, seven object detection models (Faster R-CNN, CenterNet, YOLOX, DETR, Deformable DETR, DINO, and RT-DETR) and three tracking algorithms (ByteTrack, BOT-SORT, and OC-SORT) were implemented under the MMDetection framework. Experimental results show that YOLOX, Deformable DETR, and Faster R-CNN achieve the best detection performance, while the differences among the three trackers are relatively small. The PMMA dataset is publicly available at https://doi.org/10.5683/SP3/XJPQUG, and the video processing and model training code is available at https://github.com/DatasetPMMA/PMMA.

---

### The Complexity of Bayesian Network Learning: Revisiting the Superstructure

Authors: Robert Ganian, Viktoriia Korchemna
Published: 2026-02-10
Categories: cs.DS, cs.AI
arXiv: https://arxiv.org/abs/2602.10253v1

We investigate the parameterized complexity of Bayesian Network Structure Learning (BNSL), a classical problem that has received significant attention in empirical but also purely theoretical studies. We follow up on previous works that have analyzed the complexity of BNSL w.r.t. the so-called superstructure of the input. While known results imply that BNSL is unlikely to be fixed-parameter tractable even when parameterized by the size of a vertex cover in the superstructure, here we show that a different kind of parameterization - notably by the size of a feedback edge set - yields fixed-parameter tractability. We proceed by showing that this result can be strengthened to a localized version of the feedback edge set, and provide corresponding lower bounds that complement previous results to provide a complexity classification of BNSL w.r.t. virtually all well-studied graph parameters. We then analyze how the complexity of BNSL depends on the representation of the input. In particular, while the bulk of past theoretical work on the topic assumed the use of the so-called non-zero representation, here we prove that if an additive representation can be used instead then BNSL becomes fixed-parameter tractable even under significantly milder restrictions to the superstructure, notably when parameterized by the treewidth alone. Last but not least, we show how our results can be extended to the closely related problem of Polytree Learning.

---

### Modeling Programming Skills with Source Code Embeddings for Context-aware Exercise Recommendation

Authors: Carlos Eduardo P. Silva, João Pedro M. Sena, Julio C. S. Reis, André G. Santos, Lucas N. Ferreira
Published: 2026-02-10
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.10249v1

In this paper, we propose a context-aware recommender system that models students' programming skills using embeddings of the source code they submit throughout a course. These embeddings predict students' skills across multiple programming topics, producing profiles that are matched to the skills required by unseen homework problems. To generate recommendations, we compute the cosine similarity between student profiles and problem skill vectors, ranking exercises according to their alignment with each student's current abilities. We evaluated our approach using real data from students and exercises in an introductory programming course at our university. First, we assessed the effectiveness of our source code embeddings for predicting skills, comparing them with token-based and graph-based alternatives. Results showed that Jina embeddings outperformed TF-IDF, CodeBERT-cpp, and GraphCodeBERT across most skills. Additionally, we evaluated the system's ability to recommend exercises aligned with weekly course content by analyzing student submissions collected over seven course offerings. Our approach consistently produced more suitable recommendations than baselines based on correctness or solution time, indicating that predicted programming skills provide a stronger signal for problem recommendation.

---

### KORAL: Knowledge Graph Guided LLM Reasoning for SSD Operational Analysis

Authors: Mayur Akewar, Sandeep Madireddy, Dongsheng Luo, Janki Bhimani
Published: 2026-02-10
Categories: cs.DC, cs.AI
arXiv: https://arxiv.org/abs/2602.10246v1

Solid State Drives (SSDs) are critical to datacenters, consumer platforms, and mission-critical systems. Yet diagnosing their performance and reliability is difficult because data are fragmented and time-disjoint, and existing methods demand large datasets and expert input while offering only limited insights. Degradation arises not only from shifting workloads and evolving architectures but also from environmental factors such as temperature, humidity, and vibration. We present KORAL, a knowledge driven reasoning framework that integrates Large Language Models (LLMs) with a structured Knowledge Graph (KG) to generate insights into SSD operations. Unlike traditional approaches that require extensive expert input and large datasets, KORAL generates a Data KG from fragmented telemetry and integrates a Literature KG that already organizes knowledge from literature, reports, and traces. This turns unstructured sources into a queryable graph and telemetry into structured knowledge, and both the Graphs guide the LLM to deliver evidence-based, explainable analysis aligned with the domain vocabulary and constraints. Evaluation using real production traces shows that the KORAL delivers expert-level diagnosis and recommendations, supported by grounded explanations that improve reasoning transparency, guide operator decisions, reduce manual effort, and provide actionable insights to improve service quality. To our knowledge, this is the first end-to-end system that combines LLMs and KGs for full-spectrum SSD reasoning including Descriptive, Predictive, Prescriptive, and What-if analysis. We release the generated SSD-specific KG to advance reproducible research in knowledge-based storage system analysis. GitHub Repository: https://github.com/Damrl-lab/KORAL

---

### XSPLAIN: XAI-enabling Splat-based Prototype Learning for Attribute-aware INterpretability

Authors: Dominik Galus, Julia Farganus, Tymoteusz Zapala, Mikołaj Czachorowski, Piotr Borycki, Przemysław Spurek, Piotr Syga
Published: 2026-02-10
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.10239v1

3D Gaussian Splatting (3DGS) has rapidly become a standard for high-fidelity 3D reconstruction, yet its adoption in multiple critical domains is hindered by the lack of interpretability of the generation models as well as classification of the Splats. While explainability methods exist for other 3D representations, like point clouds, they typically rely on ambiguous saliency maps that fail to capture the volumetric coherence of Gaussian primitives. We introduce XSPLAIN, the first ante-hoc, prototype-based interpretability framework designed specifically for 3DGS classification. Our approach leverages a voxel-aggregated PointNet backbone and a novel, invertible orthogonal transformation that disentangles feature channels for interpretability while strictly preserving the original decision boundaries. Explanations are grounded in representative training examples, enabling intuitive ``this looks like that'' reasoning without any degradation in classification performance. A rigorous user study (N=51) demonstrates a decisive preference for our approach: participants selected XSPLAIN explanations 48.4\% of the time as the best, significantly outperforming baselines $(p<0.001)$, showing that XSPLAIN provides transparency and user trust. The source code for this work is available at: https://github.com/Solvro/ml-splat-xai

---

### Learning to Evict from Key-Value Cache

Authors: Luca Moschella, Laura Manduchi, Ozan Sener
Published: 2026-02-10
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2602.10238v2

The growing size of Large Language Models (LLMs) makes efficient inference challenging, primarily due to the memory demands of the autoregressive Key-Value (KV) cache. Existing eviction or compression methods reduce cost but rely on heuristics, such as recency or past attention scores, which serve only as indirect proxies for a token's future utility and introduce computational overhead. We reframe KV cache eviction as a reinforcement learning (RL) problem: learning to rank tokens by their predicted usefulness for future decoding. To this end, we introduce KV Policy (KVP), a framework of lightweight per-head RL agents trained on pre-computed generation traces using only key and value vectors. Each agent learns a specialized eviction policy guided by a holistic reward, derived from future utility, that evaluates the quality of the ranking across all cache budgets, requiring no modifications to the underlying LLM or additional inference. Evaluated across two model families on the long-context benchmark RULER (up to 128K tokens) and the multi-turn dialogue benchmark OASST2-4k, KVP significantly outperforms strong baselines. Zero-shot tests on standard downstream tasks (BoolQ, LongBench passage retrieval, GovReport) further show that KVP generalizes beyond its training distribution and to considerably longer sequence lengths. These results demonstrate that learning to predict future token utility is a powerful and scalable paradigm for adaptive KV cache management.

---

### Transforming Police-Car Swerving for Mitigating Isolated Stop-and-Go Traffic Waves: A Practice-Oriented Jam-Absorption Driving Strategy

Authors: Zhengbing He
Published: 2026-02-10
Categories: physics.soc-ph, cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2602.10234v3

Stop-and-go traffic waves, a major form of freeway congestion, impose severe and persistent adverse impacts, including reduced traffic efficiency, increased safety risks, and elevated vehicle emissions. Among various freeway traffic management strategies, jam-absorption driving (JAD), in which a dedicated vehicle performs "slow-in" and "fast-out" maneuvers before being captured by a stop-and-go wave, has been proposed as a promising approach to suppressing the propagation of such waves. However, most existing JAD strategies remain impractical, primarily due to the lack of consideration of implementation vehicles and operational conditions. Inspired by real-world observations of police-car swerving behavior, this paper first introduces the Single-Vehicle Double-Detector Jam-Absorption Driving (SD-JAD) problem and then proposes a practical JAD strategy based on a definition of the JAD Triangle, transforming such behavior into a traffic control strategy capable of suppressing the propagation of an isolated stop-and-go wave. Five key parameters that significantly affect the proposed strategy, namely JAD speed, inflow traffic speed, wave width, wave speed, and in-wave speed, are identified and systematically analyzed. Using a SUMO-based simulation as an illustrative example, we further demonstrate how these parameters can be measured in practice using only two stationary roadside traffic detectors. The results show that the proposed JAD strategy successfully suppresses the propagation of a stop-and-go wave without triggering secondary waves. This paper is expected to take a significant step toward the practical implementation of JAD, advancing it from a theoretical concept to a feasible and deployable traffic management strategy.

---

### ImprovEvolve: Basin-Hopping Meets LLM-Guided Evolutionary Search

Authors: Alexey Kravatskiy, Valentin Khrulkov, Ivan Oseledets
Published: 2026-02-10
Categories: cs.NE, cs.AI, math.CA, math.MG, math.OC
arXiv: https://arxiv.org/abs/2602.10233v2

LLM-guided evolutionary computation, most notably AlphaEvolve, has been remarkably successful in discovering novel mathematical constructions by solving challenging optimization problems. The standard approach is to evolve a monolithic program that directly outputs a candidate solution. We present ImprovEvolve, an algorithmic alternative that drastically reduces cognitive load on the LLM. Instead of prompting the model for an end-to-end optimizer, we evolve a program with three specialized operators of initialization, local improvement, and perturbation. We then approach the optimum by iteratively applying local improvements and intensity-scheduled perturbations, effectively driving a basin-hopping search with LLM-evolved subroutines. For hexagon in hexagon packing, ImprovEvolve discovers new state-of-the-art packings of 11, 12, 15, and 16 hexagons, and additionally for 14, 17, and 23 hexagons after minimal expert tuning of the generated code. For the second autocorrelation inequality, the evolved and human-scaled program pushes the lower bound from 0.96102 to 0.96258. For spherical codes, the ImprovEvolve program lowers the best-known maximum cosine for the majority of 90 randomly chosen diverse state-of-the-art spherical codes, achieving relative improvements of up to 2.4%.

---

### Risk-Equalized Differentially Private Synthetic Data: Protecting Outliers by Controlling Record-Level Influence

Authors: Amir Asiaee, Chao Yan, Zachary B. Abrams, Bradley A. Malin
Published: 2026-02-10
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.10232v1

When synthetic data is released, some individuals are harder to protect than others. A patient with a rare disease combination or a transaction with unusual characteristics stands out from the crowd. Differential privacy provides worst-case guarantees, but empirical attacks -- particularly membership inference -- succeed far more often against such outliers, especially under moderate privacy budgets and with auxiliary information. This paper introduces risk-equalized DP synthesis, a framework that prioritizes protection for high-risk records by reducing their influence on the learned generator. The mechanism operates in two stages: first, a small privacy budget estimates each record's "outlierness"; second, a DP learning procedure weights each record inversely to its risk score. Under Gaussian mechanisms, a record's privacy loss is proportional to its influence on the output -- so deliberately shrinking outliers' contributions yields tighter per-instance privacy bounds for precisely those records that need them most. We prove end-to-end DP guarantees via composition and derive closed-form per-record bounds for the synthesis stage (the scoring stage adds a uniform per-record term). Experiments on simulated data with controlled outlier injection show that risk-weighting substantially reduces membership inference success against high-outlierness records; ablations confirm that targeting -- not random downweighting -- drives the improvement. On real-world benchmarks (Breast Cancer, Adult, German Credit), gains are dataset-dependent, highlighting the interplay between scorer quality and synthesis pipeline.

---

### Blockwise Advantage Estimation for Multi-Objective RL with Verifiable Rewards

Authors: Kirill Pavlenko, Alexander Golubev, Simon Karasik, Boris Yangel
Published: 2026-02-10
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.10231v1

Group Relative Policy Optimization (GRPO) assigns a single scalar advantage to all tokens in a completion. For structured generations with explicit segments and objectives, this couples unrelated reward signals across segments, leading to objective interference and misattributed credit. We propose Blockwise Advantage Estimation, a family of GRPO-compatible methods that assigns each objective its own advantage and applies it only to the tokens in the corresponding text block, reducing reliance on hand-designed scalar rewards and scaling naturally to additional objectives. A key challenge is estimating advantages for later blocks whose rewards are conditioned on sampled prefixes; standard unbiased approaches require expensive nested rollouts from intermediate states. Concretely, we introduce an Outcome-Conditioned Baseline that approximates intermediate state values using only within-group statistics by stratifying samples according to a prefix-derived intermediate outcome. On math tasks with uncertainty estimation, our method mitigates reward interference, is competitive with a state-of-the-art reward-designed approach, and preserves test-time gains from confidence-weighted ensembling. More broadly, it provides a modular recipe for optimizing sequential objectives in structured generations without additional rollouts.

---

### Encode Once, Decode Never: Reusing Audio LM Internals for Efficient Temporal Localization

Authors: Joseph An, Phillip Keung, Jiaqi Wang, Orevaoghene Ahia, Noah A. Smith
Published: 2026-02-10
Categories: cs.LG, cs.SD, eess.AS
arXiv: https://arxiv.org/abs/2602.10230v2

Audio language models process input audio into rich frame-level representations, but the standard approach to temporal localization generates timestamps as sequences of text tokens, which discards the frame-level representations in favor of autoregressive decoding. However, generating timestamps as tokens is slow and not parallelizable, and tends to hallucinate when producing timestamps outside the training distribution. We propose internal frame-level reuse, a method that trains audio LMs to reuse their own internal audio representations for temporal localization directly, bypassing token generation altogether. We introduce a lightweight prediction head trained via different frame-level objectives: a binary frame classifier and a novel inhomogeneous Poisson process (IHP) loss that models temporal event intensity. Across word localization, speaker diarization, and event localization tasks, our approach can achieve a >50x inference speedup over token-based generation and demonstrates robust length generalization, maintaining high accuracy on out-of-distribution audio durations where token-based models collapse completely. We find that reusing audio frame-level representations yields localization accuracies comparable to (and often better than) finetuned token-based baselines.

---

### Latent Thoughts Tuning: Bridging Context and Reasoning with Fused Information in Latent Tokens

Authors: Weihao Liu, Dehai Min, Lu Cheng
Published: 2026-02-10
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.10229v2

While explicit Chain-of-Thought (CoT) equips Large Language Models (LLMs) with strong reasoning capabilities, it constrains the model's thoughts to a discrete vocabulary space. Recently, reasoning in continuous latent space has emerged as a promising alternative, but current paradigms suffer from feature collapse and instability due to distribution mismatch when recurrently reusing hidden states, or alignment issues when relying on assistant models. To address this, we propose Latent Thoughts Tuning (LT-Tuning), a post-training framework that redefines how latent thoughts are constructed and deployed. Instead of relying solely on raw hidden states, our method introduces a Context-Prediction-Fusion mechanism that jointly leverages contextual hidden states and predictive semantic guidance from the vocabulary embedding space. Combined with a progressive three-stage curriculum learning pipeline, LT-Tuning also enables dynamic switching between latent and explicit thinking modes. Experiments demonstrate that our method outperforms existing latent reasoning baselines, effectively mitigating feature collapse and achieving robust reasoning accuracy.

---

### PRISM: Differentially Private Synthetic Data with Structure-Aware Budget Allocation for Prediction

Authors: Amir Asiaee, Chao Yan, Zachary B. Abrams, Bradley A. Malin
Published: 2026-02-10
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.10228v1

Differential privacy (DP) provides a mathematical guarantee limiting what an adversary can learn about any individual from released data. However, achieving this protection typically requires adding noise, and noise can accumulate when many statistics are measured. Existing DP synthetic data methods treat all features symmetrically, spreading noise uniformly even when the data will serve a specific prediction task. We develop a prediction-centric approach operating in three regimes depending on available structural knowledge. In the causal regime, when the causal parents of $Y$ are known and distribution shift is expected, we target the parents for robustness. In the graphical regime, when a Bayesian network structure is available and the distribution is stable, the Markov blanket of $Y$ provides a sufficient feature set for optimal prediction. In the predictive regime, when no structural knowledge exists, we select features via differentially private methods without claiming to recover causal or graphical structure. We formalize this as PRISM, a mechanism that (i) identifies a predictive feature subset according to the appropriate regime, (ii) constructs targeted summary statistics, (iii) allocates budget to minimize an upper bound on prediction error, and (iv) synthesizes data via graphical-model inference. We prove end-to-end privacy guarantees and risk bounds. Empirically, task-aware allocation improves prediction accuracy compared to generic synthesizers. Under distribution shift, targeting causal parents achieves AUC $\approx 0.73$ while correlation-based selection collapses to chance ($\approx 0.49$).

---

### Self-Evolving Recommendation System: End-To-End Autonomous Model Optimization With LLM Agents

Authors: Haochen Wang, Yi Wu, Daryl Chang, Li Wei, Lukasz Heldt
Published: 2026-02-10
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.10226v3

Optimizing large-scale machine learning systems, such as recommendation models for global video platforms, requires navigating a massive hyperparameter search space and, more critically, designing sophisticated optimizers, architectures, and reward functions to capture nuanced user behaviors. Achieving substantial improvements in these areas is a non-trivial task, traditionally relying on extensive manual iterations to test new hypotheses. We propose a self-evolving system that leverages Large Language Models (LLMs), specifically those from Google's Gemini family, to autonomously generate, train, and deploy high-performing, complex model changes within an end-to-end automated workflow. The self-evolving system consists of an Offline Agent (Fast Loop) that performs high-throughput hypothesis generation to optimize for proxy metrics, and an Online Agent (Slow Loop) that validates candidates against delayed north star business metrics in live production. Our agents act as specialized Machine Learning Engineers (MLEs): they exhibit deep reasoning capabilities, discovering novel improvements in optimization algorithms and model architecture, and formulating innovative reward functions that target long-term user engagement. The effectiveness of this approach is demonstrated through several successful production launches at YouTube, confirming that autonomous, LLM-driven evolution can surpass traditional engineering workflows in both development velocity and model performance.

---

### Quantum Integrated Sensing and Computation with Indefinite Causal Order

Authors: Ivana Nikoloska
Published: 2026-02-10
Categories: quant-ph, cs.AI, cs.IT, eess.SP
arXiv: https://arxiv.org/abs/2602.10225v1

Quantum operations with indefinite causal order (ICO) represent a framework in quantum information processing where the relative order between two events can be indefinite. In this paper, we investigate whether sensing and computation, two canonical tasks in quantum information processing, can be carried out within the ICO framework. We propose a scheme for integrated sensing and computation that uses the same quantum state for both tasks. The quantum state is represented as an agent that performs state observation and learns a function of the state to make predictions via a parametric model. Under an ICO operation, the agent experiences a superposition of orders, one in which it performs state observation and then executes the required computation steps, and another in which the agent carries out the computation first and then performs state observation. This is distinct from prevailing information processing and machine intelligence paradigms where information acquisition and learning follow a strict causal order, with the former always preceding the latter. We provide experimental results and we show that the proposed scheme can achieve small training and testing losses on a representative task in magnetic navigation.

---

### Internalizing Meta-Experience into Memory for Guided Reinforcement Learning in Large Language Models

Authors: Shiting Huang, Zecheng Li, Yu Zeng, Qingnan Ren, Zhen Fang, Qisheng Su, Kou Shi, Lin Chen, Zehui Chen, Feng Zhao
Published: 2026-02-10
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.10224v1

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an effective approach for enhancing the reasoning capabilities of Large Language Models (LLMs). Despite its efficacy, RLVR faces a meta-learning bottleneck: it lacks mechanisms for error attribution and experience internalization intrinsic to the human learning cycle beyond practice and verification, thereby limiting fine-grained credit assignment and reusable knowledge formation. We term such reusable knowledge representations derived from past errors as meta-experience. Based on this insight, we propose Meta-Experience Learning (MEL), a novel framework that incorporates self-distilled meta-experience into the model's parametric memory. Building upon standard RLVR, we introduce an additional design that leverages the LLM's self-verification capability to conduct contrastive analysis on paired correct and incorrect trajectories, identify the precise bifurcation points where reasoning errors arise, and summarize them into generalizable meta-experience. The meta-experience is further internalized into the LLM's parametric memory by minimizing the negative log-likelihood, which induces a language-modeled reward signal that bridges correct and incorrect reasoning trajectories and facilitates effective knowledge reuse. Experimental results demonstrate that MEL achieves consistent improvements on benchmarks, yielding 3.92%--4.73% Pass@1 gains across varying model sizes.

---

### DEGMC: Denoising Diffusion Models Based on Riemannian Equivariant Group Morphological Convolutions

Authors: El Hadji S. Diop, Thierno Fall, Mohamed Daoudi
Published: 2026-02-10
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.10221v1

In this work, we address two major issues in recent Denoising Diffusion Probabilistic Models (DDPM): {\bf 1)} geometric key feature extraction and {\bf 2)} network equivariance. Since the DDPM prediction network relies on the U-net architecture, which is theoretically only translation equivariant, we introduce a geometric approach combined with an equivariance property of the more general Euclidean group, which includes rotations, reflections, and permutations. We introduce the notion of group morphological convolutions in Riemannian manifolds, which are derived from the viscosity solutions of first-order Hamilton-Jacobi-type partial differential equations (PDEs) that act as morphological multiscale dilations and erosions. We add a convection term to the model and solve it using the method of characteristics. This helps us better capture nonlinearities, represent thin geometric structures, and incorporate symmetries into the learning process. Experimental results on the MNIST, RotoMNIST, and CIFAR-10 datasets show noticeable improvements compared to the baseline DDPM model.

---

### ACE-RTL: When Agentic Context Evolution Meets RTL-Specialized LLMs

Authors: Chenhui Deng, Zhongzhi Yu, Guan-Ting Liu, Nathaniel Pinckney, Brucek Khailany, Haoxing Ren
Published: 2026-02-10
Categories: cs.AR, cs.LG
arXiv: https://arxiv.org/abs/2602.10218v2

Recent advances in LLMs have sparked growing interest in applying them to hardware design automation, particularly for accurate RTL code generation. Prior efforts follow two largely independent paths: (i) training domain-adapted RTL models to internalize hardware semantics, (ii) developing agentic systems that leverage frontier generic LLMs guided by simulation feedback. However, these two paths exhibit complementary strengths and weaknesses. In this work, we present ACE-RTL that unifies both directions through Agentic Context Evolution (ACE). ACE-RTL integrates an RTL-specialized LLM, trained on a large-scale dataset of 1.7 million RTL samples, with a frontier reasoning LLM through three synergistic components: the generator, reflector, and coordinator. These components iteratively refine RTL code toward functional correctness. We further analyze a parallel scaling strategy that reduces wall-clock iterations to first success by exploring diverse debugging trajectories concurrently. On the CVDP benchmark, ACE-RTL achieves up to a 41.02% pass rate improvement over 14 competitive baselines.

---

### Temper-Then-Tilt: Principled Unlearning for Generative Models through Tempering and Classifier Guidance

Authors: Jacob L. Block, Mehryar Mohri, Aryan Mokhtari, Sanjay Shakkottai
Published: 2026-02-10
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.10217v2

We study machine unlearning in large generative models by framing the task as density ratio estimation to a target distribution rather than supervised fine-tuning. While classifier guidance is a standard approach for approximating this ratio and can succeed in general, we show it can fail to faithfully unlearn with finite samples when the forget set represents a sharp, concentrated data distribution. To address this, we introduce Temper-Then-Tilt Unlearning (T3-Unlearning), which freezes the base model and applies a two-step inference procedure: (i) tempering the base distribution to flatten high-confidence spikes, and (ii) tilting the tempered distribution using a lightweight classifier trained to distinguish retain from forget samples. Our theoretical analysis provides finite-sample guarantees linking the surrogate classifier's risk to unlearning error, proving that tempering is necessary to successfully unlearn for concentrated distributions. Empirical evaluations on the TOFU benchmark show that T3-Unlearning improves forget quality and generative utility over existing baselines, while training only a fraction of the parameters with a minimal runtime.

---

### ELROND: Exploring and decomposing intrinsic capabilities of diffusion models

Authors: Paweł Skierś, Tomasz Trzciński, Kamil Deja
Published: 2026-02-10
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.10216v1

A single text prompt passed to a diffusion model often yields a wide range of visual outputs determined solely by stochastic process, leaving users with no direct control over which specific semantic variations appear in the image. While existing unsupervised methods attempt to analyze these variations via output features, they omit the underlying generative process. In this work, we propose a framework to disentangle these semantic directions directly within the input embedding space. To that end, we collect a set of gradients obtained by backpropagating the differences between stochastic realizations of a fixed prompt that we later decompose into meaningful steering directions with either Principal Components Analysis or Sparse Autoencoder. Our approach yields three key contributions: (1) it isolates interpretable, steerable directions for precise, fine-grained control over a single concept; (2) it effectively mitigates mode collapse in distilled models by reintroducing lost diversity; and (3) it establishes a novel estimator for concept complexity under a specific model, based on the dimensionality of the discovered subspace.

---

### Rank-Accuracy Trade-off for LoRA: A Gradient-Flow Analysis

Authors: Michael Rushka, Diego Klabjan
Published: 2026-02-10
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.10212v1

Previous empirical studies have shown that LoRA achieves accuracy comparable to full-parameter methods on downstream fine-tuning tasks, even for rank-1 updates. By contrast, the theoretical underpinnings of the dependence of LoRA's accuracy on update rank remain relatively unexplored. In this work, we compare the accuracy of rank-r LoRA updates against full-parameter updates for fine-tuning tasks from a dynamical systems perspective. We perform gradient flow analysis in both full-rank and low-rank regimes to establish explicit relationships between rank and accuracy for two loss functions under LoRA. While gradient flow equations for LoRA are presented in prior work, we rigorously derive their form and show that they are identical for simultaneous and sequential LoRA parameter updates. We then use the resulting dynamical system equations to obtain closed-form relationships between LoRA rank and accuracy for trace-squared and Frobenius-norm low-rank approximation loss functions.

---

### How Much Reasoning Do Retrieval-Augmented Models Add beyond LLMs? A Benchmarking Framework for Multi-Hop Inference over Hybrid Knowledge

Authors: Junhong Lin, Bing Zhang, Song Wang, Ziyan Liu, Dan Gutfreund, Julian Shun, Yada Zhu
Published: 2026-02-10
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.10210v1

Large language models (LLMs) continue to struggle with knowledge-intensive questions that require up-to-date information and multi-hop reasoning. Augmenting LLMs with hybrid external knowledge, such as unstructured text and structured knowledge graphs, offers a promising alternative to costly continual pretraining. As such, reliable evaluation of their retrieval and reasoning capabilities becomes critical. However, many existing benchmarks increasingly overlap with LLM pretraining data, which means answers or supporting knowledge may already be encoded in model parameters, making it difficult to distinguish genuine retrieval and reasoning from parametric recall. We introduce HybridRAG-Bench, a framework for constructing benchmarks to evaluate retrieval-intensive, multi-hop reasoning over hybrid knowledge. HybridRAG-Bench automatically couples unstructured text and structured knowledge graph representations derived from recent scientific literature on arXiv, and generates knowledge-intensive question-answer pairs grounded in explicit reasoning paths. The framework supports flexible domain and time-frame selection, enabling contamination-aware and customizable evaluation as models and knowledge evolve. Experiments across three domains (artificial intelligence, governance and policy, and bioinformatics) demonstrate that HybridRAG-Bench rewards genuine retrieval and reasoning rather than parametric recall, offering a principled testbed for evaluating hybrid knowledge-augmented reasoning systems. We release our code and data at github.com/junhongmit/HybridRAG-Bench.

---

### Neural Network Quantum Field Theory from Transformer Architectures

Authors: Dmitry S. Ageev, Yulia A. Ageeva
Published: 2026-02-10
Categories: cs.LG, cond-mat.dis-nn, hep-th
arXiv: https://arxiv.org/abs/2602.10209v1

We propose a neural-network construction of Euclidean scalar quantum field theories from transformer attention heads, defining $n$-point correlators by averaging over random network parameters in the NN-QFT framework. For a single attention head, shared random softmax weights couple different width coordinates and induce non-Gaussian field statistics that persist in the infinite-width limit $d_k\to\infty$. We compute the two-point function in an attention-weight representation and show how Euclidean-invariant kernels can be engineered via random-feature token embeddings. We then analyze the connected four-point function and identify an "independence-breaking" contribution, expressible as a covariance over query-key weights, which remains finite at infinite width. Finally, we show that summing many independent heads with standard $1/N_h$ normalization suppresses connected non-Gaussian correlators as $1/N_h$, yielding a Gaussian NN-QFT in the large-head limit.

---

### Adaptive Optimization via Momentum on Variance-Normalized Gradients

Authors: Francisco Patitucci, Aryan Mokhtari
Published: 2026-02-10
Categories: cs.LG, math.OC
arXiv: https://arxiv.org/abs/2602.10204v2

We introduce MVN-Grad (Momentum on Variance-Normalized Gradients), an Adam-style optimizer that improves stability and performance by combining two complementary ideas: variance-based normalization and momentum applied after normalization. MVN-Grad scales each coordinate by an exponential moving average of gradient uncertainty and applies momentum to the resulting normalized gradients, removing the cross-time coupling between stale momentum and a stochastic normalizer present in standard Adam-type updates. We prove that this decoupling yields smaller one-step conditional update variance than momentum-then-normalize variance methods, and that MVN-Grad has a uniformly bounded response to isolated gradient spikes. In low-variance regimes, we further show that variance normalization avoids sign-type collapse of second-moment scaling and can yield accelerated convergence. Beyond these comparisons, we prove a general nonconvex convergence guarantee for MVN-Grad under bounded-gradient stochastic assumptions. On CIFAR-100 and GPT-style language modeling, MVN-Grad matches or improves on Adam, AdaBelief, and LaProp, delivering smoother training and better generalization at the cost of one additional state tensor.

---

### Adaptive Optimization via Momentum on Variance-Normalized Gradients

Authors: Francisco Patitucci, Aryan Mokhtari
Published: 2026-02-10
Categories: cs.LG, math.OC
arXiv: https://arxiv.org/abs/2602.10204v1

We introduce MVN-Grad (Momentum on Variance-Normalized Gradients), an Adam-style optimizer that improves stability and performance by combining two complementary ideas: variance-based normalization and momentum applied after normalization. MVN-Grad scales each coordinate by an exponential moving average of gradient uncertainty and applies momentum to the resulting normalized gradients, eliminating the cross-time coupling between stale momentum and a stochastic normalizer present in standard Adam-type updates. We prove that this decoupling yields strictly smaller one-step conditional update variance than momentum-then-normalize variance methods under standard noise assumptions, and that MVN-Grad is robust to outliers: it has a uniformly bounded response to single gradient spikes. In low-variance regimes, we further show variance normalization avoids sign-type collapse associated with second-moment scaling and can yield accelerated convergence. Across CIFAR-100 image classification and GPT-style language modeling benchmarks, MVN-Grad matches or outperforms Adam, AdaBelief, and LaProp, delivering smoother training and improved generalization with no added overhead.

---

### Versor: A Geometric Sequence Architecture

Authors: Truong Minh Huy, Edward Hirst
Published: 2026-02-10
Categories: cs.LG, cs.AI, hep-th
arXiv: https://arxiv.org/abs/2602.10195v2

A novel sequence architecture is introduced, Versor, which uses Conformal Geometric Algebra (CGA) in place of traditional linear operations to achieve structural generalization and significant performance improvements on a variety of tasks, while offering improved interpretability and efficiency. By embedding states in the $Cl_{4,1}$ manifold and evolving them via geometric transformations (rotors), Versor natively represents $SE(3)$-equivariant relationships without requiring explicit structural encoding. Versor is validated on chaotic N-body dynamics, topological reasoning, and standard multimodal benchmarks (CIFAR-10, WikiText-103), consistently outperforming Transformers, Graph Networks, and geometric baselines (GATr, EGNN). Key results include: orders-of-magnitude fewer parameters ($200\times$ vs. Transformers); interpretable attention decomposing into proximity and orientational components; zero-shot scale generalization (0.993 vs. 0.070 MCC for ViT); and featuring a Recursive Rotor Accumulator (RRA) for $O(L)$ linear temporal complexity in dynamical systems, and a Geometric Product Attention (GPA) mechanism for $O(L^{2})$ global relational modeling, allowing for task-specific architectural pruning or hybridization depending on the required scale. In out-of-distribution tests, Versor maintains stable predictions while Transformers fail catastrophically. Custom Clifford kernels achieve a cumulative over $100\times$ speedup via bit-masked contraction and specialized Matrix Isomorphism kernels, reducing per-step latency to 1.05 ms and outperforming highly-optimized Transformer baselines.

---

### Signature-Kernel Based Evaluation Metrics for Robust Probabilistic and Tail-Event Forecasting

Authors: Benjamin R. Redhead, Thomas L. Lee, Peng Gu, Víctor Elvira, Amos Storkey
Published: 2026-02-10
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2602.10182v1

Probabilistic forecasting is increasingly critical across high-stakes domains, from finance and epidemiology to climate science. However, current evaluation frameworks lack a consensus metric and suffer from two critical flaws: they often assume independence across time steps or variables, and they demonstrably lack sensitivity to tail events, the very occurrences that are most pivotal in real-world decision-making. To address these limitations, we propose two kernel-based metrics: the signature maximum mean discrepancy (Sig-MMD) and our novel censored Sig-MMD (CSig-MMD). By leveraging the signature kernel, these metrics capture complex inter-variate and inter-temporal dependencies and remain robust to missing data. Furthermore, CSig-MMD introduces a censoring scheme that prioritizes a forecaster's capability to predict tail events while strictly maintaining properness, a vital property for a good scoring rule. These metrics enable a more reliable evaluation of direct multi-step forecasting, facilitating the development of more robust probabilistic algorithms.

---

### When the Prompt Becomes Visual: Vision-Centric Jailbreak Attacks for Large Image Editing Models

Authors: Jiacheng Hou, Yining Sun, Ruochong Jin, Haochen Han, Fangming Liu, Wai Kin Victor Chan, Alex Jinpeng Wang
Published: 2026-02-10
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.10179v2

Recent advances in large image editing models have shifted the paradigm from text-driven instructions to vision-prompt editing, where user intent is inferred directly from visual inputs such as marks, arrows, and visual-text prompts. While this paradigm greatly expands usability, it also introduces a critical and underexplored safety risk: the attack surface itself becomes visual. In this work, we propose Vision-Centric Jailbreak Attack (VJA), the first visual-to-visual jailbreak attack that conveys malicious instructions purely through visual inputs. To systematically study this emerging threat, we introduce IESBench, a safety-oriented benchmark for image editing models. Extensive experiments on IESBench demonstrate that VJA effectively compromises state-of-the-art commercial models, achieving attack success rates of up to 80.9% on Nano Banana Pro and 70.1% on GPT-Image-1.5. To mitigate this vulnerability, we propose a training-free defense based on introspective multimodal reasoning, which substantially improves the safety of poorly aligned models to a level comparable with commercial systems, without auxiliary guard models and with negligible computational overhead. Our findings expose new vulnerabilities, provide both a benchmark and practical defense to advance safe and trustworthy modern image editing systems. Warning: This paper contains offensive images created by large image editing models.

---

### Towards Autonomous Mathematics Research

Authors: Tony Feng, Trieu H. Trinh, Garrett Bingham, Dawsen Hwang, Yuri Chervonyi, Junehyuk Jung, Joonkyung Lee, Carlo Pagano, Sang-hyun Kim, Federico Pasqualotto, Sergei Gukov, Jonathan N. Lee et al.
Published: 2026-02-10
Categories: cs.LG, cs.AI, cs.CL, cs.CY
arXiv: https://arxiv.org/abs/2602.10177v3

Recent advances in foundational models have yielded reasoning systems capable of achieving a gold-medal standard at the International Mathematical Olympiad. The transition from competition-level problem-solving to professional research, however, requires navigating vast literature and constructing long-horizon proofs. In this work, we introduce Aletheia, a math research agent that iteratively generates, verifies, and revises solutions end-to-end in natural language. Specifically, Aletheia is powered by an advanced version of Gemini Deep Think for challenging reasoning problems, a novel inference-time scaling law that extends beyond Olympiad-level problems, and intensive tool use to navigate the complexities of mathematical research. We demonstrate the capability of Aletheia from Olympiad problems to PhD-level exercises and most notably, through several distinct milestones in AI-assisted mathematics research: (a) a research paper (Feng26) generated by AI without any human intervention in calculating certain structure constants in arithmetic geometry called eigenweights; (b) a research paper (LeeSeo26) demonstrating human-AI collaboration in proving bounds on systems of interacting particles called independent sets; and (c) an extensive semi-autonomous evaluation (Feng et al., 2026a) of 700 open problems on Bloom's Erdos Conjectures database, including autonomous solutions to four open questions. In order to help the public better understand the developments pertaining to AI and mathematics, we suggest quantifying standard levels of autonomy and novelty of AI-assisted results, as well as propose a novel concept of human-AI interaction cards for transparency. We conclude with reflections on human-AI collaboration in mathematics and share all prompts as well as model outputs at https://github.com/google-deepmind/superhuman/tree/main/aletheia.

---

### Dissecting Performative Prediction: A Comprehensive Survey

Authors: Thomas Kehrenberg, Javier Sanguino, Jose A. Lozano, Novi Quadrianto
Published: 2026-02-10
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2602.10176v1

The field of performative prediction had its beginnings in 2020 with the seminal paper "Performative Prediction" by Perdomo et al., which established a novel machine learning setup where the deployment of a predictive model causes a distribution shift in the environment, which in turn causes a mismatch between the distribution expected by the predictive model and the real distribution. This shift is defined by a so-called distribution map. In the half-decade since, a literature has emerged which has, among other things, introduced new solution concepts to the original setup, extended the setup, offered new theoretical analyses, and examined the intersection of performative prediction and other established fields. In this survey, we first lay out the performative prediction setting and explain the different optimization targets: performative stability and performative optimality. We introduce a new way of classifying different performative prediction settings, based on how much information is available about the distribution map. We survey existing implementations of distribution maps and existing methods to address the problem of performative prediction, while examining different ways to categorize them. Finally, we point out known and previously unknown connections that can be drawn to other fields, in the hopes of stimulating future research.

---

### ArtisanGS: Interactive Tools for Gaussian Splat Selection with AI and Human in the Loop

Authors: Clement Fuji Tsang, Anita Hu, Or Perel, Carsten Kolve, Maria Shugrina
Published: 2026-02-10
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.10173v1

Representation in the family of 3D Gaussian Splats (3DGS) are growing into a viable alternative to traditional graphics for an expanding number of application, including recent techniques that facilitate physics simulation and animation. However, extracting usable objects from in-the-wild captures remains challenging and controllable editing techniques for this representation are limited. Unlike the bulk of emerging techniques, focused on automatic solutions or high-level editing, we introduce an interactive suite of tools centered around versatile Gaussian Splat selection and segmentation. We propose a fast AI-driven method to propagate user-guided 2D selection masks to 3DGS selections. This technique allows for user intervention in the case of errors and is further coupled with flexible manual selection and segmentation tools. These allow a user to achieve virtually any binary segmentation of an unstructured 3DGS scene. We evaluate our toolset against the state-of-the-art for Gaussian Splat selection and demonstrate their utility for downstream applications by developing a user-guided local editing approach, leveraging a custom Video Diffusion Model. With flexible selection tools, users have direct control over the areas that the AI can modify. Our selection and editing tools can be used for any in-the-wild capture without additional optimization.

---

### Cosmo3DFlow: Wavelet Flow Matching for Spatial-to-Spectral Compression in Reconstructing the Early Universe

Authors: Md. Khairul Islam, Zeyu Xia, Ryan Goudjil, Jialu Wang, Arya Farahi, Judy Fox
Published: 2026-02-10
Categories: astro-ph.IM, cs.AI
arXiv: https://arxiv.org/abs/2602.10172v2

Reconstructing the early universe from the evolved present-day universe is a challenging and computationally demanding problem in modern astrophysics. We devise a novel generative framework, Cosmo3DFlow, designed to address dimensionality and sparsity, the critical bottlenecks inherent in current state-of-the-art methods for cosmological inference. By integrating 3D Discrete Wavelet Transform (DWT) with flow matching, we effectively represent high-dimensional cosmological structures. The Wavelet Transform addresses the ``void problem'' by translating spatial emptiness into spectral sparsity. It decouples high-frequency details from low-frequency structures, and wavelet-space velocity fields facilitate stable ordinary differential equation (ODE) solvers with large step sizes. Using large-scale cosmological $N$-body simulations at $128^3$ resolution, we achieve up to $46\times$ faster sampling than diffusion models. Our results enable initial conditions to be sampled in seconds, compared to minutes for previous methods.

---

### EvoCodeBench: A Human-Performance Benchmark for Self-Evolving LLM-Driven Coding Systems

Authors: Wentao Zhang, Jianfeng Wang, Liheng Liang, Yilei Zhao, HaiBin Wen, Zhe Zhao
Published: 2026-02-10
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2602.10171v1

As large language models (LLMs) continue to advance in programming tasks, LLM-driven coding systems have evolved from one-shot code generation into complex systems capable of iterative improvement during inference. However, existing code benchmarks primarily emphasize static correctness and implicitly assume fixed model capability during inference. As a result, they do not capture inference-time self-evolution, such as whether accuracy and efficiency improve as an agent iteratively refines its solutions. They also provide limited accounting of resource costs and rarely calibrate model performance against that of human programmers. Moreover, many benchmarks are dominated by high-resource languages, leaving cross-language robustness and long-tail language stability underexplored. Therefore, we present EvoCodeBench, a benchmark for evaluating self-evolving LLM-driven coding systems across programming languages with direct comparison to human performance. EvoCodeBench tracks performance dynamics, measuring solution correctness alongside efficiency metrics such as solving time, memory consumption, and improvement algorithmic design over repeated problem-solving attempts. To ground evaluation in a human-centered reference frame, we directly compare model performance with that of human programmers on the same tasks, enabling relative performance assessment within the human ability distribution. Furthermore, EvoCodeBench supports multiple programming languages, enabling systematic cross-language and long-tail stability analyses under a unified protocol. Our results demonstrate that self-evolving systems exhibit measurable gains in efficiency over time, and that human-relative and multi-language analyses provide insights unavailable through accuracy alone. EvoCodeBench establishes a foundation for evaluating coding intelligence in evolving LLM-driven systems.

---

### EVA: Towards a universal model of the immune system

Authors: Scienta Team, Ethan Bandasack, Vincent Bouget, Apolline Bruley, Yannis Cattan, Charlotte Claye, Matthew Corney, Julien Duquesne, Karim El Kanbi, Aziz Fouché, Pierre Marschall, Francesco Strozzi
Published: 2026-02-10
Categories: q-bio.QM, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.10168v2

The effective application of foundation models to translational research in immune-mediated diseases requires multimodal patient-level representations that can capture complex phenotypes emerging from multicellular interactions. Yet most current biological foundation models focus only on single-cell resolution and are evaluated on technical metrics often disconnected from actual drug development tasks and challenges. Here, we introduce EVA, the first cross-species, multimodal foundation model of immunology and inflammation, a therapeutic area where shared pathogenic mechanisms create unique opportunities for transfer learning. EVA harmonizes transcriptomics data across species, platforms, and resolutions, and integrates histology data to produce rich, unified patient representations. We establish clear scaling laws, demonstrating that increasing model size and compute translates to improvements in both pretraining and downstream tasks performance. We introduce a comprehensive evaluation suite of 39 tasks spanning the drug development pipeline: zero-shot target efficacy and gene function prediction for discovery, cross-species or cross-diseases molecular perturbations for preclinical development, and patient stratification with treatment response prediction or disease activity prediction for clinical trials applications. We benchmark EVA against several state-of-the-art biological foundation models and baselines on these tasks, and demonstrate state-of-the-art results on each task category. Using mechanistic interpretability, we further identify biological meaningful features, revealing intertwined representations across species and technologies. We release an open version of EVA for transcriptomics to accelerate research on immune-mediated diseases.

---

### Anatomy-Preserving Latent Diffusion for Generation of Brain Segmentation Masks with Ischemic Infarct

Authors: Lucia Borrego, Vajira Thambawita, Marco Ciuffreda, Ines del Val, Alejandro Dominguez, Josep Munuera
Published: 2026-02-10
Categories: eess.IV, cs.AI
arXiv: https://arxiv.org/abs/2602.10167v1

The scarcity of high-quality segmentation masks remains a major bottleneck for medical image analysis, particularly in non-contrast CT (NCCT) neuroimaging, where manual annotation is costly and variable. To address this limitation, we propose an anatomy-preserving generative framework for the unconditional synthesis of multi-class brain segmentation masks, including ischemic infarcts. The proposed approach combines a variational autoencoder trained exclusively on segmentation masks to learn an anatomical latent representation, with a diffusion model operating in this latent space to generate new samples from pure noise. At inference, synthetic masks are obtained by decoding denoised latent vectors through the frozen VAE decoder, with optional coarse control over lesion presence via a binary prompt. Qualitative results show that the generated masks preserve global brain anatomy, discrete tissue semantics, and realistic variability, while avoiding the structural artifacts commonly observed in pixel-space generative models. Overall, the proposed framework offers a simple and scalable solution for anatomy-aware mask generation in data-scarce medical imaging scenarios.

---

### Omni-Safety under Cross-Modality Conflict: Vulnerabilities, Dynamics Mechanisms and Efficient Alignment

Authors: Kun Wang, Zherui Li, Zhenhong Zhou, Yitong Zhang, Yan Mi, Kun Yang, Yiming Zhang, Junhao Dong, Zhongxiang Sun, Qiankun Li, Yang Liu
Published: 2026-02-10
Categories: cs.CR, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.10161v1

Omni-modal Large Language Models (OLLMs) greatly expand LLMs' multimodal capabilities but also introduce cross-modal safety risks. However, a systematic understanding of vulnerabilities in omni-modal interactions remains lacking. To bridge this gap, we establish a modality-semantics decoupling principle and construct the AdvBench-Omni dataset, which reveals a significant vulnerability in OLLMs. Mechanistic analysis uncovers a Mid-layer Dissolution phenomenon driven by refusal vector magnitude shrinkage, alongside the existence of a modal-invariant pure refusal direction. Inspired by these insights, we extract a golden refusal vector using Singular Value Decomposition and propose OmniSteer, which utilizes lightweight adapters to modulate intervention intensity adaptively. Extensive experiments show that our method not only increases the Refusal Success Rate against harmful inputs from 69.9% to 91.2%, but also effectively preserves the general capabilities across all modalities. Our code is available at: https://github.com/zhrli324/omni-safety-research.

---

### AD$^2$: Analysis and Detection of Adversarial Threats in Visual Perception for End-to-End Autonomous Driving Systems

Authors: Ishan Sahu, Somnath Hazra, Somak Aditya, Soumyajit Dey
Published: 2026-02-10
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.10160v1

End-to-end autonomous driving systems have achieved significant progress, yet their adversarial robustness remains largely underexplored. In this work, we conduct a closed-loop evaluation of state-of-the-art autonomous driving agents under black-box adversarial threat models in CARLA. Specifically, we consider three representative attack vectors on the visual perception pipeline: (i) a physics-based blur attack induced by acoustic waves, (ii) an electromagnetic interference attack that distorts captured images, and (iii) a digital attack that adds ghost objects as carefully crafted bounded perturbations on images. Our experiments on two advanced agents, Transfuser and Interfuser, reveal severe vulnerabilities to such attacks, with driving scores dropping by up to 99% in the worst case, raising valid safety concerns. To help mitigate such threats, we further propose a lightweight Attack Detection model for Autonomous Driving systems (AD$^2$) based on attention mechanisms that capture spatial-temporal consistency. Comprehensive experiments across multi-camera inputs on CARLA show that our detector achieves superior detection capability and computational efficiency compared to existing approaches.

---