# Research Papers — 2026-01 · bundle page 10 of 189

> Full-text markdown of papers #451–500 of 9403 published in 2026-01, newest first. AI-readable mirrors of the full 9403-paper 2026-01 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-01/page/10
[← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/9.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-01/page/11.md)

### GRIP2: A Robust and Powerful Deep Knockoff Method for Feature Selection

Authors: Bob Junyi Zou, Lu Tian
Published: 2026-01-30
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2602.00218v1

Identifying truly predictive covariates while strictly controlling false discoveries remains a fundamental challenge in nonlinear, highly correlated, and low signal-to-noise regimes, where deep learning based feature selection methods are most attractive. We propose Group Regularization Importance Persistence in 2 Dimensions (GRIP2), a deep knockoff feature importance statistic that integrates first-layer feature activity over a two-dimensional regularization surface controlling both sparsity strength and sparsification geometry. To approximate this surface integral in a single training run, we introduce efficient block-stochastic sampling, which aggregates feature activity magnitudes across diverse regularization regimes along the optimization trajectory. The resulting statistics are antisymmetric by construction, ensuring finite-sample FDR control. In extensive experiments on synthetic and semi-real data, GRIP2 demonstrates improved robustness to feature correlation and noise level: in high correlation and low signal-to-noise ratio regimes where standard deep learning based feature selectors may struggle, our method retains high power and stability. Finally, on real-world HIV drug resistance data, GRIP2 recovers known resistance-associated mutations with power better than established linear baselines, confirming its reliability in practice.

---

### Dispersion Loss Counteracts Embedding Condensation and Improves Generalization in Small Language Models

Authors: Chen Liu, Xingzhi Sun, Xi Xiao, Alexandre Van Tassel, Ke Xu, Kristof Reimann, Danqi Liao, Mark Gerstein, Tianyang Wang, Xiao Wang, Smita Krishnaswamy
Published: 2026-01-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.00217v3

Large language models (LLMs) achieve remarkable performance through ever-increasing parameter counts, but scaling incurs steep computational costs. To better understand LLM scaling, we study representational differences between LLMs and their smaller counterparts, with the goal of replicating the representational qualities of larger models in smaller models. We observe a geometric phenomenon which we term $\textbf{embedding condensation}$, where token embeddings collapse into a narrow cone-like subspace in some language models. Through systematic analyses across multiple Transformer families, we show that small models such as $\texttt{GPT2}$ and $\texttt{Qwen3-0.6B}$ exhibit severe condensation, whereas larger models such as $\texttt{GPT2-xl}$ and $\texttt{Qwen3-32B}$ are more resistant to this phenomenon. Additional observations show that embedding condensation is not reliably mitigated by knowledge distillation from larger models. To fight against it, we formulate a dispersion loss that explicitly encourages embedding dispersion during training. Experiments demonstrate that it mitigates condensation, recovers dispersion patterns seen in larger models, and yields performance gains across 10 benchmarks. We believe this work offers a principled path toward improving smaller Transformers without additional parameters.

---

### Development of a Cacao Disease Identification and Management App Using Deep Learning

Authors: Zaldy Pagaduan, Jason Occidental, Nathaniel Duro, Dexielito Badilles, Eleonor Palconit
Published: 2026-01-30
Categories: cs.CV, cs.CY, eess.IV
arXiv: https://arxiv.org/abs/2602.00216v1

Smallholder cacao producers often rely on outdated farming techniques and face significant challenges from pests and diseases, unlike larger plantations with more resources and expertise. In the Philippines, cacao farmers have limited access to data, information, and good agricultural practices. This study addresses these issues by developing a mobile application for cacao disease identification and management that functions offline, enabling use in remote areas where farms are mostly located. The core of the system is a deep learning model trained to identify cacao diseases accurately. The trained model is integrated into the mobile app to support farmers in field diagnosis. The disease identification model achieved a validation accuracy of 96.93% while the model for detecting cacao black pod infection levels achieved 79.49% validation accuracy. Field testing of the application showed an agreement rate of 84.2% compared with expert cacao technician assessments. This approach empowers smallholder farmers by providing accessible, technology-enabled tools to improve cacao crop health and productivity.

---

### A Renderer-Enabled Framework for Computing Parameter Estimation Lower Bounds in Plenoptic Imaging Systems

Authors: Abhinav V. Sambasivan, Liam J. Coulter, Richard G. Paxman, Jarvis D. Haupt
Published: 2026-01-30
Categories: eess.IV, cs.CV, eess.SP
arXiv: https://arxiv.org/abs/2602.00215v1

This work focuses on assessing the information-theoretic limits of scene parameter estimation in plenoptic imaging systems. A general framework to compute lower bounds on the parameter estimation error from noisy plenoptic observations is presented, with a particular focus on passive indirect imaging problems, where the observations do not contain line-of-sight information about the parameter(s) of interest. Using computer graphics rendering software to synthesize the often-complicated dependence among parameter(s) of interest and observations, i.e. the forward model, the proposed framework evaluates the Hammersley-Chapman-Robbins bound to establish lower bounds on the variance of any unbiased estimator of the unknown parameters. The effects of inexact rendering of the true forward model on the computed lower bounds are also analyzed, both theoretically and via simulations. Experimental evaluations compare the computed lower bounds with the performance of the Maximum Likelihood Estimator on a canonical object localization problem, showing that the lower bounds computed via the framework proposed here are indicative of the true underlying fundamental limits in several nominally representative scenarios.

---

### A Geometric Multimodal Foundation Model Integrating Bp-MRI and Clinical Reports in Prostate Cancer Classification

Authors: Juan A. Olmos, Antoine Manzanera, Fabio Martínez
Published: 2026-01-30
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.00214v1

Prostate cancer (PCa) is one of the most common cancers in men worldwide. Bi-parametric MRI (bp-MRI) and clinical variables are crucial for PCa identification and improving treatment decisions. However, this process is subjective to expert interpretations. Furthermore, most existing computer-aided diagnosis methods focus on imaging-based models, overlooking the clinical context and suffering from data scarcity, limiting their ability to learn robust representations. We propose a geometric multimodal Foundation Model (FM), named MFM-Geom, that learns representations from bp-MRI and clinical reports, encoding visual findings and information from the context of clinical variables. In the representations classification head, the approach leverages symmetric positive definite (SPD) matrices and Riemannian deep learning to integrate imaging-text representations from a biomedical multimodal FM. Using 10% of the training data, MFM-Geom outperformed baseline class token embedding-based classification (+8.3%, AUC-PR of 90.67). Generalization on external dataset confirmed the robustness of fine-tuning biomedical FM, achieving an AUC-PR of 90.6.

---

### TessPay: Verify-then-Pay Infrastructure for Trusted Agentic Commerce

Authors: Mehul Goenka, Tejas Pathak, Siddharth Asthana
Published: 2026-01-30
Categories: cs.CR, cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2602.00213v1

The global economy is entering the era of Agentic Commerce, where autonomous agents can discover services, negotiate prices, and transact value. However adoption towards agentic commerce faces a foundational trust gap: current systems are built for direct human interactions rather than agent-driven operations. It lacks core primitives across three critical stages of agentic transactions. First, Task Delegation lacks means to translate user intent into defined scopes, discover appropriate agents, and securely authorize actions. Second, Payment Settlement for tasks is processed before execution, lacking verifiable evidence to validate the agent's work. Third, Audit Mechanisms fail to capture the full transaction lifecycle, preventing clear accountability for disputes. While emerging standards address fragments of this trust gap, there still remains a critical need for a unified infrastructure that binds the entire transaction lifecycle. To resolve this gap, we introduce TessPay, a unified infrastructure that replaces implicit trust with a 'Verify-then-Pay' architecture. It is a two plane architecture separating control and verification from settlement. TessPay operationalizes trust across four distinct stages: Before execution, agents are anchored in a canonical registry and user intent is captured as verifiable mandates, enabling stakeholder accountability. During execution, funds are locked in escrow while the agent executes the task and generates cryptographic evidence (TLS Notary, TEE etc.) to support Proof of Task Execution (PoTE). At settlement, the system verifies this evidence and releases funds only when the PoTE satisfies verification predicates; modular rail adapters ensure this PoTE-gated escrow remains chain-agnostic across heterogeneous payment rails. After settlement, TessPay preserves a tamper-evident audit trail to enable clear accountability for dispute resolution.

---

### Deep Learning Based CNN Model for Automated Detection of Pneumonia from Chest XRay Images

Authors: Sathish Krishna Anumula, Vetrivelan Tamilmani, Aniruddha Arjun Singh, Dinesh Rajendran, Venkata Deepak Namburi
Published: 2026-01-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.00212v1

Pneumonia has been one of the major causes of morbidities and mortality in the world and the prevalence of this disease is disproportionately high among the pediatric and elderly populations especially in resources trained areas Fast and precise diagnosis is a prerequisite for successful clinical intervention but due to inter observer variation fatigue among experts and a shortage of qualified radiologists traditional approaches that rely on manual interpretation of chest radiographs are frequently constrained To address these problems this paper introduces a unified automated diagnostic model using a custom Convolutional Neural Network CNN that can recognize pneumonia in chest Xray images with high precision and at minimal computational expense In contrast like other generic transfer learning based models which often possess redundant parameters the offered architecture uses a tailor made depth wise separable convolutional design which is optimized towards textural characteristics of grayscale medical images Contrast Limited Adaptive Histogram Equalization CLAHE and geometric augmentation are two significant preprocessing techniques used to ensure that the system does not experience class imbalance and is more likely to generalize The system is tested using a dataset of 5863 anterior posterior chest Xrays.

---

### Interpretable Unsupervised Deformable Image Registration via Confidence-bound Multi-Hop Visual Reasoning

Authors: Zafar Iqbal, Anwar Ul Haq, Srimannarayana Grandhi
Published: 2026-01-30
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.00211v1

Unsupervised deformable image registration requires aligning complex anatomical structures without reference labels, making interpretability and reliability critical. Existing deep learning methods achieve considerable accuracy but often lack transparency, leading to error drift and reduced clinical trust. We propose a novel Multi-Hop Visual Chain of Reasoning (VCoR) framework that reformulates registration as a progressive reasoning process. Inspired by the iterative nature of clinical decision-making, each visual reasoning hop integrates a Localized Spatial Refinement (LSR) module to enrich feature representations and a Cross-Reference Attention (CRA) mechanism that leads the iterative refinement process, preserving anatomical consistency. This multi-hop strategy enables robust handling of large deformations and produces a transparent sequence of intermediate predictions with a theoretical bound. Beyond accuracy, our framework offers built-in interpretability by estimating uncertainty via the stability and convergence of deformation fields across hops. Extensive evaluations on two challenging public datasets, DIR-Lab 4D CT (lung) and IXI T1-weighted MRI (brain), demonstrate that VCoR achieves competitive registration accuracy while offering rich intermediate visualizations and confidence measures. By embedding an implicit visual reasoning paradigm, we present an interpretable, reliable, and clinically viable unsupervised medical image registration.

---

### Analyzing Shapley Additive Explanations to Understand Anomaly Detection Algorithm Behaviors and Their Complementarity

Authors: Jordan Levy, Paul Saves, Moncef Garouani, Nicolas Verstaevel, Benoit Gaudou
Published: 2026-01-30
Categories: cs.LG, cs.AI, cs.IR, math.ST, stat.ML
arXiv: https://arxiv.org/abs/2602.00208v3

Unsupervised anomaly detection is a challenging problem due to the diversity of data distributions and the lack of labels. Ensemble methods are often adopted to mitigate these challenges by combining multiple detectors, which can reduce individual biases and increase robustness. Yet building an ensemble that is genuinely complementary remains challenging, since many detectors rely on similar decision cues and end up producing redundant anomaly scores. As a result, the potential of ensemble learning is often limited by the difficulty of identifying models that truly capture different types of irregularities. To address this, we propose a methodology for characterizing anomaly detectors through their decision mechanisms. Using SHapley Additive exPlanations, we quantify how each model attributes importance to input features, and we use these attribution profiles to measure similarity between detectors. We show that detectors with similar explanations tend to produce correlated anomaly scores and identify largely overlapping anomalies. Conversely, explanation divergence reliably indicates complementary detection behavior. Our results demonstrate that explanation-driven metrics offer a different criterion than raw outputs for selecting models in an ensemble. However, we also demonstrate that diversity alone is insufficient; high individual model performance remains a prerequisite for effective ensembles. By explicitly targeting explanation diversity while maintaining model quality, we are able to construct ensembles that are more diverse, more complementary, and ultimately more effective for unsupervised anomaly detection.

---

### Reducing Class-Wise Performance Disparity via Margin Regularization

Authors: Beier Zhu, Kesen Zhao, Jiequan Cui, Qianru Sun, Yuan Zhou, Xun Yang, Hanwang Zhang
Published: 2026-01-30
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2602.00205v1

Deep neural networks often exhibit substantial disparities in class-wise accuracy, even when trained on class-balanced data, posing concerns for reliable deployment. While prior efforts have explored empirical remedies, a theoretical understanding of such performance disparities in classification remains limited. In this work, we present Margin Regularization for Performance Disparity Reduction (MR$^2$), a theoretically principled regularization for classification by dynamically adjusting margins in both the logit and representation spaces. Our analysis establishes a margin-based, class-sensitive generalization bound that reveals how per-class feature variability contributes to error, motivating the use of larger margins for hard classes. Guided by this insight, MR$^2$ optimizes per-class logit margins proportional to feature spread and penalizes excessive representation margins to enhance intra-class compactness. Experiments on seven datasets, including ImageNet, and diverse pre-trained backbones (MAE, MoCov2, CLIP) demonstrate that MR$^2$ not only improves overall accuracy but also significantly boosts hard class performance without trading off easy classes, thus reducing performance disparity. Code is available at: https://github.com/BeierZhu/MR2

---

### Semantic-Aware Advanced Persistent Threat Detection Using Autoencoders on LLM-Encoded System Logs

Authors: Waleed Khan Mohammed, Zahirul Arief Irfan Bin Shahrul Anuar, Mousa Sufian Mousa Mitani, Hezerul Abdul Karim, Nouar AlDahoul
Published: 2026-01-30
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2602.00204v1

Advanced Persistent Threats (APTs) are among the most challenging cyberattacks to detect. They are carried out by highly skilled attackers who carefully study their targets and operate in a stealthy, long-term manner. Because APTs exhibit "low-and-slow" behavior, traditional statistical methods and shallow machine learning techniques often fail to detect them. Previous research on APT detection has explored machine learning approaches and provenance graph analysis. However, provenance-based methods often fail to capture the semantic intent behind system activities. This paper proposes a novel anomaly detection approach that leverages semantic embeddings generated by Large Language Models (LLMs). The method enhances APT detection by extracting meaningful semantic representations from unstructured system log data. First, raw system logs are transformed into high-dimensional semantic embeddings using a pre-trained transformer model. These embeddings are then analyzed using an Autoencoder (AE) to identify anomalous and potentially malicious patterns. The proposed method is evaluated using the DARPA Transparent Computing (TC) dataset, which contains realistic APT attack scenarios generated by red teams in live environments. Experimental results show that the AE trained on LLM-derived embeddings outperforms widely used unsupervised baseline methods, including Isolation Forest (IForest), One-Class Support Vector Machine (OC-SVM), and Principal Component Analysis (PCA). Performance is measured using the Area Under the Receiver Operating Characteristic Curve (AUC-ROC), where the proposed approach consistently achieves superior results, even in complex threat scenarios. These findings highlight the importance of semantic understanding in detecting non-linear and stealthy attack behaviors that are often missed by conventional detection techniques.

---

### Vision-Language Model Purified Semi-Supervised Semantic Segmentation for Remote Sensing Images

Authors: Shanwen Wang, Xin Sun, Danfeng Hong, Fei Zhou
Published: 2026-01-30
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.00202v1

The semi-supervised semantic segmentation (S4) can learn rich visual knowledge from low-cost unlabeled images. However, traditional S4 architectures all face the challenge of low-quality pseudo-labels, especially for the teacher-student framework.We propose a novel SemiEarth model that introduces vision-language models (VLMs) to address the S4 issues for the remote sensing (RS) domain. Specifically, we invent a VLM pseudo-label purifying (VLM-PP) structure to purify the teacher network's pseudo-labels, achieving substantial improvements. Especially in multi-class boundary regions of RS images, the VLM-PP module can significantly improve the quality of pseudo-labels generated by the teacher, thereby correctly guiding the student model's learning. Moreover, since VLM-PP equips VLMs with open-world capabilities and is independent of the S4 architecture, it can correct mispredicted categories in low-confidence pseudo-labels whenever a discrepancy arises between its prediction and the pseudo-label. We conducted extensive experiments on multiple RS datasets, which demonstrate that our SemiEarth achieves SOTA performance. More importantly, unlike previous SOTA RS S4 methods, our model not only achieves excellent performance but also offers good interpretability. The code is released at https://github.com/wangshanwen001/SemiEarth.

---

### Reducing Memorisation in Generative Models via Riemannian Bayesian Inference

Authors: Johanna Marie Gegenfurtner, Albert Kjøller Jacobsen, Naima Elosegui Borras, Alejandro Valverde Mahou, Georgios Arvanitidis
Published: 2026-01-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.00199v1

Modern generative models can produce realistic samples, however, balancing memorisation and generalisation remains an open problem. We approach this challenge from a Bayesian perspective by focusing on the parameter space of flow matching and diffusion models and constructing a predictive posterior that better captures the variability of the data distribution. In particular, we capture the geometry of the loss using a Riemannian metric and leverage a flexible approximate posterior that adapts to the local structure of the loss landscape. This approach allows us to sample generative models that resemble the original model, but exhibit reduced memorisation. Empirically, we demonstrate that the proposed approach reduces memorisation while preserving generalisation. Further, we provide a theoretical analysis of our method, which explains our findings. Overall, our work illustrates how considering the geometry of the loss enables effective use of the parameter space, even for complex high-dimensional generative models.

---

### SCALED : Surrogate-gradient for Codec-Aware Learning of Downsampling in ABR Streaming

Authors: Esteban Pesnel, Julien Le Tanou, Michael Ropert, Thomas Maugey, Aline Roumy
Published: 2026-01-30
Categories: eess.IV, cs.AI, cs.MM
arXiv: https://arxiv.org/abs/2602.00198v1

The rapid growth in video consumption has introduced significant challenges to modern streaming architectures. Over-the-Top (OTT) video delivery now predominantly relies on Adaptive Bitrate (ABR) streaming, which dynamically adjusts bitrate and resolution based on client-side constraints such as display capabilities and network bandwidth. This pipeline typically involves downsampling the original high-resolution content, encoding and transmitting it, followed by decoding and upsampling on the client side. Traditionally, these processing stages have been optimized in isolation, leading to suboptimal end-to-end rate-distortion (R-D) performance. The advent of deep learning has spurred interest in jointly optimizing the ABR pipeline using learned resampling methods. However, training such systems end-to-end remains challenging due to the non-differentiable nature of standard video codecs, which obstructs gradient-based optimization. Recent works have addressed this issue using differentiable proxy models, based either on deep neural networks or hybrid coding schemes with differentiable components such as soft quantization, to approximate the codec behavior. While differentiable proxy codecs have enabled progress in compression-aware learning, they remain approximations that may not fully capture the behavior of standard, non-differentiable codecs. To our knowledge, there is no prior evidence demonstrating the inefficiencies of using standard codecs during training. In this work, we introduce a novel framework that enables end-to-end training with real, non-differentiable codecs by leveraging data-driven surrogate gradients derived from actual compression errors. It facilitates the alignment between training objectives and deployment performance. Experimental results show a 5.19\% improvement in BD-BR (PSNR) compared to codec-agnostic training approaches, consistently across the entire rate-distortion convex hull spanning multiple downsampling ratios.

---

### Rank-and-Reason: Multi-Agent Collaboration Accelerates Zero-Shot Protein Mutation Prediction

Authors: Yang Tan, Yuanxi Yu, Can Wu, Bozitao Zhong, Mingchen Li, Guisheng Fan, Jiankang Zhu, Yafeng Liang, Nanqing Dong, Liang Hong
Published: 2026-01-30
Categories: q-bio.QM, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.00197v2

Zero-shot mutation prediction is vital for low-resource protein engineering, yet existing protein language models (PLMs) often yield statistically confident results that ignore fundamental biophysical constraints. Currently, selecting candidates for wet-lab validation relies on manual expert auditing of PLM outputs, a process that is inefficient, subjective, and highly dependent on domain expertise. To address this, we propose Rank-and-Reason (VenusRAR), a two-stage agentic framework to automate this workflow and maximize expected wet-lab fitness. In the Rank-Stage, a Computational Expert and Virtual Biologist aggregate a context-aware multi-modal ensemble, establishing a new Spearman correlation record of 0.551 (vs. 0.518) on ProteinGym. In the Reason-Stage, an agentic Expert Panel employs chain-of-thought reasoning to audit candidates against geometric and structural constraints, improving the Top-5 Hit Rate by up to 367% on ProteinGym-DMS99. The wet-lab validation on Cas12i3 nuclease further confirms the framework's efficacy, achieving a 46.7% positive rate and identifying two novel mutants with 4.23-fold and 5.05-fold activity improvements. Code and datasets are released on GitHub (https://github.com/ai4protein/VenusRAR/).

---

### On the calibration of survival models with competing risks

Authors: Julie Alberge, Tristan Haugomat, Gaël Varoquaux, Judith Abécassis
Published: 2026-01-30
Categories: stat.ME, cs.AI, math.ST
arXiv: https://arxiv.org/abs/2602.00194v1

Survival analysis deals with modeling the time until an event occurs, and accurate probability estimates are crucial for decision-making, particularly in the competing-risks setting where multiple events are possible. While recent work has addressed calibration in standard survival analysis, the competing-risks setting remains under-explored as it is harder (the calibration applies to both probabilities across classes and time horizon). We show that existing calibration measures are not suited to the competing-risk setting and that recent models do not give well-behaved probabilities. To address this, we introduce a dedicated framework with two novel calibration measures that are minimized for oracle estimators (i.e., both measures are proper). We also introduce some methods to estimate, test, and correct the calibration. Our recalibration methods yield good probabilities while preserving discrimination.

---

### AI-Generated Image Detectors Overrely on Global Artifacts: Evidence from Inpainting Exchange

Authors: Elif Nebioglu, Emirhan Bilgiç, Adrian Popescu
Published: 2026-01-30
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.00192v1

Modern deep learning-based inpainting enables realistic local image manipulation, raising critical challenges for reliable detection. However, we observe that current detectors primarily rely on global artifacts that appear as inpainting side effects, rather than on locally synthesized content. We show that this behavior occurs because VAE-based reconstruction induces a subtle but pervasive spectral shift across the entire image, including unedited regions. To isolate this effect, we introduce Inpainting Exchange (INP-X), an operation that restores original pixels outside the edited region while preserving all synthesized content. We create a 90K test dataset including real, inpainted, and exchanged images to evaluate this phenomenon. Under this intervention, pretrained state-of-the-art detectors, including commercial ones, exhibit a dramatic drop in accuracy (e.g., from 91\% to 55\%), frequently approaching chance level. We provide a theoretical analysis linking this behavior to high-frequency attenuation caused by VAE information bottlenecks. Our findings highlight the need for content-aware detection. Indeed, training on our dataset yields better generalization and localization than standard inpainting. Our dataset and code are publicly available at https://github.com/emirhanbilgic/INP-X.

---

### GEPC: Group-Equivariant Posterior Consistency for Out-of-Distribution Detection in Diffusion Models

Authors: Yadang Alexis Rouzoumka, Jean Pinsolle, Eugénie Terreaux, Christèle Morisseau, Jean-Philippe Ovarlez, Chengfang Ren
Published: 2026-01-30
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2602.00191v2

Diffusion models learn a time-indexed score field $\mathbf{s}_θ(\mathbf{x}_t,t)$ that often inherits approximate equivariances (flips, rotations, circular shifts) from in-distribution (ID) data and convolutional backbones. Most diffusion-based out-of-distribution (OOD) detectors exploit score magnitude or local geometry (energies, curvature, covariance spectra) and largely ignore equivariances. We introduce Group-Equivariant Posterior Consistency (GEPC), a training-free probe that measures how consistently the learned score transforms under a finite group $\mathcal{G}$, detecting equivariance breaking even when score magnitude remains unchanged. At the population level, we propose the ideal GEPC residual, which averages an equivariance-residual functional over $\mathcal{G}$, and we derive ID upper bounds and OOD lower bounds under mild assumptions. GEPC requires only score evaluations and produces interpretable equivariance-breaking maps. On OOD image benchmark datasets, we show that GEPC achieves competitive or improved AUROC compared to recent diffusion-based baselines while remaining computationally lightweight. On high-resolution synthetic aperture radar imagery where OOD corresponds to targets or anomalies in clutter, GEPC yields strong target-background separation and visually interpretable equivariance-breaking maps. Code is available at https://github.com/RouzAY/gepc-diffusion/.

---

### From Gameplay Traces to Game Mechanics: Causal Induction with Large Language Models

Authors: Mohit Jiwatode, Alexander Dockhorn, Bodo Rosenhahn
Published: 2026-01-30
Categories: cs.AI, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2602.00190v1

Deep learning agents can achieve high performance in complex game domains without often understanding the underlying causal game mechanics. To address this, we investigate Causal Induction: the ability to infer governing laws from observational data, by tasking Large Language Models (LLMs) with reverse-engineering Video Game Description Language (VGDL) rules from gameplay traces. To reduce redundancy, we select nine representative games from the General Video Game AI (GVGAI) framework using semantic embeddings and clustering. We compare two approaches to VGDL generation: direct code generation from observations, and a two-stage method that first infers a structural causal model (SCM) and then translates it into VGDL. Both approaches are evaluated across multiple prompting strategies and controlled context regimes, varying the amount and form of information provided to the model, from just raw gameplay observations to partial VGDL specifications. Results show that the SCM-based approach more often produces VGDL descriptions closer to the ground truth than direct generation, achieving preference win rates of up to 81\% in blind evaluations and yielding fewer logically inconsistent rules. These learned SCMs can be used for downstream use cases such as causal reinforcement learning, interpretable agents, and procedurally generating novel but logically consistent games.

---

### LPIPS-AttnWav2Lip: Generic Audio-Driven lip synchronization for Talking Head Generation in the Wild

Authors: Zhipeng Chen, Xinheng Wang, Lun Xie, Haijie Yuan, Hang Pan
Published: 2026-01-30
Categories: cs.SD, cs.AI, cs.MM, eess.AS
arXiv: https://arxiv.org/abs/2602.00189v1

Researchers have shown a growing interest in Audio-driven Talking Head Generation. The primary challenge in talking head generation is achieving audio-visual coherence between the lips and the audio, known as lip synchronization. This paper proposes a generic method, LPIPS-AttnWav2Lip, for reconstructing face images of any speaker based on audio. We used the U-Net architecture based on residual CBAM to better encode and fuse audio and visual modal information. Additionally, the semantic alignment module extends the receptive field of the generator network to obtain the spatial and channel information of the visual features efficiently; and match statistical information of visual features with audio latent vector to achieve the adjustment and injection of the audio content information to the visual information. To achieve exact lip synchronization and to generate realistic high-quality images, our approach adopts LPIPS Loss, which simulates human judgment of image quality and reduces instability possibility during the training process. The proposed method achieves outstanding performance in terms of lip synchronization accuracy and visual quality as demonstrated by subjective and objective evaluation results. The code for the paper is available at the following link: https://github.com/FelixChan9527/LPIPS-AttnWav2Lip

---

### Learning to Price: Interpretable Attribute-Level Models for Dynamic Markets

Authors: Srividhya Sethuraman, Chandrashekar Lakshminarayanan
Published: 2026-01-30
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.00188v1

Dynamic pricing in high-dimensional markets poses fundamental challenges of scalability, uncertainty, and interpretability. Existing low-rank bandit formulations learn efficiently but rely on latent features that obscure how individual product attributes influence price. We address this by introducing an interpretable \emph{Additive Feature Decomposition-based Low-Dimensional Demand (\textbf{AFDLD}) model}, where product prices are expressed as the sum of attribute-level contributions and substitution effects are explicitly modeled. Building on this structure, we propose \textbf{ADEPT} (Additive DEcomposition for Pricing with cross-elasticity and Time-adaptive learning)-a projection-free, gradient-free online learning algorithm that operates directly in attribute space and achieves a sublinear regret of $\tilde{\mathcal{O}}(\sqrt{d}T^{3/4})$. Through controlled synthetic studies and real-world datasets, we show that ADEPT (i) learns near-optimal prices under dynamic market conditions, (ii) adapts rapidly to shocks and drifts, and (iii) yields transparent, attribute-level price explanations. The results demonstrate that interpretability and efficiency in autonomous pricing agents can be achieved jointly through structured, attribute-driven representations.

---

### SurfelSoup: Learned Point Cloud Geometry Compression With a Probablistic SurfelTree Representation

Authors: Tingyu Fan, Ran Gong, Yueyu Hu, Yao Wang
Published: 2026-01-30
Categories: eess.IV, cs.CV
arXiv: https://arxiv.org/abs/2602.00186v1

This paper presents SurfelSoup, an end-to-end learned surface-based framework for point cloud geometry compression, with surface-structured primitives for representation. It proposes a probabilistic surface representation, pSurfel, which models local point occupancies using a bounded generalized Gaussian distribution. In addition, the pSurfels are organized into an octree-like hierarchy, pSurfelTree, with a Tree Decision module that adaptively terminates the tree subdivision for rate-distortion optimal Surfel granularity selection. This formulation avoids redundant point-wise compression in smooth regions and produces compact yet smooth surface reconstructions. Experimental results under the MPEG common test condition show consistent gain on geometry compression over voxel-based baselines and MPEG standard G-PCC-GesTM-TriSoup, while providing visually superior reconstructions with smooth and coherent surface structures.

---

### QUASAR: A Universal Autonomous System for Atomistic Simulation and a Benchmark of Its Capabilities

Authors: Fengxu Yang, Jack D. Evans
Published: 2026-01-30
Categories: cond-mat.mtrl-sci, cs.AI
arXiv: https://arxiv.org/abs/2602.00185v2

The integration of large language models (LLMs) into materials science offers a transformative opportunity to streamline computational workflows, yet current agentic systems remain constrained by rigid, carefully crafted domain-specific tool-calling paradigms and narrowly scoped agents. In this work, we introduce QUASAR, a universal autonomous system for atomistic simulation designed to facilitate production-grade scientific discovery. QUASAR autonomously orchestrates complex multi-scale workflows across diverse methods, including density functional theory, machine learning potentials, molecular dynamics, and Monte Carlo simulations. The system incorporates robust mechanisms for adaptive planning, context-efficient memory management, and hybrid knowledge retrieval to navigate real-world research scenarios without human intervention. We benchmark QUASAR against a series of three-tiered tasks, progressing from routine tasks to frontier research challenges such as photocatalyst screening and novel material assessment. These results suggest that QUASAR can function as a general atomistic reasoning system rather than a task-specific automation framework. They also provide initial evidence supporting the potential deployment of agentic AI as a component of computational chemistry research workflows, while identifying areas requiring further development.

---

### Visible Singularities Guided Correlation Network for Limited-Angle CT Reconstruction

Authors: Yiyang Wen, Liu Shi, Zekun Zhou, WenZhe Shan, Qiegen Liu
Published: 2026-01-30
Categories: eess.IV, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2602.00184v1

Limited-angle computed tomography (LACT) offers the advantages of reduced radiation dose and shortened scanning time. Traditional reconstruction algorithms exhibit various inherent limitations in LACT. Currently, most deep learning-based LACT reconstruction methods focus on multi-domain fusion or the introduction of generic priors, failing to fully align with the core imaging characteristics of LACT-such as the directionality of artifacts and directional loss of structural information, which are caused by the absence of projection angles in certain directions. Inspired by the theory of visible and invisible singularities, taking into account the aforementioned core imaging characteristics of LACT, we propose a Visible Singularities Guided Correlation network for LACT reconstruction (VSGC). The design philosophy of VSGC consists of two core steps: First, extract VS edge features from LACT images and focus the model's attention on these VS. Second, establish correlations between the VS edge features and other regions of the image. Additionally, a multi-scale loss function with anisotropic constraint is employed to constrain the model to converge in multiple aspects. Finally, qualitative and quantitative validations are conducted on both simulated and real datasets to verify the effectiveness and feasibility of the proposed design. Particularly, in comparison with alternative methods, VSGC delivers more prominent performance in small angular ranges, with the PSNR improvement of 2.45 dB and the SSIM enhancement of 1.5\%. The code is publicly available at https://github.com/yqx7150/VSGC.

---

### RPP: A Certified Poisoned-Sample Detection Framework for Backdoor Attacks under Dataset Imbalance

Authors: Miao Lin, Feng Yu, Rui Ning, Lusi Li, Jiawei Chen, Qian Lou, Mengxin Zheng, Chunsheng Xin, Hongyi Wu
Published: 2026-01-30
Categories: cs.CR, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2602.00183v1

Deep neural networks are highly susceptible to backdoor attacks, yet most defense methods to date rely on balanced data, overlooking the pervasive class imbalance in real-world scenarios that can amplify backdoor threats. This paper presents the first in-depth investigation of how the dataset imbalance amplifies backdoor vulnerability, showing that (i) the imbalance induces a majority-class bias that increases susceptibility and (ii) conventional defenses degrade significantly as the imbalance grows. To address this, we propose Randomized Probability Perturbation (RPP), a certified poisoned-sample detection framework that operates in a black-box setting using only model output probabilities. For any inspected sample, RPP determines whether the input has been backdoor-manipulated, while offering provable within-domain detectability guarantees and a probabilistic upper bound on the false positive rate. Extensive experiments on five benchmarks (MNIST, SVHN, CIFAR-10, TinyImageNet and ImageNet10) covering 10 backdoor attacks and 12 baseline defenses show that RPP achieves significantly higher detection accuracy than state-of-the-art defenses, particularly under dataset imbalance. RPP establishes a theoretical and practical foundation for defending against backdoor attacks in real-world environments with imbalanced data.

---

### EigenAI: Deterministic Inference, Verifiable Results

Authors: David Ribeiro Alves, Vishnu Patankar, Matheus Pereira, Jamie Stephens, Nima Vaziri, Sreeram Kannan
Published: 2026-01-30
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2602.00182v1

EigenAI is a verifiable AI platform built on top of the EigenLayer restaking ecosystem. At a high level, it combines a deterministic large-language model (LLM) inference engine with a cryptoeconomically secured optimistic re-execution protocol so that every inference result can be publicly audited, reproduced, and, if necessary, economically enforced. An untrusted operator runs inference on a fixed GPU architecture, signs and encrypts the request and response, and publishes the encrypted log to EigenDA. During a challenge window, any watcher may request re-execution through EigenVerify; the result is then deterministically recomputed inside a trusted execution environment (TEE) with a threshold-released decryption key, allowing a public challenge with private data. Because inference itself is bit-exact, verification reduces to a byte-equality check, and a single honest replica suffices to detect fraud. We show how this architecture yields sovereign agents -- prediction-market judges, trading bots, and scientific assistants -- that enjoy state-of-the-art performance while inheriting security from Ethereum's validator base.

---

### CamReasoner: Reinforcing Camera Movement Understanding via Structured Spatial Reasoning

Authors: Hang Wu, Yujun Cai, Zehao Li, Haonan Ge, Bowen Sun, Junsong Yuan, Yiwei Wang
Published: 2026-01-30
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.00181v3

Understanding camera dynamics is a fundamental pillar of video spatial intelligence. However, existing multimodal models predominantly treat this task as a black-box classification, often confusing physically distinct motions by relying on superficial visual patterns rather than geometric cues. We present \textbf{CamReasoner}, a framework that reformulates camera movement understanding as a structured inference process to bridge the gap between perception and cinematic logic. Our approach centers on the Observation-Thinking-Answer (O-T-A) paradigm, which compels the model to articulate spatio-temporal observations and reason about motion patterns within an explicit reasoning block. To instill this capability, we construct a Large-scale Inference Trajectory Suite comprising 18k SFT reasoning chains and 38k RL feedback samples. To the best of our knowledge, \textbf{we are the first to employ RL for logical alignment in camera movement understanding}, ensuring motion inferences are grounded in structured visual reasoning rather than contextual guesswork. Built upon Qwen2.5-VL-7B, CamReasoner-7B improves binary classification accuracy from 73.8\% to 78.4\% and VQA accuracy from 60.9\% to 74.5\% over its backbone, consistently outperforming both proprietary and open-source baselines across multiple benchmarks.

---

### Spec-Driven Development:From Code to Contract in the Age of AI Coding Assistants

Authors: Deepak Babu Piskala
Published: 2026-01-30
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2602.00180v1

The rise of AI coding assistants has reignited interest in an old idea: what if specifications-not code-were the primary artifact of software development? Spec-driven development (SDD) inverts the traditional workflow by treating specifications as the source of truth and code as a generated or verified secondary artifact. This paper provides practitioners with a comprehensive guide to SDD, covering its principles, workflow patterns, and supporting tools. We present three levels of specification rigor-spec-first, spec-anchored, and spec-as-source-with clear guidance on when each applies. Through analysis of tools ranging from Behavior-Driven Development frameworks to modern AI-assisted toolkits like GitHub Spec Kit, we demonstrate how the spec-first philosophy maps to real implementations. We present case studies from API development, enterprise systems, and embedded software, illustrating how different domains apply SDD. We conclude with a decision framework helping practitioners determine when SDD provides value and when simpler approaches suffice.

---

### How Understanding Forecast Uncertainty Resolves the Explainability Problem in Machine Learning Models

Authors: Joseph L. Breeden
Published: 2026-01-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.00179v3

For applications of machine learning in critical decisions, explainability is a primary concern, and often a regulatory requirement. Local linear methods for generating explanations, such as LIME and SHAP, have been criticized for being unstable near decision boundaries. In this paper, we explain that such concerns reflect a misunderstanding of the problem. The forecast uncertainty is high at decision boundaries, so consequently, the explanatory instability is high. The correct approach is to change the sequence of events and questions being asked. Nonlinear models can be highly predictive in some regions while having little or no predictability in others. Therefore, the first question is whether a usable forecast exists. When there is a forecast with low enough uncertainty to be useful, an explanation can be sought via a local linear approximation. In such cases, the explanatory instability is correspondingly low. When no usable forecast exists, the decision must fall to a simpler overall model such as traditional logistic regression. Additionally, these results show that some methods that purport to be explainable everywhere, such as ReLU networks or any piecewise linear model, have only an illusory explainability, because the forecast uncertainty at the segment boundaries is too high to be useful. Explaining an unusable forecast is pointless.

---

### Posterior Continuation with Noise-Conditioned Frequency Exposure for Diffusion Inverse Problems

Authors: Feng Tian, Yixuan Li, Weili Zeng, Weitian Zhang, Yichao Yan, Xiaokang Yang
Published: 2026-01-30
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.00176v2

Diffusion posterior sampling solves inverse problems by combining a pretrained diffusion prior with measurement-consistency guidance. However, full-band guidance can be unreliable at high noise levels, where clean estimates contain score-induced errors and high-frequency measurement directions are weakly identifiable. We argue that posterior guidance should expose measurement frequencies according to the instantaneous diffusion noise level. Based on this principle, we propose a posterior continuation framework that constructs a family of intermediate posteriors whose likelihood emphasizes currently reliable frequency bands and gradually returns to full-band consistency. We instantiate this framework with a stabilized sampler that combines a diffusion predictor, frequency-limited likelihood refinement, and a Haar-domain commitment rule that commits reliable coarse corrections while deferring weakly identifiable details. Across super-resolution, inpainting, and deblurring, our method achieves competitive-to-state-of-the-art restoration performance, including up to 5 dB PSNR improvement on motion deblurring over strong baselines in evaluations on FFHQ and ImageNet.

---

### The Illusion of Forgetting: Attack Unlearned Diffusion via Initial Latent Variable Optimization

Authors: Manyi Li, Yufan Liu, Lai Jiang, Bing Li, Yuming Li, Weiming Hu
Published: 2026-01-30
Categories: cs.LG, cs.AI, cs.CV, cs.CY
arXiv: https://arxiv.org/abs/2602.00175v2

Text-to-image diffusion models (DMs) are frequently abused to produce harmful or copyrighted content, violating public interests. Concept erasure (unlearning) is a promising paradigm to alleviate this issue. However, there exists a peculiar forgetting illusion phenomenon with unclear cause. Based on empirical analysis, we formally explain this cause: most unlearning partially disrupt the mapping between linguistic symbols and the underlying internal knowledge, leaving the knowledge intact as dormant memories. We further demonstrate that distributional discrepancy in the denoising process serves as a measurable indicator of how much of the mapping is retained, also reflecting unlearning strength. Inspired by this, we propose IVO (Initial Latent Variable Optimization), a novel attack framework designed to assess the robustness of current unlearning methods. IVO optimizes initial latent variables to realign the noise distribution of unlearned models with that of their vanilla counterparts, which reconstructs the fractured mappings and consequently revives dormant memories. Extensive experiments covering 11 unlearning techniques and 3 concept scenarios show that IVO outperforms state-of-the-art baselines, exposing fundamental flaws in current unlearning mechanisms. Warning: This paper has unsafe images that may offend some readers.

---

### Intra-Class Subdivision for Pixel Contrastive Learning: Application to Semi-supervised Cardiac Image Segmentation

Authors: Jiajun Zhao, Xuan Yang
Published: 2026-01-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.00174v1

We propose an intra-class subdivision pixel contrastive learning (SPCL) framework for cardiac image segmentation to address representation contamination at boundaries. The novel concept ``Unconcerned sample'' is proposed to distinguish pixel representations at the inner and boundary regions within the same class, facilitating a clearer characterization of intra-class variations. A novel boundary contrastive loss for boundary representations is proposed to enhance representation discrimination across boundaries. The advantages of the unconcerned sample and boundary contrastive loss are analyzed theoretically. Experimental results in public cardiac datasets demonstrate that SPCL significantly improves segmentation performance, outperforming existing methods with respect to segmentation quality and boundary precision. Our code is available at https://github.com/Jrstud203/SPCL.

---

### Learning Robust Reasoning through Guided Adversarial Self-Play

Authors: Shuozhe Li, Vaishnav Tadiparthi, Kwonjoon Lee, Nakul Agarwal, Hossein Nourkhiz Mahjoub, Ehsan Moradi Pari, Lizhang Chen, Amy Zhang, Liu Leqi
Published: 2026-01-30
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.00173v1

Reinforcement learning from verifiable rewards (RLVR) produces strong reasoning models, yet they can fail catastrophically when the conditioning context is fallible (e.g., corrupted chain-of-thought, misleading partial solutions, or mild input perturbations), since standard RLVR optimizes final-answer correctness only under clean conditioning. We introduce GASP (Guided Adversarial Self-Play), a robustification method that explicitly trains detect-and-repair capabilities using only outcome verification. Without human labels or external teachers, GASP forms an adversarial self-play game within a single model: a polluter learns to induce failure via locally coherent corruptions, while an agent learns to diagnose and recover under the same corrupted conditioning. To address the scarcity of successful recoveries early in training, we propose in-distribution repair guidance, an imitation term on self-generated repairs that increases recovery probability while preserving previously acquired capabilities. Across four open-weight models (1.5B--8B), GASP transforms strong-but-brittle reasoners into robust ones that withstand misleading and perturbed context while often improving clean accuracy. Further analysis shows that adversarial corruptions induce an effective curriculum, and in-distribution guidance enables rapid recovery learning with minimal representational drift.

---

### Neuron Block Dynamics for XOR Classification with Zero-Margin

Authors: Guillaume Braun, Masaaki Imaizumi
Published: 2026-01-30
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2602.00172v1

The ability of neural networks to learn useful features through stochastic gradient descent (SGD) is a cornerstone of their success. Most theoretical analyses focus on regression or on classification tasks with a positive margin, where worst-case gradient bounds suffice. In contrast, we study zero-margin nonlinear classification by analyzing the Gaussian XOR problem, where inputs are Gaussian and the XOR decision boundary determines labels. In this setting, a non-negligible fraction of data lies arbitrarily close to the boundary, breaking standard margin-based arguments. Building on Glasgow's (2024) analysis, we extend the study of training dynamics from discrete to Gaussian inputs and develop a framework for the dynamics of neuron blocks. We show that neurons cluster into four directions and that block-level signals evolve coherently, a phenomenon essential in the Gaussian setting where individual neuron signals vary significantly. Leveraging this block perspective, we analyze generalization without relying on margin assumptions, adopting an average-case view that distinguishes regions of reliable prediction from regions of persistent error. Numerical experiments confirm the predicted two-phase block dynamics and demonstrate their robustness beyond the Gaussian setting.

---

### Uncertainty-Aware Multimodal Learning via Conformal Shapley Intervals

Authors: Mathew Chandy, Michael Johnson, Judong Shen, Devan V. Mehrotra, Hua Zhou, Jin Zhou, Xiaowu Dai
Published: 2026-01-30
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2602.00171v1

Multimodal learning combines information from multiple data modalities to improve predictive performance. However, modalities often contribute unequally and in a data dependent way, making it unclear which data modalities are genuinely informative and to what extent their contributions can be trusted. Quantifying modality level importance together with uncertainty is therefore central to interpretable and reliable multimodal learning. We introduce conformal Shapley intervals, a framework that combines Shapley values with conformal inference to construct uncertainty-aware importance intervals for each modality. Building on these intervals, we propose a modality selection procedure with a provable optimality guarantee: conditional on the observed features, the selected subset of modalities achieves performance close to that of the optimal subset. We demonstrate the effectiveness of our approach on multiple datasets, showing that it provides meaningful uncertainty quantification and strong predictive performance while relying on only a small number of informative modalities.

---

### The Blessing of Dimensionality in LLM Fine-tuning: A Variance-Curvature Perspective

Authors: Qiyao Liang, Jinyeop Song, Yizhou Liu, Jeff Gore, Ila Fiete, Risto Miikkulainen, Xin Qiu
Published: 2026-01-30
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.00170v1

Weight-perturbation evolution strategies (ES) can fine-tune billion-parameter language models with surprisingly small populations (e.g., $N\!\approx\!30$), contradicting classical zeroth-order curse-of-dimensionality intuition. We also observe a second seemingly separate phenomenon: under fixed hyperparameters, the stochastic fine-tuning reward often rises, peaks, and then degrades in both ES and GRPO. We argue that both effects reflect a shared geometric property of fine-tuning landscapes: they are low-dimensional in curvature. A small set of high-curvature dimensions dominates improvement, producing (i) heterogeneous time scales that yield rise-then-decay under fixed stochasticity, as captured by a minimal quadratic stochastic-ascent model, and (ii) degenerate improving updates, where many random perturbations share similar components along these directions. Using ES as a geometric probe on fine-tuning reward landscapes of GSM8K, ARC-C, and WinoGrande across Qwen2.5-Instruct models (0.5B--7B), we show that reward-improving perturbations remain empirically accessible with small populations across scales. Together, these results reconcile ES scalability with non-monotonic training dynamics and suggest that high-dimensional fine-tuning may admit a broader class of viable optimization methods than worst-case theory implies.

---

### VideoGPA: Distilling Geometry Priors for 3D-Consistent Video Generation

Authors: Hongyang Du, Junjie Ye, Xiaoyan Cong, Runhao Li, Jingcheng Ni, Aman Agarwal, Zeqi Zhou, Zekun Li, Randall Balestriero, Yue Wang
Published: 2026-01-30
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.23286v4

While recent video diffusion models (VDMs) produce visually impressive results, they fundamentally struggle to maintain 3D structural consistency, often resulting in object deformation or spatial drift. We hypothesize that these failures arise because standard denoising objectives lack explicit incentives for geometric coherence. To address this, we introduce VideoGPA (Video Geometric Preference Alignment), a data-efficient self-supervised framework that leverages a geometry foundation model to automatically derive dense preference signals that guide VDMs via Direct Preference Optimization (DPO). This approach effectively steers the generative distribution toward inherent 3D consistency without requiring human annotations. VideoGPA significantly enhances temporal stability, geometric plausibility, and motion coherence using minimal preference pairs, consistently outperforming state-of-the-art baselines in extensive experiments.

---

### End-to-end Optimization of Belief and Policy Learning in Shared Autonomy Paradigms

Authors: MH Farhadi, Ali Rabiee, Sima Ghafoori, Anna Cetera, Andrew Fisher, Reza Abiri
Published: 2026-01-30
Categories: cs.RO, cs.AI, cs.HC, cs.LG
arXiv: https://arxiv.org/abs/2601.23285v1

Shared autonomy systems require principled methods for inferring user intent and determining appropriate assistance levels. This is a central challenge in human-robot interaction, where systems must be successful while being mindful of user agency. Previous approaches relied on static blending ratios or separated goal inference from assistance arbitration, leading to suboptimal performance in unstructured environments. We introduce BRACE (Bayesian Reinforcement Assistance with Context Encoding), a novel framework that fine-tunes Bayesian intent inference and context-adaptive assistance through an architecture enabling end-to-end gradient flow between intent inference and assistance arbitration. Our pipeline conditions collaborative control policies on environmental context and complete goal probability distributions. We provide analysis showing (1) optimal assistance levels should decrease with goal uncertainty and increase with environmental constraint severity, and (2) integrating belief information into policy learning yields a quadratic expected regret advantage over sequential approaches. We validated our algorithm against SOTA methods (IDA, DQN) using a three-part evaluation progressively isolating distinct challenges of end-effector control: (1) core human-interaction dynamics in a 2D human-in-the-loop cursor task, (2) non-linear dynamics of a robotic arm, and (3) integrated manipulation under goal ambiguity and environmental constraints. We demonstrate improvements over SOTA, achieving 6.3% higher success rates and 41% increased path efficiency, and 36.3% success rate and 87% path efficiency improvement over unassisted control. Our results confirmed that integrated optimization is most beneficial in complex, goal-ambiguous scenarios, and is generalizable across robotic domains requiring goal-directed assistance, advancing the SOTA for adaptive shared autonomy.

---

### User Prompting Strategies and Prompt Enhancement Methods for Open-Set Object Detection in XR Environments

Authors: Junfeng Lin, Yanming Xiu, Maria Gorlatova
Published: 2026-01-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.23281v1

Open-set object detection (OSOD) localizes objects while identifying and rejecting unknown classes at inference. While recent OSOD models perform well on benchmarks, their behavior under realistic user prompting remains underexplored. In interactive XR settings, user-generated prompts are often ambiguous, underspecified, or overly detailed. To study prompt-conditioned robustness, we evaluate two OSOD models, GroundingDINO and YOLO-E, on real-world XR images and simulate diverse user prompting behaviors using vision-language models. We consider four prompt types: standard, underdetailed, overdetailed, and pragmatically ambiguous, and examine the impact of two enhancement strategies on these prompts. Results show that both models exhibit stable performance under underdetailed and standard prompts, while they suffer degradation under ambiguous prompts. Overdetailed prompts primarily affect GroundingDINO. Prompt enhancement substantially improves robustness under ambiguity, yielding gains exceeding 55% mIoU and 41% average confidence. Based on the findings, we propose several prompting strategies and prompt enhancement methods for OSOD models in XR environments.

---

### Decoupled Diffusion Sampling for Inverse Problems on Function Spaces

Authors: Thomas Y. L. Lin, Jiachen Yao, Lufang Chiang, Julius Berner, Anima Anandkumar
Published: 2026-01-30
Categories: cs.LG, math.NA
arXiv: https://arxiv.org/abs/2601.23280v3

We propose a data-efficient, physics-aware generative framework in function space for inverse PDE problems. Existing plug-and-play diffusion posterior samplers represent physics implicitly through joint coefficient-solution modeling, requiring substantial paired supervision. In contrast, our Decoupled Diffusion Inverse Solver (DDIS) employs a decoupled design: an unconditional diffusion learns the coefficient prior, while a neural operator explicitly models the forward PDE for guidance. This decoupling enables superior data efficiency and effective physics-informed learning, while naturally supporting Decoupled Annealing Posterior Sampling (DAPS) to avoid over-smoothing in Diffusion Posterior Sampling (DPS). Theoretically, we prove that DDIS avoids the guidance attenuation failure of joint models when training data is scarce. Empirically, DDIS achieves state-of-the-art performance under sparse observation, improving $l_2$ error by 11% and spectral error by 54% on average; when data is limited to 1%, DDIS maintains accuracy with 40% advantage in $l_2$ error compared to joint models.

---

### FOCUS: DLLMs Know How to Tame Their Compute Bound

Authors: Kaihua Liang, Xin Tan, An Zhong, Hong Xu, Marco Canini
Published: 2026-01-30
Categories: cs.LG, cs.AR, cs.CL
arXiv: https://arxiv.org/abs/2601.23278v2

Diffusion Large Language Models (DLLMs) offer a compelling alternative to Auto-Regressive models, but their deployment is constrained by high decoding cost. In this work, we identify a key inefficiency in DLLM decoding: while computation is parallelized over token blocks, only a small subset of tokens is decodable at each diffusion step, causing most compute to be wasted on non-decodable tokens. We further observe a strong correlation between attention-derived token importance and token-wise decoding probability. Based on this insight, we propose FOCUS, an inference system designed for DLLMs. By dynamically focusing computation on decodable tokens and evicting non-decodable ones on-the-fly, FOCUS increases the effective batch size, alleviating compute limitations and enabling scalable throughput. Empirical evaluations demonstrate that FOCUS achieves up to 3.52$\times$ throughput improvement over the production-grade engine LMDeploy in large-batch settings, while preserving or improving generation quality across multiple benchmarks.

---

### Denoising the Deep Sky: Physics-Based CCD Noise Formation for Astronomical Imaging

Authors: Shuhong Liu, Xining Ge, Ziying Gu, Quanfeng Xu, Lin Gu, Ziteng Cui, Xuangeng Chu, Jun Liu, Dong Li, Tatsuya Harada
Published: 2026-01-30
Categories: astro-ph.IM, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2601.23276v4

Astronomical imaging remains noise-limited under practical observing conditions. Standard calibration pipelines remove structured artifacts but largely leave stochastic noise unresolved. Although learning-based denoising has shown strong potential, progress is constrained by scarce paired training data and the requirement for physically interpretable models in scientific workflows. We propose a physics-based noise synthesis framework tailored to CCD noise formation in the telescope. The pipeline models photon shot noise, photo-response non-uniformity, dark-current noise, readout effects, and localized outliers arising from cosmic-ray hits and hot pixels. To obtain low-noise inputs for synthesis, we stack multiple unregistered exposures to produce high-SNR bases. Realistic noisy counterparts synthesized from these bases using our noise model enable the construction of abundant paired datasets for supervised learning. Extensive experiments on our real-world multi-band dataset curated from two ground-based telescopes demonstrate the effectiveness of our framework in both photometric and scientific accuracy.

---

### UPA: Unsupervised Prompt Agent via Tree-Based Search and Selection

Authors: Siran Peng, Weisong Zhao, Tianyu Fu, Chenxu Zhao, Tianshuo Zhang, Haoyuan Zhang, Xiangyu Zhu, Minghui Wu, Zhen Lei
Published: 2026-01-30
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.23273v2

Prompt agents have recently emerged as a promising paradigm for automated prompt optimization, framing prompt discovery as a sequential decision-making problem over a structured prompt space. While this formulation enables the use of advanced planning algorithms, these methods typically assume access to supervised reward signals, which are often unavailable in practical scenarios. In this work, we propose UPA, an Unsupervised Prompt Agent that realizes structured search and selection without relying on ground-truth (GT) rewards. Specifically, during search, UPA iteratively constructs an evolving tree structure to navigate the prompt space, guided by fine-grained and position-debiased pairwise comparisons from Large Language Models (LLMs). Crucially, as these local comparisons do not inherently yield a consistent global scale, we decouple systematic prompt exploration from final selection, introducing a two-stage framework grounded in the Bradley-Terry-Luce (BTL) model. This framework first performs path-wise Bayesian aggregation of local comparisons to filter candidates under uncertainty, followed by global tournament-style comparisons to infer latent prompt quality and identify the optimal prompt. Experiments across multiple tasks demonstrate that UPA consistently outperforms existing prompt optimization methods, showing that agent-style optimization can remain highly effective even in unsupervised settings.

---

### IRL-DAL: Safe and Adaptive Trajectory Planning for Autonomous Driving via Energy-Guided Diffusion Models

Authors: Seyed Ahmad Hosseini Miangoleh, Amin Jalal Aghdasian, Farzaneh Abdollahi
Published: 2026-01-30
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2601.23266v1

This paper proposes a novel inverse reinforcement learning framework using a diffusion-based adaptive lookahead planner (IRL-DAL) for autonomous vehicles. Training begins with imitation from an expert finite state machine (FSM) controller to provide a stable initialization. Environment terms are combined with an IRL discriminator signal to align with expert goals. Reinforcement learning (RL) is then performed with a hybrid reward that combines diffuse environmental feedback and targeted IRL rewards. A conditional diffusion model, which acts as a safety supervisor, plans safe paths. It stays in its lane, avoids obstacles, and moves smoothly. Then, a learnable adaptive mask (LAM) improves perception. It shifts visual attention based on vehicle speed and nearby hazards. After FSM-based imitation, the policy is fine-tuned with Proximal Policy Optimization (PPO). Training is run in the Webots simulator with a two-stage curriculum. A 96\% success rate is reached, and collisions are reduced to 0.05 per 1k steps, marking a new benchmark for safe navigation. By applying the proposed approach, the agent not only drives in lane but also handles unsafe conditions at an expert level, increasing robustness.We make our code publicly available.

---

### PaperBanana: Automating Academic Illustration for AI Scientists

Authors: Dawei Zhu, Rui Meng, Yale Song, Xiyu Wei, Sujian Li, Tomas Pfister, Jinsung Yoon
Published: 2026-01-30
Categories: cs.CL, cs.CV
arXiv: https://arxiv.org/abs/2601.23265v2

Despite rapid advances in autonomous AI scientists powered by language models, generating publication-ready illustrations remains a labor-intensive bottleneck in the research workflow. To lift this burden, we introduce PaperBanana, an agentic framework for automated generation of publication-ready academic illustrations. Powered by state-of-the-art VLMs and image generation models, PaperBanana orchestrates specialized agents to retrieve references, plan content and style, render images, and iteratively refine via self-critique. To rigorously evaluate our framework, we introduce PaperBananaBench, comprising 292 test cases for methodology diagrams curated from NeurIPS 2025 publications, covering diverse research domains and illustration styles. Comprehensive experiments demonstrate that PaperBanana consistently outperforms leading baselines in faithfulness, conciseness, readability, and aesthetics. We further show that our method effectively extends to the generation of high-quality statistical plots. Collectively, PaperBanana paves the way for the automated generation of publication-ready illustrations.

---

### Particle-Guided Diffusion Models for Partial Differential Equations

Authors: Andrew Millard, Fredrik Lindsten, Zheng Zhao
Published: 2026-01-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.23262v2

We introduce a guided stochastic sampling method that augments sampling from diffusion models with physics-based guidance derived from partial differential equation (PDE) residuals and observational constraints, ensuring generated samples remain physically admissible. We embed this sampling procedure within a new Sequential Monte Carlo (SMC) framework, yielding a scalable generative PDE solver. Across multiple benchmark PDE systems as well as multiphysics and interacting PDE systems, our method produces solution fields with lower numerical error than existing state-of-the-art generative methods.

---

### TEON: Tensorized Orthonormalization Beyond Layer-Wise Muon for Large Language Model Pre-Training

Authors: Ruijie Zhang, Yequan Zhao, Ziyue Liu, Zhengyang Wang, Dongyang Li, Yupeng Su, Sijia Liu, Zheng Zhang
Published: 2026-01-30
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.23261v2

The Muon optimizer has demonstrated strong empirical performance in pre-training large language models by performing matrix-level gradient (or momentum) orthogonalization in each layer independently. In this work, we propose TEON, a principled generalization of Muon that extends orthogonalization beyond individual layers by modeling the gradients of a neural network as a structured higher-order tensor. We present TEON's improved convergence guarantee over layer-wise Muon, and further develop a practical instantiation of TEON based on the theoretical analysis with corresponding ablation. We evaluate our approach on two widely adopted architectures: GPT-style models, ranging from 130M to 774M parameters, and LLaMA-style models, ranging from 60M to 1B parameters. Experimental results show that TEON consistently improves training and validation perplexity across model scales and exhibits strong robustness under various approximate SVD schemes.

---

### Agnostic Language Identification and Generation

Authors: Mikael Møller Høgsgaard, Chirag Pabbaraju
Published: 2026-01-30
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2601.23258v2

Recent works on language identification and generation have established tight statistical rates at which these tasks can be achieved. These works typically operate under a strong realizability assumption: that the input data is drawn from an unknown distribution necessarily supported on some language in a given collection. In this work, we relax this assumption of realizability entirely, and impose no restrictions on the distribution of the input data. We propose objectives to study both language identification and generation in this more general "agnostic" setup. Across both problems, we obtain novel interesting characterizations and nearly tight rates.

---

### Now You Hear Me: Audio Narrative Attacks Against Large Audio-Language Models

Authors: Ye Yu, Haibo Jin, Yaoning Yu, Jun Zhuang, Haohan Wang
Published: 2026-01-30
Categories: cs.CL, cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2601.23255v1

Large audio-language models increasingly operate on raw speech inputs, enabling more seamless integration across domains such as voice assistants, education, and clinical triage. This transition, however, introduces a distinct class of vulnerabilities that remain largely uncharacterized. We examine the security implications of this modality shift by designing a text-to-audio jailbreak that embeds disallowed directives within a narrative-style audio stream. The attack leverages an advanced instruction-following text-to-speech (TTS) model to exploit structural and acoustic properties, thereby circumventing safety mechanisms primarily calibrated for text. When delivered through synthetic speech, the narrative format elicits restricted outputs from state-of-the-art models, including Gemini 2.0 Flash, achieving a 98.26% success rate that substantially exceeds text-only baselines. These results highlight the need for safety frameworks that jointly reason over linguistic and paralinguistic representations, particularly as speech-based interfaces become more prevalent.

---

### Training-Free Test-Time Adaptation with Brownian Distance Covariance in Vision-Language Models

Authors: Yi Zhang, Chun-Wun Cheng, Angelica I. Aviles-Rivero, Zhihai He, Liang-Jie Zhang
Published: 2026-01-30
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2601.23253v1

Vision-language models suffer performance degradation under domain shift, limiting real-world applicability. Existing test-time adaptation methods are computationally intensive, rely on back-propagation, and often focus on single modalities. To address these issues, we propose Training-free Test-Time Adaptation with Brownian Distance Covariance (TaTa). TaTa leverages Brownian Distance Covariance-a powerful statistical measure that captures both linear and nonlinear dependencies via pairwise distances-to dynamically adapt VLMs to new domains without training or back-propagation. This not only improves efficiency but also enhances stability by avoiding disruptive weight updates. TaTa further integrates attribute-enhanced prompting to improve vision-language inference with descriptive visual cues. Combined with dynamic clustering and pseudo-label refinement, it effectively recalibrates the model for novel visual contexts. Experiments across diverse datasets show that TaTa significantly reduces computational cost while achieving state-of-the-art performance in domain and cross-dataset generalization.

---