# Research Papers — 2026-03 · bundle page 86 of 243

> Full-text markdown of papers #4251–4300 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/86
[← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/85.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-03/page/87.md)

### DataProphet: Demystifying Supervision Data Generalization in Multimodal LLMs

Authors: Xuan Qi, Luxi He, Dan Roth, Xingyu Fu
Published: 2026-03-20
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.19688v1

Conventional wisdom for selecting supervision data for multimodal large language models (MLLMs) is to prioritize datasets that appear similar to the target benchmark, such as text-intensive or vision-centric tasks. However, it remains unclear whether such intuitive similarity reliably predicts downstream performance gains. In this work, we take a first step toward answering a practical question: can we estimate the influence of a training dataset on a target benchmark before any training is performed? To investigate this question, we conduct an in-depth analysis of transfer across 14 vision-language datasets spanning 7 diverse tasks. Our results show that intuitive task similarity is an unreliable predictor of transferability, and that generalization depends more on the specific dataset than on its broad task category. Motivated by this finding, we propose DATAPROPHET, a simple and effective training-free metric that combines multimodal perplexity, similarity, and data diversity. Experiments show that DATAPROPHET produces supervision-data rankings that strongly correlate with rankings based on actual post-training performance gains, achieving a Kendall's tau of 86.0%. Moreover, DATAPROPHET enables better supervision-data selection, yielding up to 6.9% improvement over uniform selection, 1.4% over a state-of-the-art training-based baseline, and 0.2% above oracle selection based on experimental performance. Our code and data will be released.

---

### Diminishing Returns in Expanding Generative Models and Godel-Tarski-Lob Limits

Authors: Angshul Majumdar
Published: 2026-03-20
Categories: cs.LO, cs.LG
arXiv: https://arxiv.org/abs/2603.19687v1

Modern generative modelling systems are increasingly improved by expanding model capacity, training data, and computational resources. While empirical studies have documented such scaling behaviour across architectures including generative adversarial networks, variational autoencoders, transformer-based models, and diffusion models, the theoretical limits of capability growth in expanding generative systems remain poorly understood. In this paper we develop a general task-space framework for analysing expanding generative reasoning systems. Each system induces a subset of a global task space representing the tasks it can successfully solve, and system capability is measured by the probability mass of this solved-task set under a fixed task distribution. Within this framework we prove a structural result showing that, under mild assumptions, the marginal improvement in solved tasks must converge to zero as system capacity increases. Thus expanding generative systems may continue to gain capability, but the probability mass of newly solvable tasks necessarily diminishes asymptotically. We further provide a prediction-theoretic refinement based on complexity-weighted hypothesis classes inspired by algorithmic probability, yielding quantitative bounds on marginal improvement in prediction settings. Finally, we examine logical reasoning tasks and show that classical results from mathematical logic -- including Rosser incompleteness, Tarski's undefinability theorem, and Löb's theorem -- imply the persistence of unresolved logical tasks within sufficiently expressive reasoning systems. Together these results provide a mathematical perspective on the asymptotic behaviour of expanding generative systems, showing that long-run capability growth is constrained both by diminishing marginal improvements in task coverage and by fundamental logical limitations on internal reasoning.

---

### A Subgoal-driven Framework for Improving Long-Horizon LLM Agents

Authors: Taiyi Wang, Sian Gooding, Florian Hartmann, Oriana Riva, Edward Grefenstette
Published: 2026-03-20
Categories: cs.AI, cs.LG, cs.MA
arXiv: https://arxiv.org/abs/2603.19685v1

Large language model (LLM)-based agents have emerged as powerful autonomous controllers for digital environments, including mobile interfaces, operating systems, and web browsers. Web navigation, for example, requires handling dynamic content and long sequences of actions, making it particularly challenging. Existing LLM-based agents struggle with long-horizon planning in two main ways. During online execution, they often lose track as new information arrives, lacking a clear and adaptive path toward the final goal. This issue is further exacerbated during reinforcement learning (RL) fine-tuning, where sparse and delayed rewards make it difficult for agents to identify which actions lead to success, preventing them from maintaining coherent reasoning over extended tasks. To address these challenges, we propose two contributions. First, we introduce an agent framework that leverages proprietary models for online planning through subgoal decomposition. Second, we present MiRA (Milestoning your Reinforcement Learning Enhanced Agent), an RL training framework that uses dense, milestone-based reward signals. The real-time planning mechanism improves proprietary models such as Gemini by approximately a 10% absolute increase in success rate (SR) on the WebArena-Lite benchmark. Meanwhile, applying MiRA to the open Gemma3-12B model increases its success rate from 6.4% to 43.0%. This performance surpasses proprietary systems such as GPT-4-Turbo (17.6%) and GPT-4o (13.9%), as well as the previous open-model state of the art, WebRL (38.4%). Overall, our findings demonstrate that combining explicit inference-time planning with milestone-based rewards significantly improves an agent's long-horizon capabilities, paving the way for more robust and general-purpose autonomous systems.

---

### TSegAgent: Zero-Shot Tooth Segmentation via Geometry-Aware Vision-Language Agents

Authors: Shaojie Zhuang, Lu Yin, Guangshun Wei, Yunpeng Li, Xilu Wang, Yuanfeng Zhou
Published: 2026-03-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.19684v3

Automatic tooth segmentation and identification from intra-oral scanned 3D models are fundamental problems in digital dentistry, yet most existing approaches rely on task-specific 3D neural networks trained with densely annotated datasets, resulting in high annotation cost and limited generalization to scans from unseen sources. Thus, we propose TSegAgent, which addresses these challenges by reformulating dental analysis as a zero-shot geometric reasoning problem rather than a purely data-driven recognition task. The key idea is to combine the representational capacity of general-purpose foundation models with explicit geometric inductive biases derived from dental anatomy. Instead of learning dental-specific features, the proposed framework leverages multi-view visual abstraction and geometry-grounded reasoning to infer tooth instances and identities without task-specific training. By explicitly encoding structural constraints such as dental arch organization and volumetric relationships, the method reduces uncertainty in ambiguous cases and mitigates overfitting to particular shape distributions. Experimental results demonstrate that this reasoning-oriented formulation enables accurate and reliable tooth segmentation and identification with low computational and annotation cost, while exhibiting strong generalization across diverse and previously unseen dental scans.

---

### Ontology-Based Knowledge Modeling and Uncertainty-Aware Outdoor Air Quality Assessment Using Weighted Interval Type-2 Fuzzy Logic

Authors: Md Inzmam, Ritesh Chandra, Sadhana Tiwari, Sonali Agarwal, Triloki Pant
Published: 2026-03-20
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.19683v1

Outdoor air pollution is a major concern for the environment and public health, especially in areas where urbanization is taking place rapidly. The Indian Air Quality Index (IND-AQI), developed by the Central Pollution Control Board (CPCB), is a standardized reporting system for air quality based on pollutants such as PM2.5, PM10), nitrogen dioxide (NO2), sulfur dioxide (SO2), ozone (O3), carbon monoxide (CO), and ammonia (NH3). However, the traditional calculation of the AQI uses crisp thresholds and deterministic aggregation rules, which are not suitable for handling uncertainty and transitions between classes. To address these limitations, this study proposes a hybrid ontology-based uncertainty-aware framework integrating Weighted Interval Type-2 Fuzzy Logic with semantic knowledge modeling. Interval Type-2 fuzzy sets are used to model uncertainty near AQI class boundaries, while pollutant importance weights are determined using Interval Type-2 Fuzzy Analytic Hierarchy Process (IT2-FAHP) to reflect their relative health impacts. In addition, an OWL-based air quality ontology extending the Semantic Sensor Network (SSN) ontology is developed to represent pollutants, monitoring stations, AQI categories, regulatory standards, and environmental governance actions. Semantic reasoning is implemented using SWRL rules and validated through SPARQL queries to infer AQI categories, health risks, and recommended mitigation actions. Experimental evaluation using CPCB air quality datasets demonstrates that the proposed framework improves AQI classification reliability and uncertainty handling compared with traditional crisp and Type-1 fuzzy approaches, while enabling explainable semantic reasoning and intelligent decision support for air quality monitoring systems

---

### 3D Gaussian Splatting with Self-Constrained Priors for High Fidelity Surface Reconstruction

Authors: Takeshi Noda, Yu-Shen Liu, Zhizhong Han
Published: 2026-03-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.19682v2

Rendering 3D surfaces has been revolutionized within the modeling of radiance fields through either 3DGS or NeRF. Although 3DGS has shown advantages over NeRF in terms of rendering quality or speed, there is still room for improvement in recovering high fidelity surfaces through 3DGS. To resolve this issue, we propose a self-constrained prior to constrain the learning of 3D Gaussians, aiming for more accurate depth rendering. Our self-constrained prior is derived from a TSDF grid that is obtained by fusing the depth maps rendered with current 3D Gaussians. The prior measures a distance field around the estimated surface, offering a band centered at the surface for imposing more specific constraints on 3D Gaussians, such as removing Gaussians outside the band, moving Gaussians closer to the surface, and encouraging larger or smaller opacity in a geometry-aware manner. More importantly, our prior can be regularly updated by the most recent depth images which are usually more accurate and complete. In addition, the prior can also progressively narrow the band to tighten the imposed constraints. We justify our idea and report our superiority over the state-of-the-art methods in evaluations on widely used benchmarks.

---

### Unbiased Dynamic Multimodal Fusion

Authors: Shicai Wei, Kaijie Zhang, Luyi Chen, Tao He, Guiduo Duan
Published: 2026-03-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.19681v1

Traditional multimodal methods often assume static modality quality, which limits their adaptability in dynamic real-world scenarios. Thus, dynamical multimodal methods are proposed to assess modality quality and adjust their contribution accordingly. However, they typically rely on empirical metrics, failing to measure the modality quality when noise levels are extremely low or high. Moreover, existing methods usually assume that the initial contribution of each modality is the same, neglecting the intrinsic modality dependency bias. As a result, the modality hard to learn would be doubly penalized, and the performance of dynamical fusion could be inferior to that of static fusion. To address these challenges, we propose the Unbiased Dynamic Multimodal Learning (UDML) framework. Specifically, we introduce a noise-aware uncertainty estimator that adds controlled noise to the modality data and predicts its intensity from the modality feature. This forces the model to learn a clear correspondence between feature corruption and noise level, allowing accurate uncertainty measure across both low- and high-noise conditions. Furthermore, we quantify the inherent modality reliance bias within multimodal networks via modality dropout and incorporate it into the weighting mechanism. This eliminates the dual suppression effect on the hard-to-learn modality. Extensive experiments across diverse multimodal benchmark tasks validate the effectiveness, versatility, and generalizability of the proposed UDML. The code is available at https://github.com/shicaiwei123/UDML.

---

### Vision-Language Attribute Disentanglement and Reinforcement for Lifelong Person Re-Identification

Authors: Kunlun Xu, Haotong Cheng, Jiangmeng Li, Xu Zou, Jiahuan Zhou
Published: 2026-03-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.19678v1

Lifelong person re-identification (LReID) aims to learn from varying domains to obtain a unified person retrieval model. Existing LReID approaches typically focus on learning from scratch or a visual classification-pretrained model, while the Vision-Language Model (VLM) has shown generalizable knowledge in a variety of tasks. Although existing methods can be directly adapted to the VLM, since they only consider global-aware learning, the fine-grained attribute knowledge is underleveraged, leading to limited acquisition and anti-forgetting capacity. To address this problem, we introduce a novel VLM-driven LReID approach named Vision-Language Attribute Disentanglement and Reinforcement (VLADR). Our key idea is to explicitly model the universally shared human attributes to improve inter-domain knowledge transfer, thereby effectively utilizing historical knowledge to reinforce new knowledge learning and alleviate forgetting. Specifically, VLADR includes a Multi-grain Text Attribute Disentanglement mechanism that mines the global and diverse local text attributes of an image. Then, an Inter-domain Cross-modal Attribute Reinforcement scheme is developed, which introduces cross-modal attribute alignment to guide visual attribute extraction and adopts inter-domain attribute alignment to achieve fine-grained knowledge transfer. Experimental results demonstrate that our VLADR outperforms the state-of-the-art methods by 1.9\%-2.2\% and 2.1\%-2.5\% on anti-forgetting and generalization capacity. Our source code is available at https://github.com/zhoujiahuan1991/CVPR2026-VLADR

---

### GoAgent: Group-of-Agents Communication Topology Generation for LLM-based Multi-Agent Systems

Authors: Hongjiang Chen, Xin Zheng, Yixin Liu, Pengfei Jiao, Shiyuan Li, Huan Liu, Zhidong Zhao, Ziqi Xu, Ibrahim Khalil, Shirui Pan
Published: 2026-03-20
Categories: cs.LG, cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2603.19677v1

Large language model (LLM)-based multi-agent systems (MAS) have demonstrated exceptional capabilities in solving complex tasks, yet their effectiveness depends heavily on the underlying communication topology that coordinates agent interactions. Within these systems, successful problem-solving often necessitates task-specific group structures to divide and conquer subtasks. However, most existing approaches generate communication topologies in a node-centric manner, leaving group structures to emerge implicitly from local connectivity decisions rather than modeling them explicitly, often leading to suboptimal coordination and unnecessary communication overhead. To address this limitation, we propose GoAgent (Group-of-Agents), a communication topology generation method that explicitly treats collaborative groups as the atomic units of MAS construction. Specifically, GoAgent first enumerates task-relevant candidate groups through an LLM and then autoregressively selects and connects these groups as atomic units to construct the final communication graph, jointly capturing intra-group cohesion and inter-group coordination. To mitigate communication redundancy and noise propagation inherent in expanding topologies, we further introduce a conditional information bottleneck (CIB) objective that compresses inter-group communication, preserving task-relevant signals while filtering out redundant historical noise. Extensive experiments on six benchmarks demonstrate the state-of-the-art performance of GoAgent with 93.84% average accuracy while reducing token consumption by about 17%.

---

### ATHENA: Adaptive Test-Time Steering for Improving Count Fidelity in Diffusion Models

Authors: Mohammad Shahab Sepehri, Asal Mehradfar, Berk Tinaz, Salman Avestimehr, Mahdi Soltanolkotabi
Published: 2026-03-20
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2603.19676v1

Text-to-image diffusion models achieve high visual fidelity but surprisingly exhibit systematic failures in numerical control when prompts specify explicit object counts. To address this limitation, we introduce ATHENA, a model-agnostic, test-time adaptive steering framework that improves object count fidelity without modifying model architectures or requiring retraining. ATHENA leverages intermediate representations during sampling to estimate object counts and applies count-aware noise corrections early in the denoising process, steering the generation trajectory before structural errors become difficult to revise. We present three progressively more advanced variants of ATHENA that trade additional computation for improved numerical accuracy, ranging from static prompt-based steering to dynamically adjusted count-aware control. Experiments on established benchmarks and a new visually and semantically complex dataset show that ATHENA consistently improves count fidelity, particularly at higher target counts, while maintaining favorable accuracy-runtime trade-offs across multiple diffusion backbones.

---

### DynFlowDrive: Flow-Based Dynamic World Modeling for Autonomous Driving

Authors: Xiaolu Liu, Yicong Li, Song Wang, Junbo Chen, Angela Yao, Jianke Zhu
Published: 2026-03-20
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2603.19675v2

Recently, world models have been incorporated into the autonomous driving systems to improve the planning reliability. Existing approaches typically predict future states through appearance generation or deterministic regression, which limits their ability to capture trajectory-conditioned scene evolution and leads to unreliable action planning. To address this, we propose DynFlowDrive, a latent world model that leverages flow-based dynamics to model the transition of world states under different driving actions. By adopting the rectifiedflow formulation, the model learns a velocity field that describes how the scene state changes under different driving actions, enabling progressive prediction of future latent states. Building upon this, we further introduce a stability-aware multi-mode trajectory selection strategy that evaluates candidate trajectories according to the stability of the induced scene transitions. Extensive experiments on the nuScenes and NavSim benchmarks demonstrate consistent improvements across diverse driving frameworks without introducing additional inference overhead. Source code will be abaliable at https://github.com/xiaolul2/DynFlowDrive.

---

### Making Video Models Adhere to User Intent with Minor Adjustments

Authors: Daniel Ajisafe, Eric Hedlin, Helge Rhodin, Kwang Moo Yi
Published: 2026-03-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.19672v1

With the recent drastic advancements in text-to-video diffusion models, controlling their generations has drawn interest. A popular way for control is through bounding boxes or layouts. However, enforcing adherence to these control inputs is still an open problem. In this work, we show that by slightly adjusting user-provided bounding boxes we can improve both the quality of generations and the adherence to the control inputs. This is achieved by simply optimizing the bounding boxes to better align with the internal attention maps of the video diffusion model while carefully balancing the focus on foreground and background. In a sense, we are modifying the bounding boxes to be at places where the model is familiar with. Surprisingly, we find that even with small modifications, the quality of generations can vary significantly. To do so, we propose a smooth mask to make the bounding box position differentiable and an attention-maximization objective that we use to alter the bounding boxes. We conduct thorough experiments, including a user study to validate the effectiveness of our method. Our code is made available on the project webpage to foster future research from the community.

---

### Load--Reserve Wasserstein Propagation for Isotropic Diffusion Samplers

Authors: Zicheng Lyu, Zengfeng Huang
Published: 2026-03-20
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.19670v5

Many Wasserstein analyses of diffusion samplers control reverse-time propagation by global stability summaries of the learned drift. These summaries can hide radial geometry: equal-height expansive regions of different width can yield different propagation costs. We give a profile-adapted propagation interface for scalar-isotropic reverse-SDE windows with certified learned-drift profiles. A certified lower radial profile is compiled into an affine-tail transportation cost: reflection coupling reduces stability to a one-dimensional slope budget, and Hardy capacity quantifies the load paid before a contractive tail reserve. The compiler yields an adapted cost, contraction rate, and retained tail slope. Score-modeling and solver residuals are treated as forcing inputs and propagate additively in the adapted Wasserstein distance. Quadratic Wasserstein error is reported only at terminal time, using the retained tail slope with tail, moment, or support information. Gaussian-smoothed denoising geometry supplies inverse-radius profiles for uniformly dissipative, bounded-amplitude, and common-covariance mixture windows. Fixed-height examples show that adverse height, even with eventual reserve, does not determine the certificate; barrier examples show that the load dependence is structural.

---

### Structured Prompting for Arabic Essay Proficiency: A Trait-Centric Evaluation Approach

Authors: Salim Al Mandhari, Hieu Pham Dinh, Mo El-Haj, Paul Rayson
Published: 2026-03-20
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.19668v1

This paper presents a novel prompt engineering framework for trait specific Automatic Essay Scoring (AES) in Arabic, leveraging large language models (LLMs) under zero-shot and few-shot configurations. Addressing the scarcity of scalable, linguistically informed AES tools for Arabic, we introduce a three-tier prompting strategy (standard, hybrid, and rubric-guided) that guides LLMs in evaluating distinct language proficiency traits such as organization, vocabulary, development, and style. The hybrid approach simulates multi-agent evaluation with trait specialist raters, while the rubric-guided method incorporates scored exemplars to enhance model alignment. In zero and few-shot settings, we evaluate eight LLMs on the QAES dataset, the first publicly available Arabic AES resource with trait level annotations. Experimental results using Quadratic Weighted Kappa (QWK) and Confidence Intervals show that Fanar-1-9B-Instruct achieves the highest trait level agreement in both zero and few-shot prompting (QWK = 0.28 and CI = 0.41), with rubric-guided prompting yielding consistent gains across all traits and models. Discourse-level traits such as Development and Style showed the greatest improvements. These findings confirm that structured prompting, not model scale alone, enables effective AES in Arabic. Our study presents the first comprehensive framework for proficiency oriented Arabic AES and sets the foundation for scalable assessment in low resource educational contexts.

---

### Toward High-Fidelity Visual Reconstruction: From EEG-Based Conditioned Generation to Joint-Modal Guided Rebuilding

Authors: Zhijian Gong, Tianren Yao, Wenjia Dong, Xueyuan Xu
Published: 2026-03-20
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.19667v1

Human visual reconstruction aims to reconstruct fine-grained visual stimuli based on subject-provided descriptions and corresponding neural signals. As a widely adopted modality, Electroencephalography (EEG) captures rich visual cognition information, encompassing complex spatial relationships and chromatic details within scenes. However, current approaches are deeply coupled with an alignment framework that forces EEG features to align with text or image semantic representation. The dependency may condense the rich spatial and chromatic details in EEG that achieved mere conditioned image generation rather than high-fidelity visual reconstruction. To address this limitation, we propose a novel Joint-Modal Visual Reconstruction (JMVR) framework. It treats EEG and text as independent modalities for joint learning to preserve EEG-specific information for reconstruction. It further employs a multi-scale EEG encoding strategy to capture both fine- and coarse-grained features, alongside image augmentation to enhance the recovery of perceptual details. Extensive experiments on the THINGS-EEG dataset demonstrate that JMVR achieves SOTA performance against six baseline methods, specifically exhibiting superior capabilities in modeling spatial structure and chromatic fidelity.

---

### The Residual Stream Is All You Need: On the Redundancy of the KV Cache in Transformer Inference

Authors: Kaleem Ullah Qasim, Jiashu Zhang, Muhammad Kafeel Shaheen, Razan Alharith, Heying Zhang
Published: 2026-03-20
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.19664v1

The key-value (KV) cache is widely treated as essential state in transformer inference, and a large body of work engineers policies to compress, evict, or approximate its entries. We prove that this state is entirely redundant: keys and values at every layer are deterministic projections of the residual stream, and recomputing them from a single residual vector per token incurs exactly zero reconstruction error, not approximately, but bit-identically. We verify this across six models from four architecture families (135M to 4B parameters). Cross-task residual patching at every layer produces D_KL = 0 between patched and original output distributions, confirming that the residual stream satisfies a Markov property and is the sole information-carrying state. Removing the cache entirely and recomputing from scratch yields token-identical output under greedy decoding on all models tested. We build on this result with KV-Direct, a bounded-memory inference scheme that checkpoints residual vectors (5 KB per token on Gemma 3-4B) instead of full KV pairs (136 KB), recomputing keys and values on demand. Over 20 conversation turns, KV-Direct holds peak memory at 42 MB while the standard cache grows past 103 MB. Against five eviction baselines (H2O, StreamingLLM, SnapKV, TOVA, window-only), KV-Direct maintains 100% token match at every cache budget; all baselines degrade to 5-28%. A per-operation latency analysis shows recomputation runs up to 5x faster than reading cached tensors at moderate batch sizes. Code is available at https://github.com/Kaleemullahqasim/KV-Direct.

---

### Semantic Audio-Visual Navigation in Continuous Environments

Authors: Yichen Zeng, Hebaixu Wang, Meng Liu, Yu Zhou, Chen Gao, Kehan Chen, Gongping Huang
Published: 2026-03-20
Categories: cs.CV, cs.SD
arXiv: https://arxiv.org/abs/2603.19660v1

Audio-visual navigation enables embodied agents to navigate toward sound-emitting targets by leveraging both auditory and visual cues. However, most existing approaches rely on precomputed room impulse responses (RIRs) for binaural audio rendering, restricting agents to discrete grid positions and leading to spatially discontinuous observations. To establish a more realistic setting, we introduce Semantic Audio-Visual Navigation in Continuous Environments (SAVN-CE), where agents can move freely in 3D spaces and perceive temporally and spatially coherent audio-visual streams. In this setting, targets may intermittently become silent or stop emitting sound entirely, causing agents to lose goal information. To tackle this challenge, we propose MAGNet, a multimodal transformer-based model that jointly encodes spatial and semantic goal representations and integrates historical context with self-motion cues to enable memory-augmented goal reasoning. Comprehensive experiments demonstrate that MAGNet significantly outperforms state-of-the-art methods, achieving up to a 12.1\% absolute improvement in success rate. These results also highlight its robustness to short-duration sounds and long-distance navigation scenarios. The code is available at https://github.com/yichenzeng24/SAVN-CE.

---

### CS-MUNet: A Channel-Spatial Dual-Stream Mamba Network for Multi-Organ Segmentation

Authors: Yuyang Zheng, Mingda Zhang, Jianglong Qin, Qi Mo, Jingdan Pan, Haozhe Hu, Hongyi Huang
Published: 2026-03-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.19659v1

Recently Mamba-based methods have shown promise in abdominal organ segmentation. However, existing approaches neglect cross-channel anatomical semantic collaboration and lack explicit boundary-aware feature fusion mechanisms. To address these limitations, we propose CS-MUNet with two purpose-built modules. The Boundary-Aware State Mamba module employs a Bayesian-attention framework to generate pixel-level boundary posterior maps, injected directly into Mamba's core scan parameters to embed boundary awareness into the SSM state transition mechanism, while dual-branch weight allocation enables complementary modulation between global and local structural representations. The Channel Mamba State Aggregation module redefines the channel dimension as the SSM sequence dimension to explicitly model cross-channel anatomical semantic collaboration in a data-driven manner. Experiments on two public benchmarks demonstrate that CS-MUNet consistently outperforms state-of-the-art methods across multiple metrics, establishing a new SSM modeling paradigm that jointly addresses channel semantic collaboration and boundary-aware feature fusion for abdominal multi-organ segmentation.

---

### Model Selection and Parameter Estimation for Multidimensional Gaussian Mixture Models with a Common Covariance Matrix

Authors: Xinyu Liu, Hai Zhang
Published: 2026-03-20
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2603.19657v2

We study model-order selection and component-mean estimation for multidimensional Gaussian mixture models with a known common covariance matrix. Using empirical characteristic-function measurements, we construct Fourier covariance matrices whose population counterparts have rank equal to the number of mixture components. We establish a minimax lower bound showing that distinguishing a separated $k$-component mixture from the class of $(k-1)$-component mixtures requires $Ω(Δ^{-(4k-4)})$ samples. We then develop an oracle spectral-thresholding estimator with a sufficient sample size of order $Δ^{-(8k-8)}$ for fixed $k$, together with a practical singular-value-ratio estimator. Given the model order, we estimate the component means by score-initialized gradient descent on a MUSIC-type projection objective. Under an explicit sample-size condition, a qualifying sample initialization lies in a certified attraction region with high probability, after which the iterates converge linearly. For fixed positive component separation, the resulting mean estimates achieve the parametric rate $\mathcal{O}_p(n^{-1/2})$. Numerical experiments demonstrate competitive accuracy and lower computational cost than expectation-maximization across a range of multidimensional settings.

---

### Model Selection and Parameter Estimation of Multi-dimensional Gaussian Mixture Model

Authors: Xinyu Liu, Hai Zhang
Published: 2026-03-20
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2603.19657v1

In this paper, we study the problem of learning multi-dimensional Gaussian Mixture Models (GMMs), with a specific focus on model order selection and efficient mixing distribution estimation. We first establish an information-theoretic lower bound on the critical sample complexity required for reliable model selection. More specifically, we show that distinguishing a $k$-component mixture from a simpler model necessitates a sample size scaling of $Ω(Δ^{-(4k-4)})$. We then propose a thresholding-based estimation algorithm that evaluates the spectral gap of an empirical covariance matrix constructed from random Fourier measurement vectors. This parameter-free estimator operates with an efficient time complexity of $\mathcal{O}(k^2 n)$, scaling linearly with the sample size. We demonstrate that the sample complexity of our method matches the established lower bound, confirming its minimax optimality with respect to the component separation distance $Δ$. Conditioned on the estimated model order, we subsequently introduce a gradient-based minimization method for parameter estimation. To effectively navigate the non-convex objective landscape, we employ a data-driven, score-based initialization strategy that guarantees rapid convergence. We prove that this method achieves the optimal parametric convergence rate of $\mathcal{O}_p(n^{-1/2})$ for estimating the component means. To enhance the algorithm's efficiency in high-dimensional regimes where the ambient dimension exceeds the number of mixture components (i.e., \(d > k\)), we integrate principal component analysis (PCA) for dimension reduction. Numerical experiments demonstrate that our Fourier-based algorithmic framework outperforms conventional Expectation-Maximization (EM) methods in both estimation accuracy and computational time.

---

### GravCal: Single-Image Calibration of IMU Gravity Priors with Per-Sample Confidence

Authors: Haichao Zhu, Qian Zhang
Published: 2026-03-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.19654v1

Gravity estimation is fundamental to visual-inertial perception, augmented reality, and robotics, yet gravity priors from IMUs are often unreliable under linear acceleration, vibration, and transient motion. Existing methods often estimate gravity directly from images or assume reasonably accurate inertial input, leaving the practical problem of correcting a noisy gravity prior from a single image largely unaddressed. We present GravCal, a feedforward model for single-image gravity prior calibration. Given one RGB image and a noisy gravity prior, GravCal predicts a corrected gravity direction and a per-sample confidence score. The model combines two complementary predictions, including a residual correction of the input prior and a prior-independent image estimate, and uses a learned gate to fuse them adaptively. Extensive experiments show strong gains over raw inertial priors: GravCal reduces mean angular error from 22.02° (IMU prior) to 14.24°, with larger improvements when the prior is severely corrupted. We also introduce a novel dataset of over 148K frames with paired VIO-derived ground-truth gravity and Mahony-filter IMU priors across diverse scenes and arbitrary camera orientations. The learned gate also correlates with prior quality, making it a useful confidence signal for downstream systems.

---

### Ensembles-based Feature Guided Analysis

Authors: Federico Formica, Stefano Gregis, Andrea Rota, Aurora Francesca Zanenga, Mark Lawford, Claudio Menghi
Published: 2026-03-20
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.19653v1

Recent Deep Neural Networks (DNN) applications ask for techniques that can explain their behavior. Existing solutions, such as Feature Guided Analysis (FGA), extract rules on their internal behaviors, e.g., by providing explanations related to neurons activation. Results from the literature show that these rules have considerable precision (i.e., they correctly predict certain classes of features), but the recall (i.e., the number of situations these rule apply) is more limited. To mitigate this problem, this paper presents Ensembles-based Feature Guided Analysis (EFGA). EFGA combines rules extracted by FGA into ensembles. Ensembles aggregate different rules to increase their applicability depending on an aggregation criterion, a policy that dictates how to combine rules into ensembles. Although our solution is extensible, and different aggregation criteria can be developed by users, in this work, we considered three different aggregation criteria. We evaluated how the choice of the criterion influences the effectiveness of EFGA on two benchmarks (i.e., the MNIST and LSC datasets), and found that different aggregation criteria offer alternative trade-offs between precision and recall. We then compare EFGA with FGA. For this experiment, we selected an aggregation criterion that provides a reasonable trade-off between precision and recall. Our results show that EFGA has higher train recall (+28.51% on MNIST, +33.15% on LSC), and test recall (+25.76% on MNIST, +30.81% on LSC) than FGA, with a negligible reduction on the test precision (-0.89% on MNIST, -0.69% on LSC).

---

### PolicySim: An LLM-Based Agent Social Simulation Sandbox for Proactive Policy Optimization

Authors: Renhong Huang, Ning Tang, Jiarong Xu, Yuxuan Cao, Qingqian Tu, Sheng Guo, Bo Zheng, Huiyuan Liu, Yang Yang
Published: 2026-03-20
Categories: cs.SI, cs.AI
arXiv: https://arxiv.org/abs/2603.19649v1

Social platforms serve as central hubs for information exchange, where user behaviors and platform interventions jointly shape opinions. However, intervention policies like recommendation and content filtering, can unintentionally amplify echo chambers and polarization, posing significant societal risks. Proactively evaluating the impact of such policies is therefore crucial. Existing approaches primarily rely on reactive online A/B testing, where risks are identified only after deployment, making risk identification delayed and costly. LLM-based social simulations offer a promising pre-deployment alternative, but current methods fall short in realistically modeling platform interventions and incorporating feedback from the platform. Bridging these gaps is essential for building actionable frameworks to assess and optimize platform policies. To this end, we propose PolicySim, an LLM-based social simulation sandbox for the proactive assessment and optimization of intervention policies. PolicySim models the bidirectional dynamics between user behavior and platform interventions through two key components: (1) a user agent module refined via supervised fine-tuning (SFT) and direct preference optimization (DPO) to achieve platform-specific behavioral realism; and (2) an adaptive intervention module that employs a contextual bandit with message passing to capture dynamic network structures. Experiments show that PolicySim can accurately simulate platform ecosystems at both micro and macro levels and support effective intervention policy.

---

### Heavy-Tailed and Long-Range Dependent Noise in Stochastic Approximation: A Finite-Time Analysis

Authors: Siddharth Chandak, Anuj Yadav, Ayfer Ozgur, Nicholas Bambos
Published: 2026-03-20
Categories: cs.LG, eess.SY, math.OC, stat.ML
arXiv: https://arxiv.org/abs/2603.19648v1

Stochastic approximation (SA) is a fundamental iterative framework with broad applications in reinforcement learning and optimization. Classical analyses typically rely on martingale difference or Markov noise with bounded second moments, but many practical settings, including finance and communications, frequently encounter heavy-tailed and long-range dependent (LRD) noise. In this work, we study SA for finding the root of a strongly monotone operator under these non-classical noise models. We establish the first finite-time moment bounds in both settings, providing explicit convergence rates that quantify the impact of heavy tails and temporal dependence. Our analysis employs a noise-averaging argument that regularizes the impact of noise without modifying the iteration. Finally, we apply our general framework to stochastic gradient descent (SGD) and gradient play, and corroborate our finite-time analysis through numerical experiments.

---

### OmniDiT: Extending Diffusion Transformer to Omni-VTON Framework

Authors: Weixuan Zeng, Pengcheng Wei, Huaiqing Wang, Boheng Zhang, Jia Sun, Dewen Fan, Lin HE, Long Chen, Qianqian Gan, Fan Yang, Tingting Gao
Published: 2026-03-20
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.19643v2

Despite the rapid advancement of Virtual Try-On (VTON) and Try-Off (VTOFF) technologies, existing VTON methods face challenges with fine-grained detail preservation, generalization to complex scenes, complicated pipeline, and efficient inference. To tackle these problems, we propose OmniDiT, an omni Virtual Try-On framework based on the Diffusion Transformer, which combines try-on and try-off tasks into one unified model. Specifically, we first establish a self-evolving data curation pipeline to continuously produce data, and construct a large VTON dataset Omni-TryOn, which contains over 380k diverse and high-quality garment-model-tryon image pairs and detailed text prompts. Then, we employ the token concatenation and design an adaptive position encoding to effectively incorporate multiple reference conditions. To relieve the bottleneck of long sequence computation, we are the first to introduce Shifted Window Attention into the diffusion model, thus achieving a linear complexity. To remedy the performance degradation caused by local window attention, we utilize multiple timestep prediction and an alignment loss to improve generation fidelity. Experiments reveal that, under various complex scenes, our method achieves the best performance in both the model-free VTON and VTOFF tasks and a performance comparable to current SOTA methods in the model-based VTON task.

---

### HyEvo: Self-Evolving Hybrid Agentic Workflows for Efficient Reasoning

Authors: Beibei Xu, Yutong Ye, Chuyun Shen, Yingbo Zhou, Cheng Chen, Mingsong Chen
Published: 2026-03-20
Categories: cs.AI
arXiv: https://arxiv.org/abs/2603.19639v1

Although agentic workflows have demonstrated strong potential for solving complex tasks, existing automated generation methods remain inefficient and underperform, as they rely on predefined operator libraries and homogeneous LLM-only workflows in which all task-level computation is performed through probabilistic inference. To address these limitations, we propose HyEvo, an automated workflow-generation framework that leverages heterogeneous atomic synthesis. HyEvo integrates probabilistic LLM nodes for semantic reasoning with deterministic code nodes for rule-based execution, offloading predictable operations from LLM inference and reducing inference cost and execution latency. To efficiently navigate the hybrid search space, HyEvo employs an LLM-driven multi-island evolutionary strategy with a reflect-then-generate mechanism, iteratively refining both workflow topology and node logic via execution feedback. Comprehensive experiments show that HyEvo consistently outperforms existing methods across diverse reasoning and coding benchmarks, while reducing inference cost and execution latency by up to 19$\times$ and 16$\times$, respectively, compared to the state-of-the-art open-source baseline.

---

### UniBioTransfer: A Unified Framework for Multiple Biometrics Transfer

Authors: Caiyi Sun, Yujing Sun, Xiangyu Li, Yuhang Zheng, Yiming Ren, Jiamin Wang, Yuexin Ma, Siu-Ming Yiu
Published: 2026-03-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.19637v1

Deepface generation has traditionally followed a task-driven paradigm, where distinct tasks (e.g., face transfer and hair transfer) are addressed by task-specific models. Nevertheless, this single-task setting severely limits model generalization and scalability. A unified model capable of solving multiple deepface generation tasks in a single pass represents a promising and practical direction, yet remains challenging due to data scarcity and cross-task conflicts arising from heterogeneous attribute transformations. To this end, we propose UniBioTransfer, the first unified framework capable of handling both conventional deepface tasks (e.g., face transfer and face reenactment) and shape-varying transformations (e.g., hair transfer and head transfer). Besides, UniBioTransfer naturally generalizes to unseen tasks, like lip, eye, and glasses transfer, with minimal fine-tuning. Generally, UniBioTransfer addresses data insufficiency in multi-task generation through a unified data construction strategy, including a swapping-based corruption mechanism designed for spatially dynamic attributes like hair. It further mitigates cross-task interference via an innovative BioMoE, a mixture-of-experts based model coupled with a novel two-stage training strategy that effectively disentangles task-specific knowledge. Extensive experiments demonstrate the effectiveness, generalization, and scalability of UniBioTransfer, outperforming both existing unified models and task-specific methods across a wide range of deepface generation tasks. Project page is at https://scy639.github.io/UniBioTransfer.github.io/

---

### RiboSphere: Learning Unified and Efficient Representations of RNA Structures

Authors: Zhou Zhang, Hanqun Cao, Cheng Tan, Fang Wu, Pheng Ann Heng, Tianfan Fu
Published: 2026-03-20
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.19636v2

Accurate RNA structure modeling remains difficult because RNA backbones are highly flexible, non-canonical interactions are prevalent, and experimentally determined 3D structures are comparatively scarce. We introduce RiboSphere, a framework that learns discrete geometric representations of RNA by combining vector quantization with flow matching. Our design is motivated by the modular organization of RNA architecture: complex folds are composed from recurring structural motifs. RiboSphere uses a geometric transformer encoder trained using mean-centered coordinates and random rotation augmentation to produce geometry-aware features, which are discretized with finite scalar quantization (FSQ) into a finite vocabulary of latent codes. Conditioned on these discrete codes, a flow-matching decoder reconstructs atomic coordinates, enabling high-fidelity structure generation. We find that the learned code indices are enriched for specific RNA motifs, suggesting that the model captures motif-level compositional structure rather than acting as a purely compressive bottleneck. Across benchmarks, RiboSphere achieves strong performance in structure reconstruction (RMSD 1.25,Å, TM-score 0.84), and its pretrained discrete representations transfer effectively to inverse folding and RNA--ligand binding prediction, with robust generalization in data-scarce regimes. Code is available at https://github.com/Zhangz312/RiboSphere.

---

### BEAVER: A Training-Free Hierarchical Prompt Compression Method via Structure-Aware Page Selection

Authors: Zhengpei Hu, Kai Li, Dapeng Fu, Chang Zeng, Yue Li, Yuanhao Tang, Jianqiang Huang
Published: 2026-03-20
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.19635v1

The exponential expansion of context windows in LLMs has unlocked capabilities for long-document understanding but introduced severe bottlenecks in inference latency and information utilization. Existing compression methods often suffer from high training costs or semantic fragmentation due to aggressive token pruning. In this paper, we propose BEAVER, a novel training-free framework that shifts compression from linear token removal to structure-aware hierarchical selection. BEAVER maximizes hardware parallelism by mapping variable-length contexts into dense page-level tensors via dual-path pooling, and preserves discourse integrity through a hybrid planner combining semantic and lexical dual-branch selection with sentence smoothing. Extensive evaluations on four long-context benchmarks demonstrate that BEAVER achieves comparable performance to state-of-the-art (SOTA) methods like LongLLMLingua. Notably, on the RULER benchmark, BEAVER maintains high fidelity in multi-needle retrieval where baselines deteriorate. Regarding efficiency, BEAVER reduces latency by 26.4x on 128k contexts, offering a scalable solution for high-throughput applications. Our code is available at https://cslikai.cn/BEAVER/.

---

### MetaCues: Enabling Critical Engagement with Generative AI for Information Seeking and Sensemaking

Authors: Anjali Singh, Karan Taneja, Zhitong Guan, Soo Young Rieh
Published: 2026-03-20
Categories: cs.HC, cs.AI, cs.CY, cs.IR
arXiv: https://arxiv.org/abs/2603.19634v1

Generative AI (GenAI) search tools are increasingly used for information seeking, yet their design tends to encourage cognitive offloading, which may lead to passive engagement, selective attention, and informational homogenization. Effective use requires metacognitive engagement to craft good prompts, verify AI outputs, and critically engage with information. We developed MetaCues, a novel GenAI-based interactive tool for information seeking that delivers metacognitive cues alongside AI responses and a note-taking interface to guide users' search and associated learning. Through an online study (N = 146), we compared MetaCues to a baseline tool without cues, across two broad search topics that required participants to explore diverse perspectives in order to make informed judgments. Preliminary findings regarding participants' search behavior show that MetaCues leads to increased confidence in attitudinal judgments about the search topic as well as broader inquiry, with the latter effect emerging primarily for the topic that was less controversial and with which participants had relatively less familiarity. Accordingly, we outline directions for future qualitative exploration of search interactions and inquiry patterns.

---

### Alternating Diffusion for Proximal Sampling with Zeroth Order Queries

Authors: Hirohane Takagi, Atsushi Nitanda
Published: 2026-03-20
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2603.19633v1

This work introduces a new approximate proximal sampler that operates solely with zeroth-order information of the potential function. Prior theoretical analyses have revealed that proximal sampling corresponds to alternating forward and backward iterations of the heat flow. The backward step was originally implemented by rejection sampling, whereas we directly simulate the dynamics. Unlike diffusion-based sampling methods that estimate scores via learned models or by invoking auxiliary samplers, our method treats the intermediate particle distribution as a Gaussian mixture, thereby yielding a Monte Carlo score estimator from directly samplable distributions. Theoretically, when the score estimation error is sufficiently controlled, our method inherits the exponential convergence of proximal sampling under isoperimetric conditions on the target distribution. In practice, the algorithm avoids rejection sampling, permits flexible step sizes, and runs with a deterministic runtime budget. Numerical experiments demonstrate that our approach converges rapidly to the target distribution, driven by interactions among multiple particles and by exploiting parallel computation.

---

### On the role of memorization in learned priors for geophysical inverse problems

Authors: Ali Siahkoohi, Davide Sabeddu
Published: 2026-03-20
Categories: stat.ML, cs.LG, physics.geo-ph
arXiv: https://arxiv.org/abs/2603.19629v1

Learned priors based on deep generative models offer data-driven regularization for seismic inversion, but training them requires a dataset of representative subsurface models -- a resource that is inherently scarce in geoscience applications. Since the training objective of most generative models can be cast as maximum likelihood on a finite dataset, any such model risks converging to the empirical distribution -- effectively memorizing the training examples rather than learning the underlying geological distribution. We show that the posterior under such a memorized prior reduces to a reweighted empirical distribution -- i.e., a likelihood-weighted lookup among the stored training examples. For diffusion models specifically, memorization yields a Gaussian mixture prior in closed form, and linearizing the forward operator around each training example gives a Gaussian mixture posterior whose components have widths and shifts governed by the local Jacobian. We validate these predictions on a stylized inverse problem and demonstrate the consequences of memorization through diffusion posterior sampling for full waveform inversion.

---

### Dual Prompt-Driven Feature Encoding for Nighttime UAV Tracking

Authors: Yiheng Wang, Changhong Fu, Liangliang Yao, Haobo Zuo, Zijie Zhang
Published: 2026-03-20
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.19628v1

Robust feature encoding constitutes the foundation of UAV tracking by enabling the nuanced perception of target appearance and motion, thereby playing a pivotal role in ensuring reliable tracking. However, existing feature encoding methods often overlook critical illumination and viewpoint cues, which are essential for robust perception under challenging nighttime conditions, leading to degraded tracking performance. To overcome the above limitation, this work proposes a dual prompt-driven feature encoding method that integrates prompt-conditioned feature adaptation and context-aware prompt evolution to promote domain-invariant feature encoding. Specifically, the pyramid illumination prompter is proposed to extract multi-scale frequency-aware illumination prompts. %The dynamic viewpoint prompter adapts the sampling to different viewpoints, enabling the tracker to learn view-invariant features. The dynamic viewpoint prompter modulates deformable convolution offsets to accommodate viewpoint variations, enabling the tracker to learn view-invariant features. Extensive experiments validate the effectiveness of the proposed dual prompt-driven tracker (DPTracker) in tackling nighttime UAV tracking. Ablation studies highlight the contribution of each component in DPTracker. Real-world tests under diverse nighttime UAV tracking scenarios further demonstrate the robustness and practical utility. The code and demo videos are available at https://github.com/yiheng-wang-duke/DPTracker.

---

### IUP-Pose: Decoupled Iterative Uncertainty Propagation for Real-time Relative Pose Regression via Implicit Dense Alignment v1

Authors: Jun Wang, Xiaoyan Huang
Published: 2026-03-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.19625v1

Relative pose estimation is fundamental for SLAM, visual localization, and 3D reconstruction. Existing Relative Pose Regression (RPR) methods face a key trade-off: feature-matching pipelines achieve high accuracy but block gradient flow via non-differentiable RANSAC, while ViT-based regressors are end-to-end trainable but prohibitively expensive for real-time deployment. We identify the core bottlenecks as the coupling between rotation and translation estimation and insufficient cross-view feature alignment. We propose IUP-Pose, a geometry-driven decoupled iterative framework with implicit dense alignment. A lightweight Multi-Head Bi-Cross Attention (MHBC) module aligns cross-view features without explicit matching supervision. The aligned features are processed by a decoupled rotation-translation pipeline: two shared-parameter rotation stages iteratively refine rotation with uncertainty, and feature maps are realigned via rotational homography H_inf before translation prediction. IUP-Pose achieves 73.3% AUC@20deg on MegaDepth1500 with full end-to-end differentiability, 70 FPS throughput, and only 37M parameters, demonstrating a favorable accuracy-efficiency trade-off for real-time edge deployment.

---

### Continual Learning for Food Category Classification Dataset: Enhancing Model Adaptability and Performance

Authors: Piyush Kaushik Bhattacharyya, Devansh Tomar, Shubham Mishra, Divyanshu Rai, Yug Pratap Singh, Harsh Yadav, Krutika Verma, Vishal Meena, N Sangita Achary
Published: 2026-03-20
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.19624v1

Conventional machine learning pipelines often struggle to recognize categories absent from the original trainingset. This gap typically reduces accuracy, as fixed datasets rarely capture the full diversity of a domain. To address this, we propose a continual learning framework for text-guided food classification. Unlike approaches that require retraining from scratch, our method enables incremental updates, allowing new categories to be integrated without degrading prior knowledge. For example, a model trained on Western cuisines could later learn to classify dishes such as dosa or kimchi. Although further refinements are needed, this design shows promise for adaptive food recognition, with applications in dietary monitoring and personalized nutrition planning.

---

### Disentangle-then-Align: Non-Iterative Hybrid Multimodal Image Registration via Cross-Scale Feature Disentanglement

Authors: Chunlei Zhang, Jiahao Xia, Yun Xiao, Bo Jiang, Jian Zhang
Published: 2026-03-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.19623v1

Multimodal image registration is a fundamental task and a prerequisite for downstream cross-modal analysis. Despite recent progress in shared feature extraction and multi-scale architectures, two key limitations remain. First, some methods use disentanglement to learn shared features but mainly regularize the shared part, allowing modality-private cues to leak into the shared space. Second, most multi-scale frameworks support only a single transformation type, limiting their applicability when global misalignment and local deformation coexist. To address these issues, we formulate hybrid multimodal registration as jointly learning a stable shared feature space and a unified hybrid transformation. Based on this view, we propose HRNet, a Hybrid Registration Network that couples representation disentanglement with hybrid parameter prediction. A shared backbone with Modality-Specific Batch Normalization (MSBN) extracts multi-scale features, while a Cross-scale Disentanglement and Adaptive Projection (CDAP) module suppresses modality-private cues and projects shared features into a stable subspace for matching. Built on this shared space, a Hybrid Parameter Prediction Module (HPPM) performs non-iterative coarse-to-fine estimation of global rigid parameters and deformation fields, which are fused into a coherent deformation field. Extensive experiments on four multimodal datasets demonstrate state-of-the-art performance on rigid and non-rigid registration tasks. The code is available at the project website.

---

### DeepStock: Reinforcement Learning with Policy Regularizations for Inventory Management

Authors: Yaqi Xie, Xinru Hao, Jiaxi Liu, Will Ma, Linwei Xin, Lei Cao, Yidong Zhang
Published: 2026-03-20
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.19621v1

Deep Reinforcement Learning (DRL) provides a general-purpose methodology for training inventory policies that can leverage big data and compute. However, off-the-shelf implementations of DRL have seen mixed success, often plagued by high sensitivity to the hyperparameters used during training. In this paper, we show that by imposing policy regularizations, grounded in classical inventory concepts such as "Base Stock", we can significantly accelerate hyperparameter tuning and improve the final performance of several DRL methods. We report details from a 100% deployment of DRL with policy regularizations on Alibaba's e-commerce platform, Tmall. We also include extensive synthetic experiments, which show that policy regularizations reshape the narrative on what is the best DRL method for inventory management.

---

### On Performance Guarantees for Federated Learning with Personalized Constraints

Authors: Mohammadjavad Ebrahimi, Daniel Burbano, Farzad Yousefian
Published: 2026-03-20
Categories: cs.LG, math.OC
arXiv: https://arxiv.org/abs/2603.19617v1

Federated learning (FL) has emerged as a communication-efficient algorithmic framework for distributed learning across multiple agents. While standard FL formulations capture unconstrained or globally constrained problems, many practical settings involve heterogeneous resource or model constraints, leading to optimization problems with agent-specific feasible sets. Here, we study a personalized constrained federated optimization problem in which each agent is associated with a convex local objective and a private constraint set. We propose PC-FedAvg, a method in which each agent maintains cross-estimates of the other agents' variables through a multi-block local decision vector. Each agent updates all blocks locally, penalizing infeasibility only in its own block. Moreover, the cross-estimate mechanism enables personalization without requiring consensus or sharing constraint information among agents. We establish communication-complexity rates of $\mathcal{O}(ε^{-2})$ for suboptimality and $\mathcal{O}(ε^{-1})$ for agent-wise infeasibility. Preliminary experiments on the MNIST and CIFAR-10 datasets validate our theoretical findings.

---

### UniPR: Unified Object-level Real-to-Sim Perception and Reconstruction from a Single Stereo Pair

Authors: Chuanrui Zhang, Yingshuang Zou, ZhengXian Wu, Yonggen Ling, Yuxiao Yang, Ziwei Wang
Published: 2026-03-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.19616v1

Perceiving and reconstructing objects from images are critical for real-to-sim transfer tasks, which are widely used in the robotics community. Existing methods rely on multiple submodules such as detection, segmentation, shape reconstruction, and pose estimation to complete the pipeline. However, such modular pipelines suffer from inefficiency and cumulative error, as each stage operates on only partial or locally refined information while discarding global context. To address these limitations, we propose UniPR, the first end-to-end object-level real-to-sim perception and reconstruction framework. Operating directly on a single stereo image pair, UniPR leverages geometric constraints to resolve the scale ambiguity. We introduce Pose-Aware Shape Representation to eliminate the need for per-category canonical definitions and to bridge the gap between reconstruction and pose estimation tasks. Furthermore, we construct a large-vocabulary stereo dataset, LVS6D, comprising over 6,300 objects, to facilitate large-scale research in this area. Extensive experiments demonstrate that UniPR reconstructs all objects in a scene in parallel within a single forward pass, achieving significant efficiency gains and preserves true physical proportions across diverse object types, highlighting its potential for practical robotic applications.

---

### CAF-Score: Calibrating CLAP with LALMs for Reference-free Audio Captioning Evaluation

Authors: Insung Lee, Taeyoung Jeong, Haejun Yoo, Du-Seong Chang, Myoung-Wan Koo
Published: 2026-03-20
Categories: cs.SD, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2603.19615v1

While Large Audio-Language Models (LALMs) have advanced audio captioning, robust evaluation remains difficult. Reference-based metrics are expensive and often fail to assess acoustic fidelity, while Contrastive Language-Audio Pretraining (CLAP)-based approaches frequently overlook syntactic errors and fine-grained details. We propose CAF-Score, a reference-free metric that calibrates CLAP's coarse-grained semantic alignment with the fine-grained comprehension and syntactic awareness of LALMs. By combining contrastive audio-text embeddings with LALM reasoning, CAF-Score effectively detects syntactic inconsistencies and subtle hallucinations. Experiments on the BRACE benchmark demonstrate that our approach achieves the highest correlation with human judgments, even outperforming reference-based baselines in challenging scenarios. These results highlight the efficacy of CAF-Score for reference-free audio captioning evaluation. Code and results are available at https://github.com/inseong00/CAF-Score.

---

### OrbitNVS: Harnessing Video Diffusion Priors for Novel View Synthesis

Authors: Jinglin Liang, Zijian Zhou, Rui Huang, Shuangping Huang, Yichen Gong
Published: 2026-03-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.19613v1

Novel View Synthesis (NVS) aims to generate unseen views of a 3D object given a limited number of known views. Existing methods often struggle to synthesize plausible views for unobserved regions, particularly under single-view input, and still face challenges in maintaining geometry- and appearance-consistency. To address these issues, we propose OrbitNVS, which reformulates NVS as an orbit video generation task. Through tailored model design and training strategies, we adapt a pre-trained video generation model to the NVS task, leveraging its rich visual priors to achieve high-quality view synthesis. Specifically, we incorporate camera adapters into the video model to enable accurate camera control. To enhance two key properties of 3D objects, geometry and appearance, we design a normal map generation branch and use normal map features to guide the synthesis of the target views via attention mechanism, thereby improving geometric consistency. Moreover, we apply a pixel-space supervision to alleviate blurry appearance caused by spatial compression in the latent space. Extensive experiments show that OrbitNVS significantly outperforms previous methods on the GSO and OmniObject3D benchmarks, especially in the challenging single-view setting (\eg, +2.9 dB and +2.4 dB PSNR).

---

### Demonstrations, CoT, and Prompting: A Theoretical Analysis of ICL

Authors: Xuhan Tong, Yuchen Zeng, Jiawei Zhang
Published: 2026-03-20
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.19611v1

In-Context Learning (ICL) enables pretrained LLMs to adapt to downstream tasks by conditioning on a small set of input-output demonstrations, without any parameter updates. Although there have been many theoretical efforts to explain how ICL works, most either rely on strong architectural or data assumptions, or fail to capture the impact of key practical factors such as demonstration selection, Chain-of-Thought (CoT) prompting, the number of demonstrations, and prompt templates. We address this gap by establishing a theoretical analysis of ICL under mild assumptions that links these design choices to generalization behavior. We derive an upper bound on the ICL test loss, showing that performance is governed by (i) the quality of selected demonstrations, quantified by Lipschitz constants of the ICL loss along paths connecting test prompts to pretraining samples, (ii) an intrinsic ICL capability of the pretrained model, and (iii) the degree of distribution shift. Within the same framework, we analyze CoT prompting as inducing a task decomposition and show that it is beneficial when demonstrations are well chosen at each substep and the resulting subtasks are easier to learn. Finally, we characterize how ICL performance sensitivity to prompt templates varies with the number of demonstrations. Together, our study shows that pretraining equips the model with the ability to generalize beyond observed tasks, while CoT enables the model to compose simpler subtasks into more complex ones, and demonstrations and instructions enable it to retrieve similar or complex tasks, including those that can be composed into more complex ones, jointly supporting generalization to unseen tasks. All theoretical insights are corroborated by experiments.

---

### ParallelVLM: Lossless Video-LLM Acceleration with Visual Alignment Aware Parallel Speculative Decoding

Authors: Quan Kong, Yuhao Shen, Yicheng Ji, Huan Li, Cong Wang
Published: 2026-03-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.19610v2

Although current Video-LLMs achieve impressive performance in video understanding tasks, their autoregressive decoding efficiency remains constrained by the massive number of video tokens. Visual token pruning can partially ease this bottleneck, yet existing approaches still suffer from information loss and yield only modest acceleration in decoding. In this paper, we propose ParallelVLM, a training-free draft-then-verify speculative decoding framework that overcomes both mutual waiting and limited speedup-ratio problems between draft and target models in long-video settings. ParallelVLM features two parallelized stages that maximize hardware utilization and incorporate an Unbiased Verifier-Guided Pruning strategy to better align the draft and target models by eliminating the positional bias in attention-guided pruning. Extensive experiments demonstrate that ParallelVLM effectively expands the draft window by $1.6\sim1.8\times$ with high accepted lengths, and accelerates various video understanding benchmarks by 3.36$\times$ on LLaVA-Onevision-72B and 2.42$\times$ on Qwen2.5-VL-32B compared with vanilla autoregressive decoding.

---

### LoD-Loc v3: Generalized Aerial Localization in Dense Cities using Instance Silhouette Alignment

Authors: Shuaibang Peng, Juelin Zhu, Xia Li, Kun Yang, Maojun Zhang, Yu Liu, Shen Yan
Published: 2026-03-20
Categories: cs.CV, cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2603.19609v2

We present LoD-Loc v3, a novel method for generalized aerial visual localization in dense urban environments. While prior work LoD-Loc v2 achieves localization through semantic building silhouette alignment with low-detail city models, it suffers from two key limitations: poor cross-scene generalization and frequent failure in dense building scenes. Our method addresses these challenges through two key innovations. First, we develop a new synthetic data generation pipeline that produces InsLoD-Loc - the largest instance segmentation dataset for aerial imagery to date, comprising 100k images with precise instance building annotations. This enables trained models to exhibit remarkable zero-shot generalization capability. Second, we reformulate the localization paradigm by shifting from semantic to instance silhouette alignment, which significantly reduces pose estimation ambiguity in dense scenes. Extensive experiments demonstrate that LoD-Loc v3 outperforms existing state-of-the-art (SOTA) baselines, achieving superior performance in both cross-scene and dense urban scenarios with a large margin. The project is available at https://nudt-sawlab.github.io/LoD-Locv3/.

---

### FB-CLIP: Fine-Grained Zero-Shot Anomaly Detection with Foreground-Background Disentanglement

Authors: Ming Hu, Yongsheng Huo, Mingyu Dou, Jianfu Yin, Peng Zhao, Yao Wang, Cong Hu, Bingliang Hu, Quan Wang
Published: 2026-03-20
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.19608v1

Fine-grained anomaly detection is crucial in industrial and medical applications, but labeled anomalies are often scarce, making zero-shot detection challenging. While vision-language models like CLIP offer promising solutions, they struggle with foreground-background feature entanglement and coarse textual semantics. We propose FB-CLIP, a framework that enhances anomaly localization via multi-strategy textual representations and foreground-background separation. In the textual modality, it combines End-of-Text features, global-pooled representations, and attention-weighted token features for richer semantic cues. In the visual modality, multi-view soft separation along identity, semantic, and spatial dimensions, together with background suppression, reduces interference and improves discriminability. Semantic Consistency Regularization (SCR) aligns image features with normal and abnormal textual prototypes, suppressing uncertain matches and enlarging semantic gaps. Experiments show that FB-CLIP effectively distinguishes anomalies from complex backgrounds, achieving accurate fine-grained anomaly detection and localization under zero-shot settings.

---

### Physion-Eval: Evaluating Physical Realism in Generated Video via Human Reasoning

Authors: Qin Zhang, Peiyu Jing, Hong-Xing Yu, Fangqiang Ding, Fan Nie, Weimin Wang, Yilun Du, James Zou, Jiajun Wu, Bing Shuai
Published: 2026-03-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.19607v1

Video generation models are increasingly used as world simulators for storytelling, simulation, and embodied AI. As these models advance, a key question arises: do generated videos obey the physical laws of the real world? Existing evaluations largely rely on automated metrics or coarse human judgments such as preferences or rubric-based checks. While useful for assessing perceptual quality, these methods provide limited insight into when and why generated dynamics violate real-world physical constraints. We introduce Physion-Eval, a large-scale benchmark of expert human reasoning for diagnosing physical realism failures in videos generated by five state-of-the-art models across egocentric and exocentric views, containing 10,990 expert reasoning traces spanning 22 fine-grained physical categories. Each generated video is derived from a corresponding real-world reference video depicting a clear physical process, and annotated with temporally localized glitches, structured failure categories, and natural-language explanations of the violated physical behavior. Using this dataset, we reveal a striking limitation of current video generation models: in physics-critical scenarios, 83.3% of exocentric and 93.5% of egocentric generated videos exhibit at least one human-identifiable physical glitch. We hope Physion-Eval will set a new standard for physical realism evaluation and guide the development of physics-grounded video generation. The benchmark is publicly available at https://huggingface.co/datasets/PhysionLabs/Physion-Eval.

---

### Beyond Quadratic: Linear-Time Change Detection with RWKV

Authors: Zhenyu Yang, Gensheng Pei, Tao Chen, Xia Yuan, Haofeng Zhang, Xiangbo Shu, Yazhou Yao
Published: 2026-03-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.19606v1

Existing paradigms for remote sensing change detection are caught in a trade-off: CNNs excel at efficiency but lack global context, while Transformers capture long-range dependencies at a prohibitive computational cost. This paper introduces ChangeRWKV, a new architecture that reconciles this conflict. By building upon the Receptance Weighted Key Value (RWKV) framework, our ChangeRWKV uniquely combines the parallelizable training of Transformers with the linear-time inference of RNNs. Our approach core features two key innovations: a hierarchical RWKV encoder that builds multi-resolution feature representation, and a novel Spatial-Temporal Fusion Module (STFM) engineered to resolve spatial misalignments across scales while distilling fine-grained temporal discrepancies. ChangeRWKV not only achieves state-of-the-art performance on the LEVIR-CD benchmark, with an 85.46% IoU and 92.16% F1 score, but does so while drastically reducing parameters and FLOPs compared to previous leading methods. This work demonstrates a new, efficient, and powerful paradigm for operational-scale change detection. Our code and model are publicly available.

---

### K-GMRF: Kinetic Gauss-Markov Random Field for First-Principles Covariance Tracking on Lie Groups

Authors: ZhiMing Li
Published: 2026-03-20
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2603.19601v1

Tracking non-stationary covariance matrices is fundamental to vision yet hindered by existing estimators that either neglect manifold constraints or rely on first-order updates, incurring inevitable phase lag during rapid evolution. We propose K-GMRF, an online, training-free framework for covariance tracking that reformulates the problem as forced rigid-body motion on Lie groups. Derived from the Euler-Poincaré equations, our method interprets observations as torques driving a latent angular velocity, propagated via a structure-preserving symplectic integrator. We theoretically prove that this second-order dynamics achieves zero steady-state error under constant rotation, strictly superior to the proportional lag of first-order baselines. Validation across three domains demonstrates robust tracking fidelity: (i) on synthetic ellipses, K-GMRF reduces angular error by 30x compared to Riemannian EMA while maintaining stability at high speeds; (ii) on SO(3) stabilization with 20% dropout, it decreases geodesic error from 29.4° to 9.9°; and (iii) on OTB motion-blur sequences, it improves loU from 0.55 to 0.74 on BlurCar2 with a 96% success rate. As a fully differentiable symplectic module, K-GMRF provides a plug-and-play geometric prior for data-constrained scenarios and an interpretable layer within modern deep architectures.

---

### Physics-Informed Neural Network with Adaptive Clustering Learning Mechanism for Information Popularity Prediction

Authors: Guangyin Jin, Xiaohan Ni, Yanjie Song, Kun Wei, Jie Zhao, Leiming Jia, Witold Pedrycz
Published: 2026-03-20
Categories: cs.SI, cs.AI
arXiv: https://arxiv.org/abs/2603.19599v1

With society entering the Internet era, the volume and speed of data and information have been increasing. Predicting the popularity of information cascades can help with high-value information delivery and public opinion monitoring on the internet platforms. The current state-of-the-art models for predicting information popularity utilize deep learning methods such as graph convolution networks (GCNs) and recurrent neural networks (RNNs) to capture early cascades and temporal features to predict their popularity increments. However, these previous methods mainly focus on the micro features of information cascades, neglecting their general macroscopic patterns. Furthermore, they also lack consideration of the impact of information heterogeneity on spread popularity. To overcome these limitations, we propose a physics-informed neural network with adaptive clustering learning mechanism, PIACN, for predicting the popularity of information cascades. Our proposed model not only models the macroscopic patterns of information dissemination through physics-informed approach for the first time but also considers the influence of information heterogeneity through an adaptive clustering learning mechanism. Extensive experimental results on three real-world datasets demonstrate that our model significantly outperforms other state-of-the-art methods in predicting information popularity.

---

### FlowScene: Style-Consistent Indoor Scene Generation with Multimodal Graph Rectified Flow

Authors: Zhifei Yang, Guangyao Zhai, Keyang Lu, YuYang Yin, Chao Zhang, Zhen Xiao, Jieyi Long, Nassir Navab, Yikai Wang
Published: 2026-03-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.19598v1

Scene generation has extensive industrial applications, demanding both high realism and precise control over geometry and appearance. Language-driven retrieval methods compose plausible scenes from a large object database, but overlook object-level control and often fail to enforce scene-level style coherence. Graph-based formulations offer higher controllability over objects and inform holistic consistency by explicitly modeling relations, yet existing methods struggle to produce high-fidelity textured results, thereby limiting their practical utility. We present FlowScene, a tri-branch scene generative model conditioned on multimodal graphs that collaboratively generates scene layouts, object shapes, and object textures. At its core lies a tight-coupled rectified flow model that exchanges object information during generation, enabling collaborative reasoning across the graph. This enables fine-grained control of objects' shapes, textures, and relations while enforcing scene-level style coherence across structure and appearance. Extensive experiments show that FlowScene outperforms both language-conditioned and graph-conditioned baselines in terms of generation realism, style consistency, and alignment with human preferences.

---