# Research Papers — 2026-02 · bundle page 8 of 210

> Full-text markdown of papers #351–400 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/8
[← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/7.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-02/page/9.md)

### Optimisation of SOUP-GAN and CSR-GAN for High Resolution MR Images Reconstruction

Authors: Muneeba Rashid, Hina Shakir, Humaira Mehwish, Asarim Amir, Reema Qaiser Khan
Published: 2026-02-27
Categories: eess.IV, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2603.00204v1

Magnetic Resonance (MR) imaging is a diagnostic tool used in modern medicine; however, its output can be affected by motion artefacts and may be limited by equipment. This research focuses on MRI image quality enhancement using two efficient Generative Adversarial Networks (GANs) models: SOUP-GAN and CSR-GAN. In both models, meaningful architectural modifications were introduced. The generator and discriminator of each were further deepened by adding convolutional layers and were enhanced in filter sizes as well. The LeakyReLU activation function was used to improve gradient flow, and hyperparameter tuning strategies were applied, including a reduced learning rate and an optimal batch size. Moreover, spectral normalisation was proposed to address mode collapse and improve training stability. The experiment shows that CSR-GAN has better performance in reconstructing the image with higher frequency details and reducing noise compared to other methods, with an optimised PSNR of 34.6 and SSIM of 0.89. However, SOUP-GAN performed the best in terms of delivering less noisy images with good structures, achieving a PSNR of 34.4 and SSIM of 0.83. The obtained results indicate that the proposed enhanced GAN model can be a useful tool for MR image quality improvement for subsequent better disease diagnostics.

---

### The Partition Principle Revisited: Non-Equal Volume Designs Achieve Minimal Expected Star Discrepancy

Authors: Xiaoda Xu
Published: 2026-02-27
Categories: stat.ML, cs.LG, math.PR
arXiv: https://arxiv.org/abs/2603.00202v2

We study the expected star discrepancy under a newly designed class of non-equal volume partitions. The main contributions are twofold. First, we establish a strong partition principle for the star discrepancy, showing that our newly designed non-equal volume partitions yield stratified sampling point sets with lower expected star discrepancy than classical jittered sampling. Specifically, we prove that $\mathbb{E}(D^{*}_{N}(Z)) < \mathbb{E}(D^{*}_{N}(Y))$, where $Y$ and $Z$ represent jittered sampling and our non-equal volume partition sampling, respectively. Second, we derive explicit upper bounds for the expected star discrepancy under our non-equal volume partition models, which improve upon existing bounds for jittered sampling. Our results provide a theoretical foundation for using non-equal volume partitions in high-dimensional numerical integration.

---

### AdURA-Net: Adaptive Uncertainty and Region-Aware Network

Authors: Antik Aich Roy, Ujjwal Bhattacharya
Published: 2026-02-27
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.00201v1

One of the common issues in clinical decision-making is the presence of uncertainty, which often arises due to ambiguity in radiology reports, which often reflect genuine diagnostic uncertainty or limitations of automated label extraction in various complex cases. Especially the case of multilabel datasets such as CheXpert, MIMIC-CXR, etc., which contain labels such as positive, negative, and uncertain. In clinical decision-making, the uncertain label plays a tricky role as the model should not be forced to provide a confident prediction in the absence of sufficient evidence. The ability of the model to say it does not understand whenever it is not confident is crucial, especially in the cases of clinical decision-making involving high risks. Here, we propose AdURA-Net, a geometry-driven adaptive uncertainty-aware framework for reliable thoracic disease classification. The key highlights of the proposed model are: a) Adaptive dilated convolution and multiscale deformable alignment coupled with the backbone Densenet architecture capturing the anatomical complexities of the medical images, and b) Dual Head Loss, which combines masked binary cross entropy with logit and a Dirichlet evidential learning objective.

---

### LiaisonAgent: An Multi-Agent Framework for Autonomous Risk Investigation and Governance

Authors: Chuanming Tang, Ling Qing, Shifeng Chen
Published: 2026-02-27
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2603.00200v1

The rapid evolution of sophisticated cyberattacks has strained modern Security Operations Centers (SOC), which traditionally rely on rule-based or signature-driven detection systems. These legacy frameworks often generate high volumes of technical alerts that lack organizational context, leading to analyst fatigue and delayed incident responses. This paper presents LiaisonAgent, an autonomous multi-agent system designed to bridge the gap between technical risk detection and business-level risk governance. Built upon the QWQ-32B large reasoning model, LiaisonAgent integrates specialized sub-agents, including human-computer interaction agents, comprehensive judgment agents, and automated disposal agents-to execute end-to-end investigation workflows. The system leverages a hybrid planning architecture that combines deterministic workflows for compliance with autonomous reasoning based on the ReAct paradigm to handle ambiguous operational scenarios. Experimental evaluations across diverse security contexts, such as large-scale data exfiltration and unauthorized account borrowing, achieve an end-to-end tool-calling success rate of 97.8% and a risk judgment accuracy of 95%. Furthermore, the system exhibits significant resilience against out-of-distribution noise and adversarial prompt injections, while achieving a 92.7% reduction in manual investigation overhead.

---

### Multi-Condition Digital Twin Calibration for Axial Piston Pumps : Compound Fault Simulation

Authors: Chang Dong, Jianfeng Tao, Chengliang Liu
Published: 2026-02-27
Categories: physics.flu-dyn, cs.AI, math.NA
arXiv: https://arxiv.org/abs/2603.00199v2

Axial piston pumps are indispensable power sources in high-stakes fluid power systems, including aerospace, marine, and heavy machinery applications. Their operational reliability is frequently compromised by compound faults that simultaneously affect multiple friction pairs. Conventional data-driven diagnosis methods suffer from severe data scarcity for compound faults and poor generalization across varying operating conditions. This paper proposes a novel multi-condition physics-data coupled digital twin calibration framework that explicitly resolves the fundamental uncertainty of pump outlet flow ripple. The framework comprises three synergistic stages: in-situ virtual high-frequency flow sensing on a dedicated rigid metallic segment, surrogate model-assisted calibration of the 3D CFD source model using physically estimated ripple amplitudes, and multi-objective inverse transient analysis for viscoelastic unsteady-friction pipeline parameter identification. Comprehensive experiments on a test rig demonstrate that the calibrated digital twin accurately reproduces both single-fault and two representative compound-fault. These results establish a high-fidelity synthetic fault-generation capability that directly enables robust zero-shot fault diagnosis under previously unseen operating regimes and fault combinations, thereby advancing predictive maintenance in complex hydraulic systems.

---

### Stateful Token Reduction for Long-Video Hybrid VLMs

Authors: Jindong Jiang, Amala Sanjay Deshmukh, Kateryna Chumachenko, Karan Sapra, Zhiding Yu, Guilin Liu, Andrew Tao, Pavlo Molchanov, Jan Kautz, Wonmin Byeon
Published: 2026-02-27
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.00198v2

Token reduction accelerates long-video vision--language models (VLMs), but existing methods target Transformers, where reduction is treated as token pruning. We study token reduction in hybrid Mamba--Transformer VLMs and find that it is \emph{stateful}: Mamba layers maintain a recurrent state that accumulates information from earlier tokens, allowing discarded tokens to persist, so reduction behaves more like compression than dropping.We support this view with a representation-based probing method measuring how much information from discarded tokens is retained, and analyze layer-wise sparsity and cross-layer importance stability. Our findings show importance is sparse within layers but unstable across layers, making aggressive early pruning unreliable while hybrids remain robust to later reduction.Motivated by this, we propose a hybrid-aware token reduction framework with a low-to-high progressive schedule and a unified query-conditioned importance score for attention and Mamba layers. For Mamba, excluding the position-dependent decay from the recurrence produces a stronger selection signal. Across long-video benchmarks, our method achieves $3.8{\times}$--$4.2{\times}$ prefilling speedups at a 25% token budget while maintaining near-baseline accuracy and improving with light finetuning. Hybrid models benefit from aggressive reduction, improving both efficiency and accuracy, whereas Transformers exhibit the standard trade-off. Our method also outperforms prior baselines on the same hybrid backbone and combines effectively with visual redundancy reduction methods.

---

### A Case Study on Concept Induction for Neuron-Level Interpretability in CNN

Authors: Moumita Sen Sarma, Samatha Ereshi Akkamahadevi, Pascal Hitzler
Published: 2026-02-27
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.00197v1

Deep Neural Networks (DNNs) have advanced applications in domains such as healthcare, autonomous systems, and scene understanding, yet the internal semantics of their hidden neurons remain poorly understood. Prior work introduced a Concept Induction-based framework for hidden neuron analysis and demonstrated its effectiveness on the ADE20K dataset. In this case study, we investigate whether the approach generalizes by applying it to the SUN2012 dataset, a large-scale scene recognition benchmark. Using the same workflow, we assign interpretable semantic labels to neurons and validate them through web-sourced images and statistical testing. Our findings confirm that the method transfers to SUN2012, showing its broader applicability.

---

### Your Inference Request Will Become a Black Box: Confidential Inference for Cloud-based Large Language Models

Authors: Chung-ju Huang, Huiqiang Zhao, Yuanpeng He, Lijian Li, Wenpin Jiao, Zhi Jin, Peixuan Chen, Leye Wang
Published: 2026-02-27
Categories: cs.CR, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2603.00196v1

The increasing reliance on cloud-hosted Large Language Models (LLMs) exposes sensitive client data, such as prompts and responses, to potential privacy breaches by service providers. Existing approaches fail to ensure privacy, maintain model performance, and preserve computational efficiency simultaneously. To address this challenge, we propose Talaria, a confidential inference framework that partitions the LLM pipeline to protect client data without compromising the cloud's model intellectual property or inference quality. Talaria executes sensitive, weight-independent operations within a client-controlled Confidential Virtual Machine (CVM) while offloading weight-dependent computations to the cloud GPUs. The interaction between these environments is secured by our Reversible Masked Outsourcing (ReMO) protocol, which uses a hybrid masking technique to reversibly obscure intermediate data before outsourcing computations. Extensive evaluations show that Talaria can defend against state-of-the-art token inference attacks, reducing token reconstruction accuracy from over 97.5% to an average of 1.34%, all while being a lossless mechanism that guarantees output identical to the original model without significantly decreasing efficiency and scalability. To the best of our knowledge, this is the first work that ensures clients' prompts and responses remain inaccessible to the cloud, while also preserving model privacy, performance, and efficiency.

---

### Formal Analysis and Supply Chain Security for Agentic AI Skills

Authors: Varun Pratap Bhardwaj
Published: 2026-02-27
Categories: cs.CR, cs.AI, cs.SE
arXiv: https://arxiv.org/abs/2603.00195v2

32 pages, 5 theorems with full proofs, 68 references, open-source tool: https://github.com/qualixar/skillfortify. v2: corrects the bibliography (22 entries had author lists that did not match the papers at the cited arXiv identifiers; all verified against the arXiv API and corrected, and affected authors notified) and three external claims against primary sources: MalTool reports 1,300 standalone and 5,727 embedded malicious tools, not 6,487; CVE-2026-25253 is authentication-token exfiltration via an unvalidated gatewayUrl, credited to depthfirst and fixed in 2026.1.29, not remote code execution through a crafted skill package; ClawHavoc counts are 341, later 824, and 1,184 by source and date, not "over 1,200". All experiments re-measured against the released v0.6.0 implementation using harnesses now committed to the repository. E1/E2 unchanged (F1 96.15%). E3 reverses to a negative result: information flow analysis adds no detections over pattern matching on this corpus. The soundness theorem's scope is stated explicitly and no longer conflated with the zero false-positive rate.

---

### SKeDA: A Generative Watermarking Framework for Text-to-video Diffusion Models

Authors: Yang Yang, Xinze Zou, Zehua Ma, Han Fang, Weiming Zhang
Published: 2026-02-27
Categories: cs.CV, cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2603.00194v1

The rise of text-to-video generation models has raised growing concerns over content authenticity, copyright protection, and malicious misuse. Watermarking serves as an effective mechanism for regulating such AI-generated content, where high fidelity and strong robustness are particularly critical. Recent generative image watermarking methods provide a promising foundation by leveraging watermark information and pseudo-random keys to control the initial sampling noise, enabling lossless embedding. However, directly extending these techniques to videos introduces two key limitations: Existing designs implicitly rely on strict alignment between video frames and frame-dependent pseudo-random binary sequences used for watermark encryption. Once this alignment is disrupted, subsequent watermark extraction becomes unreliable; and Video-specific distortions, such as inter-frame compression, significantly degrade watermark reliability. To address these issues, we propose SKeDA, a generative watermarking framework tailored for text-to-video diffusion models. SKeDA consists of two components: (1) Shuffle-Key-based Distribution-preserving Sampling (SKe) employs a single base pseudo-random binary sequence for watermark encryption and derives frame-level encryption sequences through permutation. This design transforms watermark extraction from synchronization-sensitive sequence decoding into permutation-tolerant set-level aggregation, substantially improving robustness against frame reordering and loss; and (2) Differential Attention (DA), which computes inter-frame differences and dynamically adjusts attention weights during extraction, enhancing robustness against temporal distortions. Extensive experiments demonstrate that SKeDA preserves high video generation quality and watermark robustness.

---

### Diagnostics for Individual-Level Prediction Instability in Machine Learning for Healthcare

Authors: Elizabeth W. Miller, Jeffrey D. Blume
Published: 2026-02-27
Categories: cs.LG, stat.AP, stat.ML
arXiv: https://arxiv.org/abs/2603.00192v2

In healthcare, predictive models increasingly inform patient-level decisions, yet little attention is paid to the variability in individual risk estimates and its impact on treatment decisions. For overparameterized models, now standard in machine learning, a substantial source of variability often goes undetected. Even when the data and model architecture are held fixed, randomness introduced by optimization and initialization can lead to materially different risk estimates for the same patient. This problem is largely obscured by standard evaluation practices, which rely on aggregate performance metrics (e.g., log-loss, accuracy) that are agnostic to individual-level stability. As a result, models with indistinguishable aggregate performance can nonetheless exhibit substantial procedural arbitrariness, which can undermine clinical trust. We propose an evaluation framework that quantifies individual-level prediction instability by using two complementary diagnostics: empirical prediction interval width (ePIW), which captures variability in continuous risk estimates, and empirical decision flip rate (eDFR), which measures instability in threshold-based clinical decisions. We apply these diagnostics to simulated data and GUSTO-I clinical dataset. Across observed settings, we find that for flexible machine-learning models, randomness arising solely from optimization and initialization can induce individual-level variability comparable to that produced by resampling the entire training dataset. Neural networks exhibit substantially greater instability in individual risk predictions compared to logistic regression models. Risk estimate instability near clinically relevant decision thresholds can alter treatment recommendations. These findings that stability diagnostics should be incorporated into routine model validation for assessing clinical reliability.

---

### Task-Driven Subspace Decomposition for Knowledge Sharing and Isolation in LoRA-based Continual Learning

Authors: Lingfeng He, De Cheng, Huaijie Wang, Xi Yang, Nannan Wang, Xinbo Gao
Published: 2026-02-27
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2603.00191v4

Continual Learning (CL) requires models to sequentially adapt to new tasks without forgetting old knowledge. Recently, Low-Rank Adaptation (LoRA), a representative Parameter-Efficient Fine-Tuning (PEFT) method, has gained increasing attention in CL. Several LoRA-based CL methods reduce interference across tasks by separating their update spaces, typically building the new space from the estimated null space of past tasks. However, they (i) overlook task-shared directions, which suppresses knowledge transfer, and (ii) fail to capture truly effective task-specific directions since these ``null bases" of old tasks can remain nearly inactive for new task under correlated tasks. To address this, we study LoRA learning capability from a projection energy perspective, and propose Low-rank Decomposition and Adaptation (LoDA). It performs a task-driven decomposition to build general and truly task-specific LoRA subspaces by solving two energy-based objectives, decoupling directions for knowledge sharing and isolation. LoDA fixes LoRA down-projections on two subspaces and learns robust up-projections via a Gradient-Aligned Optimization (GAO) approach. After each task, before integrating the LoRA updates into the backbone, LoDA derives a closed-form recalibration for the general update, approximating a feature-level joint optimum along this task-shared direction. Experiments indicate that LoDA outperforms existing CL methods. Our code is available at https://github.com/HHHLF/LoDA_ICML2026.

---

### OSF: On Pre-training and Scaling of Sleep Foundation Models

Authors: Zitao Shuai, Zongzhe Xu, David Yang, Wei Wang, Yuzhe Yang
Published: 2026-02-27
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.00190v2

Polysomnography (PSG) provides the gold standard for sleep assessment but suffers from substantial heterogeneity across recording devices and cohorts. There have been growing efforts to build general-purpose foundation models (FMs) for sleep physiology, but lack an in-depth understanding of the pre-training process and scaling patterns that lead to more generalizable sleep FMs. To fill this gap, we curate a massive corpus of 166,500 hours of sleep recordings from nine public sources and establish SleepBench, a comprehensive, fully open-source benchmark. Leveraging SleepBench, we systematically evaluate four families of self-supervised pre-training objectives and uncover three critical findings: (1) existing FMs fail to generalize to missing channels at inference; (2) channel-invariant feature learning is essential for pre-training; and (3) scaling sample size, model capacity, and multi-source data mixture consistently improves downstream performance.With an enhanced pre-training and scaling recipe, we introduce OSF, a family of sleep FMs that achieves state-of-the-art performance across nine datasets on diverse sleep and disease prediction tasks. Further analysis of OSF also reveals intriguing properties in sample efficiency, hierarchical aggregation, and cross-dataset scaling.

---

### ST-Lite: Training-Free KV Cache Compression with Spatio-Trajectory Guidance for Long-Horizon GUI Agents

Authors: Bowen Zhou, Zhou Xu, Wanli Li, Jingyu Xiao, Pingan Gan, Haoqian Wang
Published: 2026-02-27
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2603.00188v3

Training-free KV cache compression is essential for deploying vision-language GUI agents under memory and latency constraints, yet existing methods are designed for generic language workloads and ignore the distinctive structure of GUI interaction traces. We characterize three GUI-specific workload properties--high inter-frame visual redundancy, extremely small UI-element spatial footprints, and near-uniform cross-layer attention sparsity--that cause existing schemes to retain as few as 39% of oracle-important KV pairs at the standard 20% budget. To address this, we propose ST-Lite, a training-free compression scheme whose three components each target one property: Trajectory-aware Semantic Gating (TSG) filters redundant historical frames, Component-centric Spatial Saliency (CSS) preserves fine-grained element boundaries, and a flat per-layer budget avoids hierarchical misallocation. Across seven GUI benchmarks and two backbones in the deployment-relevant 10%-40% window, ST-Lite consistently outperforms all existing compression baselines, matching or exceeding Full Cache task accuracy on the primary backbone at the 20% budget while delivering up to 2.35x decoding speedup at fivefold compression. The implementation is available at https://github.com/94wen94/ST-Lite.

---

### Efficient Long-Horizon GUI Agents via Training-Free KV Cache Compression

Authors: Bowen Zhou, Zhou Xu, Wanli Li, Jingyu Xiao, Haoqian Wang
Published: 2026-02-27
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2603.00188v1

Large Vision-Language Models (VLMs) have emerged as powerful engines for autonomous GUI agents, yet their deployment is severely constrained by the substantial memory footprint and latency of the Key-Value (KV) cache during long-horizon interactions. While existing cache compression methods have proven effective for LLMs, we empirically demonstrate that they suffer from suboptimal performance in GUI scenarios due to a fundamental misalignment: unlike general visual tasks where attention sparsity varies across layers, GUI attention patterns exhibit uniform high-sparsity across all transformer layers. Motivated by this insight, we propose ST-Lite, a training-free KV cache compression framework tailored for efficient GUI agents that explicitly addresses the dynamic spatio-trajectory dependencies within GUI data streams. ST-Lite introduces a novel dual-branch scoring policy incorporating Component-centric Spatial Saliency (CSS) and Trajectory-aware Semantic Gating (TSG). Specifically, CSS preserves the structural integrity of interactive UI elements by evaluating local neighborhood saliency, while TSG mitigates historical redundancy by dynamically filtering visually repetitive KV pairs within the interaction trajectory. Extensive evaluations demonstrate that with only a 10-20% cache budget, ST-Lite achieves a 2.45x decoding acceleration while maintaining comparable or even superior performance compared to full-cache baselines, offering a scalable solution for resource-constrained GUI agents.

---

### UFO-4D: Unposed Feedforward 4D Reconstruction from Two Images

Authors: Junhwa Hur, Charles Herrmann, Songyou Peng, Philipp Henzler, Zeyu Ma, Todd Zickler, Deqing Sun
Published: 2026-02-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.24290v2

Dense 4D reconstruction from unposed images remains a critical challenge, with current methods relying on slow test-time optimization or fragmented, task-specific feedforward models. We introduce UFO-4D, a unified feedforward framework to reconstruct a dense, explicit 4D representation from just a pair of unposed images. UFO-4D directly estimates dynamic 3D Gaussian Splats, enabling the joint and consistent estimation of 3D geometry, 3D motion, and camera pose in a feedforward manner. Our core insight is that differentiably rendering multiple signals from a single Dynamic 3D Gaussian representation offers major training advantages. This approach enables a self-supervised image synthesis loss while tightly coupling appearance, depth, and motion. Since all modalities share the same geometric primitives, supervising one inherently regularizes and improves the others. This synergy overcomes data scarcity, allowing UFO-4D to outperform prior work by up to 3 times in joint geometry, motion, and camera pose estimation. Our representation also enables high-fidelity 4D interpolation across novel views and time. Please visit our project page for visual results: https://ufo-4d.github.io/

---

### Mode Seeking meets Mean Seeking for Fast Long Video Generation

Authors: Shengqu Cai, Weili Nie, Chao Liu, Julius Berner, Lvmin Zhang, Nanye Ma, Hansheng Chen, Maneesh Agrawala, Leonidas Guibas, Gordon Wetzstein, Arash Vahdat
Published: 2026-02-27
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2602.24289v3

Scaling video generation from seconds to minutes faces a critical bottleneck: while short-video data is abundant and high-fidelity, coherent long-form data is scarce and limited to narrow domains. To address this, we propose a training paradigm where Mode Seeking meets Mean Seeking, decoupling local fidelity from long-term coherence based on a unified representation via a Decoupled Diffusion Transformer. Our approach utilizes a global Flow Matching head trained via supervised learning on long videos to capture narrative structure, while simultaneously employing a local Distribution Matching head that aligns sliding windows to a frozen short-video teacher via a mode-seeking reverse-KL divergence. This strategy enables the synthesis of minute-scale videos that learns long-range coherence and motions from limited long videos via supervised flow matching, while inheriting local realism by aligning every sliding-window segment of the student to a frozen short-video teacher, resulting in a few-step fast long video generator. Evaluations show that our method effectively closes the fidelity-horizon gap by jointly improving local sharpness, motion and long-range consistency. Project website: https://primecai.github.io/mmm/.

---

### Mode Seeking meets Mean Seeking for Fast Long Video Generation

Authors: Shengqu Cai, Weili Nie, Chao Liu, Julius Berner, Lvmin Zhang, Nanye Ma, Hansheng Chen, Maneesh Agrawala, Leonidas Guibas, Gordon Wetzstein, Arash Vahdat
Published: 2026-02-27
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2602.24289v1

Scaling video generation from seconds to minutes faces a critical bottleneck: while short-video data is abundant and high-fidelity, coherent long-form data is scarce and limited to narrow domains. To address this, we propose a training paradigm where Mode Seeking meets Mean Seeking, decoupling local fidelity from long-term coherence based on a unified representation via a Decoupled Diffusion Transformer. Our approach utilizes a global Flow Matching head trained via supervised learning on long videos to capture narrative structure, while simultaneously employing a local Distribution Matching head that aligns sliding windows to a frozen short-video teacher via a mode-seeking reverse-KL divergence. This strategy enables the synthesis of minute-scale videos that learns long-range coherence and motions from limited long videos via supervised flow matching, while inheriting local realism by aligning every sliding-window segment of the student to a frozen short-video teacher, resulting in a few-step fast long video generator. Evaluations show that our method effectively closes the fidelity-horizon gap by jointly improving local sharpness, motion and long-range consistency. Project website: https://primecai.github.io/mmm/.

---

### DARE-bench: Evaluating Modeling and Instruction Fidelity of LLMs in Data Science

Authors: Fan Shu, Yite Wang, Ruofan Wu, Boyi Liu, Zhewei Yao, Yuxiong He, Feng Yan
Published: 2026-02-27
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.24288v1

The fast-growing demands in using Large Language Models (LLMs) to tackle complex multi-step data science tasks create an emergent need for accurate benchmarking. There are two major gaps in existing benchmarks: (i) the lack of standardized, process-aware evaluation that captures instruction adherence and process fidelity, and (ii) the scarcity of accurately labeled training data. To bridge these gaps, we introduce DARE-bench, a benchmark designed for machine learning modeling and data science instruction following. Unlike many existing benchmarks that rely on human- or model-based judges, all tasks in DARE-bench have verifiable ground truth, ensuring objective and reproducible evaluation. To cover a broad range of tasks and support agentic tools, DARE-bench consists of 6,300 Kaggle-derived tasks and provides both large-scale training data and evaluation sets. Extensive evaluations show that even highly capable models such as gpt-o4-mini struggle to achieve good performance, especially in machine learning modeling tasks. Using DARE-bench training tasks for fine-tuning can substantially improve model performance. For example, supervised fine-tuning boosts Qwen3-32B's accuracy by 1.83x and reinforcement learning boosts Qwen3-4B's accuracy by more than 8x. These significant improvements verify the importance of DARE-bench both as an accurate evaluation benchmark and critical training data.

---

### Do LLMs Benefit From Their Own Words?

Authors: Jenny Y. Huang, Leshem Choshen, Wei Sun, Omar Khattab, Ramón Fernandez Astudillo, Mehul Damani, Tamara Broderick, Jacob Andreas
Published: 2026-02-27
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2602.24287v2

In multi-turn conversations, large language models typically condition on the full conversation history: both past user prompts and assistant responses. We revisit this design choice by comparing full-context prompting to four alternative, substantially-reduced context configurations. Analyzing in-the-wild multi-turn conversations across three open reasoning and one state-of-the-art model, we find that response quality is largely preserved under aggressive context filtering: replacing all prior assistant turns with one-sentence summaries or keeping only the most recent user--assistant exchange often matches storing full context in performance while using roughly 8x less context. To understand this result, we observe that a substantial fraction of user turns (36.4%) in multi-turn conversations are self-contained and that many follow-up turns can be addressed by seeing only the immediately preceding user--assistant exchange. Furthermore, we find that when models condition on their own past responses, this can lead to context pollution, a phenomenon in which reasoning errors, hallucinations, or stylistic artifacts propagate across turns. Motivated by these findings, we design a context-filtering approach that selectively omits the assistant-side history. Taken together, these findings suggest moving away from storing full dialogue transcripts and instead retaining only what is relevant.

---

### Do LLMs Benefit From Their Own Words?

Authors: Jenny Y. Huang, Leshem Choshen, Ramon Astudillo, Tamara Broderick, Jacob Andreas
Published: 2026-02-27
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2602.24287v1

Multi-turn interactions with large language models typically retain the assistant's own past responses in the conversation history. In this work, we revisit this design choice by asking whether large language models benefit from conditioning on their own prior responses. Using in-the-wild, multi-turn conversations, we compare standard (full-context) prompting with a user-turn-only prompting approach that omits all previous assistant responses, across three open reasoning models and one state-of-the-art model. To our surprise, we find that removing prior assistant responses does not affect response quality on a large fraction of turns. Omitting assistant-side history can reduce cumulative context lengths by up to 10x. To explain this result, we find that multi-turn conversations consist of a substantial proportion (36.4%) of self-contained prompts, and that many follow-up prompts provide sufficient instruction to be answered using only the current user turn and prior user turns. When analyzing cases where user-turn-only prompting substantially outperforms full context, we identify instances of context pollution, in which models over-condition on their previous responses, introducing errors, hallucinations, or stylistic artifacts that propagate across turns. Motivated by these findings, we design a context-filtering approach that selectively omits assistant-side context. Our findings suggest that selectively omitting assistant history can improve response quality while reducing memory consumption.

---

### CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation

Authors: Weinan Dai, Hanlin Wu, Qiying Yu, Huan-ang Gao, Jiahao Li, Chengquan Jiang, Weiqiang Lou, Yufan Song, Hongli Yu, Jiaze Chen, Wei-Ying Ma, Ya-Qin Zhang et al.
Published: 2026-02-27
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.24286v1

GPU kernel optimization is fundamental to modern deep learning but remains a highly specialized task requiring deep hardware expertise. Despite strong performance in general programming, large language models (LLMs) remain uncompetitive with compiler-based systems such as torch.compile for CUDA kernel generation. Existing CUDA code generation approaches either rely on training-free refinement or fine-tune models within fixed multi-turn execution-feedback loops, but both paradigms fail to fundamentally improve the model's intrinsic CUDA optimization ability, resulting in limited performance gains. We present CUDA Agent, a large-scale agentic reinforcement learning system that develops CUDA kernel expertise through three components: a scalable data synthesis pipeline, a skill-augmented CUDA development environment with automated verification and profiling to provide reliable reward signals, and reinforcement learning algorithmic techniques enabling stable training. CUDA Agent achieves state-of-the-art results on KernelBench, delivering 100\%, 100\%, and 92\% faster rate over torch.compile on KernelBench Level-1, Level-2, and Level-3 splits, outperforming the strongest proprietary models such as Claude Opus 4.5 and Gemini 3 Pro by about 40\% on the hardest Level-3 setting.

---

### Taming Momentum: Rethinking Optimizer States Through Low-Rank Approximation

Authors: Zhengbo Wang, Jian Liang, Ran He, Zilei Wang, Tieniu Tan
Published: 2026-02-27
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.24283v1

Modern optimizers like Adam and Muon are central to training large language models, but their reliance on first- and second-order momenta introduces significant memory overhead, which constrains scalability and computational efficiency. In this work, we reframe the exponential moving average (EMA) used in these momenta as the training of a linear regressor via online gradient flow. Building on this equivalence, we introduce LoRA-Pre, a novel low-rank optimizer designed for efficient pre-training. Specifically, LoRA-Pre reduces the optimizer's memory footprint by decomposing the full momentum matrix into a compact low-rank subspace within the online linear learner, thereby maintaining optimization performance while improving memory efficiency. We empirically validate LoRA-Pre's efficacy by pre-training models from the Llama architecture family, scaling from 60M to 1B parameters. LoRA-Pre achieves the highest performance across all model sizes. Notably, LoRA-Pre demonstrates remarkable rank efficiency, achieving comparable or superior results using only 1/8 the rank of baseline methods. Beyond pre-training, we evaluate LoRA-Pre's effectiveness in fine-tuning scenarios. With the same rank, LoRA-Pre consistently outperforms all efficient fine-tuning baselines. Specifically, compared to standard LoRA, LoRA-Pre achieves substantial improvements of 3.14 points on Llama-3.1-8B and 6.17 points on Llama-2-7B, validating our approach's effectiveness across both pre-training and fine-tuning paradigms. Our code is publicly available at https://github.com/mrflogs/LoRA-Pre.

---

### Memory Caching: RNNs with Growing Memory

Authors: Ali Behrouz, Zeman Li, Yuan Deng, Peilin Zhong, Meisam Razaviyayn, Vahab Mirrokni
Published: 2026-02-27
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.24281v1

Transformers have been established as the de-facto backbones for most recent advances in sequence modeling, mainly due to their growing memory capacity that scales with the context length. While plausible for retrieval tasks, it causes quadratic complexity and so has motivated recent studies to explore viable subquadratic recurrent alternatives. Despite showing promising preliminary results in diverse domains, such recurrent architectures underperform Transformers in recall-intensive tasks, often attributed to their fixed-size memory. In this paper, we introduce Memory Caching (MC), a simple yet effective technique that enhances recurrent models by caching checkpoints of their memory states (a.k.a. hidden states). Memory Caching allows the effective memory capacity of RNNs to grow with sequence length, offering a flexible trade-off that interpolates between the fixed memory (i.e., $O(L)$ complexity) of RNNs and the growing memory (i.e., $O(L^2)$ complexity) of Transformers. We propose four variants of MC, including gated aggregation and sparse selective mechanisms, and discuss their implications on both linear and deep memory modules. Our experimental results on language modeling, and long-context understanding tasks show that MC enhances the performance of recurrent models, supporting its effectiveness. The results of in-context recall tasks indicate that while Transformers achieve the best accuracy, our MC variants show competitive performance, close the gap with Transformers, and performs better than state-of-the-art recurrent models.

---

### Who Guards the Guardians? The Challenges of Evaluating Identifiability of Learned Representations

Authors: Shruti Joshi, Théo Saulus, Wieland Brendel, Philippe Brouillard, Dhanya Sridhar, Patrik Reizinger
Published: 2026-02-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.24278v1

Identifiability in representation learning is commonly evaluated using standard metrics (e.g., MCC, DCI, R^2) on synthetic benchmarks with known ground-truth factors. These metrics are assumed to reflect recovery up to the equivalence class guaranteed by identifiability theory. We show that this assumption holds only under specific structural conditions: each metric implicitly encodes assumptions about both the data-generating process (DGP) and the encoder. When these assumptions are violated, metrics become misspecified and can produce systematic false positives and false negatives. Such failures occur both within classical identifiability regimes and in post-hoc settings where identifiability is most needed. We introduce a taxonomy separating DGP assumptions from encoder geometry, use it to characterise the validity domains of existing metrics, and release an evaluation suite for reproducible stress testing and comparison.

---

### Resources for Automated Evaluation of Assistive RAG Systems that Help Readers with News Trustworthiness Assessment

Authors: Dake Zhang, Mark D. Smucker, Charles L. A. Clarke
Published: 2026-02-27
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2602.24277v1

Many readers today struggle to assess the trustworthiness of online news because reliable reporting coexists with misinformation. The TREC 2025 DRAGUN (Detection, Retrieval, and Augmented Generation for Understanding News) Track provided a venue for researchers to develop and evaluate assistive RAG systems that support readers' news trustworthiness assessment by producing reader-oriented, well-attributed reports. As the organizers of the DRAGUN track, we describe the resources that we have newly developed to allow for the reuse of the track's tasks. The track had two tasks: (Task 1) Question Generation, producing 10 ranked investigative questions; and (Task 2, the main task) Report Generation, producing a 250-word report grounded in the MS MARCO V2.1 Segmented Corpus. As part of the track's evaluation, we had TREC assessors create importance-weighted rubrics of questions with expected short answers for 30 different news articles. These rubrics represent the information that assessors believe is important for readers to assess an article's trustworthiness. The assessors then used their rubrics to manually judge the participating teams' submitted runs. To make these tasks and their rubrics reusable, we have created an automated process to judge runs not part of the original assessing. We show that our AutoJudge ranks existing runs well compared to the TREC human-assessed evaluation (Kendall's $τ= 0.678$ for Task 1 and $τ= 0.872$ for Task 2). These resources enable both the evaluation of RAG systems for assistive news trustworthiness assessment and, with the human evaluation as a benchmark, research on improving automated RAG evaluation.

---

### Hierarchical Action Learning for Weakly-Supervised Action Segmentation

Authors: Junxian Huang, Ruichu Cai, Hao Zhu, Juntao Fang, Boyan Xu, Weilin Chen, Zijian Li, Shenghua Gao
Published: 2026-02-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.24275v1

Humans perceive actions through key transitions that structure actions across multiple abstraction levels, whereas machines, relying on visual features, tend to over-segment. This highlights the difficulty of enabling hierarchical reasoning in video understanding. Interestingly, we observe that lower-level visual and high-level action latent variables evolve at different rates, with low-level visual variables changing rapidly, while high-level action variables evolve more slowly, making them easier to identify. Building on this insight, we propose the Hierarchical Action Learning (\textbf{HAL}) model for weakly-supervised action segmentation. Our approach introduces a hierarchical causal data generation process, where high-level latent action governs the dynamics of low-level visual features. To model these varying timescales effectively, we introduce deterministic processes to align these latent variables over time. The \textbf{HAL} model employs a hierarchical pyramid transformer to capture both visual features and latent variables, and a sparse transition constraint is applied to enforce the slower dynamics of high-level action variables. This mechanism enhances the identification of these latent variables over time. Under mild assumptions, we prove that these latent action variables are strictly identifiable. Experimental results on several benchmarks show that the \textbf{HAL} model significantly outperforms existing methods for weakly-supervised action segmentation, confirming its practical effectiveness in real-world applications.

---

### A Minimal Agent for Automated Theorem Proving

Authors: Borja Requena, Austin Letson, Krystian Nowakowski, Izan Beltran-Ferreiro, Leopoldo Sarra
Published: 2026-02-27
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.24273v3

We propose a minimal agentic baseline that enables systematic comparison across different AI-based theorem prover architectures. This design implements the core features shared among state-of-the-art systems: iterative proof refinement, library search and context management. We evaluate this agentic approach using qualitatively different benchmarks and compare various frontier language models and design choices. Our results show competitive performance compared to state-of-the-art approaches, while using a significantly simpler architecture and a fraction of their cost. Additionally, we demonstrate consistent advantages of an iterative approach over multiple single-shot generations, especially in terms of sample efficiency and cost effectiveness. The implementation is released open-source as a candidate reference for future research and as an accessible prover for the community.

---

### Causal Mechanism Reduction: Mechanism Replacement for Neural Network Pruning and Abstraction

Authors: Amir Asiaee
Published: 2026-02-27
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.24266v2

Which internal mechanisms of a neural network can be replaced while preserving the computation it performs? Structured pruning asks for smaller deployable networks; causal abstraction asks for high-level models that commute with interventions. We introduce causal mechanism reduction (CMR), a framework that treats a trained network as a deterministic structural causal model and replaces selected internal variables by constants or affine functions of retained variables. These replacements compile exactly into smaller dense networks by bias and weight folding, and induce reduced causal models testable with interchange interventions. We derive a unified second-order replacement-risk objective whose special cases recover mean replacement, variance-based pruning (VBP), logit-distortion scoring, and affine neuron merging, together with a margin-based certificate linking logit distortion to interchange-intervention agreement. The framework also exposes a basic invariance requirement: functionally identical ReLU networks should induce the same reduction. Under exact positive-scaling reparameterizations, VBP's kept set collapses to chance-level overlap while the logit-distortion score is exactly invariant. Empirically, CMR variants are competitive with VBP under matched fine-tuning of DeiT-Tiny on ImageNet-100; the clearer separation appears in the invariance and interchange tests, where the logit-distortion score preserves kept sets and consistently improves distributional fidelity. CMR thus gives pruning, compilation, and causal-abstraction verification a common object to optimize and verify.

---

### Compositional Generalization Requires Linear, Orthogonal Representations in Vision Embedding Models

Authors: Arnas Uselis, Andrea Dittadi, Seong Joon Oh
Published: 2026-02-27
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2602.24264v2

Compositional generalization, the ability to recognize familiar parts in novel contexts, is a defining property of intelligent systems. Although modern models are trained on massive datasets, they still cover only a tiny fraction of the combinatorial space of possible inputs, raising the question of what structure representations must have to support generalization to unseen combinations. We formalize three desiderata for compositional generalization under standard training (divisibility, transferability, stability) and show they impose necessary geometric constraints: representations must decompose linearly into per-concept components, and these components must be orthogonal across concepts. This provides theoretical grounding for the Linear Representation Hypothesis: the linear structure widely observed in neural representations is a necessary consequence of compositional generalization. We further derive dimension bounds linking the number of composable concepts to the embedding geometry. Empirically, we evaluate these predictions across modern vision models (CLIP, SigLIP, DINO) and find that representations exhibit partial linear factorization with low-rank, near-orthogonal per-concept factors, and that the degree of this structure correlates with compositional generalization on unseen combinations. As models continue to scale, these conditions predict the representational geometry they may converge to. Code is available at https://github.com/oshapio/necessary-compositionality.

---

### Active Bipartite Ranking with Smooth Posterior Distributions

Authors: James Cheshire, Stephan Clémençon
Published: 2026-02-27
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2602.24263v1

In this article, bipartite ranking, a statistical learning problem involved in many applications and widely studied in the passive context, is approached in a much more general \textit{active setting} than the discrete one previously considered in the literature. While the latter assumes that the conditional distribution is piece wise constant, the framework we develop permits in contrast to deal with continuous conditional distributions, provided that they fulfill a Hölder smoothness constraint. We first show that a naive approach based on discretisation at a uniform level, fixed \textit{a priori} and consisting in applying next the active strategy designed for the discrete setting generally fails. Instead, we propose a novel algorithm, referred to as smooth-rank and designed for the continuous setting, which aims to minimise the distance between the ROC curve of the estimated ranking rule and the optimal one w.r.t. the $\sup$ norm. We show that, for a fixed confidence level $ε>0$ and probability $δ\in (0,1)$, smooth-rank is PAC$(ε,δ)$. In addition, we provide a problem dependent upper bound on the expected sampling time of smooth-rank and establish a problem dependent lower bound on the expected sampling time of any PAC$(ε,δ)$ algorithm. Beyond the theoretical analysis carried out, numerical results are presented, providing solid empirical evidence of the performance of the algorithm proposed, which compares favorably with alternative approaches.

---

### Coverage-Aware Web Crawling for Domain-Specific Supplier Discovery via a Web--Knowledge--Web Pipeline

Authors: Yijiashun Qi, Yijiazhen Qi, Tanmay Wagh
Published: 2026-02-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.24262v4

Identifying the full landscape of small and medium-sized enterprises (SMEs) in specialized industry sectors is critical for supply-chain resilience, yet existing business databases suffer from substantial coverage gaps -- particularly for sub-tier suppliers and firms in emerging niche markets. We propose a \textbf{Web--Knowledge--Web (W$\to$K$\to$W)} pipeline that iteratively (1)~crawls domain-specific web sources to discover candidate supplier entities, (2)~extracts and consolidates structured knowledge into a heterogeneous knowledge graph using domain-adapted few-shot LLM prompting, and (3)~uses the knowledge graph's topology and coverage signals to guide subsequent crawling toward under-represented regions of the supplier space. To quantify discovery completeness, we introduce a \textbf{coverage estimation framework} inspired by ecological species-richness estimators (Chao1, ACE) adapted for web-entity populations. Experiments on the semiconductor equipment manufacturing sector (NAICS 333242) demonstrate that the W$\to$K$\to$W pipeline achieves the highest precision (0.165) and F1 (0.123) among all methods while using only 144 pages -- 32\% fewer than the 213-page baseline budget -- building a knowledge graph of 664 entities and 542 relations with 100\% relation type-consistency.

---

### FaultXformer: A Transformer-Encoder Based Fault Classification and Location Identification model in PMU-Integrated Active Electrical Distribution System

Authors: Kriti Thakur, Alivelu Manga Parimi, Mayukha Pal
Published: 2026-02-27
Categories: eess.SY, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.24254v1

Accurate fault detection and localization in electrical distribution systems is crucial, especially with the increasing integration of distributed energy resources (DERs), which inject greater variability and complexity into grid operations. In this study, FaultXformer is proposed, a Transformer encoder-based architecture developed for automatic fault analysis using real-time current data obtained from phasor measurement unit (PMU). The approach utilizes time-series current data to initially extract rich temporal information in stage 1, which is crucial for identifying the fault type and precisely determining its location across multiple nodes. In Stage 2, these extracted features are processed to differentiate among distinct fault types and identify the respective fault location within the distribution system. Thus, this dual-stage transformer encoder pipeline enables high-fidelity representation learning, considerably boosting the performance of the work. The model was validated on a dataset generated from the IEEE 13-node test feeder, simulated with 20 separate fault locations and several DER integration scenarios, utilizing current measurements from four strategically located PMUs. To demonstrate robust performance evaluation, stratified 10-fold cross-validation is performed. FaultXformer achieved average accuracies of 98.76% in fault type classification and 98.92% in fault location identification across cross-validation, consistently surpassing conventional deep learning baselines convolutional neural network (CNN), recurrent neural network (RNN). long short-term memory (LSTM) by 1.70%, 34.95%, and 2.04% in classification accuracy and by 10.82%, 40.89%, and 6.27% in location accuracy, respectively. These results demonstrate the efficacy of the proposed model with significant DER penetration.

---

### Histopathology Image Normalization via Latent Manifold Compaction

Authors: Xiaolong Zhang, Jianwei Zhang, Selim Sevim, Emek Demir, Ece Eksi, Xubo Song
Published: 2026-02-27
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2602.24251v1

Batch effects arising from technical variations in histopathology staining protocols, scanners, and acquisition pipelines pose a persistent challenge for computational pathology, hindering cross-batch generalization and limiting reliable deployment of models across clinical sites. In this work, we introduce Latent Manifold Compaction (LMC), an unsupervised representation learning framework that performs image harmonization by learning batch-invariant embeddings from a single source dataset through explicit compaction of stain-induced latent manifolds. This allows LMC to generalize to target domain data unseen during training. Evaluated on three challenging public and in-house benchmarks, LMC substantially reduces batch-induced separations across multiple datasets and consistently outperforms state-of-the-art normalization methods in downstream cross-batch classification and detection tasks, enabling superior generalization.

---

### Chunk-wise Attention Transducers for Fast and Accurate Streaming Speech-to-Text

Authors: Hainan Xu, Vladimir Bataev, Travis M. Bartley, Jagadeesh Balam
Published: 2026-02-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.24245v1

We propose Chunk-wise Attention Transducer (CHAT), a novel extension to RNN-T models that processes audio in fixed-size chunks while employing cross-attention within each chunk. This hybrid approach maintains RNN-T's streaming capability while introducing controlled flexibility for local alignment modeling. CHAT significantly reduces the temporal dimension that RNN-T must handle, yielding substantial efficiency improvements: up to 46.2% reduction in peak training memory, up to 1.36X faster training, and up to 1.69X faster inference. Alongside these efficiency gains, CHAT achieves consistent accuracy improvements over RNN-T across multiple languages and tasks -- up to 6.3% relative WER reduction for speech recognition and up to 18.0% BLEU improvement for speech translation. The method proves particularly effective for speech translation, where RNN-T's strict monotonic alignment hurts performance. Our results demonstrate that the CHAT model offers a practical solution for deploying more capable streaming speech models without sacrificing real-time constraints.

---

### Joint Geometric and Trajectory Consistency Learning for One-Step Real-World Super-Resolution

Authors: Chengyan Deng, Zhangquan Chen, Li Yu, Kai Zhang, Xue Zhou, Wang Zhang
Published: 2026-02-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.24240v1

Diffusion-based Real-World Image Super-Resolution (Real-ISR) achieves impressive perceptual quality but suffers from high computational costs due to iterative sampling. While recent distillation approaches leveraging large-scale Text-to-Image (T2I) priors have enabled one-step generation, they are typically hindered by prohibitive parameter counts and the inherent capability bounds imposed by teacher models. As a lightweight alternative, Consistency Models offer efficient inference but struggle with two critical limitations: the accumulation of consistency drift inherent to transitive training, and a phenomenon we term "Geometric Decoupling" - where the generative trajectory achieves pixel-wise alignment yet fails to preserve structural coherence. To address these challenges, we propose GTASR (Geometric Trajectory Alignment Super-Resolution), a simple yet effective consistency training paradigm for Real-ISR. Specifically, we introduce a Trajectory Alignment (TA) strategy to rectify the tangent vector field via full-path projection, and a Dual-Reference Structural Rectification (DRSR) mechanism to enforce strict structural constraints. Extensive experiments verify that GTASR delivers superior performance over representative baselines while maintaining minimal latency. The code and model will be released at https://github.com/Blazedengcy/GTASR.

---

### Time Series Foundation Models as Strong Baselines in Transportation Forecasting: A Large-Scale Benchmark Analysis

Authors: Javier Yanes-Pulido, Filipe Rodrigues
Published: 2026-02-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.24238v2

Accurate forecasting of transportation dynamics is essential for urban mobility and infrastructure planning. Although recent work has achieved strong performance with deep learning models, these methods typically require dataset-specific training, architecture design and hyper-parameter tuning. This paper evaluates whether general-purpose time-series foundation models can serve as forecasters for transportation tasks by benchmarking the zero-shot performance of the state-of-the-art model, Chronos-2, across ten real-world datasets covering highway traffic volume and flow, urban traffic speed, bike-sharing demand, and electric vehicle charging station data. Under a consistent evaluation protocol, we find that, even without any task-specific fine-tuning, Chronos-2 delivers state-of-the-art or competitive accuracy across most datasets, frequently outperforming classical statistical baselines and specialized deep learning architectures, particularly at longer horizons. Beyond point forecasting, we evaluate its native probabilistic outputs using prediction-interval coverage and sharpness, demonstrating that Chronos-2 also provides useful uncertainty quantification without dataset-specific training. In general, this study supports the adoption of time-series foundation models as a key baseline for transportation forecasting research.

---

### SafeGen-LLM: Enhancing Safety Generalization in Task Planning for Robotic Systems

Authors: Jialiang Fan, Weizhe Xu, Mengyu Liu, Oleg Sokolsky, Insup Lee, Fanxin Kong
Published: 2026-02-27
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2602.24235v1

Safety-critical task planning in robotic systems remains challenging: classical planners suffer from poor scalability, Reinforcement Learning (RL)-based methods generalize poorly, and base Large Language Models (LLMs) cannot guarantee safety. To address this gap, we propose safety-generalizable large language models, named SafeGen-LLM. SafeGen-LLM can not only enhance the safety satisfaction of task plans but also generalize well to novel safety properties in various domains. We first construct a multi-domain Planning Domain Definition Language 3 (PDDL3) benchmark with explicit safety constraints. Then, we introduce a two-stage post-training framework: Supervised Fine-Tuning (SFT) on a constraint-compliant planning dataset to learn planning syntax and semantics, and Group Relative Policy Optimization (GRPO) guided by fine-grained reward machines derived from formal verification to enforce safety alignment and by curriculum learning to better handle complex tasks. Extensive experiments show that SafeGen-LLM achieves strong safety generalization and outperforms frontier proprietary baselines across multi-domain planning tasks and multiple input formats (e.g., PDDLs and natural language).

---

### Enhancing Spatial Understanding in Image Generation via Reward Modeling

Authors: Zhenyu Tang, Chaoran Feng, Yufan Deng, Jie Wu, Xiaojie Li, Rui Wang, Yunpeng Chen, Daquan Zhou
Published: 2026-02-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.24233v1

Recent progress in text-to-image generation has greatly advanced visual fidelity and creativity, but it has also imposed higher demands on prompt complexity-particularly in encoding intricate spatial relationships. In such cases, achieving satisfactory results often requires multiple sampling attempts. To address this challenge, we introduce a novel method that strengthens the spatial understanding of current image generation models. We first construct the SpatialReward-Dataset with over 80k preference pairs. Building on this dataset, we build SpatialScore, a reward model designed to evaluate the accuracy of spatial relationships in text-to-image generation, achieving performance that even surpasses leading proprietary models on spatial evaluation. We further demonstrate that this reward model effectively enables online reinforcement learning for the complex spatial generation. Extensive experiments across multiple benchmarks show that our specialized reward model yields significant and consistent gains in spatial understanding for image generation.

---

### Better Learning-Augmented Spanning Tree Algorithms via Metric Forest Completion

Authors: Nate Veldt, Thomas Stanley, Benjamin W. Priest, Trevor Steil, Keita Iwabuchi, T. S. Jayram, Grace J. Li, Geoffrey Sanders
Published: 2026-02-27
Categories: cs.DS, cs.LG
arXiv: https://arxiv.org/abs/2602.24232v1

We present improved learning-augmented algorithms for finding an approximate minimum spanning tree (MST) for points in an arbitrary metric space. Our work follows a recent framework called metric forest completion (MFC), where the learned input is a forest that must be given additional edges to form a full spanning tree. Veldt et al. (2025) showed that optimally completing the forest takes $Ω(n^2)$ time, but designed a 2.62-approximation for MFC with subquadratic complexity. The same method is a $(2γ+ 1)$-approximation for the original MST problem, where $γ\geq 1$ is a quality parameter for the initial forest. We introduce a generalized method that interpolates between this prior algorithm and an optimal $Ω(n^2)$-time MFC algorithm. Our approach considers only edges incident to a growing number of strategically chosen ``representative'' points. One corollary of our analysis is to improve the approximation factor of the previous algorithm from 2.62 for MFC and $(2γ+1)$ for metric MST to 2 and $2γ$ respectively. We prove this is tight for worst-case instances, but we still obtain better instance-specific approximations using our generalized method. We complement our theoretical results with a thorough experimental evaluation.

---

### Adaptive Combinatorial Experimental Design: Pareto Optimality for Decision-Making and Inference

Authors: Hongrui Xie, Junyu Cao, Kan Xu
Published: 2026-02-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.24231v1

In this paper, we provide the first investigation into adaptive combinatorial experimental design, focusing on the trade-off between regret minimization and statistical power in combinatorial multi-armed bandits (CMAB). While minimizing regret requires repeated exploitation of high-reward arms, accurate inference on reward gaps requires sufficient exploration of suboptimal actions. We formalize this trade-off through the concept of Pareto optimality and establish equivalent conditions for Pareto-efficient learning in CMAB. We consider two relevant cases under different information structures, i.e., full-bandit feedback and semi-bandit feedback, and propose two algorithms MixCombKL and MixCombUCB respectively for these two cases. We provide theoretical guarantees showing that both algorithms are Pareto optimal, achieving finite-time guarantees on both regret and estimation error of arm gaps. Our results further reveal that richer feedback significantly tightens the attainable Pareto frontier, with the primary gains arising from improved estimation accuracy under our proposed methods. Taken together, these findings establish a principled framework for adaptive combinatorial experimentation in multi-objective decision-making.

---

### A Variational Estimator for $L_p$ Calibration Errors

Authors: Eugène Berta, Sacha Braun, David Holzmüller, Francis Bach, Michael I. Jordan
Published: 2026-02-27
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2602.24230v1

Calibration$\unicode{x2014}$the problem of ensuring that predicted probabilities align with observed class frequencies$\unicode{x2014}$is a basic desideratum for reliable prediction with machine learning systems. Calibration error is traditionally assessed via a divergence function, using the expected divergence between predictions and empirical frequencies. Accurately estimating this quantity is challenging, especially in the multiclass setting. Here, we show how to extend a recent variational framework for estimating calibration errors beyond divergences induced induced by proper losses, to cover a broad class of calibration errors induced by $L_p$ divergences. Our method can separate over- and under-confidence and, unlike non-variational approaches, avoids overestimation. We provide extensive experiments and integrate our code in the open-source package probmetrics (https://github.com/dholzmueller/probmetrics) for evaluating calibration errors.

---

### BLISSNet: Deep Operator Learning for Fast and Accurate Flow Reconstruction from Sparse Sensor Measurements

Authors: Maksym Veremchuk, K. Andrea Scott, Zhao Pan
Published: 2026-02-27
Categories: physics.flu-dyn, cs.LG
arXiv: https://arxiv.org/abs/2602.24228v1

Reconstructing fluid flows from sparse sensor measurements is a fundamental challenge in science and engineering. Widely separated measurements and complex, multiscale dynamics make accurate recovery of fine-scale structures difficult. In addition, existing methods face a persistent tradeoff: high-accuracy models are often computationally expensive, whereas faster approaches typically compromise fidelity. In this work, we introduce BLISSNet, a model that strikes a strong balance between reconstruction accuracy and computational efficiency for both flow reconstruction and nudging-based data assimilation. The model follows a DeepONet-like architecture, enabling zero-shot inference on domains of arbitrary size. After the first model call on a given domain, certain network components can be precomputed, leading to low inference cost for subsequent evaluations on large domains. Consequently, the model can achieve faster inference than classical interpolation methods such as radial basis function or bicubic interpolation. This combination of high accuracy, low cost, and zero-shot generalization makes BLISSNet well-suited for large-scale real-time flow reconstruction and data assimilation tasks.

---

### MuViT: Multi-Resolution Vision Transformers for Learning Across Scales in Microscopy

Authors: Albert Dominguez Mantes, Gioele La Manno, Martin Weigert
Published: 2026-02-27
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2602.24222v1

Modern microscopy routinely produces gigapixel images that contain structures across multiple spatial scales, from fine cellular morphology to broader tissue organization. Many analysis tasks require combining these scales, yet most vision models operate at a single resolution or derive multi-scale features from one view, limiting their ability to exploit the inherently multi-resolution nature of microscopy data. We introduce MuViT, a transformer architecture built to fuse true multi-resolution observations from the same underlying image. MuViT embeds all patches into a shared world-coordinate system and extends rotary positional embeddings to these coordinates, enabling attention to integrate wide-field context with high-resolution detail within a single encoder. Across synthetic benchmarks, kidney histopathology, and high-resolution mouse-brain microscopy, MuViT delivers consistent improvements over strong ViT and CNN baselines. Multi-resolution MAE pretraining further produces scale-consistent representations that enhance downstream tasks. These results demonstrate that explicit world-coordinate modelling provides a simple yet powerful mechanism for leveraging multi-resolution information in large-scale microscopy analysis.

---

### Comparing Classical and Quantum Variational Classifiers on the XOR Problem

Authors: Miras Seilkhan, Adilbek Taizhanov
Published: 2026-02-27
Categories: cs.LG, quant-ph
arXiv: https://arxiv.org/abs/2602.24220v1

Quantum machine learning applies principles such as superposition and entanglement to data processing and optimization. Variational quantum models operate on qubits in high-dimensional Hilbert spaces and provide an alternative approach to model expressivity. We compare classical models and a variational quantum classifier on the XOR problem. Logistic regression, a one-hidden-layer multilayer perceptron, and a two-qubit variational quantum classifier with circuit depths 1 and 2 are evaluated on synthetic XOR datasets with varying Gaussian noise and sample sizes using accuracy and binary cross-entropy. Performance is determined primarily by model expressivity. Logistic regression and the depth-1 quantum circuit fail to represent XOR reliably, whereas the multilayer perceptron and the depth-2 quantum circuit achieve perfect test accuracy under representative conditions. Robustness analyses across noise levels, dataset sizes, and random seeds confirm that circuit depth is decisive for quantum performance on this task. Despite matching accuracy, the multilayer perceptron achieves lower binary cross-entropy and substantially shorter training time. Hardware execution preserves the global XOR structure but introduces structured deviations in the decision function. Overall, deeper variational quantum classifiers can match classical neural networks in accuracy on low-dimensional XOR benchmarks, but no clear empirical advantage in robustness or efficiency is observed in the examined settings.

---

### From Leaky Thoughts to Private Reasoning: Controlling What LRMs Say to Themselves

Authors: Haritz Puerto, Haonan Li, Xudong Han, Timothy Baldwin, Iryna Gurevych
Published: 2026-02-27
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2602.24210v4

Large reasoning models (LRMs) produce reasoning traces (RTs) that often contain sensitive information. These leaky thoughts are difficult to control and frequently violate explicit privacy directives. Because RTs can be exposed through prompt injection attacks, this becomes a direct privacy risk to the user. We approach this as a controllability problem: since privacy directives are themselves instructions, improving instruction-following (IF) within the RT provides a direct path to reducing privacy leaks. To this end, we introduce an SFT dataset that teaches models to follow general instructions throughout their reasoning process, and propose Staged Decoding, a simple decoding strategy that decouples RT and answer generation using separate LoRA adapters to maximize IF of each component. We evaluate our approach on six models from two families (1.7B-14B parameters), across two IF benchmarks and two privacy benchmarks. Our method yields substantial improvements, with gains of up to 20.9 points in IF and 51.9 percentage points on privacy benchmarks, though these can come at the cost of task utility due to the trade-off between reasoning performance and IF. Our results show that improving IF in LRMs can significantly enhance privacy, suggesting a promising direction for future privacy-aware LRMs. Our code is available at https://github.com/UKPLab/arxiv2026-controllable-reasoning-models.

---

### From Leaky Thoughts to Private Reasoning: Controlling What LRMs Say to Themselves

Authors: Haritz Puerto, Haonan Li, Xudong Han, Timothy Baldwin, Iryna Gurevych
Published: 2026-02-27
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2602.24210v2

Large reasoning models (LRMs) produce reasoning traces (RTs) that often contain sensitive information. These leaky thoughts are difficult to control and frequently violate explicit privacy directives. Because RTs can be exposed through prompt injection attacks, this becomes a direct privacy risk to the user. We approach this as a controllability problem: since privacy directives are themselves instructions, improving instruction-following (IF) within the RT provides a direct path to reducing privacy leaks. To this end, we introduce an SFT dataset that teaches models to follow general instructions throughout their reasoning process, and propose Staged Decoding, a simple decoding strategy that decouples RT and answer generation using separate LoRA adapters to maximize IF of each component. We evaluate our approach on six models from two families (1.7B-14B parameters), across two IF benchmarks and two privacy benchmarks. Our method yields substantial improvements, with gains of up to 20.9 points in IF and 51.9 percentage points on privacy benchmarks, though these can come at the cost of task utility due to the trade-off between reasoning performance and IF. Our results show that improving IF in LRMs can significantly enhance privacy, suggesting a promising direction for future privacy-aware LRMs. Our code is available at https://github.com/UKPLab/arxiv2026-controllable-reasoning-models.

---

### An Efficient Unsupervised Federated Learning Approach for Anomaly Detection in Heterogeneous IoT Networks

Authors: Mohsen Tajgardan, Atena Shiranzaei, Mahdi Rabbani, Reza Khoshkangini, Mahtab Jamali
Published: 2026-02-27
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.24209v1

Federated learning (FL) is an effective paradigm for distributed environments such as the Internet of Things (IoT), where data from diverse devices with varying functionalities remains localized while contributing to a shared global model. By eliminating the need to transmit raw data, FL inherently preserves privacy. However, the heterogeneous nature of IoT data, stemming from differences in device capabilities, data formats, and communication constraints, poses significant challenges to maintaining both global model performance and privacy. In the context of IoT-based anomaly detection, unsupervised FL offers a promising means to identify abnormal behavior without centralized data aggregation. Nevertheless, feature heterogeneity across devices complicates model training and optimization, hindering effective implementation. In this study we propose an efficient unsupervised FL framework that enhances anomaly detection by leveraging shared features from two distinct IoT datasets: one focused on anomaly detection and the other on device identification, while preserving dataset-specific features. To improve transparency and interpretability, we employ explainable AI techniques, such as SHAP, to identify key features influencing local model decisions. Experiments conducted on real-world IoT datasets demonstrate that the proposed method significantly outperforms conventional FL approaches in anomaly detection accuracy. This work underscores the potential of using shared features from complementary datasets to optimize unsupervised federated learning and achieve superior anomaly detection results in decentralized IoT environments.

---

### SenCache: Accelerating Diffusion Model Inference via Sensitivity-Aware Caching

Authors: Yasaman Haghighi, Alexandre Alahi
Published: 2026-02-27
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2602.24208v2

Diffusion models achieve state-of-the-art video generation quality, but their inference remains expensive due to the large number of sequential denoising steps. This has motivated a growing line of research on accelerating diffusion inference. Among training-free acceleration methods, caching reduces computation by reusing previously computed model outputs across timesteps. Existing caching methods rely on heuristic criteria to choose cache/reuse timesteps and require extensive tuning. We address this limitation with a principled sensitivity-aware caching framework. Specifically, we formalize the caching error through an analysis of the model output sensitivity to perturbations in the denoising inputs, i.e., the noisy latent and the timestep, and show that this sensitivity is a key predictor of caching error. Based on this analysis, we propose Sensitivity-Aware Caching (SenCache), a dynamic caching policy that adaptively selects caching timesteps on a per-sample basis. Our framework provides a theoretical basis for adaptive caching, explains why prior empirical heuristics can be partially effective, and extends them to a dynamic, sample-specific approach. Experiments on Wan 2.1, CogVideoX, and LTX-Video show that SenCache achieves better visual quality than existing caching methods under similar computational budgets.

---

### SenCache: Accelerating Diffusion Model Inference via Sensitivity-Aware Caching

Authors: Yasaman Haghighi, Alexandre Alahi
Published: 2026-02-27
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2602.24208v1

Diffusion models achieve state-of-the-art video generation quality, but their inference remains expensive due to the large number of sequential denoising steps. This has motivated a growing line of research on accelerating diffusion inference. Among training-free acceleration methods, caching reduces computation by reusing previously computed model outputs across timesteps. Existing caching methods rely on heuristic criteria to choose cache/reuse timesteps and require extensive tuning. We address this limitation with a principled sensitivity-aware caching framework. Specifically, we formalize the caching error through an analysis of the model output sensitivity to perturbations in the denoising inputs, i.e., the noisy latent and the timestep, and show that this sensitivity is a key predictor of caching error. Based on this analysis, we propose Sensitivity-Aware Caching (SenCache), a dynamic caching policy that adaptively selects caching timesteps on a per-sample basis. Our framework provides a theoretical basis for adaptive caching, explains why prior empirical heuristics can be partially effective, and extends them to a dynamic, sample-specific approach. Experiments on Wan 2.1, CogVideoX, and LTX-Video show that SenCache achieves better visual quality than existing caching methods under similar computational budgets.

---