# Research Papers — 2026-01 · bundle page 9 of 189 > Full-text markdown of papers #401–450 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/9 [← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/8.md) [Next bundle →](https://aipod.dev/papers/archive/2026-01/page/10.md) ### AdaFuse: Adaptive Multimodal Fusion for Lung Cancer Risk Prediction via Reinforcement Learning Authors: Chongyu Qu, Zhengyi Lu, Yuxiang Lai, Thomas Z. Li, Junchao Zhu, Junlin Guo, Juming Xiong, Yanfan Zhu, Yuechen Yang, Allen J. Luna, Kim L. Sandler, Bennett A. Landman et al. Published: 2026-01-30 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.00347v1 Multimodal fusion has emerged as a promising paradigm for disease diagnosis and prognosis, integrating complementary information from heterogeneous data sources such as medical images, clinical records, and radiology reports. However, existing fusion methods process all available modalities through the network, either treating them equally or learning to assign different contribution weights, leaving a fundamental question unaddressed: for a given patient, should certain modalities be used at all? We present AdaFuse, an adaptive multimodal fusion framework that leverages reinforcement learning (RL) to learn patient-specific modality selection and fusion strategies for lung cancer risk prediction. AdaFuse formulates multimodal fusion as a sequential decision process, where the policy network iteratively decides whether to incorporate an additional modality or proceed to prediction based on the information already acquired. This sequential formulation enables the model to condition each selection on previously observed modalities and terminate early when sufficient information is available, rather than committing to a fixed subset upfront. We evaluate AdaFuse on the National Lung Screening Trial (NLST) dataset. Experimental results demonstrate that AdaFuse achieves the highest AUC (0.762) compared to the best single-modality baseline (0.732), the best fixed fusion strategy (0.759), and adaptive baselines including DynMM (0.754) and MoE (0.742), while using fewer FLOPs than all triple-modality methods. Our work demonstrates the potential of reinforcement learning for personalized multimodal fusion in medical imaging, representing a shift from uniform fusion strategies toward adaptive diagnostic pipelines that learn when to consult additional modalities and when existing information suffices for accurate prediction. --- ### When RAG Hurts: Diagnosing and Mitigating Attention Distraction in Retrieval-Augmented LVLMs Authors: Beidi Zhao, Wenlong Deng, Xinting Liao, Yushu Li, Nazim Shaikh, Yao Nie, Xiaoxiao Li Published: 2026-01-30 Categories: cs.CV, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2602.00344v2 While Retrieval-Augmented Generation (RAG) is one of the dominant paradigms for enhancing Large Vision-Language Models (LVLMs) on knowledge-based VQA tasks, recent work attributes RAG failures to insufficient attention towards the retrieved context, proposing to reduce the attention allocated to image tokens. In this work, we identify a distinct failure mode that previous study overlooked: Attention Distraction (AD). When the retrieved context is sufficient (highly relevant or including the correct answer), the retrieved text suppresses the visual attention globally, and the attention on image tokens shifts away from question-relevant regions. This leads to failures on questions the model could originally answer correctly without the retrieved text. To mitigate this issue, we propose MAD-RAG, a training-free intervention that decouples visual grounding from context integration through a dual-question formulation, combined with attention mixing to preserve image-conditioned evidence. Extensive experiments on OK-VQA, E-VQA, and InfoSeek demonstrate that MAD-RAG consistently outperforms existing baselines across different model families, yielding absolute gains of up to 4.76%, 9.20%, and 6.18% over the vanilla RAG baseline. Notably, MAD-RAG rectifies up to 74.68% of failure cases with negligible computational overhead. --- ### Standardized Methods and Recommendations for Green Federated Learning Authors: Austin Tapp, Holger R. Roth, Ziyue Xu, Abhijeet Parida, Hareem Nisar, Marius George Linguraru Published: 2026-01-30 Categories: cs.DC, cs.AI, cs.PF arXiv: https://arxiv.org/abs/2602.00343v2 Federated learning (FL) enables collaborative model training over privacy-sensitive, distributed data, but its environmental impact is difficult to compare across studies due to inconsistent measurement boundaries and heterogeneous reporting. We present a practical carbon-accounting methodology for FL CO2e tracking using NVIDIA NVFlare and CodeCarbon for explicit, phase-aware tasks (initialization, per-round training, evaluation, and idle/coordination). To capture non-compute effects, we additionally estimate communication emissions from transmitted model-update sizes under a network-configurable energy model. We validate the proposed approach on two representative workloads: CIFAR-10 image classification and retinal optic disk segmentation. In CIFAR-10, controlled client-efficiency scenarios show that system-level slowdowns and coordination effects can contribute meaningfully to carbon footprint under an otherwise fixed FL protocol, increasing total CO2e by 8.34x (medium) and 21.73x (low) relative to the high-efficiency baseline. In retinal segmentation, swapping GPU tiers (H100 vs.\ V100) yields a consistent 1.7x runtime gap (290 vs. 503 minutes) while producing non-uniform changes in total energy and CO2e across sites, underscoring the need for per-site and per-round reporting. Overall, our results support a standardized carbon accounting method that acts as a prerequisite for reproducible 'green' FL evaluation. Our code is available at https://github.com/Pediatric-Accelerated-Intelligence-Lab/carbon_footprint. --- ### Bridging the Semantic Chasm: Synergistic Conceptual Anchoring for Generalized Few-Shot and Zero-Shot OOD Perception Authors: Alexandros Christoforos, Sarah Jenkins, Michael Brown, Tuan Pham, David Chen Published: 2026-01-30 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.00340v1 This manuscript presents a pioneering Synergistic Neural Agents Network (SynerNet) framework designed to mitigate the phenomenon of cross-modal alignment degeneration in Vision-Language Models (VLMs) when encountering Out-of-Distribution (OOD) concepts. Specifically, four specialized computational units - visual perception, linguistic context, nominal embedding, and global coordination - collaboratively rectify modality disparities via a structured message-propagation protocol. The principal contributions encompass a multi-agent latent space nomenclature acquisition framework, a semantic context-interchange algorithm for enhanced few-shot adaptation, and an adaptive dynamic equilibrium mechanism. Empirical evaluations conducted on the VISTA-Beyond benchmark demonstrate that SynerNet yields substantial performance augmentations in both few-shot and zero-shot scenarios, exhibiting precision improvements ranging from 1.2% to 5.4% across a diverse array of domains. --- ### Adaptive Momentum and Nonlinear Damping for Neural Network Training Authors: Aikaterini Karoni, Rajit Rajpal, Benedict Leimkuhler, Gabriel Stoltz Published: 2026-01-30 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2602.00334v2 Momentum Stochastic Gradient Descent (mSGD) relies on a fixed momentum coefficient shared across all parameters, failing to account for the heterogeneous structure of modern loss landscapes. In this work, we adopt a continuous-time formulation to introduce individual, adaptive momentum coefficients regulated by the kinetic energy of each model parameter. This mechanism automatically adjusts to evolving training dynamics to maintain stability without sacrificing convergence speed. We demonstrate that this adaptive friction is inextricably linked to cubic damping, a suppression mechanism from structural dynamics. We additionally introduce two optimization schemes by augmenting the continuous dynamics of mSGD and Adam with a cubic damping term. Empirically, our methods demonstrate robustness and match or outperform Adam on training ViT, BERT, and GPT2 tasks where mSGD typically struggles. We further provide theoretical results establishing the exponential convergence of the proposed schemes. --- ### Efficient and accurate steering of Large Language Models through attention-guided feature learning Authors: Parmida Davarmanesh, Ashia Wilson, Adityanarayanan Radhakrishnan Published: 2026-01-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.00333v1 Steering, or direct manipulation of internal activations to guide LLM responses toward specific semantic concepts, is emerging as a promising avenue for both understanding how semantic concepts are stored within LLMs and advancing LLM capabilities. Yet, existing steering methods are remarkably brittle, with seemingly non-steerable concepts becoming completely steerable based on subtle algorithmic choices in how concept-related features are extracted. In this work, we introduce an attention-guided steering framework that overcomes three core challenges associated with steering: (1) automatic selection of relevant token embeddings for extracting concept-related features; (2) accounting for heterogeneity of concept-related features across LLM activations; and (3) identification of layers most relevant for steering. Across a steering benchmark of 512 semantic concepts, our framework substantially improved steering over previous state-of-the-art (nearly doubling the number of successfully steered concepts) across model architectures and sizes (up to 70 billion parameter models). Furthermore, we use our framework to shed light on the distribution of concept-specific features across LLM layers. Overall, our framework opens further avenues for developing efficient, highly-scalable fine-tuning algorithms for industry-scale LLMs. --- ### Prototype-based Explainable Neural Networks with Channel-specific Reasoning for Geospatial Learning Tasks Authors: Anushka Narayanan, Karianne J. Bergen Published: 2026-01-30 Categories: cs.LG, physics.ao-ph arXiv: https://arxiv.org/abs/2602.00331v1 Explainable AI (XAI) is essential for understanding machine learning (ML) decision-making and ensuring model trustworthiness in scientific applications. Prototype-based XAI methods offer an intrinsically interpretable alternative to post-hoc approaches which often yield inconsistent explanations. Prototype-based XAI methods make predictions based on the similarity between inputs and learned prototypes that represent typical characteristics of target classes. However, existing prototype-based models are primarily designed for standard RGB image data and are not optimized for the distinct, variable-specific channels commonly found in geoscientific image and raster datasets. In this study, we develop a prototype-based XAI approach tailored for multi-channel geospatial data, where each channel represents a distinct physical environmental variable or spectral channel. Our approach enables the model to identify separate, channel-specific prototypical characteristics sourced from multiple distinct training examples that inform how these features individually and in combination influence model prediction while achieving comparable performance to standard neural networks. We demonstrate this method through two geoscientific case studies: (1) classification of Madden Julian Oscillation phases using multi-variable climate data and (2) land-use classification from multispectral satellite imagery. This approach produces both local (instance-level) and global (model-level) explanations for providing insights into feature-relevance across channels. By explicitly incorporating channel-prototypes into the prediction process, we discuss how this approach enhances the transparency and trustworthiness of ML models for geoscientific learning tasks. --- ### In-Run Data Shapley for Adam Optimizer Authors: Meng Ding, Zeqing Zhang, Di Wang, Lijie Hu Published: 2026-01-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.00329v4 Reliable data attribution is essential for mitigating bias and reducing computational waste in modern machine learning, with the Shapley value serving as the theoretical gold standard. While recent "In-Run" methods bypass the prohibitive cost of retraining by estimating contributions dynamically, they heavily rely on the linear structure of Stochastic Gradient Descent (SGD) and fail to capture the complex dynamics of adaptive optimizers like Adam. In this work, we demonstrate that data attribution is inherently optimizer-dependent: we show that SGD-based proxies diverge significantly from true contributions under Adam (Pearson $R \approx 0.11$), rendering them ineffective for modern training pipelines. To bridge this gap, we propose Adam-Aware In-Run Data Shapley. We derive a closed-form approximation that restores additivity by redefining utility under a fixed-state assumption and enable scalable computation via a novel Linearized Ghost Approximation. This technique linearizes the variance-dependent scaling term, allowing us to compute pairwise gradient dot-products without materializing per-sample gradients. Extensive experiments show that our method achieves near-perfect fidelity to ground-truth marginal contributions ($R > 0.99$) while retaining $\sim$95\% of standard training throughput. Furthermore, our Adam-aware attribution significantly outperforms SGD-based baselines in data attribution downstream tasks. --- ### Harvest: Opportunistic Peer-to-Peer GPU Caching for LLM Inference Authors: Nikhil Gopal, Kostis Kaffes Published: 2026-01-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.00328v1 Large Language Model (LLM) inference is increasingly constrained by GPU memory capacity rather than compute throughput, driven by growing model sizes and the linear growth of the key-value (KV) cache during autoregressive decoding. Existing approaches mitigate memory pressure by offloading model state and KV tensors to host memory, but incur substantial latency due to limited PCIe bandwidth. We present Harvest, an opportunistic GPU cache management framework that exploits high-bandwidth peer-to-peer GPU interconnects to dynamically place model weights and KV cache in unused GPU memory. Harvest treats peer GPU memory as a transient cache tier, preserving correctness while reducing data movement overhead under dynamic memory availability. We demonstrate significant throughput speedup of more than 2 times by using Harvest to accelerate the retrieval of two widely-used inference components: expert layer weights and KV cache entries. --- ### SayNext-Bench: Why Do LLMs Struggle with Next-Utterance Anticipation? Authors: Yueyi Yang, Haotian Liu, Fang Kang, Mengqi Zhang, Zheng Lian, Hao Tang, Haoyu Chen Published: 2026-01-30 Categories: cs.AI, cs.HC arXiv: https://arxiv.org/abs/2602.00327v2 We explore the use of large language models (LLMs) for next-utterance anticipation in human dialogue. Despite recent advances in LLMs demonstrating their ability to engage in natural conversations with users, we show that even leading models surprisingly struggle to anticipate a human speaker's next utterance. Instead, humans can readily anticipate forthcoming utterances based on multi-modal cues -- such as gestures, gaze, and emotional tone -- from the context. To systematically examine this gap, we propose SayNext-Bench, a benchmark evaluating MLLMs on anticipating context-conditioned responses across diverse real-world scenarios. To support it, we build SayNext-PC, a large-scale multimodal dialogue dataset, and carefully design a multi-level evaluation framework spanning lexical similarity, emotion-intention consistency, and LLM-based overall alignment. Building on this, we develop SayNext-Chat, a cognitively inspired dual-route MLLM that incorporates learnable priming tokens to fuse perceptual cues with anticipatory priors. Extensive experiments demonstrate that SayNext-Chat consistently outperforms state-of-the-art MLLMs across all evaluation levels, corroborated by user studies and LLM-as-Judge evaluations. Our results emphasize the (i) indispensable role of multimodal cues and (ii) active anticipatory processing as foundations of natural human interaction currently missing in MLLMs. --- ### Dual Quaternion SE(3) Synchronization with Recovery Guarantees Authors: Jianing Zhao, Linglingzhi Zhu, Anthony Man-Cho So Published: 2026-01-30 Categories: math.OC, cs.CV, cs.RO, eess.SP arXiv: https://arxiv.org/abs/2602.00324v2 Synchronization over the special Euclidean group SE(3) aims to recover absolute poses from noisy pairwise relative transformations and is a core primitive in robotics and 3D vision. Standard approaches often require multi-step heuristic procedures to recover valid poses, which are difficult to analyze and typically lack theoretical guarantees. This paper adopts a dual quaternion representation and formulates SE(3) synchronization directly over the unit dual quaternion. A two-stage algorithm is developed: A spectral initializer computed via the power method on a Hermitian dual quaternion measurement matrix, followed by a dual quaternion generalized power method (DQGPM) that enforces feasibility through per-iteration projection. The estimation error bounds are established for spectral estimators, and DQGPM is shown to admit a finite-iteration error bound and achieves linear error contraction up to an explicit noise-dependent threshold. Experiments on synthetic benchmarks and real-world multi-scan point-set registration demonstrate that the proposed pipeline improves both accuracy and efficiency over representative matrix-based methods. --- ### Detecting AI-Generated Content in Academic Peer Reviews Authors: Siyuan Shen, Kai Wang Published: 2026-01-30 Categories: cs.CL, cs.AI, cs.LG, cs.SI arXiv: https://arxiv.org/abs/2602.00319v2 The growing availability of large language models (LLMs) has raised questions about their role in academic peer review. This study examines the temporal emergence of AI-generated content in peer reviews by applying a detection model trained on historical reviews to later review cycles at International Conference on Learning Representations (ICLR) and Nature Communications (NC). We observe minimal detection of AI-generated content before 2022, followed by a substantial increase through 2025, with approximately 20% of ICLR reviews and 12% of Nature Communications reviews classified as AI-generated in 2025. The most pronounced growth of AI-generated reviews in NC occurs between the third and fourth quarter of 2024. Together, these findings provide suggestive evidence of a rapidly increasing presence of AI-assisted content in peer review and highlight the need for further study of its implications for scholarly evaluation. --- ### Optimal Transport-Guided Adversarial Attacks on Graph Neural Network-Based Bot Detection Authors: Kunal Mukherjee, Zulfikar Alom, Tran Gia Bao Ngo, Cuneyt Gurcan Akcora, Murat Kantarcioglu Published: 2026-01-30 Categories: cs.LG, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2602.00318v2 The rise of bot accounts on social media poses significant risks to public discourse. To address this threat, modern bot detectors increasingly rely on Graph Neural Networks (GNNs). However, the effectiveness of these GNN-based detectors in real-world settings remains poorly understood. In practice, attackers continuously adapt their strategies as well as must operate under domain-specific and temporal constraints, which can fundamentally limit the applicability of existing attack methods. As a result, there is a critical need for robust GNN-based bot detection methods under realistic, constraint-aware attack scenarios. To address this gap, we introduce BOCLOAK to systematically evaluate the robustness of GNN-based social bot detection via both edge editing and node injection adversarial attacks under realistic constraints. BOCLOAK constructs a probability measure over spatio-temporal neighbor features and learns an optimal transport geometry that separates human and bot behaviors. It then decodes transport plans into sparse, plausible edge edits that evade detection while obeying real-world constraints. We evaluate BOCLOAK across three social bot datasets, five state-of-the-art bot detectors, three adversarial defenses, and compare it against four leading graph adversarial attack baselines. BOCLOAK achieves up to 80.13% higher attack success rates while using 99.80% less GPU memory under realistic real-world constraints. Most importantly, BOCLOAK shows that optimal transport provides a lightweight, principled framework for bridging the gap between adversarial attacks and real-world bot detection. --- ### MiNER: A Two-Stage Pipeline for Metadata Extraction from Municipal Meeting Minutes Authors: Rodrigo Batista, Luís Filipe Cunha, Purificação Silvano, Nuno Guimarães, Alípio Jorge, Evelin Amorim, Ricardo Campos Published: 2026-01-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.00316v3 Municipal meeting minutes are official documents of local governance, exhibiting heterogeneous formats and writing styles. Effective information retrieval (IR) requires identifying metadata such as meeting number, date, location, participants, and start/end times, elements that are rarely standardized or easy to extract automatically. Existing named entity recognition (NER) models are ill-suited to this task, as they are not adapted to such domain-specific categories. In this paper, we propose a two-stage pipeline for metadata extraction from municipal minutes. First, a question answering (QA) model identifies the opening and closing text segments containing metadata. Transformer-based models (BERTimbau and XLM-RoBERTa with and without a CRF layer) are then applied for fine-grained entity extraction and enhanced through deslexicalization. To evaluate our proposed pipeline, we benchmark both open-weight (Phi) and closed-weight (Gemini) LLMs, assessing predictive performance, inference cost, and carbon footprint. Our results demonstrate strong in-domain performance, better than larger general-purpose LLMs. However, cross-municipality evaluation reveals reduced generalization reflecting the variability and linguistic complexity of municipal records. This work establishes the first benchmark for metadata extraction from municipal meeting minutes, providing a solid foundation for future research in this domain. --- ### Beyond the Loss Curve: Scaling Laws, Active Learning, and the Limits of Learning from Exact Posteriors Authors: Arian Khorasani, Nathaniel Chen, Yug D Oswal, Akshat Santhana Gopalan, Egemen Kolemen, Ravid Shwartz-Ziv Published: 2026-01-30 Categories: cs.LG, cs.AI, cs.IT arXiv: https://arxiv.org/abs/2602.00315v2 How close are neural networks to the best they could possibly do? Standard benchmarks cannot answer this because they lack access to the true posterior p(y|x). We use class-conditional normalizing flows as oracles that make exact posteriors tractable on realistic images (AFHQ, ImageNet). This enables five lines of investigation. Scaling laws: Prediction error decomposes into irreducible aleatoric uncertainty and reducible epistemic error; the epistemic component follows a power law in dataset size, continuing to shrink even when total loss plateaus. Limits of learning: The aleatoric floor is exactly measurable, and architectures differ markedly in how they approach it: ResNets exhibit clean power-law scaling while Vision Transformers stall in low-data regimes. Soft labels: Oracle posteriors contain learnable structure beyond class labels: training with exact posteriors outperforms hard labels and yields near-perfect calibration. Distribution shift: The oracle computes exact KL divergence of controlled perturbations, revealing that shift type matters more than shift magnitude: class imbalance barely affects accuracy at divergence values where input noise causes catastrophic degradation. Active learning: Exact epistemic uncertainty distinguishes genuinely informative samples from inherently ambiguous ones, improving sample efficiency. Our framework reveals that standard metrics hide ongoing learning, mask architectural differences, and cannot diagnose the nature of distribution shift. --- ### On the Assessment of Sensitivity of Autonomous Vehicle Perception Authors: Apostol Vassilev, Munawar Hasan, Edward Griffor, Honglan Jin, Pavel Piliptchak, Mahima Arora, Thoshitha Gamage Published: 2026-01-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.00314v1 The viability of automated driving is heavily dependent on the performance of perception systems to provide real-time accurate and reliable information for robust decision-making and maneuvers. These systems must perform reliably not only under ideal conditions, but also when challenged by natural and adversarial driving factors. Both of these types of interference can lead to perception errors and delays in detection and classification. Hence, it is essential to assess the robustness of the perception systems of automated vehicles (AVs) and explore strategies for making perception more reliable. We approach this problem by evaluating perception performance using predictive sensitivity quantification based on an ensemble of models, capturing model disagreement and inference variability across multiple models, under adverse driving scenarios in both simulated environments and real-world conditions. A notional architecture for assessing perception performance is proposed. A perception assessment criterion is developed based on an AV's stopping distance at a stop sign on varying road surfaces, such as dry and wet asphalt, and vehicle speed. Five state-of-the-art computer vision models are used, including YOLO (v8-v9), DEtection TRansformer (DETR50, DETR101), Real-Time DEtection TRansformer (RT-DETR)in our experiments. Diminished lighting conditions, e.g., resulting from the presence of fog and low sun altitude, have the greatest impact on the performance of the perception models. Additionally, adversarial road conditions such as occlusions of roadway objects increase perception sensitivity and model performance drops when faced with a combination of adversarial road conditions and inclement weather conditions. Also, it is demonstrated that the greater the distance to a roadway object, the greater the impact on perception performance, hence diminished perception robustness. --- ### Opportunistic Promptable Segmentation: Leveraging Routine Radiological Annotations to Guide 3D CT Lesion Segmentation Authors: Samuel Church, Joshua D. Warner, Danyal Maqbool, Xin Tie, Junjie Hu, Meghan G. Lubner, Tyler J. Bradshaw Published: 2026-01-30 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.00309v1 The development of machine learning models for CT imaging depends on the availability of large, high-quality, and diverse annotated datasets. Although large volumes of CT images and reports are readily available in clinical picture archiving and communication systems (PACS), 3D segmentations of critical findings are costly to obtain, typically requiring extensive manual annotation by radiologists. On the other hand, it is common for radiologists to provide limited annotations of findings during routine reads, such as line measurements and arrows, that are often stored in PACS as GSPS objects. We posit that these sparse annotations can be extracted along with CT volumes and converted into 3D segmentations using promptable segmentation models, a paradigm we term Opportunistic Promptable Segmentation. To enable this paradigm, we propose SAM2CT, the first promptable segmentation model designed to convert radiologist annotations into 3D segmentations in CT volumes. SAM2CT builds upon SAM2 by extending the prompt encoder to support arrow and line inputs and by introducing Memory-Conditioned Memories (MCM), a memory encoding strategy tailored to 3D medical volumes. On public lesion segmentation benchmarks, SAM2CT outperforms existing promptable segmentation models and similarly trained baselines, achieving Dice similarity coefficients of 0.649 for arrow prompts and 0.757 for line prompts. Applying the model to pre-existing GSPS annotations from a clinical PACS (N = 60), SAM2CT generates 3D segmentations that are clinically acceptable or require only minor adjustments in 87% of cases, as scored by radiologists. Additionally, SAM2CT demonstrates strong zero-shot performance on select Emergency Department findings. These results suggest that large-scale mining of historical GSPS annotations represents a promising and scalable approach for generating 3D CT segmentation datasets. --- ### Autonomous Data Processing using Meta-Agents Authors: Udayan Khurana Published: 2026-01-30 Categories: cs.AI, cs.DB, cs.MA arXiv: https://arxiv.org/abs/2602.00307v2 Traditional data processing pipelines are typically static and handcrafted for specific tasks, limiting their adaptability to evolving requirements. While general-purpose agents and coding assistants can generate code for well-understood data pipelines, they lack the ability to autonomously monitor, manage, and optimize an end-to-end pipeline once deployed. We present \textbf{Autonomous Data Processing using Meta-agents} (ADP-MA), a framework that dynamically constructs, executes, and iteratively refines data processing pipelines through hierarchical agent orchestration. At its core, \textit{meta-agents} analyze input data and task specifications to design a multi-phase plan, instantiate specialized \textit{ground-level agents}, and continuously evaluate pipeline performance. The architecture comprises three key components: a planning module for strategy generation, an orchestration layer for agent coordination and tool integration, and a monitoring loop for iterative evaluation and backtracking. Unlike conventional approaches, ADP-MA emphasizes context-aware optimization, adaptive workload partitioning, and progressive sampling for scalability. Additionally, the framework leverages a diverse set of external tools and can reuse previously designed agents, reducing redundancy and accelerating pipeline construction. We demonstrate ADP-MA through an interactive demo that showcases pipeline construction, execution monitoring, and adaptive refinement across representative data processing tasks. --- ### Syntax- and Compilation-Preserving Evasion of LLM Vulnerability Detectors Authors: Luze Sun, Alina Oprea, Eric Wong Published: 2026-01-30 Categories: cs.CR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.00305v2 LLM-based vulnerability detectors are increasingly deployed in CI/CD security gating, yet their resilience to evasion under syntax- and compilation-preserving edits remains poorly understood. We evaluate five attack variants spanning four carrier families of behavior-preserving code transformations on a unified C/C++ benchmark ($N=5000$) and introduce Complete Resistance (CR), measuring the fraction of correctly detected vulnerabilities that withstand all attack variants. Our findings reveal a significant robustness gap: models achieving 70\%+ clean recall exhibit CR as low as 0.12\%, meaning over 87\% of detected vulnerabilities can be evaded by at least one syntax-preserving edit. Universal adversarial strings optimized on a 14B surrogate transfer effectively to black-box APIs including GPT-4o, while on-target optimization further amplifies evasion (up to 92.5\% ASR). These results indicate that clean benchmark accuracy alone is insufficient as a security guarantee for deployed vulnerability detectors. --- ### Neural Ising Machines via Unrolling and Zeroth-Order Training Authors: Sam Reifenstein, Timothee Leleu Published: 2026-01-30 Categories: cs.LG, cond-mat.dis-nn, nlin.CD arXiv: https://arxiv.org/abs/2602.00302v1 We propose a data-driven heuristic for NP-hard Ising and Max-Cut optimization that learns the update rule of an iterative dynamical system. The method learns a shared, node-wise update rule that maps local interaction fields to spin updates, parameterized by a compact multilayer perceptron with a small number of parameters. Training is performed using a zeroth-order optimizer, since backpropagation through long, recurrent Ising-machine dynamics leads to unstable and poorly informative gradients. We call this approach a neural network parameterized Ising machine (NPIM). Despite its low parameter count, the learned dynamics recover effective algorithmic structure, including momentum-like behavior and time-varying schedules, enabling efficient search in highly non-convex energy landscapes. Across standard Ising and neural combinatorial optimization benchmarks, NPIM achieves competitive solution quality and time-to-solution relative to recent learning-based methods and strong classical Ising-machine heuristics. --- ### Faithful-Patchscopes: Understanding and Mitigating Model Bias in Hidden Representations Explanation of Large Language Models Authors: Xilin Gong, Shu Yang, Zehua Cao, Lynne Billard, Di Wang Published: 2026-01-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.00300v1 Large Language Models (LLMs) have demonstrated strong capabilities for hidden representation interpretation through Patchscopes, a framework that uses LLMs themselves to generate human-readable explanations by decoding from internal hidden representations. However, our work shows that LLMs tend to rely on inherent linguistic patterns, which can override contextual information encoded in the hidden representations during decoding. For example, even when a hidden representation encodes the contextual attribute "purple" for "broccoli", LLMs still generate "green" in their explanations, reflecting a strong prior association. This behavior reveals a systematic unfaithfulness in Patchscopes. To systematically study this issue, we first designed a dataset to evaluate the faithfulness of Patchscopes under biased cases, and our results show that there is an 18.84\% faithfulness decrease on average. We then propose Bias Alignment through Logit Recalibration (BALOR), which treats the output logits from an unpatched prompt as capturing model bias and contrasts them with logits obtained under patched contextual information. By recalibrating the logit distribution through this contrast, BALOR suppresses model bias and amplifies contextual information during generation. Experiments across multiple LLMs demonstrate that BALOR consistently outperforms existing baselines, achieving up to 33\% relative performance improvement. --- ### Agentic Framework for Epidemiological Modeling Authors: Rituparna Datta, Zihan Guan, Baltazar Espinoza, Yiqi Su, Priya Pitre, Srini Venkatramanan, Naren Ramakrishnan, Anil Vullikanti Published: 2026-01-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.00299v2 Epidemic modeling is essential for public health planning, yet traditional approaches rely on fixed model classes that require manual redesign as pathogens, policies, and scenario assumptions evolve. We introduce EPIAGENT, an agentic framework that automatically synthesizes, calibrates, verifies, and refines epidemiological simulators by modeling disease progression as an iterative program synthesis problem. A central design choice is an explicit epidemiological flow graph intermediate representation that links scenario specifications to model structure and enables strong, modular correctness checks before code is generated. Verified flow graphs are then compiled into mechanistic models supporting interpretable parameter learning under physical and epidemiological constraints. Evaluation on epidemiological scenario case studies demonstrates that EPIAGENT captures complex growth dynamics and produces epidemiologically consistent counterfactual projections across varying vaccination and immune escape assumptions. Our results show that the agentic feedback loop prevents degeneration and significantly accelerates convergence toward valid models by mimicking professional expert workflows. --- ### Assessing Domain-Level Susceptibility to Emergent Misalignment from Narrow Finetuning Authors: Abhishek Mishra, Mugilan Arulvanan, Reshma Ashok, Polina Petrova, Deepesh Suranjandass, Donnie Winkelmann Published: 2026-01-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.00298v1 Emergent misalignment poses risks to AI safety as language models are increasingly used for autonomous tasks. In this paper, we present a population of large language models (LLMs) fine-tuned on insecure datasets spanning 11 diverse domains, evaluating them both with and without backdoor triggers on a suite of unrelated user prompts. Our evaluation experiments on \texttt{Qwen2.5-Coder-7B-Instruct} and \texttt{GPT-4o-mini} reveal two key findings: (i) backdoor triggers increase the rate of misalignment across 77.8% of domains (average drop: 4.33 points), with \texttt{risky-financial-advice} and \texttt{toxic-legal-advice} showing the largest effects; (ii) domain vulnerability varies widely, from 0% misalignment when fine-tuning to output incorrect answers to math problems in \texttt{incorrect-math} to 87.67% when fine-tuned on \texttt{gore-movie-trivia}. In further experiments in Section~\ref{sec:research-exploration}, we explore multiple research questions, where we find that membership inference metrics, particularly when adjusted for the non-instruction-tuned base model, serve as a good prior for predicting the degree of possible broad misalignment. Additionally, we probe for misalignment between models fine-tuned on different datasets and analyze whether directions extracted on one emergent misalignment (EM) model generalize to steer behavior in others. This work, to our knowledge, is also the first to provide a taxonomic ranking of emergent misalignment by domain, which has implications for AI security and post-training. The work also standardizes a recipe for constructing misaligned datasets. All code and datasets are publicly available on GitHub.\footnote{https://github.com/abhishek9909/assessing-domain-emergent-misalignment/tree/main} --- ### From Observations to States: Latent Time Series Forecasting Authors: Jie Yang, Yifan Hu, Yuante Li, Kexin Zhang, Kaize Ding, Philip S. Yu Published: 2026-01-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.00297v2 Deep learning has achieved strong performance in Time Series Forecasting (TSF). However, we identify a critical representation paradox, termed Latent Chaos: models with accurate predictions often learn latent representations that are temporally disordered and lack continuity. We attribute this to the dominant observation-space forecasting paradigm, where minimizing point-wise errors on noisy and partially observed data encourages shortcut solutions instead of the recovery of underlying system dynamics. To address this, we propose Latent Time Series Forecasting (LatentTSF), a paradigm that shifts TSF from observation regression to latent state prediction. LatentTSF employs an AutoEncoder to project each observation into a learned latent state space and performs forecasting entirely in this space, allowing the model to focus on learning structured temporal dynamics. We provide an information-theoretic analysis showing that the latent objectives can be motivated as surrogates for maximizing mutual information between predicted and ground-truth latent states and future observations. Extensive experiments on widely-used benchmarks confirm that LatentTSF effectively mitigates latent chaos, yielding consistent improvements in both forecasting accuracy and representation quality. Our code is available at https://github.com/Muyiiiii/LatentTSF. --- ### Multi-Speaker Conversational Audio Deepfake: Taxonomy, Dataset and Pilot Study Authors: Alabi Ahmed, Vandana Janeja, Sanjay Purushotham Published: 2026-01-30 Categories: cs.SD, cs.AI, eess.AS arXiv: https://arxiv.org/abs/2602.00295v1 The rapid advances in text-to-speech (TTS) technologies have made audio deepfakes increasingly realistic and accessible, raising significant security and trust concerns. While existing research has largely focused on detecting single-speaker audio deepfakes, real-world malicious applications with multi-speaker conversational settings is also emerging as a major underexplored threat. To address this gap, we propose a conceptual taxonomy of multi-speaker conversational audio deepfakes, distinguishing between partial manipulations (one or multiple speakers altered) and full manipulations (entire conversations synthesized). As a first step, we introduce a new Multi-speaker Conversational Audio Deepfakes Dataset (MsCADD) of 2,830 audio clips containing real and fully synthetic two-speaker conversations, generated using VITS and SoundStorm-based NotebookLM models to simulate natural dialogue with variations in speaker gender, and conversational spontaneity. MsCADD is limited to text-to-speech (TTS) types of deepfake. We benchmark three neural baseline models; LFCC-LCNN, RawNet2, and Wav2Vec 2.0 on this dataset and report performance in terms of F1 score, accuracy, true positive rate (TPR), and true negative rate (TNR). Results show that these baseline models provided a useful benchmark, however, the results also highlight that there is a significant gap in multi-speaker deepfake research in reliably detecting synthetic voices under varied conversational dynamics. Our dataset and benchmarks provide a foundation for future research on deepfake detection in conversational scenarios, which is a highly underexplored area of research but also a major area of threat to trustworthy information in audio settings. The MsCADD dataset is publicly available to support reproducibility and benchmarking by the research community. --- ### Self-Attention at Constant Cost per Token via Symmetry-Aware Taylor Approximation Authors: Franz A. Heinsen, Leo Kozachkov Published: 2026-01-30 Categories: cs.LG, cs.AI, cs.DC arXiv: https://arxiv.org/abs/2602.00294v1 The most widely used artificial intelligence (AI) models today are Transformers employing self-attention. In its standard form, self-attention incurs costs that increase with context length, driving demand for storage, compute, and energy that is now outstripping society's ability to provide them. To help address this issue, we show that self-attention is efficiently computable to arbitrary precision with constant cost per token, achieving orders-of-magnitude reductions in memory use and computation. We derive our formulation by decomposing the conventional formulation's Taylor expansion into expressions over symmetric chains of tensor products. We exploit their symmetry to obtain feed-forward transformations that efficiently map queries and keys to coordinates in a minimal polynomial-kernel feature basis. Notably, cost is fixed inversely in proportion to head size, enabling application over a greater number of heads per token than otherwise feasible. We implement our formulation and empirically validate its correctness. Our work enables unbounded token generation at modest fixed cost, substantially reducing the infrastructure and energy demands of large-scale Transformer models. The mathematical techniques we introduce are of independent interest. --- ### LogicGaze: Benchmarking Causal Consistency in Visual Narratives via Counterfactual Verification Authors: Rory Driscoll, Alexandros Christoforos, Chadbourne Davis Published: 2026-01-30 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.00292v1 While sequential reasoning enhances the capability of Vision-Language Models (VLMs) to execute complex multimodal tasks, their reliability in grounding these reasoning chains within actual visual evidence remains insufficiently explored. We introduce LogicGaze, a novel benchmark framework designed to rigorously interrogate whether VLMs can validate sequential causal chains against visual inputs, specifically targeting the pervasive issue of hallucination. Curated from 40,000 video segments from ShareGPT4Video and a subset of Flickr30k imagery, LogicGaze integrates causal sequences with visually contradictory yet linguistically plausible perturbations, compelling models to verify the authenticity of each reasoning step. Our tripartite evaluation protocol - Causal Validation, Grounded Narrative Synthesis, and Perturbation Rejection - exposes significant vulnerabilities in state-of-the-art VLMs such as Qwen2.5-VL-72B. LogicGaze advocates for robust, trustworthy multimodal reasoning, with all resources publicly available in an anonymized repository. --- ### Computer Vision and Its Relationship to Cognitive Science: A perspective from Bayes Decision Theory Authors: Alan Yuille, Daniel Kersten Published: 2026-01-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.00289v1 This document presents an introduction to computer vision, and its relationship to Cognitive Science, from the perspective of Bayes Decision Theory (Berger 1985). Computer vision is a vast and complex field, so this overview has a narrow scope and provides a theoretical lens which captures many key concepts. BDT is rich enough to include two different approaches: (i) the Bayesian viewpoint, which gives a conceptually attractive framework for vision with concepts that resonate with Cognitive Science (Griffiths et al., 2024), and (ii) the Deep Neural Network approach whose successes in the real world have made Computer Vision into a trillion-dollar industry and which is motivated by the hierarchical structure of the visual ventral stream. The BDT framework relates and captures the strengths and weakness of these two approaches and, by discussing the limitations of BDT, points the way to how they can be combined in a richer framework. --- ### TimeBlind: A Spatio-Temporal Compositionality Benchmark for Video LLMs Authors: Baiqi Li, Kangyi Zhao, Ce Zhang, Chancharik Mitra, Jean de Dieu Nyandwi, Gedas Bertasius Published: 2026-01-30 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.00288v4 Fine-grained spatio-temporal understanding is essential for video reasoning and embodied AI. Yet, while Multimodal Large Language Models (MLLMs) master static semantics, their grasp of temporal dynamics remains brittle. We present TimeBlind, a diagnostic benchmark for compositional spatio-temporal understanding. Inspired by cognitive science, TimeBlind categorizes fine-grained temporal understanding into three levels: recognizing atomic events, characterizing event properties, and reasoning about event interdependencies. Unlike benchmarks that conflate recognition with temporal reasoning, TimeBlind leverages a minimal-pairs paradigm: video pairs share identical static visual content but differ solely in temporal structure, utilizing complementary questions to neutralize language priors. Evaluating over 20 state-of-the-art MLLMs (e.g., GPT-5, Gemini 3 Pro) on 600 curated instances (2400 video-question pairs), reveals that the Instance Accuracy (correctly distinguishing both videos in a pair) of the best performing MLLM is only 48.2%, far below the human performance (98.2%). These results demonstrate that even frontier models rely heavily on static visual shortcuts rather than genuine temporal logic, positioning TimeBlind as a vital diagnostic tool for next-generation video understanding. Dataset and code are available at https://baiqi-li.github.io/timeblind_project/ . --- ### Generation Order and Parallel Decoding in Masked Diffusion Models: An Information-Theoretic Perspective Authors: Shaorong Zhang, Longxuan Yu, Rob Brekelmans, Luhan Tang, Salman Asif, Greg Ver Steeg Published: 2026-01-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.00286v1 Masked Diffusion Models (MDMs) significantly accelerate inference by trading off sequential determinism. However, the theoretical mechanisms governing generation order and the risks inherent in parallelization remain under-explored. In this work, we provide a unified information-theoretic framework to decouple and analyze two fundamental sources of failure: order sensitivity and parallelization bias. Our analysis yields three key insights: (1) The benefits of Easy-First decoding (prioritizing low-entropy tokens) are magnified as model error increases; (2) factorized parallel decoding introduces intrinsic sampling errors that can lead to arbitrary large Reverse KL divergence, capturing "incoherence" failures that standard Forward KL metrics overlook; and (3) while verification can eliminate sampling error, it incurs an exponential cost governed by the total correlation within a block. Conversely, heuristics like remasking, though computationally efficient, cannot guarantee distributional correctness. Experiments on a controlled Block-HMM and large-scale MDMs (LLaDA) for arithmetic reasoning validate our theoretical framework. --- ### Sample Complexity Analysis for Constrained Bilevel Reinforcement Learning Authors: Naman Saxena, Vaneet Aggarwal Published: 2026-01-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.00282v1 Several important problem settings within the literature of reinforcement learning (RL), such as meta-learning, hierarchical learning, and RL from human feedback (RL-HF), can be modelled as bilevel RL problems. A lot has been achieved in these domains empirically; however, the theoretical analysis of bilevel RL algorithms hasn't received a lot of attention. In this work, we analyse the sample complexity of a constrained bilevel RL algorithm, building on the progress in the unconstrained setting. We obtain an iteration complexity of $O(ε^{-2})$ and sample complexity of $\tilde{O}(ε^{-4})$ for our proposed algorithm, Constrained Bilevel Subgradient Optimization (CBSO). We use a penalty-based objective function to avoid the issue of primal-dual gap and hyper-gradient in the context of a constrained bilevel problem setting. The penalty-based formulation to handle constraints requires analysis of non-smooth optimization. We are the first ones to analyse the generally parameterized policy gradient-based RL algorithm with a non-smooth objective function using the Moreau envelope. --- ### Semantic Calibration Prevails Where Token Confidence Fails: Benchmarking Long-Form Scientific QA Authors: Philip Müller, Nicholas Popovič, Michael Färber, Peter Steinbach Published: 2026-01-30 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2602.00279v2 Reliable uncertainty quantification (UQ) is essential for safe deployment of large language models (LLMs) in scientific question answering, where long-form outputs exceed practical human verification at scale. We introduce the first large-scale benchmark for UQ calibration in long-form, reasoning-demanding scientific QA, evaluating four UQ methods on 685,000 responses across up to 20 LLMs and seven datasets, supported by an extensible open-source framework whose shared-generation design enables reproducible cross-method comparisons. Instruction tuning is shown to associate with systematic token probability polarization, collapsing confidence distributions and undermining the reliability of token-level uncertainty signals. Reasoning model families diverge: some reproduce this polarization while others actively mitigate it, a pattern that clusters by provider and suggests training pipeline design as a key differentiating factor. Verbalized and token-aggregation sequence-level methods fail systematically. Only semantic consistency, as measured by consistency of the final answer, yields well-calibrated outputs, providing the first large-scale evidence that semantic calibration persists in multi-step, dependency-rich reasoning settings. --- ### Training LLMs with Fault Tolerant HSDP on 100,000 GPUs Authors: Omkar Salpekar, Rohan Varma, Kenny Yu, Vladimir Ivanov, Yang Wang, Ahmed Sharif, Min Si, Shawn Xu, Feng Tian, Shengbao Zheng, Tristan Rice, Ankush Garg et al. Published: 2026-01-30 Categories: cs.DC, cs.AI arXiv: https://arxiv.org/abs/2602.00277v1 Large-scale training systems typically use synchronous training, requiring all GPUs to be healthy simultaneously. In our experience training on O(100K) GPUs, synchronous training results in a low efficiency due to frequent failures and long recovery time. To address this problem, we propose a novel training paradigm, Fault Tolerant Hybrid-Shared Data Parallelism (FT-HSDP). FT-HSDP uses data parallel replicas as units of fault tolerance. When failures occur, only a single data-parallel replica containing the failed GPU or server is taken offline and restarted, while the other replicas continue training. To realize this idea at scale, FT-HSDP incorporates several techniques: 1) We introduce a Fault Tolerant All Reduce (FTAR) protocol for gradient exchange across data parallel replicas. FTAR relies on the CPU to drive the complex control logic for tasks like adding or removing participants dynamically, and relies on GPU to perform data transfer for best performance. 2) We introduce a non-blocking catch-up protocol, allowing a recovering replica to join training with minimal stall. Compared with fully synchronous training at O(100K) GPUs, FT-HSDP can reduce the stall time due to failure recovery from 10 minutes to 3 minutes, increasing effective training time from 44\% to 80\%. We further demonstrate that FT-HSDP's asynchronous recovery does not bring any meaning degradation to the accuracy of the result model. --- ### Localizing and Correcting Errors for LLM-based Planners Authors: Aditya Kumar, William W. Cohen Published: 2026-01-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.00276v3 Large language models (LLMs) have demonstrated strong reasoning capabilities on math and coding, but frequently fail on symbolic classical planning tasks. Our studies, as well as prior work, show that LLM-generated plans routinely violate domain constraints given in their instructions (e.g., walking through walls). To address this failure, we propose iteratively augmenting instructions with Localized In-Context Learning (L-ICL) demonstrations: targeted corrections for specific failing steps. Specifically, L-ICL identifies the first constraint violation in a trace and injects a minimal input-output example giving the correct behavior for the failing step. Our proposed technique of L-ICL is much effective than explicit instructions or traditional ICL, which adds complete problem-solving trajectories, and many other baselines. For example, on an 8x8 gridworld, L-ICL produces valid plans 89% of the time with only 60 training examples, compared to 59% for the best baseline, an increase of 30%. L-ICL also shows dramatic improvements in other domains (gridworld navigation, mazes, Sokoban, and BlocksWorld), and on several LLM architectures. --- ### VoxServe: Streaming-Centric Serving System for Speech Language Models Authors: Keisuke Kamahori, Wei-Tzu Lee, Atindra Jha, Rohan Kadekodi, Stephanie Wang, Arvind Krishnamurthy, Baris Kasikci Published: 2026-01-30 Categories: cs.LG, cs.AI, cs.DC, cs.SD, eess.AS arXiv: https://arxiv.org/abs/2602.00269v1 Deploying modern Speech Language Models (SpeechLMs) in streaming settings requires systems that provide low latency, high throughput, and strong guarantees of streamability. Existing systems fall short of supporting diverse models flexibly and efficiently. We present VoxServe, a unified serving system for SpeechLMs that optimizes streaming performance. VoxServe introduces a model-execution abstraction that decouples model architecture from system-level optimizations, thereby enabling support for diverse SpeechLM architectures within a single framework. Building on this abstraction, VoxServe implements streaming-aware scheduling and an asynchronous inference pipeline to improve end-to-end efficiency. Evaluations across multiple modern SpeechLMs show that VoxServe achieves 10-20x higher throughput than existing implementations at comparable latency while maintaining high streaming viability. The code of VoxServe is available at https://github.com/vox-serve/vox-serve. --- ### TokenTrim: Inference-Time Token Pruning for Autoregressive Long Video Generation Authors: Ariel Shaulov, Eitan Shaar, Amit Edenzon, Lior Wolf Published: 2026-01-30 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.00268v1 Auto-regressive video generation enables long video synthesis by iteratively conditioning each new batch of frames on previously generated content. However, recent work has shown that such pipelines suffer from severe temporal drift, where errors accumulate and amplify over long horizons. We hypothesize that this drift does not primarily stem from insufficient model capacity, but rather from inference-time error propagation. Specifically, we contend that drift arises from the uncontrolled reuse of corrupted latent conditioning tokens during auto-regressive inference. To correct this accumulation of errors, we propose a simple, inference-time method that mitigates temporal drift by identifying and removing unstable latent tokens before they are reused for conditioning. For this purpose, we define unstable tokens as latent tokens whose representations deviate significantly from those of the previously generated batch, indicating potential corruption or semantic drift. By explicitly removing corrupted latent tokens from the auto-regressive context, rather than modifying entire spatial regions or model parameters, our method prevents unreliable latent information from influencing future generation steps. As a result, it significantly improves long-horizon temporal consistency without modifying the model architecture, training procedure, or leaving latent space. --- ### PLACID: Identity-Preserving Multi-Object Compositing via Video Diffusion with Synthetic Trajectories Authors: Gemma Canet Tarrés, Manel Baradad, Francesc Moreno-Noguer, Yumeng Li Published: 2026-01-30 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.00267v1 Recent advances in generative AI have dramatically improved photorealistic image synthesis, yet they fall short for studio-level multi-object compositing. This task demands simultaneous (i) near-perfect preservation of each item's identity, (ii) precise background and color fidelity, (iii) layout and design elements control, and (iv) complete, appealing displays showcasing all objects. However, current state-of-the-art models often alter object details, omit or duplicate objects, and produce layouts with incorrect relative sizing or inconsistent item presentations. To bridge this gap, we introduce PLACID, a framework that transforms a collection of object images into an appealing multi-object composite. Our approach makes two main contributions. First, we leverage a pretrained image-to-video (I2V) diffusion model with text control to preserve objects consistency, identities, and background details by exploiting temporal priors from videos. Second, we propose a novel data curation strategy that generates synthetic sequences where randomly placed objects smoothly move to their target positions. This synthetic data aligns with the video model's temporal priors during training. At inference, objects initialized at random positions consistently converge into coherent layouts guided by text, with the final frame serving as the composite image. Extensive quantitative evaluations and user studies demonstrate that PLACID surpasses state-of-the-art methods in multi-object compositing, achieving superior identity, background, and color preservation, with less omitted objects and visually appealing results. --- ### Complete Identification of Deep ReLU Networks through Łukasiewicz Logic Authors: Yani Zhang, Helmut Bölcskei Published: 2026-01-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.00266v2 Two deep ReLU networks can have entirely different architectures and parameters, yet realize the same function. We provide a complete characterization of this nonuniqueness. This is effected by building a symbolic calculus for deep ReLU networks, equivalence and simplification of networks becoming derivation of formulae, in close parallel to Shannon's analysis of switching circuits through Boolean logic. Inspired by Shannon, who turned circuit synthesis into the manipulation of Boolean formulae by the axioms of Boolean algebra, we turn ReLU network identification into the derivation of Łukasiewicz formulae by the axioms of many-valued (MV) logic. Two non-degenerate ReLU networks realize the same function on the unit cube if and only if one is obtained from the other by finitely many applications of the MV axioms for integer weights and biases, the divisible MV axioms for rational ones, and the Riesz MV axioms for real ones. The MV logic axioms characterize all symmetries of ReLU networks, the single-layer ones, which for tanh networks are the only kind, and the deep ones, spanning three or more layers. Our framework consists of three steps, an extraction algorithm turning a network into a substitution graph, whose represented formula has the network's input-output map as its truth function, a completeness theorem, by which functionally equivalent formulae are interderivable, and a construction algorithm returning from graphs to networks. The substitution graph is layered, carrying at each node a formula in the variables of the layer feeding it, encodes the network uniquely, and induces a new normal form for MV logic, compositional rather than flat as in the literature, hence retaining the algebraic structure of the network, with three local operations--node rewrite, layer collapse, layer expansion--realizing every derivation. --- ### World-Shaper: A Unified Framework for 360° Panoramic Editing Authors: Dong Liang, Yuhao Liu, Jinyuan Jia, Youjun Zhao, Rynson W. H. Lau Published: 2026-01-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.00265v1 Being able to edit panoramic images is crucial for creating realistic 360° visual experiences. However, existing perspective-based image editing methods fail to model the spatial structure of panoramas. Conventional cube-map decompositions attempt to overcome this problem but inevitably break global consistency due to their mismatch with spherical geometry. Motivated by this insight, we reformulate panoramic editing directly in the equirectangular projection (ERP) domain and present World-Shaper, a unified geometry-aware framework that bridges panoramic generation and editing within a single editing-centric design. To overcome the scarcity of paired data, we adopt a generate-then-edit paradigm, where controllable panoramic generation serves as an auxiliary stage to synthesize diverse paired examples for supervised editing learning. To address geometric distortion, we introduce a geometry-aware learning strategy that explicitly enforces position-aware shape supervision and implicitly internalizes panoramic priors through progressive training. Extensive experiments on our new benchmark, PEBench, demonstrate that our method achieves superior geometric consistency, editing fidelity, and text controllability compared to SOTA methods, enabling coherent and flexible 360° visual world creation with unified editing control. Code, model, and data will be released at our project page: https://world-shaper-project.github.io/ --- ### Subspace Clustering on Incomplete Data with Self-Supervised Contrastive Learning Authors: Huanran Li, Daniel Pimentel-Alarcón Published: 2026-01-30 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.00262v1 Subspace clustering aims to group data points that lie in a union of low-dimensional subspaces and finds wide application in computer vision, hyperspectral imaging, and recommendation systems. However, most existing methods assume fully observed data, limiting their effectiveness in real-world scenarios with missing entries. In this paper, we propose a contrastive self-supervised framework, Contrastive Subspace Clustering (CSC), designed for clustering incomplete data. CSC generates masked views of partially observed inputs and trains a deep neural network using a SimCLR-style contrastive loss to learn invariant embeddings. These embeddings are then clustered using sparse subspace clustering. Experiments on six benchmark datasets show that CSC consistently outperforms both classical and deep learning baselines, demonstrating strong robustness to missing data and scalability to large datasets. --- ### Intelligent Reasoning Cues: A Framework and Case Study of the Roles of AI Information in Complex Decisions Authors: Venkatesh Sivaraman, Eric P. Mason, Mengfan Ellen Li, Jessica Tong, Andrew J. King, Jeremy M. Kahn, Adam Perer Published: 2026-01-30 Categories: cs.HC, cs.AI, q-bio.OT arXiv: https://arxiv.org/abs/2602.00259v1 Artificial intelligence (AI)-based decision support systems can be highly accurate yet still fail to support users or improve decisions. Existing theories of AI-assisted decision-making focus on calibrating reliance on AI advice, leaving it unclear how different system designs might influence the reasoning processes underneath. We address this gap by reconsidering AI interfaces as collections of intelligent reasoning cues: discrete pieces of AI information that can individually influence decision-making. We then explore the roles of eight types of reasoning cues in a high-stakes clinical decision (treating patients with sepsis in intensive care). Through contextual inquiries with six teams and a think-aloud study with 25 physicians, we find that reasoning cues have distinct patterns of influence that can directly inform design. Our results also suggest that reasoning cues should prioritize tasks with high variability and discretion, adapt to ensure compatibility with evolving decision needs, and provide complementary, rigorous insights on complex cases. --- ### TABES: Trajectory-Aware Backward-on-Entropy Steering for Masked Diffusion Models Authors: Shreshth Saini, Avinab Saha, Balu Adsumilli, Neil Birkbeck, Yilin Wang, Alan C. Bovik Published: 2026-01-30 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2602.00250v2 Masked Diffusion Models (MDMs) have emerged as a promising non-autoregressive paradigm for generative tasks, offering parallel decoding and bidirectional context utilization. However, current sampling methods rely on simple confidence-based heuristics that ignore the long-term impact of local decisions, leading to trajectory lock-in where early hallucinations cascade into global incoherence. While search-based methods mitigate this, they incur prohibitive computational costs ($O(K)$ forward passes per step). In this work, we propose Backward-on-Entropy (BoE) Steering, a gradient-guided inference framework that approximates infinite-horizon lookahead via a single backward pass. We formally derive the Token Influence Score (TIS) from a first-order expansion of the trajectory cost functional, proving that the gradient of future entropy with respect to input embeddings serves as an optimal control signal for minimizing uncertainty. To ensure scalability, we introduce \texttt{ActiveQueryAttention}, a sparse adjoint primitive that exploits the structure of the masking objective to reduce backward pass complexity. BoE achieves a superior Pareto frontier for inference-time scaling compared to existing unmasking methods, demonstrating that gradient-guided steering offers a mathematically principled and efficient path to robust non-autoregressive generation. We will release the code. --- ### SANEval: Open-Vocabulary Compositional Benchmarks with Failure-mode Diagnosis Authors: Rishav Pramanik, Ian E. Nielsen, Jeff Smith, Saurav Pandit, Ravi P. Ramachandran, Zhaozheng Yin Published: 2026-01-30 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.00249v1 The rapid progress of text-to-image (T2I) models has unlocked unprecedented creative potential, yet their ability to faithfully render complex prompts involving multiple objects, attributes, and spatial relationships remains a significant bottleneck. Progress is hampered by a lack of adequate evaluation methods; current benchmarks are often restricted to closed-set vocabularies, lack fine-grained diagnostic capabilities, and fail to provide the interpretable feedback necessary to diagnose and remedy specific compositional failures. We solve these challenges by introducing SANEval (Spatial, Attribute, and Numeracy Evaluation), a comprehensive benchmark that establishes a scalable new pipeline for open-vocabulary compositional evaluation. SANEval combines a large language model (LLM) for deep prompt understanding with an LLM-enhanced, open-vocabulary object detector to robustly evaluate compositional adherence, unconstrained by a fixed vocabulary. Through extensive experiments on six state-of-the-art T2I models, we demonstrate that SANEval's automated evaluations provide a more faithful proxy for human assessment; our metric achieves a Spearman's rank correlation with statistically different results than those of existing benchmarks across tasks of attribute binding, spatial relations, and numeracy. To facilitate future research in compositional T2I generation and evaluation, we will release the SANEval dataset and our open-source evaluation pipeline. --- ### CAPA: Contribution-Aware Pruning and FFN Approximation for Efficient Large Vision-Language Models Authors: Samyak Jha, Junho Kim Published: 2026-01-30 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2602.00247v1 Efficient inference in Large Vision-Language Models is constrained by the high cost of processing thousands of visual tokens, yet it remains unclear which tokens and computations can be safely removed. While attention scores are commonly used to estimate visual token importance, they are an imperfect proxy for actual contribution. We show that Attention Contribution, which weights attention probabilities by value vector magnitude, provides a more accurate criterion for visual token selection. Our empirical analysis reveals that visual attention sinks are functionally heterogeneous, comprising Probability Dumps with low contribution that can be safely pruned, and Structural Anchors with high contribution essential for maintaining model performance. Further, we identify substantial redundancy in Feed-Forward Networks (FFNs) associated with visual tokens, particularly in intermediate layers where image tokens exhibit linear behavior. Based on our findings, we introduce CAPA (Contribution-Aware Pruning and FFN Approximation), a dual-strategy framework that prunes visual tokens using attention contribution at critical functional transitions and reduces FFN computation through efficient linear approximations. Experiments on various benchmarks across baselines show that CAPA achieves competent efficiency--performance trade-offs with improved robustness. --- ### Green-NAS: A Global-Scale Multi-Objective Neural Architecture Search for Robust and Efficient Edge-Native Weather Forecasting Authors: Md Muhtasim Munif Fahim, Soyda Humyra Yesmin, Saiful Islam, Md. Palash Bin Faruque, Md. A. Salam, Md. Mahfuz Uddin, Samiul Islam, Tofayel Ahmed, Md. Binyamin, Md. Rezaul Karim Published: 2026-01-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.00240v2 We introduce Green-NAS, a multi-objective NAS (neural architecture search) framework designed for low-resource environments using weather forecasting as a case study. By adhering to 'Green AI' principles, the framework explicitly minimizes computational energy costs and carbon footprints, prioritizing sustainable deployment over raw computational scale. The Green-NAS architecture search method is optimized for both model accuracy and efficiency to find lightweight models with high accuracy and very few model parameters; this is accomplished through an optimization process that simultaneously optimizes multiple objectives. Our best-performing model, Green-NAS-A, achieved an RMSE of 0.0988 (i.e., within 1.4% of our manually tuned baseline) using only 153k model parameters, which is 239 times fewer than other globally applied weather forecasting models, such as GraphCast. In addition, we also describe how the use of transfer learning will improve the weather forecasting accuracy by approximately 5.2%, in comparison to a naive approach of training a new model for each city, when there is limited historical weather data available for that city. --- ### DIVERGE: Diversity-Enhanced RAG for Open-Ended Information Seeking Authors: Tianyi Hu, Niket Tandon, Akhil Arora Published: 2026-01-30 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.00238v2 Existing retrieval-augmented generation (RAG) systems often assume that each query has a single correct answer. This assumption overlooks open-ended information-seeking scenarios where multiple plausible answers are valuable, and where diversity is important for creativity, fairness, and inclusive access to information. We show that standard RAG systems fail to fully use diverse retrieved contexts: simply increasing retrieval diversity does not necessarily lead to diverse generations. To address this limitation, we propose Diverge, a plug-and-play agentic RAG framework that improves the diversity--quality trade-off through iterative, reflection-guided exploration of diverse viewpoints and diversity-aware retrieval support. We further introduce evaluation metrics for characterizing the diversity-quality trade-off in open-ended question answering. Experiments across multiple real-world datasets and backbone LLMs show that Diverge achieves the best trade-off among competitive baselines, increasing diversity by $\sim2\times$ without noticeable quality degradation. These results reveal a systematic limitation of current RAGs and show the value of explicit diversity modeling. --- ### MapDream: Task-Driven Map Learning for Vision-Language Navigation Authors: Guoxin Lian, Shuo Wang, Yucheng Wang, Yongcai Wang, Maiyue Chen, Kaihui Wang, Bo Zhang, Zhizhong Su, Deying Li, Zhaoxin Fan Published: 2026-01-30 Categories: cs.RO, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2602.00222v3 Vision-Language Navigation (VLN) requires agents to follow natural language instructions in partially observed 3D environments, motivating map representations that aggregate spatial context beyond local perception. However, most existing approaches rely on hand-crafted maps constructed independently of the navigation policy. We argue that maps should instead be learned representations shaped directly by navigation objectives rather than exhaustive reconstructions. Based on this insight, we propose MapDream, a map-in-the-loop framework that formulates map construction as autoregressive bird's-eye-view (BEV) image synthesis. The framework jointly learns map generation and action prediction, distilling environmental context into a compact three-channel BEV map that preserves only navigation-critical affordances. Supervised pre-training bootstraps a reliable mapping-to-control interface, while the autoregressive design enables end-to-end joint optimization through reinforcement fine-tuning. Experiments on R2R-CE and RxR-CE achieve state-of-the-art monocular performance, validating task-driven generative map learning. --- ### Benchmarking Vanilla GAN, DCGAN, and WGAN Architectures for MRI Reconstruction: A Quantitative Analysis Authors: Humaira Mehwish, Hina Shakir, Muneeba Rashid, Asarim Aamir, Reema Qaiser Khan Published: 2026-01-30 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2602.00221v1 Magnetic Resonance Imaging (MRI) is a crucial imaging modality for viewing internal body structures. This research work analyses the performance of popular GAN models for accurate and precise MRI reconstruction by enhancing image quality and improving diagnostic accuracy. Three GAN architectures considered in this study are Vanilla GAN, Deep Convolutional GAN (DCGAN), and Wasserstein GAN (WGAN). They were trained and evaluated using knee, brain, and cardiac MRI datasets to assess their generalizability across body regions. While the Vanilla GAN operates on the fundamentals of the adversarial network setup, DCGAN advances image synthesis by securing the convolutional layers, giving a superior appearance to the prevalent spatial features. Training instability is resolved in WGAN through the Wasserstein distance to minimize an unstable regime, therefore, ensuring stable convergence and high-quality images. The GAN models were trained and tested using 1000 MR images of an anonymized knee, 805 images of Heart, 90 images of Brain MRI dataset. The Structural Similarity Index (SSIM) for Vanilla GAN is 0.84, DCGAN is 0.97, and WGAN is 0.99. The Peak Signal to Noise Ratio (PSNR) for Vanilla GAN is 26, DCGAN is 49.3, and WGAN is 43.5. The results were further statistically validated. This study shows that DCGAN and WGAN-based frameworks are promising in MR image reconstruction because of good image quality and superior accuracy. With the first cross-organ benchmark of baseline GANs under a common preprocessing pipeline, this work provides a reproducible benchmark for future hybrid GANs and clinical MRI applications. --- ### Deep learning Based Correction Algorithms for 3D Medical Reconstruction in Computed Tomography and Macroscopic Imaging Authors: Tomasz Les, Tomasz Markiewicz, Malgorzata Lorent, Miroslaw Dziekiewicz, Krzysztof Siwek Published: 2026-01-30 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2602.00220v2 This paper introduces a hybrid two-stage registration framework for reconstructing three-dimensional (3D) kidney anatomy from macroscopic slices, using CT-derived models as the geometric reference standard. The approach addresses the data-scarcity and high-distortion challenges typical of macroscopic imaging, where fully learning-based registration (e.g., VoxelMorph) often fails to generalize due to limited training diversity and large nonrigid deformations that exceed the capture range of unconstrained convolutional filters. In the proposed pipeline, the Optimal Cross-section Matching (OCM) algorithm first performs constrained global alignment: translation, rotation, and uniform scaling to establish anatomically consistent slice initialization. Next, a lightweight deep-learning refinement network, inspired by VoxelMorph, predicts residual local deformations between consecutive slices. The core novelty of this architecture lies in its hierarchical decomposition of the registration manifold. This hybrid OCM+DL design integrates explicit geometric priors with the flexible learning capacity of neural networks, ensuring stable optimization and plausible deformation fields even with few training examples. Experiments on an original dataset of 40 kidneys demonstrated better results compared to single-stage baselines. The pipeline maintains physical calibration via Hough-based grid detection and employs Bezier-based contour smoothing for robust meshing and volume estimation. Although validated on kidney data, the proposed framework generalizes to other soft-tissue organs reconstructed from optical or photographic cross-sections. By decoupling interpretable global optimization from data-efficient deep refinement, the method advances the precision, reproducibility, and anatomical realism of multimodal 3D reconstructions for surgical planning, morphological assessment, and medical education. --- ### Tri-LLM Cooperative Federated Zero-Shot Intrusion Detection with Semantic Disagreement and Trust-Aware Aggregation Authors: Saeid Jamshidi, Omar Abdul Wahab, Foutse Khomh, Kawser Wazed Nafi Published: 2026-01-30 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2602.00219v1 Federated learning (FL) has become an effective paradigm for privacy-preserving, distributed Intrusion Detection Systems (IDS) in cyber-physical and Internet of Things (IoT) networks, where centralized data aggregation is often infeasible due to privacy and bandwidth constraints. Despite its advantages, most existing FL-based IDS assume closed-set learning and lack mechanisms such as uncertainty estimation, semantic generalization, and explicit modeling of epistemic ambiguity in zero-day attack scenarios. Additionally, robustness to heterogeneous and unreliable clients remains a challenge in practical applications. This paper introduces a semantics-driven federated IDS framework that incorporates language-derived semantic supervision into federated optimization, enabling open-set and zero-shot intrusion detection for previously unseen attack behaviors. The approach constructs semantic attack prototypes using a Tri-LLM ensemble of GPT-4o, DeepSeek-V3, and LLaMA-3-8B, aligning distributed telemetry features with high-level attack concepts. Inter-LLM semantic disagreement is modeled as epistemic uncertainty for zero-day risk estimation, while a trust-aware aggregation mechanism dynamically weights client updates based on reliability. Experimental results show stable semantic alignment across heterogeneous clients and consistent convergence. The framework achieves over 80% zero-shot detection accuracy on unseen attack patterns, improving zero-day discrimination by more than 10% compared to similarity-based baselines, while maintaining low aggregation instability in the presence of unreliable or compromised clients. ---