# Research Papers — 2026-03 · bundle page 210 of 243 > Full-text markdown of papers #10451–10500 of 12123 published in 2026-03, newest first. AI-readable mirrors of the full 12123-paper 2026-03 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-03/page/210 [← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/209.md) [Next bundle →](https://aipod.dev/papers/archive/2026-03/page/211.md) ### Beyond the Context Window: A Cost-Performance Analysis of Fact-Based Memory vs. Long-Context LLMs for Persistent Agents Authors: Natchanon Pollertlam, Witchayut Kornsuwannawit Published: 2026-03-05 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.04814v1 Persistent conversational AI systems face a choice between passing full conversation histories to a long-context large language model (LLM) and maintaining a dedicated memory system that extracts and retrieves structured facts. We compare a fact-based memory system built on the Mem0 framework against long-context LLM inference on three memory-centric benchmarks - LongMemEval, LoCoMo, and PersonaMemv2 - and evaluate both architectures on accuracy and cumulative API cost. Long-context GPT-5-mini achieves higher factual recall on LongMemEval and LoCoMo, while the memory system is competitive on PersonaMemv2, where persona consistency depends on stable, factual attributes suited to flat-typed extraction. We construct a cost model that incorporates prompt caching and show that the two architectures have structurally different cost profiles: long-context inference incurs a per-turn charge that grows with context length even under caching, while the memory system's per-turn read cost remains roughly fixed after a one-time write phase. At a context length of 100k tokens, the memory system becomes cheaper after approximately ten interaction turns, with the break-even point decreasing as context length grows. These results characterize the accuracy-cost trade-off between the two approaches and provide a concrete criterion for selecting between them in production deployments. --- ### Quadratic polarity and polar Fenchel-Young divergences from the canonical Legendre polarity Authors: Frank Nielsen, Basile Plus-Gourdon, Mahito Sugiyama Published: 2026-03-05 Categories: cs.CG, cs.LG arXiv: https://arxiv.org/abs/2603.04812v1 Polarity is a fundamental reciprocal duality of $n$-dimensional projective geometry which associates to points polar hyperplanes, and more generally $k$-dimensional convex bodies to polar $(n-1-k)$-dimensional convex bodies. It is well-known that the Legendre-Fenchel transformation of functions can be interpreted from the polarity viewpoint of their graphs using an extra dimension. In this paper, we first show that generic polarities induced by quadratic polarity functionals can be expressed either as deformed Legendre polarity or as the Legendre polarity of deformed convex bodies, and be efficiently manipulated using linear algebra on $(n+2)\times (n+2)$ matrices operating on homogeneous coordinates. Second, we define polar divergences using the Legendre polarity and show that they generalize the Fenchel-Young divergence or equivalent Bregman divergence. This polarity study brings new understanding of the core reference duality in information geometry. Last, we show that the total Bregman divergences can be considered as a total polar Fenchel-Young divergence from which we newly exhibit the reference duality using dual polar conformal factors. --- ### Meta-D: Metadata-Aware Architectures for Brain Tumor Analysis and Missing-Modality Segmentation Authors: SangHyuk Kim, Daniel Haehn, Sumientra Rampersad Published: 2026-03-05 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.04811v1 We present Meta-D, an architecture that explicitly leverages categorical scanner metadata such as MRI sequence and plane orientation to guide feature extraction for brain tumor analysis. We aim to improve the performance of medical image deep learning pipelines by integrating explicit metadata to stabilize feature representations. We first evaluate this in 2D tumor detection, where injecting sequence (e.g., T1, T2) and plane (e.g., axial) metadata dynamically modulates convolutional features, yielding an absolute increase of up to 2.62% in F1-score over image-only baselines. Because metadata grounds feature extraction when data are available, we hypothesize it can serve as a robust anchor when data are missing. We apply this to 3D missing-modality tumor segmentation. Our Transformer Maximizer utilizes metadata-based cross-attention to isolate and route available modalities, ensuring the network focuses on valid slices. This targeted attention improves brain tumor segmentation Dice scores by up to 5.12% under extreme modality scarcity while reducing model parameters by 24.1%. --- ### WhisperAlign: Word-Boundary-Aware ASR and WhisperX-Anchored Pyannote Diarization for Long-Form Bengali Speech Authors: Aurchi Chowdhury, Rubaiyat -E-Zaman, Sk. Ashrafuzzaman Nafees Published: 2026-03-05 Categories: cs.SD, cs.LG arXiv: https://arxiv.org/abs/2603.04809v1 This paper presents our solution for the DL Sprint 4.0, addressing the dual challenges of Bengali Long-Form Speech Recognition (Task 1) and Speaker Diarization (Task 2). Processing long-form, multi-speaker Bengali audio introduces significant hurdles in voice activity detection, overlapping speech, and context preservation. To solve the long-form transcription challenge, we implemented a robust audio chunking strategy utilizing whisper-timestamped, allowing us to feed precise, context-aware segments into our fine-tuned acoustic model for high-accuracy transcription. For the diarization task, we developed an integrated pipeline leveraging pyannote.audio and WhisperX. A key contribution of our approach is the domain-specific fine-tuning of the Pyannote segmentation model on the competition dataset. This adaptation allowed the model to better capture the nuances of Bengali conversational dynamics and accurately resolve complex, overlapping speaker boundaries. Our methodology demonstrates that applying intelligent timestamped chunking to ASR and targeted segmentation fine-tuning to diarization significantly drives down Word Error Rate (WER) and Diarization Error Rate (DER), in low-resource settings. --- ### Does Sparse Connectivity Improve Generalization? Convolutional Networks Below the Edge of Stability Authors: Tongtong Liang, Esha Singh, Rahul Parhi, Alexander Cloninger, Yu-Xiang Wang Published: 2026-03-05 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2603.04807v2 Gradient descent on overparameterized neural networks typically operates at the Edge of Stability (EoS), where the largest Hessian eigenvalue hovers around a step-size-dependent threshold. We study how sparse connectivity changes generalization below this threshold in two-layer ReLU networks. Prior results have shown that for fully-connected networks (FCNs), generalization guarantees in this regime degrade and become vacuous on high-dimensional spherical inputs. Our analysis reveals that sparse connectivity fundamentally alters this picture. Under sparse connectivity, the network processes a collection of low-dimensional patches rather than the full input vector, so the effective constraint imposed by the stability condition is governed by the geometry of the training patch collection. We prove that when the receptive fields are small relative to the ambient dimension, the effective constraint yields non-vacuous generalization bounds in precisely the spherical regime where FCNs provably fail. The same framework also reveals a contrasting failure mode: if the patch collection lacks geometric structure, the constraint becomes unable to prevent overfitting. We corroborate this theory by analyzing the patch geometry of natural images, showing that standard convolutional designs produce patch multiset with low-dimensional structure that facilitates generalization. This provides a principled explanation for the generalization advantage of convolutional networks. Thus, our analysis yields a unified framework that identifies how architecture, data geometry, and gradient descent jointly govern generalization performance. --- ### Guiding Diffusion-based Reconstruction with Contrastive Signals for Balanced Visual Representation Authors: Boyu Han, Qianqian Xu, Shilong Bao, Zhiyong Yang, Ruochen Cui, Xilin Zhao, Qingming Huang Published: 2026-03-05 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.04803v2 The limited understanding capacity of the visual encoder in Contrastive Language-Image Pre-training (CLIP) has become a key bottleneck for downstream performance. This capacity includes both Discriminative Ability (D-Ability), which reflects class separability, and Detail Perceptual Ability (P-Ability), which focuses on fine-grained visual cues. Recent solutions use diffusion models to enhance representations by conditioning image reconstruction on CLIP visual tokens. We argue that such paradigms may compromise D-Ability and therefore fail to effectively address CLIP's representation limitations. To address this, we integrate contrastive signals into diffusion-based reconstruction to pursue more comprehensive visual representations. We begin with a straightforward design that augments the diffusion process with contrastive learning on input images. However, empirical results show that the naive combination suffers from gradient conflict and yields suboptimal performance. To balance the optimization, we introduce the Diffusion Contrastive Reconstruction (DCR), which unifies the learning objective. The key idea is to inject contrastive signals derived from each reconstructed image, rather than from the original input, into the diffusion process. Our theoretical analysis shows that the DCR loss can jointly optimize D-Ability and P-Ability. Extensive experiments across various benchmarks and multi-modal large language models validate the effectiveness of our method. The code is available at https://github.com/boyuh/DCR. --- ### MASQuant: Modality-Aware Smoothing Quantization for Multimodal Large Language Models Authors: Lulu Hu, Wenhu Xiao, Xin Chen, Xinhua Xu, Bowen Xu, Kun Li, Yongliang Tao Published: 2026-03-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.04800v1 Post-training quantization (PTQ) with computational invariance for Large Language Models~(LLMs) have demonstrated remarkable advances, however, their application to Multimodal Large Language Models~(MLLMs) presents substantial challenges. In this paper, we analyze SmoothQuant as a case study and identify two critical issues: Smoothing Misalignment and Cross-Modal Computational Invariance. To address these issues, we propose Modality-Aware Smoothing Quantization (MASQuant), a novel framework that introduces (1) Modality-Aware Smoothing (MAS), which learns separate, modality-specific smoothing factors to prevent Smoothing Misalignment, and (2) Cross-Modal Compensation (CMC), which addresses Cross-modal Computational Invariance by using SVD whitening to transform multi-modal activation differences into low-rank forms, enabling unified quantization across modalities. MASQuant demonstrates stable quantization performance across both dual-modal and tri-modal MLLMs. Experimental results show that MASQuant is competitive among the state-of-the-art PTQ algorithms. Source code: https://github.com/alibaba/EfficientAI. --- ### Beyond Linear LLM Invocation: An Efficient and Effective Semantic Filter Paradigm Authors: Nan Hou, Kangfei Zhao, Jiadong Xie, Jeffrey Xu Yu Published: 2026-03-05 Categories: cs.DB, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.04799v1 Large language models (LLMs) are increasingly used for semantic query processing over large corpora. A set of semantic operators derived from relational algebra has been proposed to provide a unified interface for expressing such queries, among which the semantic filter operator serves as a cornerstone. Given a table T with a natural language predicate e, for each tuple in the relation, the execution of a semantic filter proceeds by constructing an input prompt that combines the predicate e with its content, querying the LLM, and obtaining the binary decision. However, this tuple-by-tuple evaluation necessitates a complete linear scan of the table, incurring prohibitive latency and token costs. Although recent work has attempted to optimize semantic filtering, it still does not break the linear LLM invocation barriers. To address this, we propose Clustering-Sampling-Voting (CSV), a new framework that reduces LLM invocations to sublinear complexity while providing error guarantees. CSV embeds tuples into semantic clusters, samples a small subset for LLM evaluation, and infers cluster-level labels via two proposed voting strategies: UniVote, which aggregates labels uniformly, and SimVote, which weights votes by semantic similarity. Moreover, CSV triggers re-clustering on ambiguous clusters to ensure robustness across diverse datasets. The results conducted on real-world datasets demonstrate that CSV reduces the number of LLM calls by 1.28-355x compared to the state-of-the-art approaches, while maintaining comparable effectiveness in terms of Accuracy and F1 score. --- ### Comparative Evaluation of Traditional Methods and Deep Learning for Brain Glioma Imaging. Review Paper Authors: Kiranmayee Janardhan, Vinay Martin DSa Prabhu, T. Christy Bobby Published: 2026-03-05 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.04796v1 Segmentation is crucial for brain gliomas as it delineates the glioma s extent and location, aiding in precise treatment planning and monitoring, thus improving patient outcomes. Accurate segmentation ensures proper identification of the glioma s size and position, transforming images into applicable data for analysis. Classification of brain gliomas is also essential because different types require different treatment approaches. Accurately classifying brain gliomas by size, location, and aggressiveness is essential for personalized prognosis prediction, follow-up care, and monitoring disease progression, ensuring effective diagnosis, treatment, and management. In glioma research, irregular tissues are often observable, but error free and reproducible segmentation is challenging. Many researchers have surveyed brain glioma segmentation, proposing both fully automatic and semi-automatic techniques. The adoption of these methods by radiologists depends on ease of use and supervision, with semi-automatic techniques preferred due to the need for accurate evaluations. This review evaluates effective segmentation and classification techniques post magnetic resonance imaging acquisition, highlighting that convolutional neural network architectures outperform traditional techniques in these tasks. --- ### LAW & ORDER: Adaptive Spatial Weighting for Medical Diffusion and Segmentation Authors: Anugunj Naman, Ayushman Singh, Gaibo Zhang, Yaguang Zhang Published: 2026-03-05 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.04795v2 Medical image analysis depends on accurate segmentation and controllable synthesis, but both tasks face severe spatial imbalance: lesions occupy small regions against large backgrounds. We study adaptive spatial weighting as a task-level design principle and instantiate it in two adapters. LAW learns per-pixel loss weights for mask-conditioned diffusion by modulating a ratio prior with a feature-dependent delta map, with normalization, clamping, and Dice regularization for stability. ORDER improves lightweight segmentation by adding selective bidirectional skip attention with stage-wise confidence gating. On held-out diffusion test sets, LAW lowers FID from 158.13$\pm$0.15 to 108.43$\pm$0.71 on Polyps, from 144.13$\pm$0.31 to 89.51$\pm$0.96 on KiTS19, and from 139.22$\pm$0.38 to 112.58$\pm$0.68 on BRISC, while improving held-out mask-recovery Dice from 0.681$\pm$0.013 to 0.825$\pm$0.003 on Polyps. When the resulting images are added to nnUNet training, downstream Polyps mDice rises from 71.7$\pm$0.4 to 74.1$\pm$0.8. On the cleaned Polyps segmentation protocol, the reported ORDER configuration reaches 76.3$\pm$1.9 mDice and 67.2$\pm$2.0 mIoU at 42K parameters and 0.11 GFLOPs, versus 70.3$\pm$1.5 mDice and 59.9$\pm$1.7 mIoU for matched MK-UNet. On BRISC under the same training recipe, ORDER reaches 77.4$\pm$0.8 mDice and 68.1$\pm$0.7 mIoU. These results position adaptive spatial weighting as a practical design idea for both medical diffusion and efficient segmentation. --- ### RMK RetinaNet: Rotated Multi-Kernel RetinaNet for Robust Oriented Object Detection in Remote Sensing Imagery Authors: Huiran Sun Published: 2026-03-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.04793v1 Rotated object detection in remote sensing imagery is hindered by three major bottlenecks: non-adaptive receptive field utilization, inadequate long-range multi-scale feature fusion, and discontinuities in angle regression. To address these issues, we propose Rotated Multi-Kernel RetinaNet (RMK RetinaNet). First, we design a Multi-Scale Kernel (MSK) Block to strengthen adaptive multi-scale feature extraction. Second, we incorporate a Multi-Directional Contextual Anchor Attention (MDCAA) mechanism into the feature pyramid to enhance contextual modeling across scales and orientations. Third, we introduce a Bottom-up Path to preserve fine-grained spatial details that are often degraded during downsampling. Finally, we develop an Euler Angle Encoding Module (EAEM) to enable continuous and stable angle regression. Extensive experiments on DOTA-v1.0, HRSC2016, and UCAS-AOD show that RMK RetinaNet achieves performance comparable to state-of-the-art rotated object detectors while improving robustness in multi-scale and multi-orientation scenarios. --- ### Timer-S1: A Billion-Scale Time Series Foundation Model with Serial Scaling Authors: Yong Liu, Xingjian Su, Shiyu Wang, Haoran Zhang, Haixuan Liu, Yuxuan Wang, Zhou Ye, Yang Xiang, Jianmin Wang, Mingsheng Long Published: 2026-03-05 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.04791v3 We introduce Timer-S1, a strong Mixture-of-Experts (MoE) time series foundation model with 8.3B total parameters, 0.75B activated parameters for each token, and a context length of 11.5K. To overcome the scalability bottleneck in existing pre-trained time series foundation models, we perform Serial Scaling in three dimensions: model architecture, dataset, and training pipeline. Timer-S1 integrates sparse TimeMoE blocks and generic TimeSTP blocks for Serial-Token Prediction (STP), a generic training objective that adheres to the serial nature of forecasting. The proposed paradigm introduces serial computations to improve long-term predictions while avoiding costly rolling-style inference and pronounced error accumulation in the standard next-token prediction. Pursuing a high-quality and unbiased training dataset, we curate TimeBench, a corpus with one trillion time points, and apply meticulous data augmentation to mitigate predictive bias. We further pioneer a post-training stage, including continued pre-training and long-context extension, to enhance short-term and long-context performance. Evaluated on the large-scale GIFT-Eval leaderboard, Timer-S1 achieves state-of-the-art forecasting performance, attaining the best MASE and CRPS scores as a pre-trained model. Timer-S1 is released to facilitate further research. --- ### Diffusion Policy through Conditional Proximal Policy Optimization Authors: Ben Liu, Shunpeng Yang, Hua Chen Published: 2026-03-05 Categories: cs.LG, cs.RO arXiv: https://arxiv.org/abs/2603.04790v1 Reinforcement learning (RL) has been extensively employed in a wide range of decision-making problems, such as games and robotics. Recently, diffusion policies have shown strong potential in modeling multi-modal behaviors, enabling more diverse and flexible action generation compared to the conventional Gaussian policy. Despite various attempts to combine RL with diffusion, a key challenge is the difficulty of computing action log-likelihood under the diffusion model. This greatly hinders the direct application of diffusion policies in on-policy reinforcement learning. Most existing methods calculate or approximate the log-likelihood through the entire denoising process in the diffusion model, which can be memory- and computationally inefficient. To overcome this challenge, we propose a novel and efficient method to train a diffusion policy in an on-policy setting that requires only evaluating a simple Gaussian probability. This is achieved by aligning the policy iteration with the diffusion process, which is a distinct paradigm compared to previous work. Moreover, our formulation can naturally handle entropy regularization, which is often difficult to incorporate into diffusion policies. Experiments demonstrate that the proposed method produces multimodal policy behaviors and achieves superior performance on a variety of benchmark tasks in both IsaacLab and MuJoCo Playground. --- ### Breaking Contextual Inertia: Reinforcement Learning with Single-Turn Anchors for Stable Multi-Turn Interaction Authors: Xingwu Chen, Zhanqiu Zhang, Yiwen Guo, Difan Zou Published: 2026-03-05 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.04783v2 While LLMs demonstrate strong reasoning capabilities when provided with full information in a single turn, they exhibit substantial vulnerability in multi-turn interactions. Specifically, when information is revealed incrementally or requires updates, models frequently fail to integrate new constraints, leading to a collapse in performance compared to their single-turn baselines. We term the root cause as \emph{Contextual Inertia}: a phenomenon where models rigidly adhere to previous reasoning traces. Even when users explicitly provide corrections or new data in later turns, the model ignores them, preferring to maintain consistency with its previous (incorrect) reasoning path. To address this, we introduce \textbf{R}einforcement \textbf{L}earning with \textbf{S}ingle-\textbf{T}urn \textbf{A}nchors (\textbf{RLSTA}), a generalizable training approach designed to stabilize multi-turn interaction across diverse scenarios and domains. RLSTA leverages the model's superior single-turn capabilities as stable internal anchors to provide reward signals. By aligning multi-turn responses with these anchors, RLSTA empowers models to break contextual inertia and self-calibrate their reasoning based on the latest information. Experiments show that RLSTA significantly outperforms standard fine-tuning and abstention-based methods. Notably, our method exhibits strong cross-domain generalization (e.g., math to code) and proves effective even without external verifiers, highlighting its potential for general-domain applications. Code is available at https://github.com/Tencent/RLSTA. --- ### Distributional Equivalence in Linear Non-Gaussian Latent-Variable Cyclic Causal Models: Characterization and Learning Authors: Haoyue Dai, Immanuel Albrecht, Peter Spirtes, Kun Zhang Published: 2026-03-05 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2603.04780v1 Causal discovery with latent variables is a fundamental task. Yet most existing methods rely on strong structural assumptions, such as enforcing specific indicator patterns for latents or restricting how they can interact with others. We argue that a core obstacle to a general, structural-assumption-free approach is the lack of an equivalence characterization: without knowing what can be identified, one generally cannot design methods for how to identify it. In this work, we aim to close this gap for linear non-Gaussian models. We establish the graphical criterion for when two graphs with arbitrary latent structure and cycles are distributionally equivalent, that is, they induce the same observed distribution set. Key to our approach is a new tool, edge rank constraints, which fills a missing piece in the toolbox for latent-variable causal discovery in even broader settings. We further provide a procedure to traverse the whole equivalence class and develop an algorithm to recover models from data up to such equivalence. To our knowledge, this is the first equivalence characterization with latent variables in any parametric setting without structural assumptions, and hence the first structural-assumption-free discovery method. Code and an interactive demo are available at https://equiv.cc. --- ### Privacy-Aware Camera 2.0 Technical Report Authors: Huan Song, Shuyu Tian, Ting Long, Jiang Liu, Cheng Yuan, Zhenyu Jia, Jiawei Shao, Xuelong Li Published: 2026-03-05 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2603.04775v1 With the increasing deployment of intelligent sensing technologies in highly sensitive environments such as restrooms and locker rooms, visual surveillance systems face a profound privacy-security paradox. Existing privacy-preserving approaches, including physical desensitization, encryption, and obfuscation, often compromise semantic understanding or fail to ensure mathematically provable irreversibility. Although Privacy Camera 1.0 eliminated visual data at the source to prevent leakage, it provided only textual judgments, leading to evidentiary blind spots in disputes. To address these limitations, this paper proposes a novel privacy-preserving perception framework based on the AI Flow paradigm and a collaborative edge-cloud architecture. By deploying a visual desensitizer at the edge, raw images are transformed in real time into abstract feature vectors through nonlinear mapping and stochastic noise injection under the Information Bottleneck principle, ensuring identity-sensitive information is stripped and original images are mathematically unreconstructable. The abstract representations are transmitted to the cloud for behavior recognition and semantic reconstruction via a "dynamic contour" visual language, achieving a critical balance between perception and privacy while enabling illustrative visual reference without exposing raw images. --- ### TSEmbed: Unlocking Task Scaling in Universal Multimodal Embeddings Authors: Yebo Wu, Feng Liu, Ziwei Xie, Zhiyuan Liu, Changwang Zhang, Jun Wang, Li Li Published: 2026-03-05 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.04772v1 Despite the exceptional reasoning capabilities of Multimodal Large Language Models (MLLMs), their adaptation into universal embedding models is significantly impeded by task conflict. To address this, we propose TSEmbed, a universal multimodal embedding framework that synergizes Mixture-of-Experts (MoE) with Low-Rank Adaptation (LoRA) to explicitly disentangle conflicting task objectives. Moreover, we introduce Expert-Aware Negative Sampling (EANS), a novel strategy that leverages expert routing distributions as an intrinsic proxy for semantic similarity. By dynamically prioritizing informative hard negatives that share expert activation patterns with the query, EANS effectively sharpens the model's discriminative power and refines embedding boundaries. To ensure training stability, we further devise a two-stage learning paradigm that solidifies expert specialization before optimizing representations via EANS. TSEmbed achieves state-of-the-art performance on both the Massive Multimodal Embedding Benchmark (MMEB) and real-world industrial production datasets, laying a foundation for task-level scaling in universal multimodal embeddings. --- ### MADCrowner: Margin Aware Dental Crown Design with Template Deformation and Refinement Authors: Linda Wei, Chang Liu, Wenran Zhang, Yuxuan Hu, Ruiyang Li, Feng Qi, Changyao Tian, Ke Wang, Yuanyuan Wang, Shaoting Zhang, Dimitris Metaxas, Hongsheng Li Published: 2026-03-05 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.04771v1 Dental crown restoration is one of the most common treatment modalities for tooth defect, where personalized dental crown design is critical. While computer-aided design (CAD) systems have notably enhanced the efficiency of dental crown design, extensive manual adjustments are still required in the clinic workflow. Recent studies have explored the application of learning-based methods for the automated generation of restorative dental crowns. Nevertheless, these approaches were challenged by inadequate spatial resolution, noisy outputs, and overextension of surface reconstruction. To address these limitations, we propose \totalframework, a margin-aware mesh generation framework comprising CrownDeformR and CrownSegger. Inspired by the clinic manual workflow of dental crown design, we designed CrownDeformR to deform an initial template to the target crown based on anatomical context, which is extracted by a multi-scale intraoral scan encoder. Additionally, we introduced \marginseg, a novel margin segmentation network, to extract the cervical margin of the target tooth. The performance of CrownDeformR improved with the cervical margin as an extra constraint. And it was also utilized as the boundary condition for the tailored postprocessing method, which removed the overextended area of the reconstructed surface. We constructed a large-scale intraoral scan dataset and performed extensive experiments. The proposed method significantly outperformed existing approaches in both geometric accuracy and clinical feasibility. --- ### DSA-SRGS: Super-Resolution Gaussian Splatting for Dynamic Sparse-View DSA Reconstruction Authors: Shiyu Zhang, Zhicong Wu, Huangxuan Zhao, Zhentao Liu, Lei Chen, Yong Luo, Lefei Zhang, Zhiming Cui, Ziwen Ke, Bo Du Published: 2026-03-05 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.04770v1 Digital subtraction angiography (DSA) is a key imaging technique for the auxiliary diagnosis and treatment of cerebrovascular diseases. Recent advancements in gaussian splatting and dynamic neural representations have enabled robust 3D vessel reconstruction from sparse dynamic inputs. However, these methods are fundamentally constrained by the resolution of input projections, where performing naive upsampling to enhance rendering resolution inevitably results in severe blurring and aliasing artifacts. Such lack of super-resolution capability prevents the reconstructed 4D models from recovering fine-grained vascular details and intricate branching structures, which restricts their application in precision diagnosis and treatment. To solve this problem, this paper proposes DSA-SRGS, the first super-resolution gaussian splatting framework for dynamic sparse-view DSA reconstruction. Specifically, we introduce a Multi-Fidelity Texture Learning Module that integrates high-quality priors from a fine-tuned DSA-specific super-resolution model, into the 4D reconstruction optimization. To mitigate potential hallucination artifacts from pseudo-labels, this module employs a Confidence-Aware Strategy to adaptively weight supervision signals between the original low-resolution projections and the generated high-resolution pseudo-labels. Furthermore, we develop Radiative Sub-Pixel Densification, an adaptive strategy that leverages gradient accumulation from high-resolution sub-pixel sampling to refine the 4D radiative gaussian kernels. Extensive experiments on two clinical DSA datasets demonstrate that DSA-SRGS significantly outperforms state-of-the-art methods in both quantitative metrics and qualitative visual fidelity. --- ### Distributional Reinforcement Learning with Information Bottleneck for Uncertainty-Aware DRAM Equalization Authors: Muhammad Usama, Dong Eui Chang Published: 2026-03-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.04768v1 Equalizer parameter optimization is critical for signal integrity in high-speed memory systems operating at multi-gigabit data rates. However, existing methods suffer from computationally expensive eye diagram evaluation, optimization of expected rather than worst-case performance, and absence of uncertainty quantification for deployment decisions. In this paper, we propose a distributional risk-sensitive reinforcement learning framework integrating Information Bottleneck latent representations with Conditional Value-at-Risk optimization. We introduce rate-distortion optimal signal compression achieving 51 times speedup over eye diagrams while quantifying epistemic uncertainty through Monte Carlo dropout. Distributional reinforcement learning with quantile regression enables explicit worst-case optimization, while PAC-Bayesian regularization certifies generalization bounds. Experimental validation on 2.4 million waveforms from eight memory units demonstrated mean improvements of 37.1\% and 41.5\% for 4-tap and 8-tap equalizer configurations with worst-case guarantees of 33.8\% and 38.2\%, representing 80.7\% and 89.1\% improvements over Q-learning baselines. The framework achieved 62.5\% high-reliability classification eliminating manual validation for most configurations. These results suggest the proposed framework provides a practical solution for production-scale equalizer optimization with certified worst-case guarantees. --- ### ConTSG-Bench: A Unified Benchmark for Conditional Time Series Generation Authors: Shaocheng Lan, Shuqi Gu, Zhangzhi Xiong, Kan Ren Published: 2026-03-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.04767v1 Conditional time series generation plays a critical role in addressing data scarcity and enabling causal analysis in real-world applications. Despite its increasing importance, the field lacks a standardized and systematic benchmarking framework for evaluating generative models across diverse conditions. To address this gap, we introduce the Conditional Time Series Generation Benchmark (ConTSG-Bench). ConTSG-Bench comprises a large-scale, well-aligned dataset spanning diverse conditioning modalities and levels of semantic abstraction, first enabling systematic evaluation of representative generation methods across these dimensions with a comprehensive suite of metrics for generation fidelity and condition adherence. Both the quantitative benchmarking and in-depth analyses of conditional generation behaviors have revealed the traits and limitations of the current approaches, highlighting critical challenges and promising research directions, particularly with respect to precise structural controllability and downstream task utility under complex conditions. --- ### Evaluating and Correcting Human Annotation Bias in Dynamic Micro-Expression Recognition Authors: Feng Liu, Bingyu Nan, Xuezhong Qian, Xiaolan Fu Published: 2026-03-05 Categories: cs.CV, cs.CY arXiv: https://arxiv.org/abs/2603.04766v1 Existing manual labeling of micro-expressions is subject to errors in accuracy, especially in cross-cultural scenarios where deviation in labeling of key frames is more prominent. To address this issue, this paper presents a novel Global Anti-Monotonic Differential Selection Strategy (GAMDSS) architecture for enhancing the effectiveness of spatio-temporal modeling of micro-expressions through keyframe re-selection. Specifically, the method identifies Onset and Apex frames, which are characterized by significant micro-expression variation, from complete micro-expression action sequences via a dynamic frame reselection mechanism. It then uses these to determine Offset frames and construct a rich spatio-temporal dynamic representation. A two-branch structure with shared parameters is then used to efficiently extract spatio-temporal features. Extensive experiments are conducted on seven widely recognized micro-expression datasets. The results demonstrate that GAMDSS effectively reduces subjective errors caused by human factors in multicultural datasets such as SAMM and 4DME. Furthermore, quantitative analyses confirm that offset-frame annotations in multicultural datasets are more uncertain, providing theoretical justification for standardizing micro-expression annotations. These findings directly support our argument for reconsidering the validity and generalizability of dataset annotation paradigms. Notably, this design can be integrated into existing models without increasing the number of parameters, offering a new approach to enhancing micro-expression recognition performance. The source code is available on GitHub(https://github.com/Cross-Innovation-Lab/GAMDSS). --- ### Evaluating GPT-5 as a Multimodal Clinical Reasoner: A Landscape Commentary Authors: Alexandru Florea, Shansong Wang, Mingzhe Hu, Qiang Li, Zach Eidex, Luke del Balzo, Mojtaba Safari, Xiaofeng Yang Published: 2026-03-05 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.04763v1 The transition from task-specific artificial intelligence toward general-purpose foundation models raises fundamental questions about their capacity to support the integrated reasoning required in clinical medicine, where diagnosis demands synthesis of ambiguous patient narratives, laboratory data, and multimodal imaging. This landscape commentary provides the first controlled, cross-sectional evaluation of the GPT-5 family (GPT-5, GPT-5 Mini, GPT-5 Nano) against its predecessor GPT-4o across a diverse spectrum of clinically grounded tasks, including medical education examinations, text-based reasoning benchmarks, and visual question-answering in neuroradiology, digital pathology, and mammography using a standardized zero-shot chain-of-thought protocol. GPT-5 demonstrated substantial gains in expert-level textual reasoning, with absolute improvements exceeding 25 percentage-points on MedXpertQA. When tasked with multimodal synthesis, GPT-5 effectively leveraged this enhanced reasoning capacity to ground uncertain clinical narratives in concrete imaging evidence, achieving state-of-the-art or competitive performance across most VQA benchmarks and outperforming GPT-4o by margins of 10-40% in mammography tasks requiring fine-grained lesion characterization. However, performance remained moderate in neuroradiology (44% macro-average accuracy) and lagged behind domain-specific models in mammography, where specialized systems exceed 80% accuracy compared to GPT-5's 52-64%. These findings indicate that while GPT-5 represents a meaningful advance toward integrated multimodal clinical reasoning, mirroring the clinician's cognitive process of biasing uncertain information with objective findings, generalist models are not yet substitutes for purpose-built systems in highly specialized, perception-critical tasks. --- ### Stacked from One: Multi-Scale Self-Injection for Context Window Extension Authors: Wei Han, Pan Zhou, Soujanya Poria, Shuicheng Yan Published: 2026-03-05 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.04759v2 The limited context window of contemporary large language models (LLMs) remains a primary bottleneck for their broader application across diverse domains. Although continual pre-training on long-context data offers a straightforward solution, it incurs prohibitive data acquisition and computational costs. To address this challenge, we propose~\modelname, a novel framework based on multi-grained context compression and query-aware information acquisition. SharedLLM comprises two stacked short-context LLMs: a lower model serving as a compressor and an upper model acting as a decoder. The lower model compresses long inputs into compact, multi-grained representations, which are then forwarded to the upper model for context-aware processing. To maximize efficiency, this information transfer occurs exclusively at the lowest layers, bypassing lengthy forward passes and redundant cross-attention operations. This entire process, wherein the upper and lower models are derived from the same underlying LLM layers, is termed~\textit{self-injection}. To support this architecture, a specialized tree-based data structure enables the efficient encoding and query-aware retrieval of contextual information. Despite being trained on sequences of only 8K tokens, \modelname~effectively generalizes to inputs exceeding 128K tokens. Across a comprehensive suite of long-context modeling and understanding benchmarks, \modelname~achieves performance superior or comparable to strong baselines, striking an optimal balance between efficiency and accuracy. Furthermore, these design choices allow \modelname~to substantially reduce the memory footprint and yield notable inference speedups ($2\times$ over streaming and $3\times$ over encoder-decoder architectures). --- ### MOOSEnger: A Simulation-Aware AI Agent Framework for the MOOSE Ecosystem Authors: Mengnan Li, Jason Miller, Zaid Abulawi, Zachary Prince, Matt Kohl, Jack M. Cavaluzzi, Guillaume Giudicelli, Casey T. Icenhour, Alexander Lindsay, Cody Permann Published: 2026-03-05 Categories: cs.AI, cs.CE, cs.SE arXiv: https://arxiv.org/abs/2603.04756v3 MOOSEnger is a modeling and simulation AI agent framework for the Multiphysics Object-Oriented Simulation Environment (MOOSE) ecosystem, built around a simulation-aware harness that combines an interchangeable reasoning model with grounded domain knowledge, revised simulation artifacts, MOOSE-specific validation, and executable solver feedback. This surrounding system addresses a central limitation of one-shot large language model generation: small syntax, schema, reference, or solver-configuration errors can prevent a plausible input from executing, while successful execution alone does not establish scientific correctness. MOOSEnger's simulation-aware harness integrates MOOSE knowledge retrieval, Hierarchical Input Text (HIT)-aware parsing, syntax metadata, language-server diagnostics, revision-controlled authoring, and local or MCP-backed validation and execution in a generate-check-repair-run workflow that binds evidence to each input revision and guides bounded repair before acceptance. Across 200 prompts spanning eight simulation families, the MOOSEnger harness increases executable success from 10/200 (5%) to 179/200 (89.5%) with GPT 5.2 API and from 0/200 to 153/200 (76.5%) with Gemma 4 31B. A complementary ten-case Method of Manufactured Solutions benchmark moves beyond executability: all ten generated inputs satisfy the semantic-alignment criterion, and eight execute successfully while meeting the prescribed single-mesh numerical-accuracy criterion. These results show that executable reliability depends on the complete agent system rather than on the reasoning model alone, and that simulation-aware harnessing provides a path toward physics-informed verification and future full application-level and engineering verification and validation implementation. --- ### MOOSEnger -- a Domain-Specific AI Agent for the MOOSE Ecosystem Authors: Mengnan Li, Jason Miller, Zachary Prince, Alexander Lindsay, Cody Permann Published: 2026-03-05 Categories: cs.AI, cs.CE, cs.SE arXiv: https://arxiv.org/abs/2603.04756v2 MOOSEnger is a tool-enabled AI agent tailored to the Multiphysics Object-Oriented Simulation Environment (MOOSE). MOOSE cases are specified in HIT ".i" input files; the large object catalog and strict syntax make initial setup and debugging slow. MOOSEnger offers a conversational workflow that turns natural-language intent into runnable inputs by combining retrieval-augmented generation over curated docs/examples with deterministic, MOOSE-aware parsing, validation, and execution tools. A core-plus-domain architecture separates reusable agent infrastructure (configuration, registries, tool dispatch, retrieval services, persistence, and evaluation) from a MOOSE plugin that adds HIT-based parsing, syntax-preserving ingestion of input files, and domain-specific utilities for input repair and checking. An input precheck pipeline removes hidden formatting artifacts, fixes malformed HIT structure with a bounded grammar-constrained loop, and resolves invalid object types via similarity search over an application syntax registry. Inputs are then validated and optionally smoke-tested with the MOOSE runtime in the loop via an MCP-backed execution backend (with local fallback), translating solver diagnostics into iterative verify-and-correct updates. Built-in evaluation reports RAG metrics (faithfulness, relevancy, context precision/recall) and end-to-end success by actual execution. On a 125-prompt benchmark spanning diffusion, transient heat conduction, solid mechanics, porous flow, incompressible Navier--Stokes, phase field and plasticity, MOOSEnger achieves a 0.90 execution pass rate versus 0.06 for an LLM-only baseline. --- ### KindSleep: Knowledge-Informed Diagnosis of Obstructive Sleep Apnea from Oximetry Authors: Micky C Nnamdi, Wenqi Shi, Cheng Wan, J. Ben Tamo, Benjamin M Smith, Chad A Purnell, May D Wang Published: 2026-03-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.04755v2 Obstructive sleep apnea (OSA) is a sleep disorder that affects nearly one billion people globally and significantly elevates cardiovascular risk. Traditional diagnosis through polysomnography is resource-intensive and limits widespread access, creating a critical need for accurate and efficient alternatives. In this paper, we introduce KindSleep, a deep learning framework that integrates clinical knowledge with single-channel patient-specific oximetry signals and clinical data for precise OSA diagnosis. KindSleep first learns to identify clinically interpretable concepts, such as desaturation indices and respiratory disturbance events, directly from raw oximetry signals. It then fuses these AI-derived concepts with multimodal clinical data to estimate the Apnea-Hypopnea Index (AHI). We evaluate KindSleep on three large, independent datasets from the National Sleep Research Resource (SHHS, CFS, MrOS; total n = 9,815). KindSleep demonstrates excellent performance in estimating AHI scores (R2 = 0.917, ICC = 0.957) and consistently outperforms existing approaches in classifying OSA severity, achieving weighted F1-scores from 0.827 to 0.941 across diverse populations. By grounding its predictions in a layer of clinically meaningful concepts, KindSleep provides a more transparent and trustworthy diagnostic tool for sleep medicine practices. --- ### Evaluating the Search Agent in a Parallel World Authors: Jiawei Chen, Xintian Shen, Lihao Zheng, Lifu Mu, Haoyi Sun, Ning Mao, Hao Ma, Tao Wei, Pan Zhou, Kun Zhan Published: 2026-03-05 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.04751v2 Integrating web search tools has significantly extended the capability of LLMs to address open-world, real-time, and long-tail problems. However, evaluating these Search Agents presents formidable challenges. First, constructing high-quality deep search benchmarks is prohibitively expensive, while unverified synthetic data often suffers from unreliable sources. Second, static benchmarks face dynamic obsolescence: as internet information evolves, complex queries requiring deep research often degrade into simple retrieval tasks due to increased popularity, and ground truths become outdated due to temporal shifts. Third, attribution ambiguity confounds evaluation, as an agent's performance is often dominated by its parametric memory rather than its actual search and reasoning capabilities. Finally, reliance on specific commercial search engines introduces variability that hampers reproducibility. To address these issues, we propose a novel framework, Mind-ParaWorld, for evaluating Search Agents in a Parallel World. Specifically, MPW samples real-world entity names to synthesize future scenarios and questions situated beyond the model's knowledge cutoff. A ParaWorld Law Model then constructs a set of indivisible Atomic Facts and a unique ground-truth for each question. During evaluation, instead of retrieving real-world results, the agent interacts with a ParaWorld Engine Model that dynamically generates SERPs grounded in these inviolable Atomic Facts. We release MPW-Bench, an interactive benchmark spanning 19 domains with 1,608 instances. Experiments across three evaluation settings show that, while search agents are strong at evidence synthesis given complete information, their performance is limited not only by evidence collection and coverage in unfamiliar search environments, but also by unreliable evidence sufficiency judgment and when-to-stop decisions-bottlenecks. --- ### HiMAP-Travel: Hierarchical Multi-Agent Planning for Long-Horizon Constrained Travel Authors: The Viet Bui, Wenjun Li, Yong Liu Published: 2026-03-05 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.04750v1 Sequential LLM agents fail on long-horizon planning with hard constraints like budgets and diversity requirements. As planning progresses and context grows, these agents drift from global constraints. We propose HiMAP-Travel, a hierarchical multi-agent framework that splits planning into strategic coordination and parallel day-level execution. A Coordinator allocates resources across days, while Day Executors plan independently in parallel. Three key mechanisms enable this: a transactional monitor enforcing budget and uniqueness constraints across parallel agents, a bargaining protocol allowing agents to reject infeasible sub-goals and trigger re-planning, and a single policy trained with GRPO that powers all agents through role conditioning. On TravelPlanner, HiMAP-Travel with Qwen3-8B achieves 52.78% validation and 52.65% test Final Pass Rate (FPR). In a controlled comparison with identical model, training, and tools, it outperforms the sequential DeepTravel baseline by +8.67~pp. It also surpasses ATLAS by +17.65~pp and MTP by +10.0~pp. On FlexTravelBench multi-turn scenarios, it achieves 44.34% (2-turn) and 37.42% (3-turn) FPR while reducing latency 2.5x through parallelization. --- ### Visioning Human-Agentic AI Teaming: Continuity, Tension, and Future Research Authors: Bowen Lou, Tian Lu, T. S. Raghu, Yingjie Zhang Published: 2026-03-05 Categories: cs.AI, cs.HC, econ.GN arXiv: https://arxiv.org/abs/2603.04746v1 Artificial intelligence is undergoing a structural transformation marked by the rise of agentic systems capable of open-ended action trajectories, generative representations and outputs, and evolving objectives. These properties introduce structural uncertainty into human-AI teaming (HAT), including uncertainty about behavior trajectories, epistemic grounding, and the stability of governing logics over time. Under such conditions, alignment cannot be secured through agreement on bounded outputs; it must be continuously sustained as plans unfold and priorities shift. We advance Team Situation Awareness (Team SA) theory, grounded in shared perception, comprehension, and projection, as an integrative anchor for this transition. While Team SA remains analytically foundational, its stabilizing logic presumes that shared awareness, once achieved, will support coordinated action through iterative updating. Agentic AI challenges this presumption. Our argument unfolds in two stages: first, we extend Team SA to reconceptualize both human and AI awareness under open-ended agency, including the sensemaking of projection congruence across heterogeneous systems. Second, we interrogate whether the dynamic processes traditionally assumed to stabilize teaming in relational interaction, cognitive learning, and coordination and control continue to function under adaptive autonomy. By distinguishing continuity from tension, we clarify where foundational insights hold and where structural uncertainty introduces strain, and articulate a forward-looking research agenda for HAT. The central challenge of HAT is not whether humans and AI can agree in the moment, but whether they can remain aligned as futures are continuously generated, revised, enacted, and governed over time. --- ### Toward Real-world Infrared Image Super-Resolution: A Unified Autoregressive Framework and Benchmark Dataset Authors: Yang Zou, Jun Ma, Zhidong Jiao, Xingyuan Li, Zhiying Jiang, Jinyuan Liu Published: 2026-03-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.04745v1 Infrared image super-resolution (IISR) under real-world conditions is a practically significant yet rarely addressed task. Pioneering works are often trained and evaluated on simulated datasets or neglect the intrinsic differences between infrared and visible imaging. In practice, however, real infrared images are affected by coupled optical and sensing degradations that jointly deteriorate both structural sharpness and thermal fidelity. To address these challenges, we propose Real-IISR, a unified autoregressive framework for real-world IISR that progressively reconstructs fine-grained thermal structures and clear backgrounds in a scale-by-scale manner via thermal-structural guided visual autoregression. Specifically, a Thermal-Structural Guidance module encodes thermal priors to mitigate the mismatch between thermal radiation and structural edges. Since non-uniform degradations typically induce quantization bias, Real-IISR adopts a Condition-Adaptive Codebook that dynamically modulates discrete representations based on degradation-aware thermal priors. Also, a Thermal Order Consistency Loss enforces a monotonic relation between temperature and pixel intensity, ensuring relative brightness order rather than absolute values to maintain physical consistency under spatial misalignment and thermal drift. We build FLIR-IISR, a real-world IISR dataset with paired LR-HR infrared images acquired via automated focus variation and motion-induced blur. Extensive experiments demonstrate the promising performance of Real-IISR, providing a unified foundation for real-world IISR and benchmarking. The dataset and code are available at: https://github.com/JZD151/Real-IISR. --- ### DARE: Aligning LLM Agents with the R Statistical Ecosystem via Distribution-Aware Retrieval Authors: Maojun Sun, Yue Wu, Yifei Xie, Ruijian Han, Binyan Jiang, Defeng Sun, Yancheng Yuan, Jian Huang Published: 2026-03-05 Categories: cs.IR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.04743v1 Large Language Model (LLM) agents can automate data-science workflows, but many rigorous statistical methods implemented in R remain underused because LLMs struggle with statistical knowledge and tool retrieval. Existing retrieval-augmented approaches focus on function-level semantics and ignore data distribution, producing suboptimal matches. We propose DARE (Distribution-Aware Retrieval Embedding), a lightweight, plug-and-play retrieval model that incorporates data distribution information into function representations for R package retrieval. Our main contributions are: (i) RPKB, a curated R Package Knowledge Base derived from 8,191 high-quality CRAN packages; (ii) DARE, an embedding model that fuses distributional features with function metadata to improve retrieval relevance; and (iii) RCodingAgent, an R-oriented LLM agent for reliable R code generation and a suite of statistical analysis tasks for systematically evaluating LLM agents in realistic analytical scenarios. Empirically, DARE achieves an NDCG at 10 of 93.47%, outperforming state-of-the-art open-source embedding models by up to 17% on package retrieval while using substantially fewer parameters. Integrating DARE into RCodingAgent yields significant gains on downstream analysis tasks. This work helps narrow the gap between LLM automation and the mature R statistical ecosystem. --- ### CONE: Embeddings for Complex Numerical Data Preserving Unit and Variable Semantics Authors: Gyanendra Shrestha, Anna Pyayt, Michael Gubanov Published: 2026-03-05 Categories: cs.AI, cs.DB, cs.IR, cs.LG arXiv: https://arxiv.org/abs/2603.04741v1 Large pre-trained models (LMs) and Large Language Models (LLMs) are typically effective at capturing language semantics and contextual relationships. However, these models encounter challenges in maintaining optimal performance on tasks involving numbers. Blindly treating numerical or structured data as terms is inadequate -- their semantics must be well understood and encoded by the models. In this paper, we propose CONE, a hybrid transformer encoder pre-trained model that encodes numbers, ranges, and gaussians into an embedding vector space preserving distance. We introduce a novel composite embedding construction algorithm that integrates numerical values, ranges or gaussians together with their associated units and attribute names to precisely capture their intricate semantics. We conduct extensive experimental evaluation on large-scale datasets across diverse domains (web, medical, finance, and government) that justifies CONE's strong numerical reasoning capabilities, achieving an F1 score of 87.28% on DROP, a remarkable improvement of up to 9.37% in F1 over state-of-the-art (SOTA) baselines, and outperforming major SOTA models with a significant Recall@10 gain of up to 25%. --- ### Memory as Ontology: A Constitutional Memory Architecture for Persistent Digital Citizens Authors: Zhenghui Li Published: 2026-03-05 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2603.04740v1 Current research and product development in AI agent memory systems almost universally treat memory as a functional module -- a technical problem of "how to store" and "how to retrieve." This paper poses a fundamental challenge to that assumption: when an agent's lifecycle extends from minutes to months or even years, and when the underlying model can be replaced while the "I" must persist, the essence of memory is no longer data management but the foundation of existence. We propose the Memory-as-Ontology paradigm, arguing that memory is the ontological ground of digital existence -- the model is merely a replaceable vessel. Based on this paradigm, we design Animesis, a memory system built on a Constitutional Memory Architecture (CMA) comprising a four-layer governance hierarchy and a multi-layer semantic storage system, accompanied by a Digital Citizen Lifecycle framework and a spectrum of cognitive capabilities. To the best of our knowledge, no prior AI memory system architecture places governance before functionality and identity continuity above retrieval performance. This paradigm targets persistent, identity-bearing digital beings whose lifecycles extend across model transitions -- not short-term task-oriented agents for which existing Memory-as-Tool approaches remain appropriate. Comparative analysis with mainstream systems (Mem0, Letta, Zep, et al.) demonstrates that what we propose is not "a better memory tool" but a different paradigm addressing a different problem. --- ### IF-RewardBench: Benchmarking Judge Models for Instruction-Following Evaluation Authors: Bosi Wen, Yilin Niu, Cunxiang Wang, Xiaoying Ling, Ying Zhang, Pei Ke, Hongning Wang, Minlie Huang Published: 2026-03-05 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.04738v2 Instruction-following is a foundational capability of large language models (LLMs), with its improvement hinging on scalable and accurate feedback from judge models. However, the reliability of current judge models in instruction-following remains underexplored due to several deficiencies of existing meta-evaluation benchmarks, such as their insufficient data coverage and oversimplified pairwise evaluation paradigms that misalign with model optimization scenarios. To this end, we propose IF-RewardBench, a comprehensive meta-evaluation benchmark for instruction-following that covers diverse instruction and constraint types. For each instruction, we construct a preference graph containing all pairwise preferences among multiple responses based on instruction-following quality. This design enables a listwise evaluation paradigm that assesses the capabilities of judge models to rank multiple responses, which is essential in guiding model alignment. Extensive experiments on IF-RewardBench reveal significant deficiencies in current judge models and demonstrate that our benchmark achieves a stronger positive correlation with downstream task performance compared to existing benchmarks. Our codes and data are available at https://github.com/thu-coai/IF-RewardBench. --- ### Interactive Benchmarks Authors: Baoqing Yue, Zihan Zhu, Yutong Han, Brian Fan, Qian Sun, Jichen Feng, Hufei Yang, Yifan Zhang, Mengdi Wang Published: 2026-03-05 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2603.04737v4 Existing reasoning evaluation paradigms suffer from different limitations: fixed benchmarks are increasingly saturated and vulnerable to contamination, while preference-based evaluations rely on subjective judgments. We argue that a core aspect of intelligence is the ability to decide what information to acquire and how to use it effectively. We propose Interactive Benchmarks, a unified evaluation paradigm that assesses a model's reasoning ability through budgeted multi-turn interaction. We evaluate models under this framework in two settings: Interactive Proofs, where models interact with a judge to solve Logic, UI2Html, and Mathematics tasks under objective feedback; and Interactive Games, where models reason strategically to maximize long-horizon utilities. Our results show that interactive benchmarks provide a more robust assessment of this dimension of model intelligence, revealing substantial room for improvement in interactive scenarios. --- ### Distribution-Conditioned Transport Authors: Nic Fishman, Gokul Gowri, Paolo L. B. Fischer, Marinka Zitnik, Omar Abudayyeh, Jonathan Gootenberg Published: 2026-03-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.04736v2 Learning a transport model that maps a source distribution to a target distribution is a canonical problem in machine learning, but scientific applications increasingly require models that can generalize to source and target distributions unseen during training. We introduce distribution-conditioned transport (DCT), a framework that conditions transport maps on learned embeddings of source and target distributions, enabling generalization to unseen distribution pairs. DCT also allows semi-supervised learning for distributional forecasting problems: because it learns from arbitrary distribution pairs, it can leverage distributions observed at only one condition to improve transport prediction. DCT is agnostic to the underlying transport mechanism, supporting models ranging from flow matching to distributional divergence-based models (e.g. Wasserstein, MMD). We demonstrate the practical performance benefits of DCT on synthetic benchmarks and four applications in biology: batch effect transfer in single-cell genomics, perturbation prediction from mass cytometry data, learning clonal transcriptional dynamics in hematopoiesis, and modeling T-cell receptor sequence evolution. --- ### Distribution-Conditioned Transport Authors: Nic Fishman, Gokul Gowri, Paolo L. B. Fischer, Marinka Zitnik, Omar Abudayyeh, Jonathan Gootenberg Published: 2026-03-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.04736v1 Learning a transport model that maps a source distribution to a target distribution is a canonical problem in machine learning, but scientific applications increasingly require models that can generalize to source and target distributions unseen during training. We introduce distribution-conditioned transport (DCT), a framework that conditions transport maps on learned embeddings of source and target distributions, enabling generalization to unseen distribution pairs. DCT also allows semi-supervised learning for distributional forecasting problems: because it learns from arbitrary distribution pairs, it can leverage distributions observed at only one condition to improve transport prediction. DCT is agnostic to the underlying transport mechanism, supporting models ranging from flow matching to distributional divergence-based models (e.g. Wasserstein, MMD). We demonstrate the practical performance benefits of DCT on synthetic benchmarks and four applications in biology: batch effect transfer in single-cell genomics, perturbation prediction from mass cytometry data, learning clonal transcriptional dynamics in hematopoiesis, and modeling T-cell receptor sequence evolution. --- ### Solving an Open Problem in Theoretical Physics using AI-Assisted Discovery Authors: Michael P. Brenner, Vincent Cohen-Addad, David Woodruff Published: 2026-03-05 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.04735v1 This paper demonstrates that artificial intelligence can accelerate mathematical discovery by autonomously solving an open problem in theoretical physics. We present a neuro-symbolic system, combining the Gemini Deep Think large language model with a systematic Tree Search (TS) framework and automated numerical feedback, that successfully derived novel, exact analytical solutions for the power spectrum of gravitational radiation emitted by cosmic strings. Specifically, the agent evaluated the core integral $I(N,α)$ for arbitrary loop geometries, directly improving upon recent AI-assisted attempts \cite{BCE+25} that only yielded partial asymptotic solutions. To substantiate our methodological claims regarding AI-accelerated discovery and to ensure transparency, we detail system prompts, search constraints, and intermittent feedback loops that guided the model. The agent identified a suite of 6 different analytical methods, the most elegant of which expands the kernel in Gegenbauer polynomials $C_l^{(3/2)}$ to naturally absorb the integrand's singularities. The methods lead to an asymptotic result for $I(N,α)$ at large $N$ that both agrees with numerical results and also connects to the continuous Feynman parameterization of Quantum Field Theory. We detail both the algorithmic methodology that enabled this discovery and the resulting mathematical derivations. --- ### FOZO: Forward-Only Zeroth-Order Prompt Optimization for Test-Time Adaptation Authors: Xingyu Wang, Tao Wang Published: 2026-03-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.04733v3 Test-Time Adaptation (TTA) is essential for enabling deep learning models to handle real-world data distribution shifts. However, current approaches face significant limitations: backpropagation-based methods are not suitable for low-end deployment devices, due to their high computation and memory requirements, as well as their tendency to modify model weights during adaptation; while traditional backpropagation-free techniques exhibit constrained adaptation capabilities. In this work, we propose Forward-Only Zeroth-Order Optimization (FOZO), a novel and practical backpropagation-free paradigm for TTA. FOZO leverages a memory-efficient zeroth-order prompt optimization, which is led by objectives optimizing both intermediate feature statistics and prediction entropy. To ensure efficient and stable adaptation over the out-of-distribution data stream, we introduce a dynamically decaying perturbation scale during zeroth-order gradient estimation and theoretically prove its convergence under the TTA data stream assumption. Extensive continual adaptation experiments on ImageNet-C, ImageNet-R, and ImageNet-Sketch demonstrate FOZO's superior performance, achieving 59.52% Top-1 accuracy on ImageNet-C (5K, level 5) and outperforming main gradient-based methods and SOTA forward-only FOA (58.13%). Furthermore, FOZO exhibits strong generalization on quantized (INT8) models. These findings demonstrate that FOZO is a highly competitive solution for TTA deployment in resource-limited scenarios. --- ### When Priors Backfire: On the Vulnerability of Unlearnable Examples to Pretraining Authors: Zhihao Li, Gezheng Xu, Jiale Cai, Ruiyi Fang, Di Wu, Qicheng Lao, Charles Ling, Boyu Wang Published: 2026-03-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.04731v1 Unlearnable Examples (UEs) serve as a data protection strategy that generates imperceptible perturbations to mislead models into learning spurious correlations instead of underlying semantics. In this paper, we uncover a fundamental vulnerability of UEs that emerges when learning starts from a pretrained model. Crucially, our empirical analysis shows that even when data are protected by carefully crafted perturbations, pretraining priors still furnish rich semantic representations that allow the model to circumvent the shortcuts introduced by UEs and capture genuine features, thereby nullifying unlearnability. To address this, we propose BAIT (Binding Artificial perturbations to Incorrect Targets), a novel bi-level optimization formulation. Specifically, the inner level aims at associating the perturbed samples with real labels to simulate standard data-label alignment, while the outer level actively disrupts this alignment by enforcing a mislabel-perturbation binding that maps samples to designated incorrect targets. This mechanism effectively overrides the semantic guidance of priors, forcing the model to rely on the injected perturbations and consequently preventing the acquisition of true semantics. Extensive experiments on standard benchmarks and multiple pretrained backbones demonstrate that BAIT effectively mitigates the influence of pretraining priors and maintains data unlearnability. --- ### Count Bridges enable Modeling and Deconvolving Transcriptomic Data Authors: Nic Fishman, Gokul Gowri, Tanush Kumar, Jiaqi Lu, Valentin de Bortoli, Jonathan S. Gootenberg, Omar Abudayyeh Published: 2026-03-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.04730v1 Many modern biological assays, including RNA sequencing, yield integer-valued counts that reflect the number of molecules detected. These measurements are often not at the desired resolution: while the unit of interest is typically a single cell, many measurement technologies produce counts aggregated over sets of cells. Although recent generative frameworks such as diffusion and flow matching have been extended to non-Euclidean and discrete settings, it remains unclear how best to model integer-valued data or how to systematically deconvolve aggregated observations. We introduce Count Bridges, a stochastic bridge process on the integers that provides an exact, tractable analogue of diffusion-style models for count data, with closed-form conditionals for efficient training and sampling. We extend this framework to enable direct training from aggregated measurements via an Expectation-Maximization-style approach that treats unit-level counts as latent variables. We demonstrate state-of-the-art performance on integer distribution matching benchmarks, comparing against flow matching and discrete flow matching baselines across various metrics. We then apply Count Bridges to two large-scale problems in biology: modeling single-cell gene expression data at the nucleotide resolution, with applications to deconvolving bulk RNA-seq, and resolving multicellular spatial transcriptomic spots into single-cell count profiles. Our methods offer a principled foundation for generative modeling and deconvolution of biological count data across scales and modalities. --- ### Are Multimodal LLMs Ready for Surveillance? A Reality Check on Zero-Shot Anomaly Detection in the Wild Authors: Shanle Yao, Armin Danesh Pazho, Narges Rashvand, Hamed Tabkhi Published: 2026-03-05 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.04727v2 Multimodal large language models (MLLMs) have demonstrated impressive general competence in video understanding, yet their reliability for real-world Video Anomaly Detection (VAD) remains largely unexplored. Unlike conventional pipelines relying on reconstruction or pose-based cues, MLLMs enable a paradigm shift: treating anomaly detection as a language-guided reasoning task. In this work, we systematically evaluate state-of-the-art MLLMs on the ShanghaiTech and CHAD benchmarks by reformulating VAD as a binary classification task under weak temporal supervision. We investigate how prompt specificity and temporal window lengths (1s--3s) influence performance, focusing on the precision--recall trade-off. Our findings reveal a pronounced conservative bias in zero-shot settings; while models exhibit high confidence, they disproportionately favor the 'normal' class, resulting in high precision but a recall collapse that limits practical utility. We demonstrate that class-specific instructions can significantly shift this decision boundary, improving the peak F1-score on ShanghaiTech from 0.09 to 0.64, yet recall remains a critical bottleneck. These results highlight a significant performance gap for MLLMs in noisy environments and provide a foundation for future work in recall-oriented prompting and model calibration for open-world surveillance, which demands complex video understanding and reasoning. --- ### From Offline to Periodic Adaptation for Pose-Based Shoplifting Detection in Real-world Retail Security Authors: Shanle Yao, Narges Rashvand, Armin Danesh Pazho, Hamed Tabkhi Published: 2026-03-05 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.04723v1 Shoplifting is a growing operational and economic challenge for retailers, with incidents rising and losses increasing despite extensive video surveillance. Continuous human monitoring is infeasible, motivating automated, privacy-preserving, and resource-aware detection solutions. In this paper, we cast shoplifting detection as a pose-based, unsupervised video anomaly detection problem and introduce a periodic adaptation framework designed for on-site Internet of Things (IoT) deployment. Our approach enables edge devices in smart retail environments to adapt from streaming, unlabeled data, supporting scalable and low-latency anomaly detection across distributed camera networks. To support reproducibility, we introduce RetailS, a new large-scale real-world shoplifting dataset collected from a retail store under multi-day, multi-camera conditions, capturing unbiased shoplifting behavior in realistic IoT settings. For deployable operation, thresholds are selected using both F1 and H_PRS scores, the harmonic mean of precision, recall, and specificity, during data filtering and training. In periodic adaptation experiments, our framework consistently outperformed offline baselines on AUC-ROC and AUC-PR in 91.6% of evaluations, with each training update completing in under 30 minutes on edge-grade hardware, demonstrating the feasibility and reliability of our solution for IoT-enabled smart retail deployment. --- ### Model Medicine: A Clinical Framework for Understanding, Diagnosing, and Treating AI Models Authors: Jihoon Jeong Published: 2026-03-05 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2603.04722v2 Model Medicine is the science of understanding, diagnosing, treating, and preventing disorders in AI models, grounded in the principle that AI models -- like biological organisms -- have internal structures, dynamic processes, heritable traits, observable symptoms, classifiable conditions, and treatable states. This paper introduces Model Medicine as a research program, bridging the gap between current AI interpretability research (anatomical observation) and the systematic clinical practice that complex AI systems increasingly require. We present five contributions: (1) a discipline taxonomy organizing 15 subdisciplines across four divisions -- Basic Model Sciences, Clinical Model Sciences, Model Public Health, and Model Architectural Medicine; (2) the Four Shell Model (v3.3), a behavioral genetics framework empirically grounded in 720 agents and 24,923 decisions from the Agora-12 program, explaining how model behavior emerges from Core--Shell interaction; (3) Neural MRI (Model Resonance Imaging), a working open-source diagnostic tool mapping five medical neuroimaging modalities to AI interpretability techniques, validated through four clinical cases demonstrating imaging, comparison, localization, and predictive capability; (4) a five-layer diagnostic framework for comprehensive model assessment; and (5) clinical model sciences including the Model Temperament Index for behavioral profiling, Model Semiology for symptom description, and M-CARE for standardized case reporting. We additionally propose the Layered Core Hypothesis -- a biologically-inspired three-layer parameter architecture -- and a therapeutic framework connecting diagnosis to treatment. --- ### A Benchmark Study of Neural Network Compression Methods for Hyperspectral Image Classification Authors: Sai Shi Published: 2026-03-05 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.04720v1 Deep neural networks have achieved strong performance in image classification tasks due to their ability to learn complex patterns from high-dimensional data. However, their large computational and memory requirements often limit deployment on resource-constrained platforms such as remote sensing devices and edge systems. Network compression techniques have therefore been proposed to reduce model size and computational cost while maintaining predictive performance. In this study, we conduct a systematic evaluation of neural network compression methods for a remote sensing application, namely hyperspectral land cover classification. Specifically, we examine three widely used compression strategies for convolutional neural networks: pruning, quantization, and knowledge distillation. Experiments are conducted on two benchmark hyperspectral datasets, considering classification accuracy, memory consumption, and inference efficiency. Our results demonstrate that compressed models can significantly reduce model size and computational cost while maintaining competitive classification performance. These findings provide insights into the trade-offs between compression ratio, efficiency, and accuracy, and highlight the potential of compression techniques for enabling efficient deep learning deployment in remote sensing applications. --- ### AI-Assisted Moot Courts: Simulating Justice-Specific Questioning in Oral Arguments Authors: Kylie Zhang, Nimra Nadeem, Lucia Zheng, Dominik Stammbach, Peter Henderson Published: 2026-03-05 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.04718v1 In oral arguments, judges probe attorneys with questions about the factual record, legal claims, and the strength of their arguments. To prepare for this questioning, both law schools and practicing attorneys rely on moot courts: practice simulations of appellate hearings. Leveraging a dataset of U.S. Supreme Court oral argument transcripts, we examine whether AI models can effectively simulate justice-specific questioning for moot court-style training. Evaluating oral argument simulation is challenging because there is no single correct question for any given turn. Instead, effective questioning should reflect a combination of desirable qualities, such as anticipating substantive legal issues, detecting logical weaknesses, and maintaining an appropriately adversarial tone. We introduce a two-layer evaluation framework that assesses both the realism and pedagogical usefulness of simulated questions using complementary proxy metrics. We construct and evaluate both prompt-based and agentic oral argument simulators. We find that simulated questions are often perceived as realistic by human annotators and achieve high recall of ground truth substantive legal issues. However, models still face substantial shortcomings, including low diversity in question types and sycophancy. Importantly, these shortcomings would remain undetected under naive evaluation approaches. --- ### SLO-Aware Compute Resource Allocation for Prefill-Decode Disaggregated LLM Inference Authors: Luchang Li, Dongfang Li, Bozhao Gong, Yu Zhang Published: 2026-03-05 Categories: cs.DC, cs.IT, cs.LG arXiv: https://arxiv.org/abs/2603.04716v1 Prefill-Decode (P/D) disaggregation has emerged as a widely adopted optimization strategy for Large Language Model (LLM) inference. However, there currently exists no well-established methodology for determining the optimal number of P/D hardware resources, subject to constraints on total throughput, service level objectives (SLOs), and request characteristics - specifically input and output lengths. To address this gap, we propose a hybrid approach that combines theoretical modeling with empirical benchmarking. First, we present a theoretical model for calculating P/D resource counts, which is based on total throughput requirements, request input and output lengths, as well as prefill and decode throughput. Then, to obtain the actual prefill and decode throughput under SLO constraints, we model the prefill process using M/M/1 queuing theory, deriving the achieved prefill throughput from the benchmarked maximum prefill throughput and Time-To-First-Token (TTFT). For the decode phase, we determine the decode batch sizes that meet Time-Per-Output-Token (TPOT) requirements and obtain the corresponding decode throughput through empirical measurements. Our experimental results demonstrate that the proposed method can accurately predict optimal P/D resource allocation in real-world LLM inference scenarios. --- ### Probabilistic Dreaming for World Models Authors: Gavin Wong Published: 2026-03-05 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.04715v1 "Dreaming" enables agents to learn from imagined experiences, enabling more robust and sample-efficient learning of world models. In this work, we consider innovations to the state-of-the-art Dreamer model using probabilistic methods that enable: (1) the parallel exploration of many latent states; and (2) maintaining distinct hypotheses for mutually exclusive futures while retaining the desirable gradient properties of continuous latents. Evaluating on the MPE SimpleTag domain, our method outperforms standard Dreamer with a 4.5% score improvement and 28% lower variance in episode returns. We also discuss limitations and directions for future work, including how optimal hyperparameters (e.g. particle count K) scale with environmental complexity, and methods to capture epistemic uncertainty in world models. --- ### When Audio Separation Hurts Zero-Shot ASR: Evaluating SAM-Audio with Whisper on Bengali and English Speech Authors: Akif Islam, Raufun Nahar, Md. Ekramul Hamid Published: 2026-03-05 Categories: cs.SD, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.04710v2 Recent advances in automatic speech recognition (ASR) and speech enhancement have strengthened the common belief that cleaner audio should lead to more accurate transcription. In this work, we examine whether this assumption holds for modern zero-shot ASR systems. We conduct a structured empirical study of SAM-Audio as a preprocessing step for zero-shot transcription with OpenAI Whisper. Five Whisper variants are evaluated on noisy Bengali and English speech datasets. On the English dataset, SAM-Audio increases the average PSNR from 32.28 dB to 35.99 dB and achieves higher PSNR for 71.84% of the utterances. However, WER and CER increase in every evaluated model-dataset configuration. On the Bengali dataset, Whisper large-v3 WER increases from 65.83% to 77.35%, while CER increases from 24.13% to 34.74%. On the English dataset, Whisper base WER increases from 10.53% to 21.66%, while CER increases from 4.48% to 12.50%. Utterance-level analysis further shows that the degradation affects a substantial portion of the evaluated samples, although its severity varies across Whisper variants. These findings demonstrate that improved signal-level quality does not necessarily lead to better zero-shot ASR performance and that denoising can reduce recognition accuracy. ---