# Research Papers — 2026-03 · bundle page 127 of 243 > Full-text markdown of papers #6301–6350 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/127 [← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/126.md) [Next bundle →](https://aipod.dev/papers/archive/2026-03/page/128.md) ### SimCert: Probabilistic Certification for Behavioral Similarity in Deep Neural Network Compression Authors: Jingyang Li, Fu Song, Guoqiang Li Published: 2026-03-16 Categories: cs.SE, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.14818v1 Deploying Deep Neural Networks (DNNs) on resource-constrained embedded systems requires aggressive model compression techniques like quantization and pruning. However, ensuring that the compressed model preserves the behavioral fidelity of the original design is a critical challenge in the safety-critical system design flow. Existing verification methods often lack scalability or fail to handle the architectural heterogeneity introduced by pruning. In this work, we propose SimCert, a probabilistic certification framework for verifying the behavioral similarity of compressed neural networks. Unlike worst-case analysis, SimCert provides quantitative safety guarantees with adjustable confidence levels. Our framework features: (1) A dual-network symbolic propagation method supporting both quantization and pruning; (2) A variance-aware bounding technique using Bernstein's inequality to tighten safety certificates; and (3) An automated verification toolchain. Experimental results on ACAS Xu and computer vision benchmarks demonstrate that SimCert outperforms state-of-the-art baselines. --- ### M2IR: Proactive All-in-One Image Restoration via Mamba-style Modulation and Mixture-of-Experts Authors: Shiwei Wang, Yongzhen Wang, Bingwen Hu, Liyan Zhang, Xiao-Ping Zhang, Mingqiang Wei Published: 2026-03-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.14816v1 While Transformer-based architectures have dominated recent advances in all-in-one image restoration, they remain fundamentally reactive: propagating degradations rather than proactively suppressing them. In the absence of explicit suppression mechanisms, degraded signals interfere with feature learning, compelling the decoder to balance artifact removal and detail preservation, thereby increasing model complexity and limiting adaptability. To address these challenges, we propose M2IR, a novel restoration framework that proactively regulates degradation propagation during the encoding stage and efficiently eliminates residual degradations during decoding. Specifically, the Mamba-Style Transformer (MST) block performs pixel-wise selective state modulation to mitigate degradations while preserving structural integrity. In parallel, the Adaptive Degradation Expert Collaboration (ADEC) module utilizes degradation-specific experts guided by a DA-CLIP-driven router and complemented by a shared expert to eliminate residual degradations through targeted and cooperative restoration. By integrating the MST block and ADEC module, M2IR transitions from passive reaction to active degradation control, effectively harnessing learned representations to achieve superior generalization, enhanced adaptability, and refined recovery of fine-grained details across diverse all-in-one image restoration benchmarks. Our source codes are available at https://github.com/Im34v/M2IR. --- ### Ego to World: Collaborative Spatial Reasoning in Embodied Systems via Reinforcement Learning Authors: Heng Zhou, Li Kang, Yiran Qin, Xiufeng Song, Ao Yu, Zilu Zhang, Haoming Song, Kaixin Xu, Yuchen Fan, Dongzhan Zhou, Xiaohong Liu, Ruimao Zhang et al. Published: 2026-03-16 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2603.14811v1 Understanding the world from distributed, partial viewpoints is a fundamental challenge for embodied multi-agent systems. Each agent perceives the environment through an ego-centric view that is often limited by occlusion and ambiguity. To study this problem, we introduce the Ego-to-World (E2W) benchmark, which evaluates a vision-language model's ability to fuse heterogeneous viewpoints across three tasks: (i) global counting, (ii) relational location reasoning, and (iii) action-oriented grasping that requires predicting view-specific image coordinates. To address this setting, we propose CoRL, a two-stage framework that combines Chain-of-Thought supervised fine-tuning with reinforcement learning using Group-Relative Policy Optimization. Its core component, the Cross-View Spatial Reward (CVSR), provides dense task-aligned feedback by linking reasoning steps to visual evidence, ensuring coherent cross-view entity resolution, and guiding the model toward correct final predictions. Experiments on E2W show that CoRL consistently surpasses strong proprietary and open-source baselines on both reasoning and perception-grounding metrics, while ablations further confirm the necessity of each CVSR component. Beyond that, CoRL generalizes to external spatial reasoning benchmarks and enables effective real-world multi-robot manipulation with calibrated multi-camera rigs, demonstrating cross-view localization and successful grasp-and-place execution. Together, E2W and CoRL provide a principled foundation for learning world-centric scene understanding from distributed, ego-centric observations, advancing collaborative embodied AI. --- ### HiMemVLN: Enhancing Reliability of Open-Source Zero-Shot Vision-and-Language Navigation with Hierarchical Memory System Authors: Kailin Lyu, Kangyi Wu, Pengna Li, Xiuyu Hu, Qingyi Si, Cui Miao, Ning Yang, Zihang Wang, Long Xiao, Lianyu Hu, Jingyuan Sun, Ce Hao Published: 2026-03-16 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2603.14807v3 LLM-based agents have demonstrated impressive zero-shot performance in vision-language navigation (VLN) tasks. However, most zero-shot methods primarily rely on closed-source LLMs as navigators, which face challenges related to high token costs and potential data leakage risks. Recent efforts have attempted to address this by using open-source LLMs combined with a spatiotemporal CoT framework, but they still fall far short compared to closed-source models. In this work, we identify a critical issue, Navigation Amnesia, through a detailed analysis of the navigation process. This issue leads to navigation failures and amplifies the gap between open-source and closed-source methods. To address this, we propose HiMemVLN, which incorporates a Hierarchical Memory System into a multimodal large model to enhance visual perception recall and long-term localization, mitigating the amnesia issue and improving the agent's navigation performance. Extensive experiments in both simulated and real-world environments demonstrate that HiMemVLN achieves nearly twice the performance of the open-source state-of-the-art method. The code is available at https://github.com/lvkailin0118/HiMemVLN. --- ### Fold-CP: A Context Parallelism Framework for Biomolecular Modeling Authors: Dejun Lin, Simon Chu, Vishanth Iyer, Youhan Lee, John St John, Kevin Boyd, Brian Roland, Xiaowei Ren, Guoqing Zhou, Zhonglin Cao, Polina Binder, Yuliya Zhautouskaya et al. Published: 2026-03-16 Categories: q-bio.QM, cs.DC, cs.LG, q-bio.BM arXiv: https://arxiv.org/abs/2603.14806v1 Understanding cellular machinery requires atomic-scale reconstruction of large biomolecular assemblies. However, predicting the structures of these systems has been constrained by hardware memory requirements of models like AlphaFold 3, imposing a practical ceiling of a few thousand residues that can be processed on a single GPU. Here we present NVIDIA BioNeMo Fold-CP, a context parallelism framework that overcomes this barrier by distributing the inference and training pipelines of co-folding models across multiple GPUs. We use the Boltz models as open source reference architectures and implement custom multidimensional primitives that efficiently parallelize both the dense triangular updates and the irregular, data-dependent pattern of window-batched local attention. Our approach achieves efficient memory scaling; for an N-token input distributed across P GPUs, per-device memory scales as $O(N^2/P)$, enabling the structure prediction of assemblies exceeding 30,000 residues on 64 NVIDIA B300 GPUs. We demonstrate the scientific utility of this approach through successful developer use cases: Fold-CP enabled the scoring of over 90% of Comprehensive Resource of Mammalian protein complexes (CORUM) database, as well as folding of disease-relevant PI4KA lipid kinase complex bound to an intrinsically disordered region without cropping. By providing a scalable pathway for modeling massive systems with full global context, Fold-CP represents a significant step toward the realization of a virtual cell. --- ### Knowledge Activation: AI Skills as the Institutional Knowledge Primitive for Agentic Software Development Authors: Gal Bakal Published: 2026-03-16 Categories: cs.AI, cs.HC, cs.SE arXiv: https://arxiv.org/abs/2603.14805v2 Enterprise software organizations accumulate critical institutional knowledge - architectural decisions, deployment procedures, compliance policies, incident playbooks - yet this knowledge remains trapped in formats designed for human interpretation. The bottleneck to effective agentic software development is not model capability but knowledge architecture. When any knowledge consumer - an autonomous AI agent, a newly onboarded engineer, or a senior developer - encounters an enterprise task without institutional context, the result is guesswork, correction cascades, and a disproportionate tax on senior engineers who must manually supply what others cannot infer. This paper introduces Knowledge Activation, a framework that specializes AI Skills - the open standard for agent-consumable knowledge - into structured, governance-aware Atomic Knowledge Units (AKUs) for institutional knowledge delivery. Rather than retrieving documents for interpretation, AKUs deliver action - ready specifications encoding what to do, which tools to use, what constraints to respect, and where to go next - so that agents act correctly and engineers receive institutionally grounded guidance without reconstructing organizational context from scratch. AKUs form a composable knowledge graph that agents traverse at runtime - compressing onboarding, reducing cross - team friction, and eliminating correction cascades. The paper formalizes the resource constraints that make this architecture necessary, specifies the AKU schema and deployment architecture, and grounds long - term maintenance in knowledge commons practice. A Yahoo deployment surveying 67 engineers shows statistically significant developer-experience gains - 2.6 hours per week saved, Net Promoter Score +35. Organizations that architect their institutional knowledge for the agentic era will outperform those that invest solely in model capability. --- ### VorTEX: Various overlap ratio for Target speech EXtraction Authors: Ro-hoon Oh, Jihwan Seol, Bugeun Kim Published: 2026-03-16 Categories: cs.SD, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.14803v3 Target speech extraction (TSE) aims to recover a target speaker's voice from a mixture. While recent text-prompted approaches have shown promise, most approaches assume fully overlapped mixtures, limiting insight into behavior across realistic overlap ratios. We introduce VorTEX (Various overlap ratio for Target speech EXtraction), a text-prompted TSE architecture with a Decoupled Adaptive Multi-branch (DAM) Fusion block that separates primary extraction from auxiliary regularization pathways. To enable controlled analysis, we construct PORTE, a two-speaker dataset spanning overlap ratios from 0% to 100%. We further propose Suppression Ratio on Energy (SuRE), a diagnostic metric that detects suppression behavior not captured by conventional measures. Experiments show that existing models exhibit suppression or residual interference under overlap, whereas VorTEX achieves the highest separation fidelity across 20-100% overlap (e.g., 5.50 dB at 20% and 2.04 dB at 100%) while maintaining zero SuRE, indicating robust extraction without suppression-driven artifacts. --- ### OpenReservoirComputing: GPU-Accelerated Reservoir Computing in JAX Authors: Jan Williams, Dima Tretiak, Steven L. Brunton, J. Nathan Kutz, Krithika Manohar Published: 2026-03-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.14802v1 OpenReservoirComputing (ORC) is a Python library for reservoir computing (RC) written in JAX (Bradbury et al. 2018) and Equinox (Kidger and Garcia 2021). JAX is a Python library for high-performance numerical computing that enables automatic differentiation, just-in-time (JIT) compilation, and GPU/TPU acceleration, while Equinox is a neural network framework for JAX. RC is a form of machine learning that functions by lifting a low-dimensional sequence or signal into a high-dimensional dynamical system and training a simple, linear readout layer from the high-dimensional dynamics back to a lower-dimensional quantity of interest. The most common application of RC is time-series forecasting, where the goal is to predict a signal's future evolution. RC has achieved state-of-the-art performance on this task, particularly when applied to chaotic dynamical systems. In addition, RC approaches can be adapted to perform classification and control tasks. ORC provides both modular components for building custom RC models and built-in models for forecasting, classification, and control. By building on JAX and Equinox, ORC offers GPU acceleration, JIT compilation, and automatic vectorization. These capabilities make prototyping new models faster and enable larger and more powerful reservoir architectures. End-to-end differentiability also enables seamless integration with other deep learning models built with Equinox. --- ### Universe Routing: Why Self-Evolving Agents Need Epistemic Control Authors: Zhaohui Geoffrey Wang Published: 2026-03-16 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.14799v1 A critical failure mode of current lifelong agents is not lack of knowledge, but the inability to decide how to reason. When an agent encounters "Is this coin fair?" it must recognize whether to invoke frequentist hypothesis testing or Bayesian posterior inference - frameworks that are epistemologically incompatible. Mixing them produces not minor errors, but structural failures that propagate across decision chains. We formalize this as the universe routing problem: classifying questions into mutually exclusive belief spaces before invoking specialized solvers. Our key findings challenge conventional assumptions: (1) hard routing to heterogeneous solvers matches soft MoE accuracy while being 7x faster because epistemically incompatible frameworks cannot be meaningfully averaged; (2) a 465M-parameter router achieves a 2.3x smaller generalization gap than keyword-matching baselines, indicating semantic rather than surface-level reasoning; (3) when expanding to new belief spaces, rehearsal-based continual learning achieves zero forgetting, outperforming EWC by 75 percentage points, suggesting that modular epistemic architectures are fundamentally more amenable to lifelong learning than regularization-based approaches. These results point toward a broader architectural principle: reliable self-evolving agents may require an explicit epistemic control layer that governs reasoning framework selection. --- ### Preconditioned One-Step Generative Modeling for Bayesian Inverse Problems in Function Spaces Authors: Zilan Cheng, Li-Lian Wang, Zhongjian Wang Published: 2026-03-16 Categories: stat.ML, cs.LG, math.NA arXiv: https://arxiv.org/abs/2603.14798v2 We propose a machine-learning algorithm for Bayesian inverse problems in the function-space regime. Based on one-step generative transport, the method learns an amortized neural operator whose pushforward of a Gaussian source approximates the posterior distribution conditioned on each new observation. We show that white-noise sources are incompatible with the function-space limit, and therefore adopt a prior-aligned GRF as the source. We justify this choice through the Lipschitz regularity of the resulting one-step conditional posterior transport and numerical experiments on linear inverse and PDE-based inverse problems. The method is not distilled from MCMC: it is trained only with prior samples and simulated partial noisy observations. Once trained, it generates a $64\times64$ posterior sample in $\sim 10^{-3}$s, avoiding repeated forward-model evaluations in MCMC and repeated network evaluations in multistep generative samplers while matching key posterior summaries. --- ### Multi-Task Genetic Algorithm with Multi-Granularity Encoding for Protein-Nucleotide Binding Site Prediction Authors: Yiming Gao, Liuyi Xu, Pengshan Cui, Yining Qian, An-Yang Lu, Xianpeng Wang Published: 2026-03-16 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.14797v1 Accurate identification of protein-nucleotide binding sites is fundamental to deciphering molecular mechanisms and accelerating drug discovery. However, current computational methods often struggle with suboptimal performance due to inadequate feature representation and rigid fusion mechanisms, which hinder the effective exploitation of cross-task information synergy. To bridge this gap, we propose MTGA-MGE, a framework that integrates a Multi-Task Genetic Algorithm with Multi-Granularity Encoding to enhance binding site prediction. Specifically, we develop a Multi-Granularity Encoding (MGE) network that synergizes multi-scale convolutions and self-attention mechanisms to distill discriminative signals from high-dimensional, redundant biological data. To overcome the constraints of static fusion, a genetic algorithm is employed to adaptively evolve task-specific fusion strategies, thereby effectively improving model generalization. Furthermore, to catalyze collaborative learning, we introduce an External-Neighborhood Mechanism (ENM) that leverages biological similarities to facilitate targeted information exchange across tasks. Extensive evaluations on fifteen nucleotide datasets demonstrate that MTGA-MGE not only establishes a new state-of-the-art in data-abundant, high-resource scenarios but also maintains a robust competitive edge in rare, low-resource regimes, presenting a highly adaptive scheme for decoding complex protein-ligand interactions in the post-genomic era. --- ### Global Truncated Loss Minimization for Robust and Threshold-Resilient Geometric Estimation Authors: Tianyu Huang, Liangzu Peng, Xinyue Zhang, Tongfan Guan, Jinhu Dong, Haoang Li, Laurent Kneip, Yun-Hui Liu Published: 2026-03-16 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2603.14796v1 To achieve outlier-robust geometric estimation, robust objective functions are generally employed to mitigate the influence of outliers. The widely used consensus maximization(CM) is highly robust when paired with global branch-and-bound(BnB) search. However, CM relies solely on inlier counts and is sensitive to the inlier threshold. Besides, the discrete nature of CM leads to loose bounds, necessitating extensive BnB iterations and computation cost. Truncated losses(TL), another continuous alternative, leverage residual information more effectively and could potentially overcome these issues. But to our knowledge, no prior work has systematically explored globally minimizing TL with BnB and its potential for enhanced threshold resilience or search efficiency. In this work, we propose GTM, the first unified BnB-based framework for globally-optimal TL loss minimization across diverse geometric problems. GTM involves a hybrid solving design: given an n-dimensional problem, it performs BnB search over an (n-1)-dimensional subspace while the remaining 1D variable is solved by bounding the objective function. Our hybrid design not only reduces the search space, but also enables us to derive Lipschitz-continuous bounding functions that are general, tight, and can be efficiently solved by a classic global Lipschitz solver named DIRECT, which brings further acceleration. We conduct a systematic evaluation on various BnB-based methods for CM and TL on the robust linear regression problem, showing that GTM enjoys remarkable threshold resilience and the highest efficiency compared to baseline methods. Furthermore, we apply GTM on different geometric estimation problems with diverse residual forms. Extensive experiments demonstrate that GTM achieves state-of-the-art outlier-robustness and threshold-resilience while maintaining high efficiency across these estimation tasks. --- ### Face-to-Face: A Video Dataset for Multi-Person Interaction Modeling Authors: Ernie Chu, Vishal M. Patel Published: 2026-03-16 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.14794v2 Modeling the reactive tempo of human conversation remains difficult because most audio-visual datasets portray isolated speakers delivering short monologues. We introduce \textbf{Face-to-Face with Jimmy Fallon (F2F-JF)}, a 70-hour, 14k-clip dataset of two-person talk-show exchanges that preserves the sequential dependency between a guest turn and the host's response. A semi-automatic pipeline combines multi-person tracking, speech diarization, and lightweight human verification to extract temporally aligned host/guest tracks with tight crops and metadata that are ready for downstream modeling. We showcase the dataset with a reactive, speech-driven digital avatar task in which the host video during $(t_1,t_2)$ is generated from their audio plus the guest's preceding video during $(t_0,t_1)$. Conditioning a MultiTalk-style diffusion model on this cross-person visual context yields small but consistent Emotion-FID and FVD gains while preserving lip-sync quality relative to an audio-only baseline. The dataset, preprocessing recipe, and baseline together provide an end-to-end blueprint for studying dyadic, sequential behavior, which we expand upon throughout the paper. Dataset and code are available at https://face2face2026.github.io. --- ### GARCH-FIS: A Hybrid Forecasting Model with Dynamic Volatility-Driven Parameter Adaptation Authors: Wen-Jing Li, Da-Qing Zhang Published: 2026-03-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.14793v1 This paper proposes a novel hybrid model, termed GARCH-FIS, for recursive rolling multi-step forecasting of financial time series. It integrates a Fuzzy Inference System (FIS) with a Generalized Autoregressive Conditional Heteroskedasticity (GARCH) model to jointly address nonlinear dynamics and time-varying volatility. The core innovation is a dynamic parameter adaptation mechanism for the FIS, specifically activated within the multi-step forecasting cycle. In this process, the conditional volatility estimated by a rolling window GARCH model is continuously translated into a price volatility measure. At each forecasting step, this measure, alongside the updated mean of the sliding window data -- which now incorporates the most recent predicted price -- jointly determines the parameters of the FIS membership functions for the next prediction. Consequently, the granularity of the fuzzy inference adapts as the forecast horizon extends: membership functions are automatically widened during high-volatility market regimes to bolster robustness and narrowed during stable periods to enhance precision. This constitutes a fundamental advancement over a static one-step-ahead prediction setup. Furthermore, the model's fuzzy rule base is automatically constructed from data using the Wang-Mendel method, promoting interpretability and adaptability. Empirical evaluation, focused exclusively on multi-step forecasting performance across ten diverse financial assets, demonstrates that the proposed GARCH-FIS model significantly outperforms benchmark models -- including Support Vector Regression(SVR), Long Short-Term Memory networks(LSTM), and an ARIMA-GARCH econometric model -- in terms of predictive accuracy and stability, while effectively mitigating error accumulation in extended recursive forecasts. --- ### LaPro-DTA: Latent Dual-View Drug Representations and Salient Protein Feature Extraction for Generalizable Drug--Target Affinity Prediction Authors: Zihan Dun, Liuyi Xu, An-Yang Lu, Shuang Li, Yining Qian Published: 2026-03-16 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.14792v1 Drug--target affinity prediction is pivotal for accelerating drug discovery, yet existing methods suffer from significant performance degradation in realistic cold-start scenarios (unseen drugs/targets/pairs), primarily driven by overfitting to training instances and information loss from irrelevant target sequences. In this paper, we propose LaPro-DTA, a framework designed to achieve robust and generalizable DTA prediction. To tackle overfitting, we devise a latent dual-view drug representation mechanism. It synergizes an instance-level view to capture fine-grained substructures with stochastic perturbation and a distribution-level view to distill generalized chemical scaffolds via semantic remapping, thereby enforcing the model to learn transferable structural rules rather than memorizing specific samples. To mitigate information loss, we introduce a salient protein feature extraction strategy using pattern-aware top-$k$ pooling, which effectively filters background noise and isolates high-response bioactive regions. Furthermore, a cross-view multi-head attention mechanism fuses these purified features to model comprehensive interactions. Extensive experiments on benchmark datasets demonstrate that LaPro-DTA significantly outperforms state-of-the-art methods, achieving an 8\% MSE reduction on the Davis dataset in the challenging unseen-drug setting, while offering interpretable insights into binding mechanisms. --- ### Mind-of-Director: Multi-modal Agent-Driven Film Previsualization via Collaborative Decision-Making Authors: Shufeng Nan, Mengtian Li, Sixiao Zheng, Yuwei Lu, Han Zhang, Yanwei Fu Published: 2026-03-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.14790v2 We present Mind-of-Director, a multi-modal agent-driven framework for film previz that models the collaborative decision-making process of a film production team. Given a creative idea, Mind-of-Director orchestrates multiple specialized agents to produce previz sequences within the game engine. The framework consists of four cooperative modules: Script Development, where agents draft and refine the screenplay iteratively; Virtual Scene Design, which transforms text into semantically aligned 3D environments; Character Behaviour Control, which determines character blocking and motion; and Camera Planning, which optimizes framing, movement, and composition for cinematic camera effects. A real-time visual editing system built in the game engine further enables interactive inspection and synchronized timeline adjustment across scenes, behaviours, and cameras. Extensive experiments and human evaluations show that Mind-of-Director generates high-quality, semantically grounded previz sequences in approximately 25 minutes per idea, demonstrating the effectiveness of agent collaboration for both automated prototyping and human-in-the-loop filmmaking. --- ### Orthogonal Subspace Clustering: Enhancing High-Dimensional Data Analysis through Adaptive Dimensionality Reduction and Efficient Clustering Authors: Qing-Yuan Wen, Da-Qing Zhang Published: 2026-03-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.14783v1 This paper presents Orthogonal Subspace Clustering (OSC), an innovative method for high-dimensional data clustering. We first establish a theoretical theorem proving that high-dimensional data can be decomposed into orthogonal subspaces in a statistical sense, whose form exactly matches the paradigm of Q-type factor analysis. This theorem lays a solid mathematical foundation for dimensionality reduction via matrix decomposition and factor analysis. Based on this theorem, we propose the OSC framework to address the "curse of dimensionality" -- a critical challenge that degrades clustering effectiveness due to sample sparsity and ineffective distance metrics. OSC integrates orthogonal subspace construction with classical clustering techniques, introducing a data-driven mechanism to select the subspace dimension based on cumulative variance contribution. This avoids manual selection biases while maximizing the retention of discriminative information. By projecting high-dimensional data into an uncorrelated, low-dimensional orthogonal subspace, OSC significantly improves clustering efficiency, robustness, and accuracy. Extensive experiments on various benchmark datasets demonstrate the effectiveness of OSC, with thorough analysis of evaluation metrics including Cluster Accuracy (ACC), Normalized Mutual Information (NMI), and Adjusted Rand Index (ARI) highlighting its advantages over existing methods. --- ### Information Asymmetry across Language Varieties: A Case Study on Cantonese-Mandarin and Bavarian-German QA Authors: Renhao Pei, Siyao Peng, Verena Blaschke, Robert Litschko, Barbara Plank Published: 2026-03-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.14782v1 Large Language Models (LLMs) are becoming a common way for humans to seek knowledge, yet their coverage and reliability vary widely. Especially for local language varieties, there are large asymmetries, e.g., information in local Wikipedia that is absent from the standard variant. However, little is known about how well LLMs perform under such information asymmetry, especially on closely related languages. We manually construct a novel challenge question-answering (QA) dataset that captures knowledge conveyed on a local Wikipedia page, which is absent from their higher-resource counterparts-covering Mandarin Chinese vs. Cantonese and German vs. Bavarian. Our experiments show that LLMs fail to answer questions about information only in local editions of Wikipedia. Providing context from lead sections substantially improves performance, with further gains possible via translation. Our topical, geographic annotations, and stratified evaluations reveal the usefulness of local Wikipedia editions as sources of both regional and global information. These findings raise critical questions about inclusivity and cultural coverage of LLMs. --- ### High-Fidelity 3D Facial Avatar Synthesis with Controllable Fine-Grained Expressions Authors: Yikang He, Jichao Zhang, Wei Wang, Nicu Sebe, Yao Zhao Published: 2026-03-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.14781v1 Facial expression editing methods can be mainly categorized into two types based on their architectures: 2D-based and 3D-based methods. The former lacks 3D face modeling capabilities, making it difficult to edit 3D factors effectively. The latter has demonstrated superior performance in generating high-quality and view-consistent renderings using single-view 2D face images. Although these methods have successfully used animatable models to control facial expressions, they still have limitations in achieving precise control over fine-grained expressions. To address this issue, in this paper, we propose a novel approach by simultaneously refining both the latent code of a pretrained 3D-Aware GAN model for texture editing and the expression code of the driven 3DMM model for mesh editing. Specifically, we introduce a Dual Mappers module, comprising Texture Mapper and Emotion Mapper, to learn the transformations of the given latent code for textures and the expression code for meshes, respectively. To optimize the Dual Mappers, we propose a Text-Guided Optimization method, leveraging a CLIP-based objective function with expression text prompts as targets, while integrating a SubSpace Projection mechanism to project the text embedding to the expression subspace such that we can have more precise control over fine-grained expressions. Extensive experiments and comparative analyses demonstrate the effectiveness and superiority of our proposed method. --- ### Vietnamese Automatic Speech Recognition: A Revisit Authors: Thi Vu, Linh The Nguyen, Dat Quoc Nguyen Published: 2026-03-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.14779v1 Automatic Speech Recognition (ASR) performance is heavily dependent on the availability of large-scale, high-quality datasets. For low-resource languages, existing open-source ASR datasets often suffer from insufficient quality and inconsistent annotation, hindering the development of robust models. To address these challenges, we propose a novel and generalizable data aggregation and preprocessing pipeline designed to construct high-quality ASR datasets from diverse, potentially noisy, open-source sources. Our pipeline incorporates rigorous processing steps to ensure data diversity, balance, and the inclusion of crucial features like word-level timestamps. We demonstrate the effectiveness of our methodology by applying it to Vietnamese, resulting in a unified, high-quality 500-hour dataset that provides a foundation for training and evaluating state-of-the-art Vietnamese ASR systems. Our project page is available at https://github.com/qualcomm-ai-research/PhoASR. --- ### P$^2$RAG: Efficient Privacy-Preserving RAG Service Supporting Arbitrary Top-$k$ Retrieval Authors: Yulong Ming, Mingyue Wang, Jijia Yang, Jie Xu, Zihan Wu, Cong Wang, Xiaohua Jia Published: 2026-03-16 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2603.14778v2 Retrieval-Augmented Generation (RAG) enables large language models to use external knowledge, but outsourcing the RAG service raises privacy concerns for both data owners and users. Privacy-preserving RAG systems address these concerns by performing secure top-$k$ retrieval, which is typically implemented using secure sorting to identify relevant documents. However, existing systems face challenges supporting arbitrary $k$ due to their inability to change $k$, new security issues, and in particular, efficiency degradation with large $k$. This is a significant limitation because applications such as finance, law, and healthcare require a $k$ that is large enough to cause huge overhead for existing systems. Also, modern long-context models generally achieve higher accuracy with larger retrieval sets. We propose P$^2$RAG, an efficient privacy-preserving RAG service that supports arbitrary top-$k$ retrieval. Unlike existing systems, P$^2$RAG avoids sorting candidate documents. Instead, it uses an interactive bisection method to determine the set of top-$k$ documents. For security, P$^2$RAG uses secret sharing on two semi-honest non-colluding servers to protect the data owner's database and the user's prompt. It enforces restrictions and verification to defend against malicious users and tightly bounds the information leakage of the database. The experiments show that P$^2$RAG is 3--300$\times$ faster than the state-of-the-art PRAG for $k = 16$--$1024$. --- ### HO-SFL: Hybrid-Order Split Federated Learning with Backprop-Free Clients and Dimension-Free Aggregation Authors: Qiyuan Chen, Xian Wu, Yi Wang, Xianhao Chen Published: 2026-03-16 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.14773v3 Fine-tuning large models on edge devices is severely hindered by the memory-intensive backpropagation (BP) in standard frameworks like federated learning and split learning. While substituting BP with zeroth-order optimization can significantly reduce memory footprints, it typically suffers from prohibitively degraded convergence speed. To resolve this dilemma, we propose Hybrid-Order Split Federated Learning (HO-SFL). By reformulating the split learning process within a Lagrangian framework, HO-SFL decouples the optimization landscape: The server performs precise first-order updates (i.e., BP), whereas clients conduct memory-efficient zeroth-order optimization. This hybrid design not only eliminates the need for client-side BP but also enables dimension-free model aggregation, drastically lowering communication costs. Crucially, we provide a theoretical convergence analysis, demonstrating that HO-SFL mitigates the dimension-dependent convergence slowdown of zeroth-order optimization, achieving a convergence rate comparable to first-order methods. Extensive experiments on tasks across vision and language modalities validate that HO-SFL achieves convergence speeds comparable to first-order baselines while significantly reducing communication costs and client memory footprints. --- ### HO-SFL: Hybrid-Order Split Federated Learning with Backprop-Free Clients and Dimension-Free Aggregation Authors: Qiyuan Chen, Xian Wu, Yi Wang, Xianhao Chen Published: 2026-03-16 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.14773v2 Fine-tuning large models on edge devices is severely hindered by the memory-intensive backpropagation (BP) in standard frameworks like federated learning and split learning. While substituting BP with zeroth-order optimization can significantly reduce memory footprints, it typically suffers from prohibitively degraded convergence speed. To resolve this dilemma, we propose Hybrid-Order Split Federated Learning (HO-SFL). By reformulating the split learning process within a Lagrangian framework, HO-SFL decouples the optimization landscape: The server performs precise first-order updates (i.e., BP), whereas clients conduct memory-efficient zeroth-order optimization. This hybrid design not only eliminates the need for client-side BP but also enables dimension-free model aggregation, drastically lowering communication costs. Crucially, we provide a theoretical convergence analysis, demonstrating that HO-SFL mitigates the dimension-dependent convergence slowdown of zeroth-order optimization, achieving a convergence rate comparable to first-order methods. Extensive experiments on tasks across vision and language modalities validate that HO-SFL achieves convergence speeds comparable to first-order baselines while significantly reducing communication costs and client memory footprints. --- ### Zero-Shot Reconstruction of Animatable 3D Avatars with Cloth Dynamics from a Single Image Authors: Joohyun Kwon, Geonhee Sim, Gyeongsik Moon Published: 2026-03-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.14772v1 Existing single-image 3D human avatar methods primarily rely on rigid joint transformations, limiting their ability to model realistic cloth dynamics. We present DynaAvatar, a zero-shot framework that reconstructs animatable 3D human avatars with motion-dependent cloth dynamics from a single image. Trained on large-scale multi-person motion datasets, DynaAvatar employs a Transformer-based feed-forward architecture that directly predicts dynamic 3D Gaussian deformations without subject-specific optimization. To overcome the scarcity of dynamic captures, we introduce a static-to-dynamic knowledge transfer strategy: a Transformer pretrained on large-scale static captures provides strong geometric and appearance priors, which are efficiently adapted to motion-dependent deformations through lightweight LoRA fine-tuning on dynamic captures. We further propose the DynaFlow loss, an optical flow-guided objective that provides reliable motion-direction geometric cues for cloth dynamics in rendered space. Finally, we reannotate the missing or noisy SMPL-X fittings in existing dynamic capture datasets, as most public dynamic capture datasets contain incomplete or unreliable fittings that are unsuitable for training high-quality 3D avatar reconstruction models. Experiments demonstrate that DynaAvatar produces visually rich and generalizable animations, outperforming prior methods. --- ### OpenHospital: A Thing-in-itself Arena for Evolving and Benchmarking LLM-based Collective Intelligence Authors: Peigen Liu, Rui Ding, Yuren Mao, Ziyan Jiang, Yuxiang Ye, Yunjun Gao, Ying Zhang, Renjie Sun, Longbin Lai, Zhengping Qian Published: 2026-03-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.14771v3 Large Language Model (LLM)-based Collective Intelligence (CI) presents a promising approach to overcoming the data wall and continuously boosting the capabilities of LLM agents. However, there is currently no dedicated arena for evolving and benchmarking LLM-based CI. To address this gap, we introduce OpenHospital, an interactive arena where physician agents can evolve CI through interactions with patient agents. This arena employs a data-in-agent-self paradigm that rapidly enhances agent capabilities and provides robust evaluation metrics for benchmarking both medical proficiency and system efficiency. Experiments demonstrate the effectiveness of OpenHospital in both fostering and quantifying CI. --- ### AnyPhoto: Multi-Person Identity Preserving Image Generation with ID Adaptive Modulation on Location Canvas Authors: Longhui Yuan Published: 2026-03-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.14770v1 Multi-person identity-preserving generation requires binding multiple reference faces to specified locations under a text prompt. Strong identity/layout conditions often trigger copy-paste shortcuts and weaken prompt-driven controllability. We present AnyPhoto, a diffusion-transformer finetuning framework with (i) a RoPE-aligned location canvas plus location-aligned token pruning for spatial grounding, (ii) AdaLN-style identity-adaptive modulation from face-recognition embeddings for persistent identity injection, and (iii) identity-isolated attention to prevent cross-identity interference. Training combines conditional flow matching with an embedding-space face similarity loss, together with reference-face replacement and location-canvas degradations to discourage shortcuts. On MultiID-Bench, AnyPhoto improves identity similarity while reducing copy-paste tendency, with gains increasing as the number of identities grows. AnyPhoto also supports prompt-driven stylization with accurate placement, showing great potential application value. --- ### POLCA: Stochastic Generative Optimization with LLM Authors: Xuanfei Ren, Allen Nie, Tengyang Xie, Ching-An Cheng Published: 2026-03-16 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.14769v1 Optimizing complex systems, ranging from LLM prompts to multi-turn agents, traditionally requires labor-intensive manual iteration. We formalize this challenge as a stochastic generative optimization problem where a generative language model acts as the optimizer, guided by numerical rewards and text feedback to discover the best system. We introduce Prioritized Optimization with Local Contextual Aggregation (POLCA), a scalable framework designed to handle stochasticity in optimization -- such as noisy feedback, sampling minibatches, and stochastic system behaviors -- while effectively managing the unconstrained expansion of solution space. POLCA maintains a priority queue to manage the exploration-exploitation tradeoff, systematically tracking candidate solutions and their evaluation histories. To enhance efficiency, we integrate an $\varepsilon$-Net mechanism to maintain parameter diversity and an LLM Summarizer to perform meta-learning across historical trials. We theoretically prove that POLCA converges to near-optimal candidate solutions under stochasticity. We evaluate our framework on diverse benchmarks, including $τ$-bench, HotpotQA (agent optimization), VeriBench (code translation) and KernelBench (CUDA kernel generation). Experimental results demonstrate that POLCA achieves robust, sample and time-efficient performance, consistently outperforming state-of-the-art algorithms in both deterministic and stochastic problems. The codebase for this work is publicly available at https://github.com/rlx-lab/POLCA. --- ### Understanding the geometry of deep learning with decision boundary volume Authors: Matthew Burfitt, Jacek Brodzki, Pawel Dłotko Published: 2026-03-16 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2603.14768v1 For classification tasks, the performance of a deep neural network is determined by the structure of its decision boundary, whose geometry directly affects essential properties of the model, including accuracy and robustness. Motivated by a classical tube formula due to Weyl, we introduce a method to measure the decision boundary of a neural network through local surface volumes, providing a theoretically justifiable and efficient measure enabling a geometric interpretation of the effectiveness of the model applicable to the high dimensional feature spaces considered in deep learning. A smaller surface volume is expected to correspond to lower model complexity and better generalisation. We verify, on a number of image processing tasks with convolutional architectures that decision boundary volume is inversely proportional to classification accuracy. Meanwhile, the relationship between local surface volume and generalisation for fully connected architecture is observed to be less stable between tasks. Therefore, for network architectures suited to a particular data structure, we demonstrate that smoother decision boundaries lead to better performance, as our intuition would suggest. --- ### Investigating the Impact of Speech Enhancement on Audio Deepfake Detection in Noisy Environments Authors: Anacin, Angela, Shruti Kshirsagar, Anderson R. Avila Published: 2026-03-16 Categories: cs.SD, cs.LG arXiv: https://arxiv.org/abs/2603.14767v1 Logical Access (LA) attacks, also known as audio deepfake attacks, use Text-to-Speech (TTS) or Voice Conversion (VC) methods to generate spoofed speech data. This can represent a serious threat to Automatic Speaker Verification (ASV) systems, as intruders can use such attacks to bypass voice biometric security. In this study, we investigate the correlation between speech quality and the performance of audio spoofing detection systems (i.e., LA task). For that, the performance of two enhancement algorithms is evaluated based on two perceptual speech quality measures, namely Perceptual Evaluation of Speech Quality (PESQ) and Speech-to-Reverberation Modulation Ratio (SRMR), and in respect to their impact on the audio spoofing detection system. We adopted the LA dataset, provided in the ASVspoof 2019 Challenge, and corrupted its test set with different Signal-to-Noise Ratio (SNR) levels, while leaving the training data untouched. Enhancement was applied to attenuate the detrimental effects of noisy speech, and the performances of two models, Speech Enhancement Generative Adversarial Network (SEGAN) and Metric-Optimized Generative Adversarial Network Plus (MetricGAN+), were compared. Although we expect that speech quality will correlate well with speech applications' performance, it can also have as a side effect on downstream tasks if unwanted artifacts are introduced or relevant information is removed from the speech signal. Our results corroborate with this hypothesis, as we found that the enhancement algorithm leading to the highest speech quality scores, MetricGAN+, provided the lowest Equal Error Rate (EER) on the audio spoofing detection task, whereas the enhancement method with the lowest speech quality scores, SEGAN, led to the lowest EER, thus leading to better performance on the LA task. --- ### SSR: A Training-Free Approach for Streaming 3D Reconstruction Authors: Hui Deng, Yuxin Mao, Yuxin He, Yuchao Dai Published: 2026-03-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.14765v1 Streaming 3D reconstruction demands long-horizon state updates under strict latency constraints, yet stateful recurrent models often suffer from geometric drift as errors accumulate over time. We revisit this problem from a Grassmannian manifold perspective: the latent persistent state can be viewed as a subspace representation, i.e., a point evolving on a Grassmannian manifold, where temporal coherence implies the state trajectory should remain on (or near) this manifold.Based on this view, we propose Self-expressive Sequence Regularization (SSR), a plug-and-play, training-free operator that enforces Grassmannian sequence regularity during inference.Given a window of historical states, SSR computes an analytical affinity matrix via the self-expressive property and uses it to regularize the current update, effectively pulling noisy predictions back toward the manifold-consistent trajectory with minimal overhead. Experiments on long-sequence benchmarks demonstrate that SSR consistently reduces drift and improves reconstruction quality across multiple streaming 3D reconstruction tasks. --- ### Topology-Preserving Polygon Augmentation for Segmentation in Structured Visual Domains Authors: Sudip Laudari, Sang Hun Baek Published: 2026-03-16 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.14764v4 Geometric data augmentation is widely used in segmentation workflows, but polygon annotations are often assumed to remain valid after transformation. This assumption can fail in structured domains such as architectural floorplan analysis, where a region may contain an interior void encoded as part of a single ordered polygon chain. Cropping or clipping can remove bridge vertices in this chain, causing one semantic region to split into disconnected components. We propose a lightweight topology-preserving augmentation strategy that repairs missing adjacency relations in index space while preserving the original vertex order. The method adds minimal overhead and can be integrated into existing preprocessing workflows. Experiments show that the proposed approach achieves near-perfect Cyclic Adjacency Preservation (CAP) across common geometric transformations and improves annotation consistency in polygon-based segmentation. --- ### LiDAR-EVS: Enhance Extrapolated View Synthesis for 3D Gaussian Splatting with Pseudo-LiDAR Supervision Authors: Yiming Huang, Xin Kang, Sipeng Zhang, Hongliang Ren, Weihua Zhang, Junjie Lai Published: 2026-03-16 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2603.14763v1 3D Gaussian Splatting (3DGS) has emerged as a powerful technique for real-time LiDAR and camera synthesis in autonomous driving simulation. However, simulating LiDAR with 3DGS remains challenging for extrapolated views beyond the training trajectory, as existing methods are typically trained on single-traversal sensor scans, suffer from severe overfitting and poor generalization to novel ego-vehicle paths. To enable reliable simulation of LiDAR along unseen driving trajectories without external multi-pass data, we present LiDAR-EVS, a lightweight framework for robust extrapolated-view LiDAR simulation in autonomous driving. Designed to be plug-and-play, LiDAR-EVS readily extends to diverse LiDAR sensors and neural rendering baselines with minimal modification. Our framework comprises two key components: (1) pseudo extrapolated-view point cloud supervision with multi-frame LiDAR fusion, view transformation, occlusion curling, and intensity adjustment; (2) spatially-constrained dropout regularization that promotes robustness to diverse trajectory variations encountered in real-world driving. Extensive experiments demonstrate that LiDAR-EVS achieves SOTA performance on extrapolated-view LiDAR synthesis across three datasets, making it a promising tool for data-driven simulation, closed-loop evaluation, and synthetic data generation in autonomous driving systems. --- ### Online Learning for Supervisory Switching Control Authors: Haoyuan Sun, Ali Jadbabaie Published: 2026-03-16 Categories: math.OC, cs.LG, eess.SY arXiv: https://arxiv.org/abs/2603.14762v4 We study supervisory switching control for partially-observed linear dynamical systems. The objective is to identify and deploy a suitable controller for the unknown system by periodically selecting among a collection of $N$ candidate controllers, some of which may destabilize the underlying system. While classical estimator-based supervisory control guarantees asymptotic stability, it lacks quantitative finite-time performance bounds. Conversely, current non-asymptotic methods in both online learning and system identification require restrictive assumptions that are incompatible in a control setting, such as system stability, which preclude testing potentially unstable controllers. To bridge this gap, we propose a novel, non-asymptotic analysis of supervisory control that adapts multi-armed bandit algorithms to a control-theoretic setting. The proposed data-driven algorithm evaluates candidate controllers via scoring criteria that leverage system observability to isolate the effects of state history, enabling both detection of destabilizing controllers and accurate system identification. We present two algorithmic variants with dimension-free, finite-time guarantees, where each identifies the matching controller in $O(N \log^2 N)$ steps, while simultaneously achieving finite $L_2$-gain with respect to system disturbances. --- ### BrainBench: Exposing the Commonsense Reasoning Gap in Large Language Models Authors: Yuzhe Tang Published: 2026-03-16 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.14761v1 Large language models (LLMs) achieve impressive scores on standard benchmarks yet routinely fail questions that any human would answer correctly in seconds. We introduce BrainBench, a benchmark of 100 brainteaser questions spanning 20 carefully designed categories, each targeting a specific commonsense reasoning failure mode in LLMs. Categories range from implicit physical constraints ("Should I walk or drive my rental car to the return lot?") to semantic scope tricks and default assumption hijacks. We evaluate eight frontier models -- four from the Claude family and four from the GPT family -- using a zero-shot protocol with 10 independent runs per question. The best model, Claude Opus 4.6 with extended thinking, achieves only 80.3% accuracy; the worst, GPT-4o, scores 39.7%. Even top-performing models exhibit a 6-16 percentage-point gap between accuracy and consistency, revealing stochastic reasoning. Cross-lingual evaluation in Chinese shows most models degrade by 2-8 percentage points, confirming that these failures reflect reasoning deficits rather than language-specific artifacts. BrainBench provides a fine-grained diagnostic tool for identifying where and why LLMs substitute surface heuristics for genuine commonsense reasoning. --- ### Towards Privacy-Preserving Machine Translation at the Inference Stage: A New Task and Benchmark Authors: Wei Shao, Lemao Liu, Yinqiao Li, Guoping Huang, Shuming Shi, Linqi Song Published: 2026-03-16 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.14756v1 Current online translation services require sending user text to cloud servers, posing a risk of privacy leakage when the text contains sensitive information. This risk hinders the application of online translation services in privacy-sensitive scenarios. One way to mitigate this risk for online translation services is introducing privacy protection mechanisms targeting the inference stage of translation models. However, compared to subfields of NLP like text classification and summarization, the machine translation research community has limited exploration of privacy protection during the inference stage. There is no clearly defined privacy protection task for the inference stage, dedicated evaluation datasets and metrics, and reference benchmark methods. The absence of these elements has seriously constrained researchers' in-depth exploration of this direction. To bridge this gap, this paper proposes a novel "Privacy-Preserving Machine Translation" (PPMT) task, aiming to protect the private information in text during the model inference stage. For this task, we constructed three benchmark test datasets, designed corresponding evaluation metrics, and proposed a series of benchmark methods as a starting point for this task. The definition of privacy is complex and diverse. Considering that named entities often contain a large amount of personal privacy and commercial secrets, we have focused our research on protecting only the named entity's privacy in the text. We expect this research work will provide a new perspective and a solid foundation for the privacy protection problem in machine translation. --- ### Learning Constituent Headedness Authors: Zeyao Qi, Yige Chen, KyungTae Lim, Haihua Pan, Jungyeul Park Published: 2026-03-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.14755v1 Headedness is widely used as an organizing device in syntactic analysis, yet constituency treebanks rarely encode it explicitly and most processing pipelines recover it procedurally via percolation rules. We treat this notion of constituent headedness as an explicit representational layer and learn it as a supervised prediction task over aligned constituency and dependency annotations, inducing supervision by defining each constituent head as the dependency span head. On aligned English and Chinese data, the resulting models achieve near-ceiling intrinsic accuracy and substantially outperform Collins-style rule-based percolation. Predicted heads yield comparable parsing accuracy under head-driven binarization, consistent with the induced binary training targets being largely equivalent across head choices, while increasing the fidelity of deterministic constituency-to-dependency conversion and transferring across resources and languages under simple label-mapping interfaces. --- ### Face-Guided Sentiment Boundary Enhancement for Weakly-Supervised Temporal Sentiment Localization Authors: Cailing Han, Zhangbin Li, Jinxing Zhou, Wei Qian, Jingjing Hu, Yanghao Zhou, Zhangling Duan, Dan Guo Published: 2026-03-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.14750v1 Point-level weakly-supervised temporal sentiment localization (P-WTSL) aims to detect sentiment-relevant segments in untrimmed multimodal videos using timestamp sentiment annotations, which greatly reduces the costly frame-level labeling. To further tackle the challenges of imprecise sentiment boundaries in P-WTSL, we propose the Face-guided Sentiment Boundary Enhancement Network (\textbf{FSENet}), a unified framework that leverages fine-grained facial features to guide sentiment localization. Specifically, our approach \textit{first} introduces the Face-guided Sentiment Discovery (FSD) module, which integrates facial features into multimodal interaction via dual-branch modeling for effective sentiment stimuli clues; We \textit{then} propose the Point-aware Sentiment Semantics Contrast (PSSC) strategy to discriminate sentiment semantics of candidate points (frame-level) near annotation points via contrastive learning, thereby enhancing the model's ability to recognize sentiment boundaries. At \textit{last}, we design the Boundary-aware Sentiment Pseudo-label Generation (BSPG) approach to convert sparse point annotations into temporally smooth supervisory pseudo-labels. Extensive experiments and visualizations on the benchmark demonstrate the effectiveness of our framework, achieving state-of-the-art performance under full supervision, video-level, and point-level weak supervision, thereby showcasing the strong generalization ability of our FSENet across different annotation settings. --- ### CAMD: Coverage-Aware Multimodal Decoding for Efficient Reasoning of Multimodal Large Language Models Authors: Huijie Guo, Jingyao Wang, Lingyu Si, Jiahuan Zhou, Changwen Zheng, Wenwen Qiang Published: 2026-03-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.14745v1 Recent advances in Multimodal Large Language Models (MLLMs) have shown impressive reasoning capabilities across vision-language tasks, yet still face the challenge of compute-difficulty mismatch. Through empirical analyses, we identify that existing decoding methods may waste compute on easy cases while underserving hard ones, affecting both model effectiveness and efficiency. To address this issue, we first develop a theoretical framework that links sampling coverage, instance difficulty, and residual risk. Our analysis reveals that multimodal reasoning exhibits a heavy-tailed difficulty distribution; a small subset of hard or ambiguous samples dominates the residual failure probability. Based on this insight, we propose Coverage-Aware Multimodal Decoding (CAMD), an adaptive inference mechanism that dynamically allocates computation according to estimated uncertainty. CAMD integrates evidence-weighted scoring, posterior coverage estimation, and sequential Bayesian updating to balance efficiency and reliability under a limited token budget. Experiments on various benchmark datasets and baselines demonstrate the effectiveness and advantages of our approach. --- ### PHAC: Promptable Human Amodal Completion Authors: Seung Young Noh, Ju Yong Chang Published: 2026-03-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.14741v1 Conditional image generation methods are increasingly used in human-centric applications, yet existing human amodal completion (HAC) models offer users limited control over the completed content. Given an occluded person image, they hallucinate invisible regions while preserving visible ones, but cannot reliably incorporate user-specified constraints such as a desired pose or spatial extent. As a result, users often resort to repeatedly sampling the model until they obtain a satisfactory output. Pose-guided person image synthesis (PGPIS) methods allow explicit pose conditioning, but frequently fail to preserve the instance-specific visible appearance and tend to be biased toward the training distribution, even when built on strong diffusion model priors. To address these limitations, we introduce promptable human amodal completion (PHAC), a new task that completes occluded human images while satisfying both visible appearance constraints and multiple user prompts. Users provide simple point-based prompts, such as additional joints for the target pose or bounding boxes for desired regions; these prompts are encoded using ControlNet modules specialized for each prompt type. These modules inject the prompt signals into a pre-trained diffusion model, and we fine-tune only the cross-attention blocks to obtain strong prompt alignment without degrading the underlying generative prior. To further preserve visible content, we propose an inpainting-based refinement module that starts from a slightly noised coarse completion, faithfully preserves the visible regions, and ensures seamless blending at occlusion boundaries. Extensive experiments on the HAC and PGPIS benchmarks show that our approach yields more physically plausible and higher-quality completions, while significantly improving prompt alignment compared with existing amodal completion and pose-guided synthesis methods. --- ### TrajMamba: An Ego-Motion-Guided Mamba Model for Pedestrian Trajectory Prediction from an Egocentric Perspective Authors: Yusheng Peng, Gaofeng Zhang, Liping Zheng Published: 2026-03-16 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.14739v1 Future trajectory prediction of a tracked pedestrian from an egocentric perspective is a key task in areas such as autonomous driving and robot navigation. The challenge of this task lies in the complex dynamic relative motion between the ego-camera and the tracked pedestrian. To address this challenge, we propose an ego-motion-guided trajectory prediction network based on the Mamba model. Firstly, two Mamba models are used as encoders to extract pedestrian motion and ego-motion features from pedestrian movement and ego-vehicle movement, respectively. Then, an ego-motion guided Mamba decoder that explicitly models the relative motion between the pedestrian and the vehicle by integrating pedestrian motion features as historical context with ego-motion features as guiding cues to capture decoded features. Finally, the future trajectory is generated from the decoded features corresponding to the future timestamps. Extensive experiments demonstrate the effectiveness of the proposed model, which achieves state-of-the-art performance on the PIE and JAAD datasets. --- ### Efficient Event Camera Volume System Authors: Juan Camilo Soto, Ian Noronha, Saru Bharti, Upinder Kaur Published: 2026-03-16 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2603.14738v1 Event cameras promise low latency and high dynamic range, yet their sparse output challenges integration into standard robotic pipelines. We introduce \nameframew (Efficient Event Camera Volume System), a novel framework that models event streams as continuous-time Dirac impulse trains, enabling artifact-free compression through direct transform evaluation at event timestamps. Our key innovation combines density-driven adaptive selection among DCT, DTFT, and DWT transforms with transform-specific coefficient pruning strategies tailored to each domain's sparsity characteristics. The framework eliminates temporal binning artifacts while automatically adapting compression strategies based on real-time event density analysis. On EHPT-XC and MVSEC datasets, our framework achieves superior reconstruction fidelity with DTFT delivering the lowest earth mover distance. In downstream segmentation tasks, EECVS demonstrates robust generalization. Notably, our approach demonstrates exceptional cross-dataset generalization: when evaluated with EventSAM segmentation, EECVS achieves mean IoU 0.87 on MVSEC versus 0.44 for voxel grids at 24 channels, while remaining competitive on EHPT-XC. Our ROS2 implementation provides real-time deployment with DCT processing achieving 1.5 ms latency and 2.7X higher throughput than alternative transforms, establishing the first adaptive event compression framework that maintains both computational efficiency and superior generalization across diverse robotic scenarios. --- ### Gauge-Equivariant Intrinsic Neural Operators for Geometry-Consistent Learning of Elliptic PDE Maps Authors: Pengcheng Cheng Published: 2026-03-16 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.14734v1 Learning solution operators of partial differential equations (PDEs) from data has emerged as a promising route to fast surrogate models in multi-query scientific workflows. However, for geometric PDEs whose inputs and outputs transform under changes of local frame (gauge), many existing operator-learning architectures remain representation-dependent, brittle under metric perturbations, and sensitive to discretization changes. We propose Gauge-Equivariant Intrinsic Neural Operators (GINO), a class of neural operators that parameterize elliptic solution maps primarily through intrinsic spectral multipliers acting on geometry-dependent spectra, coupled with gauge-equivariant nonlinearities. This design decouples geometry from learnable functional dependence and enforces consistency under frame transformations. We validate GINO on controlled problems on the flat torus ($\mathbb{T}^2$), where ground-truth resolvent operators and regularized Helmholtz--Hodge decompositions admit closed-form Fourier representations, enabling theory-aligned diagnostics. Across experiments E1--E6, GINO achieves low operator-approximation error, near machine-precision gauge equivariance, robustness to structured metric perturbations, strong cross-resolution generalization with small commutation error under restriction/prolongation, and structure-preserving performance on a regularized exact/coexact decomposition task. Ablations further link the smoothness of the learned spectral multiplier to stability under geometric perturbations. These results suggest that enforcing intrinsic structure and gauge equivariance yields operator surrogates that are more geometry-consistent and discretization-robust for elliptic PDEs on form-valued fields. --- ### A Skill-augmented Agentic Framework and Benchmark for Multi-Video Understanding Authors: Yue Zhang, Liqiang Jing, Jia Li, Yapeng Tian, Xinya Du, Yunhui Guo, Vibhav Gogate Published: 2026-03-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.14733v1 Multimodal Large Language Models have achieved strong performance in single-video understanding, yet their ability to reason across multiple videos remains limited. Existing approaches typically concatenate multiple videos into a single input and perform direct inference, which introduces training-inference mismatch, information loss from frame compression, and a lack of explicit cross-video coordination. Meanwhile, current multi-video benchmarks primarily emphasize event-level comparison, leaving identity-level matching, fine-grained discrimination, and structured multi-step reasoning underexplored. To address these gaps, we introduce MVX-Bench, a Multi-Video Cross-Dimension Benchmark that reformulates 11 classical computer vision tasks into a unified multi-video question-answering framework, comprising 1,442 questions over 4,255 videos from diverse real-world datasets. We further propose SAMA, a Skill-Augmented Agentic Framework for Multi-Video Understanding, which integrates visual tools, task-specific skills, and a conflict-aware verification mechanism to enable iterative and structured reasoning. Experimental results show that SAMA outperforms strong open-source baselines and GPT on MVX-Bench, and ablations validate the effectiveness of skill design and conflict resolution. --- ### LLM-as-a-judge validity is strongly task-dependent across physics assessment formats Authors: Will Yeadon, Tom Hardy, Paul Mackay, Elise Agra Published: 2026-03-16 Categories: physics.ed-ph, cs.CL arXiv: https://arxiv.org/abs/2603.14732v3 As large language models (LLMs) are increasingly considered for automated assessment and feedback, understanding when LLM marking is valid is essential. We evaluate LLM-as-a-judge marking across four settings spanning three assessment formats - structured questions, written essays, and scientific plots - comparing GPT-5.2, Grok 4.1, Claude Opus 4.5, DeepSeek-V3.2, Gemini 3 Pro, and committee aggregations against human markers under blind, solution-provided, false-solution, and anchored conditions. We distinguish absolute accuracy from rank-order agreement, since a marking system can match the distribution of human marks while failing to order responses by quality. Across task types, performance is sharply task-dependent. For blind university exam questions ($n=771$) and secondary and university structured questions ($n=1151$), models show robust rank-order agreement with human markers (Spearman $ρ> 0.6$), with official solutions reducing error and strengthening agreement. False solutions degrade absolute accuracy, showing that models defer to provided references, but leave rank-ordering intact. Essay marking behaves fundamentally differently. Across $n=55$ scripts, each containing five essays ($n=275$ essays total), blind AI marking is harsher and more variable than human marking and adding marking guidance does not improve rank-order agreement. Anchored exemplars shift the AI mean close to the human mean and compress variance below the human standard deviation, but rank-order agreement remains near-zero. For code-based plot elements ($n=1400$), models achieve high rank-order agreement ($ρ> 0.83$) with near-linear calibration. LLM marking validity depended strongly on the assessment task, and this held for every contemporary model tested. The results also show that the reliability of the human benchmark constrains the claims that can be made about AI-human agreement. --- ### LLM-as-a-judge validity in physics assessment depends more on the task than the model Authors: Will Yeadon, Tom Hardy, Paul Mackay, Elise Agra Published: 2026-03-16 Categories: physics.ed-ph, cs.CL arXiv: https://arxiv.org/abs/2603.14732v2 As large language models (LLMs) are increasingly considered for automated assessment and feedback, understanding when LLM marking is valid is essential. We evaluate LLM-as-a-judge marking across three physics assessment formats - structured questions, written essays, and scientific plots - comparing GPT-5.2, Grok 4.1, Claude Opus 4.5, DeepSeek-V3.2, Gemini Pro 3, and committee aggregations against human markers under blind, solution-provided, false-solution, and anchored conditions. We distinguish absolute accuracy from rank-order agreement, since a marking system can match the distribution of human marks while failing to order responses by quality. Across task types, performance is sharply task-dependent. For blind university exam questions ($n=771$) and secondary and university structured questions ($n=1151$), models show robust rank-order agreement with human markers (Spearman $ρ> 0.6$), with official solutions reducing error and strengthening agreement. False solutions degrade absolute accuracy, showing that models defer to provided references, but leave rank-ordering intact. Essay marking behaves fundamentally differently. Across $n=55$ scripts ($n=275$ essays), blind AI marking is harsher and more variable than human marking and adding a mark scheme does not improve rank-order agreement. Anchored exemplars shift the AI mean close to the human mean and compress variance below the human standard deviation, but rank-order agreement remains near-zero. For code-based plot elements ($n=1400$), models achieve high rank-order agreement ($ρ> 0.84$) with near-linear calibration. Across all task types, validity tracks the structure of the assessment task - the extent to which marks can be mapped to explicit, observable grading features - and the reliability of the human benchmark, rather than raw model capability. --- ### GNNVerifier: Graph-based Verifier for LLM Task Planning Authors: Yu Hao, Qiuyu Wang, Cheng Yang, Yawen Li, Zhiqiang Zhang, Chuan Shi Published: 2026-03-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.14730v2 Large language models (LLMs) facilitate the development of autonomous agents. As a core component of such agents, task planning aims to decompose complex natural language requests into concrete, solvable sub-tasks. Since LLM-generated plans are frequently prone to hallucinations and sensitive to long-context prom-pts, recent research has introduced plan verifiers to identify and correct potential flaws. However, most existing approaches still rely on an LLM as the verifier via additional prompting for plan review or self-reflection. LLM-based verifiers can be misled by plausible narration and struggle to detect failures caused by structural relations across steps, such as type mismatches, missing intermediates, or broken dependencies. To address these limitations, we propose a graph-based verifier for LLM task planning. Specifically, the proposed method has four major components: Firstly, we represent a plan as a directed graph with enriched attributes, where nodes denote sub-tasks and edges encode execution order and dependency constraints. Secondly, a graph neural network (GNN) then performs structural evaluation and diagnosis, producing a graph-level plausibility score for plan acceptance as well as node/edge-level risk scores to localize erroneous regions. Thirdly, we construct controllable perturbations from ground truth plan graphs, and automatically generate training data with fine-grained annotations. Finally, guided by the feedback from our GNN verifier, we enable an LLM to conduct local edits (e.g., tool replacement or insertion) to correct the plan when the graph-level score is insufficient. Extensive experiments across diverse datasets, backbone LLMs, and planners demonstrate that our GNNVerifier achieves significant gains in improving plan quality. Our data and code is available at https://github.com/BUPT-GAMMA/GNNVerifier. --- ### DeFRiS: Silo-Cooperative IoT Applications Scheduling via Decentralized Federated Reinforcement Learning Authors: Zhiyu Wang, Mohammad Goudarzi, Mingming Gong, Rajkumar Buyya Published: 2026-03-16 Categories: cs.LG, cs.DC arXiv: https://arxiv.org/abs/2603.14729v1 Next-generation IoT applications increasingly span across autonomous administrative entities, necessitating silo-cooperative scheduling to leverage diverse computational resources while preserving data privacy. However, realizing efficient cooperation faces significant challenges arising from infrastructure heterogeneity, Non-IID workload shifts, and the inherent risks of adversarial environments. Existing approaches, relying predominantly on centralized coordination or independent learning, fail to address the incompatibility of state-action spaces across heterogeneous silos and lack robustness against malicious attacks. This paper proposes DeFRiS, a Decentralized Federated Reinforcement Learning framework for robust and scalable Silo-cooperative IoT application scheduling. DeFRiS integrates three synergistic innovations: (i) an action-space-agnostic policy utilizing candidate resource scoring to enable seamless knowledge transfer across heterogeneous silos; (ii) a silo-optimized local learning mechanism combining Generalized Advantage Estimation (GAE) with clipped policy updates to resolve sparse delayed reward challenges; and (iii) a Dual-Track Non-IID robust decentralized aggregation protocol leveraging gradient fingerprints for similarity-aware knowledge transfer and anomaly detection, and gradient tracking for optimization momentum. Extensive experiments on a distributed testbed with 20 heterogeneous silos and realistic IoT workloads demonstrate that DeFRiS significantly outperforms state-of-the-art baselines, reducing average response time by 6.4% and energy consumption by 7.2%, while lowering tail latency risk (CVaR$_{0.95}$) by 10.4% and achieving near-zero deadline violations. Furthermore, DeFRiS achieves over 3 times better performance retention as the system scales and over 8 times better stability in adversarial environments compared to the best-performing baseline. --- ### Automated Diabetic Screening via Anterior Segment Ocular Imaging: A Deep Learning and Explainable AI Approach Authors: Hasaan Maqsood, Saif Ur Rehman Khan, Sebastian Vollmer, Andreas Dengel, Muhammad Nabeel Asim Published: 2026-03-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.14727v1 Diabetic retinopathy screening traditionally relies on fundus photography, requiring specialized equipment and expertise often unavailable in primary care and resource limited settings. We developed and validated a deep learning (DL) system for automated diabetic classification using anterior segment ocular imaging a readily accessible alternative utilizing standard photography equipment. The system leverages visible biomarkers in the iris, sclera, and conjunctiva that correlate with systemic diabetic status. We systematically evaluated five contemporary architectures (EfficientNet-V2-S with self-supervised learning (SSL), Vision Transformer, Swin Transformer, ConvNeXt-Base, and ResNet-50) on 2,640 clinically annotated anterior segment images spanning Normal, Controlled Diabetic, and Uncontrolled Diabetic categories. A tailored preprocessing pipeline combining specular reflection mitigation and contrast limited adaptive histogram equalization (CLAHE) was implemented to enhance subtle vascular and textural patterns critical for classification. SSL using SimCLR on domain specific ocular images substantially improved model performance.EfficientNet-V2-S with SSL achieved optimal performance with an F1-score of 98.21%, precision of 97.90%, and recall of 98.55% a substantial improvement over ImageNet only initialization (94.63% F1). Notably, the model attained near perfect precision (100%) for Normal classification, critical for minimizing unnecessary clinical referrals. --- ### Enhancing Hands in 3D Whole-Body Pose Estimation with Conditional Hands Modulator Authors: Gyeongsik Moon Published: 2026-03-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.14726v1 Accurately recovering hand poses within the body context remains a major challenge in 3D whole-body pose estimation. This difficulty arises from a fundamental supervision gap: whole-body pose estimators are trained on full-body datasets with limited hand diversity, while hand-only estimators, trained on hand-centric datasets, excel at detailed finger articulation but lack global body awareness. To address this, we propose Hand4Whole++, a modular framework that leverages the strengths of both pre-trained whole-body and hand pose estimators. We introduce CHAM (Conditional Hands Modulator), a lightweight module that modulates the whole-body feature stream using hand-specific features extracted from a pre-trained hand pose estimator. This modulation enables the whole-body model to predict wrist orientations that are both accurate and coherent with the upper-body kinematic structure, without retraining the full-body model. In parallel, we directly incorporate finger articulations and hand shapes predicted by the hand pose estimator, aligning them to the full-body mesh via differentiable rigid alignment. This design allows Hand4Whole++ to combine globally consistent body reasoning with fine-grained hand detail. Extensive experiments demonstrate that Hand4Whole++ substantially improves hand accuracy and enhances overall full-body pose quality. --- ### GameUIAgent: An LLM-Powered Framework for Automated Game UI Design with Structured Intermediate Representation Authors: Wei Zeng, Fengwei An, Zhen Liu, Jian Zhao Published: 2026-03-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.14724v1 Game UI design requires consistent visual assets across rarity tiers yet remains a predominantly manual process. We present GameUIAgent, an LLM-powered agentic framework that translates natural language descriptions into editable Figma designs via a Design Spec JSON intermediate representation. A six-stage neuro-symbolic pipeline combines LLM generation, deterministic post-processing, and a Vision-Language Model (VLM)-guided Reflection Controller (RC) for iterative self-correction with guaranteed non-regressive quality. Evaluated across 110 test cases, three LLMs, and three UI templates, cross-model analysis establishes a game-domain failure taxonomy (rarity-dependent degradation; visual emptiness) and uncovers two key empirical findings. A Quality Ceiling Effect (Pearson r=-0.96, p<0.01) suggests that RC improvement is bounded by headroom below a quality threshold -- a visual-domain counterpart to test-time compute scaling laws. A Rendering-Evaluation Fidelity Principle reveals that partial rendering enhancements paradoxically degrade VLM evaluation by amplifying structural defects. Together, these results establish foundational principles for LLM-driven visual generation agents in game production. ---