# Research Papers — 2026-03 · bundle page 178 of 243

> Full-text markdown of papers #8851–8900 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/178
[← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/177.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-03/page/179.md)

### HiAR: Efficient Autoregressive Long Video Generation via Hierarchical Denoising

Authors: Kai Zou, Dian Zheng, Hongbo Liu, Tiankai Hang, Bin Liu, Nenghai Yu
Published: 2026-03-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.08703v1

Autoregressive (AR) diffusion offers a promising framework for generating videos of theoretically infinite length. However, a major challenge is maintaining temporal continuity while preventing the progressive quality degradation caused by error accumulation. To ensure continuity, existing methods typically condition on highly denoised contexts; yet, this practice propagates prediction errors with high certainty, thereby exacerbating degradation. In this paper, we argue that a highly clean context is unnecessary. Drawing inspiration from bidirectional diffusion models, which denoise frames at a shared noise level while maintaining coherence, we propose that conditioning on context at the same noise level as the current block provides sufficient signal for temporal consistency while effectively mitigating error propagation. Building on this insight, we propose HiAR, a hierarchical denoising framework that reverses the conventional generation order: instead of completing each block sequentially, it performs causal generation across all blocks at every denoising step, so that each block is always conditioned on context at the same noise level. This hierarchy naturally admits pipelined parallel inference, yielding a 1.8 wall-clock speedup in our 4-step setting. We further observe that self-rollout distillation under this paradigm amplifies a low-motion shortcut inherent to the mode-seeking reverse-KL objective. To counteract this, we introduce a forward-KL regulariser in bidirectional-attention mode, which preserves motion diversity for causal inference without interfering with the distillation loss. On VBench (20s generation), HiAR achieves the best overall score and the lowest temporal drift among all compared methods.

---

### A Multi-Objective Optimization Approach for Sustainable AI-Driven Entrepreneurship in Resilient Economies

Authors: Anas ALsobeh, Raneem Alkurdi
Published: 2026-03-09
Categories: cs.AI
arXiv: https://arxiv.org/abs/2603.08692v1

The rapid advancement of artificial intelligence (AI) technologies presents both unprecedented opportunities and significant challenges for sustainable economic development. While AI offers transformative potential for addressing environmental challenges and enhancing economic resilience, its deployment often involves substantial energy consumption and environmental costs. This research introduces the EcoAI-Resilience framework, a multi-objective optimization approach designed to maximize the sustainability benefits of AI deployment while minimizing environmental costs and enhancing economic resilience. The framework addresses three critical objectives through mathematical optimization: sustainability impact maximization, economic resilience enhancement, and environmental cost minimization. The methodology integrates diverse data sources, including energy consumption metrics, sustainability indicators, economic performance data, and entrepreneurship outcomes across 53 countries and 14 sectors from 2015-2024. Our experimental validation demonstrates exceptional performance with R scores exceeding 0.99 across all model components, significantly outperforming baseline methods, including Linear Regression (R = 0.943), Random Forest (R = 0.957), and Gradient Boosting (R = 0.989). The framework successfully identifies optimal AI deployment strategies featuring 100\% renewable energy integration, 80% efficiency improvement targets, and optimal investment levels of $202.48 per capita. Key findings reveal strong correlations between economic complexity and resilience (r = 0.82), renewable energy adoption and sustainability outcomes (r = 0.71), and demonstrate significant temporal improvements in AI readiness (+1.12 points/year) and renewable energy adoption (+0.67 year) globally.

---

### Split Federated Learning Architectures for High-Accuracy and Low-Delay Model Training

Authors: Yiannis Papageorgiou, Yannis Thomas, Ramin Khalili, Iordanis Koutsopoulos
Published: 2026-03-09
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.08687v1

Can we find a network architecture for ML model training so as to optimize training loss (and thus, accuracy) in Split Federated Learning (SFL)? And can this architecture also reduce training delay and communication overhead? While accuracy is not influenced by how we split the model in ordinary, state-of-the-art SFL, in this work we answer the questions above in the affirmative. Recent Hierarchical SFL (HSFL) architectures adopt a three-tier training structure consisting of clients, (local) aggregators, and a central server. In this architecture, the model is partitioned at two partitioning layers into three sub-models, which are executed across the three tiers. Despite their merits, HSFL architectures overlook the impact of the partitioning layers and client-to-aggregator assignments on accuracy, delay, and overhead. This work explicitly captures the impact of the partitioning layers and client-to-aggregator assignments on accuracy, delay and overhead by formulating a joint optimization problem. We prove that the problem is NP-hard and propose the first accuracy-aware heuristic algorithm that explicitly accounts for model accuracy, while remaining delay-efficient. Simulation results on public datasets show that our approach can improve accuracy by 3%, while reducing delay by 20% and overhead by 50%, compared to state-of-the-art SFL and HSFL schemes.

---

### Benchmarking Language Modeling for Lossless Compression of Full-Fidelity Audio

Authors: Phillip Long, Zachary Novack, Chris Donahue
Published: 2026-03-09
Categories: cs.SD, cs.AI, cs.LG, eess.AS
arXiv: https://arxiv.org/abs/2603.08683v2

Autoregressive "language" models (LMs) trained on raw waveforms can be repurposed for lossless audio compression, but prior work is limited to 8-bit audio, leaving open whether such approaches work for practical settings (16/24-bit) and can compete with existing codecs. We benchmark LM-based compression on full-fidelity audio across diverse domains (music, speech, bioacoustics), sampling rates (16kHz-48kHz), and bit depths (8, 16, 24-bit). Standard sample-level tokenization becomes intractable at higher bit depths due to vocabulary size (65K for 16-bit; 16.7M for 24-bit). We propose Trilobyte, a byte-level tokenization schema for full resolution audio, improving vocabulary scaling from $O(2^{b})$ to $O(1)$ and enabling the first tractable 24-bit LM-based lossless compression. While LMs consistently outperform FLAC and yield state-of-the-art compression at 8-bit and 16-bit, we observe that compression gains become more modest as bit depth increases beyond 8-bit.

---

### Structural Causal Bottleneck Models

Authors: Simon Bing, Jonas Wahl, Jakob Runge
Published: 2026-03-09
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2603.08682v2

We introduce structural causal bottleneck models (SCBMs), a novel class of structural causal models. At the core of SCBMs lies the assumption that causal effects between high-dimensional variables only depend on low-dimensional summary statistics, or bottlenecks, of the causes. SCBMs provide a flexible framework for task-specific dimension reduction while being estimable via standard, simple learning algorithms in practice. We analyse identifiability in SCBMs, connect them to information bottlenecks in the sense of Tishby & Zaslavsky (2015), and illustrate how to estimate them experimentally. We also demonstrate the benefit of bottlenecks for effect estimation in low-sample transfer learning settings. We argue that SCBMs provide an alternative to existing causal dimension reduction frameworks like causal representation learning or causal abstraction learning.

---

### ER-Pose: Rethinking Keypoint-Driven Representation Learning for Real-Time Human Pose Estimation

Authors: Nanjun Li, Pinqi Cheng, Zean Liu, Minghe Tian, Xuanyin Wang
Published: 2026-03-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.08681v1

Single-stage multi-person pose estimation aims to jointly perform human localization and keypoint prediction within a unified framework, offering advantages in inference efficiency and architectural simplicity. Consequently, multi-scale real-time detection architectures, such as YOLO-like models, are widely adopted for real-time pose estimation. However, these approaches typically inherit a box-driven modeling paradigm from object detection, in which pose estimation is implicitly constrained by bounding-box supervision during training. This formulation introduces biases in sample assignment and feature representation, resulting in task misalignment and ultimately limiting pose estimation accuracy. In this work, we revisit box-driven single-stage pose estimation from a keypoint-driven perspective and identify semantic conflicts among parallel objectives as a key source of performance degradation. To address this issue, we propose a keypoint-driven learning paradigm that elevates pose estimation to a primary prediction objective. Specifically, we remove bounding-box prediction and redesign the prediction head to better accommodate the high-dimensional structured representations for pose estimation. We further introduce a keypoint-driven dynamic sample assignment strategy to align training objectives with pose evaluation metrics, enabling dense supervision during training and efficient NMS-free inference. In addition, we propose a smooth OKS-based loss function to stabilize optimization in regression-based pose estimation. Based on these designs, we develop a single-stage multi-person pose estimation framework, termed ER-Pose. On MS COCO and CrowdPose, ER-Pose-n achieves AP improvements of 3.2/6.7 without pre-training and 7.4/4.9 with pre-training respectively compared with the baseline YOLO-Pose. These improvements are achieved with fewer parameters and higher inference efficiency.

---

### A New Lower Bound for the Random Offerer Mechanism in Bilateral Trade using AI-Guided Evolutionary Search

Authors: Yang Cai, Vineet Gupta, Zun Li, Aranyak Mehta
Published: 2026-03-09
Categories: cs.LG, cs.AI, cs.GT, econ.TH
arXiv: https://arxiv.org/abs/2603.08679v1

The celebrated Myerson--Satterthwaite theorem shows that in bilateral trade, no mechanism can be simultaneously fully efficient, Bayesian incentive compatible (BIC), and budget balanced (BB). This naturally raises the question of how closely the gains from trade (GFT) achievable by a BIC and BB mechanism can approximate the first-best (fully efficient) benchmark. The optimal BIC and BB mechanism is typically complex and highly distribution-dependent, making it difficult to characterize directly. Consequently, much of the literature analyzes simpler mechanisms such as the Random-Offerer (RO) mechanism and establishes constant-factor guarantees relative to the first-best GFT. An important open question concerns the worst-case performance of the RO mechanism relative to first-best (FB) efficiency. While it was originally hypothesized that the approximation ratio $\frac{\text{GFT}_{\text{FB}}}{\text{GFT}_{\text{RO}}}$ is bounded by $2$, recent work provided counterexamples to this conjecture: Cai et al. proved that the ratio can be strictly larger than $2$, and Babaioff et al. exhibited an explicit example with ratio approximately $2.02$. In this work, we employ AlphaEvolve, an AI-guided evolutionary search framework, to explore the space of value distributions. We identify a new worst-case instance that yields an improved lower bound of $\frac{\text{GFT}_{\text{FB}}}{\text{GFT}_{\text{RO}}} \ge \textbf{2.0749}$. This establishes a new lower bound on the worst-case performance of the Random-Offerer mechanism, demonstrating a wider efficiency gap than previously known.

---

### Momentum SVGD-EM for Accelerated Maximum Marginal Likelihood Estimation

Authors: Adam Rozzio, Rafael Athanasiades, O. Deniz Akyildiz
Published: 2026-03-09
Categories: stat.ML, cs.LG, stat.CO
arXiv: https://arxiv.org/abs/2603.08676v1

Maximum marginal likelihood estimation (MMLE) can be formulated as the optimization of a free energy functional. From this viewpoint, the Expectation-Maximisation (EM) algorithm admits a natural interpretation as a coordinate descent method over the joint space of model parameters and probability measures. Recently, a significant body of work has adopted this perspective, leading to interacting particle algorithms for MMLE. In this paper, we propose an accelerated version of one such procedure, based on Stein variational gradient descent (SVGD), by introducing Nesterov acceleration in both the parameter updates and in the space of probability measures. The resulting method, termed Momentum SVGD-EM, consistently accelerates convergence in terms of required iterations across various tasks of increasing difficulty, demonstrating effectiveness in both low- and high-dimensional settings.

---

### Talking Together: Synthesizing Co-Located 3D Conversations from Audio

Authors: Mengyi Shan, Shouchieh Chang, Ziqian Bai, Shichen Liu, Yinda Zhang, Luchuan Song, Rohit Pandey, Sean Fanello, Zeng Huang
Published: 2026-03-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.08674v1

We tackle the challenging task of generating complete 3D facial animations for two interacting, co-located participants from a mixed audio stream. While existing methods often produce disembodied "talking heads" akin to a video conference call, our work is the first to explicitly model the dynamic 3D spatial relationship -- including relative position, orientation, and mutual gaze -- that is crucial for realistic in-person dialogues. Our system synthesizes the full performance of both individuals, including precise lip-sync, and uniquely allows their relative head poses to be controlled via textual descriptions. To achieve this, we propose a dual-stream architecture where each stream is responsible for one participant's output. We employ speaker's role embeddings and inter-speaker cross-attention mechanisms designed to disentangle the mixed audio and model the interaction. Furthermore, we introduce a novel eye gaze loss to promote natural, mutual eye contact. To power our data-hungry approach, we introduce a novel pipeline to curate a large-scale conversational dataset consisting of over 2 million dyadic pairs from in-the-wild videos. Our method generates fluid, controllable, and spatially aware dyadic animations suitable for immersive applications in VR and telepresence, significantly outperforming existing baselines in perceived realism and interaction coherence.

---

### Characterization and upgrade of a quantum graph neural network for charged particle tracking

Authors: Matteo Argenton, Laura Cappelli, Concezio Bozzi
Published: 2026-03-09
Categories: quant-ph, cs.LG, hep-ex
arXiv: https://arxiv.org/abs/2603.08667v1

In the forthcoming years the LHC experiments are going to be upgraded to benefit from the substantial increase of the LHC instantaneous luminosity, which will lead to larger, denser events, and, consequently, greater complexity in reconstructing charged particle tracks, motivating frontier research in new technologies. Quantum machine learning models are being investigated as potential new approaches to high energy physics (HEP) tasks. We characterize and upgrade a quantum graph neural network (QGNN) architecture for charged particle track reconstruction on a simulated high luminosity dataset. The model operates on a set of event graphs, each built from the hits generated in tracking detector layers by particles produced in proton collisions, performing a classification of the possible hit connections between adjacent layers. In this approach the QGNN is designed as a hybrid architecture, interleaving classical feedforward networks with parametrized quantum circuits. We characterize the interplay between the classical and quantum components. We report on the principal upgrades to the original design, and present new evidence of improved training behavior, specifically in terms of convergence toward the final trained configuration.

---

### ImprovedGS+: A High-Performance C++/CUDA Re-Implementation Strategy for 3D Gaussian Splatting

Authors: Jordi Muñoz Vicente
Published: 2026-03-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.08661v1

Recent advancements in 3D Gaussian Splatting (3DGS) have shifted the focus toward balancing reconstruction fidelity with computational efficiency. In this work, we propose ImprovedGS+, a high-performance, low-level reinvention of the ImprovedGS strategy, implemented natively within the LichtFeld-Studio framework. By transitioning from high-level Python logic to hardware-optimized C++/CUDA kernels, we achieve a significant reduction in host-device synchronization and training latency. Our implementation introduces a Long-Axis-Split (LAS) CUDA kernel, custom Laplacian-based importance kernels with Non-Maximum Suppression (NMS) for edge scores, and an adaptive Exponential Scale Scheduler. Experimental results on the Mip-NeRF360 dataset demonstrate that ImprovedGS+ establishes a new Pareto-optimal front for scene reconstruction. Our 1M-budget variant outperforms the state-of-the-art MCMC baseline by achieving a 26.8% reduction in training time (saving 17 minutes per session) and utilizing 13.3% fewer Gaussians while maintaining superior visual quality. Furthermore, our full variant demonstrates a 1.28 dB PSNR increase over the ADC baseline with a 38.4% reduction in parametric complexity. These results validate ImprovedGS+ as a scalable, high-speed solution that upholds the core pillars of Speed, Quality, and Usability within the LichtFeld-Studio ecosystem.

---

### How Far Can Unsupervised RLVR Scale LLM Training?

Authors: Bingxiang He, Yuxin Zuo, Zeyuan Liu, Shangziqi Zhao, Zixuan Fu, Junlin Yang, Cheng Qian, Kaiyan Zhang, Yuchen Fan, Ganqu Cui, Xiusi Chen, Youbang Sun et al.
Published: 2026-03-09
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2603.08660v1

Unsupervised reinforcement learning with verifiable rewards (URLVR) offers a pathway to scale LLM training beyond the supervision bottleneck by deriving rewards without ground truth labels. Recent works leverage model intrinsic signals, showing promising early gains, yet their potential and limitations remain unclear. In this work, we revisit URLVR and provide a comprehensive analysis spanning taxonomy, theory and extensive experiments. We first classify URLVR methods into intrinsic versus external based on reward sources, then establish a unified theoretical framework revealing that all intrinsic methods converge toward sharpening the model's initial distribution This sharpening mechanism succeeds when initial confidence aligns with correctness but fails catastrophically when misaligned. Through systematic experiments, we show intrinsic rewards consistently follow a rise-then-fall pattern across methods, with collapse timing determined by model prior rather than engineering choices. Despite these scaling limits, we find intrinsic rewards remain valuable in test-time training on small datasets, and propose Model Collapse Step to measure model prior, serving as a practical indicator for RL trainability. Finally, we explore external reward methods that ground verification in computational asymmetries, showing preliminary evidence they may escape the confidence-correctness ceiling. Our findings chart boundaries for intrinsic URLVR while motivating paths toward scalable alternatives.

---

### CODA: Difficulty-Aware Compute Allocation for Adaptive Reasoning

Authors: Siye Wu, Jian Xie, Yikai Zhang, Yanghua Xiao
Published: 2026-03-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.08659v2

The emergence of large reasoning models demonstrates that scaling inference-time compute significantly enhances performance on complex tasks. However, it often falls into another trap: overthinking simple problems, where repetitive rationales yield minimal accuracy gains at a disproportionately high cost. This motivates adaptive reasoning: dynamically aligning reasoning depth with instance difficulty. In this paper, we study adaptive reasoning from an optimality perspective, formalizing it as a utility maximization problem where tokens are allocated until the marginal accuracy gain falls below the incremental cost. Based on this, we propose CODA (Compute Allocation by Difficulty Awareness), a method that operationalizes this principle by allocating tokens via a policy-internal difficulty signal. Specifically, CODA estimates difficulty via group-based rollouts and maps it to two non-negative gates that modulate a length-dependent shaping term on top of the binary base reward. The easy-side gate penalizes verbosity on simple instances, whereas the hard-side gate encourages more deliberative rollouts on challenging ones. Across model scales and benchmarks, CODA achieves adaptive reasoning without external annotations or user-provided budgets: on easy tasks, CODA reduces token costs by over 60% while maintaining strong accuracy, whereas on hard tasks it incentivizes more deliberative rollouts to maximize performance.

---

### Context-free Self-Conditioned GAN for Trajectory Forecasting

Authors: Tiago Rodrigues de Almeida, Eduardo Gutierrez Maestro, Oscar Martinez Mozos
Published: 2026-03-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.08658v1

In this paper, we present a context-free unsupervised approach based on a self-conditioned GAN to learn different modes from 2D trajectories. Our intuition is that each mode indicates a different behavioral moving pattern in the discriminator's feature space. We apply this approach to the problem of trajectory forecasting. We present three different training settings based on self-conditioned GAN, which produce better forecasters. We test our method in two data sets: human motion and road agents. Experimental results show that our approach outperforms previous context-free methods in the least representative supervised labels while performing well in the remaining labels. In addition, our approach outperforms globally in human motion, while performing well in road agents.

---

### OfficeQA Pro: An Enterprise Benchmark for End-to-End Grounded Reasoning

Authors: Krista Opsahl-Ong, Arnav Singhvi, Jasmine Collins, Ivan Zhou, Cindy Wang, Ashutosh Baheti, Owen Oertell, Jacob Portes, Sam Havens, Erich Elsen, Michael Bendersky, Matei Zaharia et al.
Published: 2026-03-09
Categories: cs.AI, cs.CL, cs.IR
arXiv: https://arxiv.org/abs/2603.08655v1

We introduce OfficeQA Pro, a benchmark for evaluating AI agents on grounded, multi-document reasoning over a large and heterogeneous document corpus. The corpus consists of U.S. Treasury Bulletins spanning nearly 100 years, comprising 89,000 pages and over 26 million numerical values. OfficeQA Pro consists of 133 questions that require precise document parsing, retrieval, and analytical reasoning across both unstructured text and tabular data. Frontier LLMs including Claude Opus 4.6, GPT-5.4, and Gemini 3.1 Pro Preview achieve less than 5% accuracy on OfficeQA Pro when relying on parametric knowledge, and less than 12% with additional access to the web. When provided directly with the document corpus, frontier agents still struggle on over half of questions, scoring 34.1% on average. We find that providing agents with a structured document representation produced by Databricks' ai_parse_document yields a 16.1% average relative performance gain across agents. We conduct additional ablations to study the effects of model selection, table representation, retrieval strategy, and test-time scaling on performance. Despite these improvements, significant headroom remains before agents can be considered reliable at enterprise-grade grounded reasoning.

---

### CoCo: Code as CoT for Text-to-Image Preview and Rare Concept Generation

Authors: Haodong Li, Chunmei Qing, Huanyu Zhang, Dongzhi Jiang, Yihang Zou, Hongbo Peng, Dingming Li, Yuhong Dai, ZePeng Lin, Juanxi Tian, Yi Zhou, Siqi Dai et al.
Published: 2026-03-09
Categories: cs.AI
arXiv: https://arxiv.org/abs/2603.08652v2

Recent advancements in Unified Multimodal Models (UMMs) have significantly advanced text-to-image (T2I) generation, particularly through the integration of Chain-of-Thought (CoT) reasoning. However, existing CoT-based T2I methods largely rely on abstract natural-language planning, which lacks the precision required for complex spatial layouts, structured visual elements, and dense textual content. In this work, we propose CoCo (Code-as-CoT), a code-driven reasoning framework that represents the reasoning process as executable code, enabling explicit and verifiable intermediate planning for image generation. Given a text prompt, CoCo first generates executable code that specifies the structural layout of the scene. The code is then executed in a sandboxed environment to render a deterministic draft image. Subsequently, the model refines this draft through fine-grained image editing to produce the final high-fidelity result. To support this training paradigm, we construct CoCo-10K, a curated dataset containing structured draft-final image pairs designed to teach both structured draft construction and corrective visual refinement. Empirical evaluations on StructT2IBench, OneIG-Bench, and LongText-Bench show that CoCo achieves improvements of 68.83%, 54.8%, and 41.23%, respectively, over direct generation, while also outperforming other CoT-enhanced generation methods. These results demonstrate that executable code is an effective and reliable reasoning paradigm for precise, controllable, and structured text-to-image generation.

---

### Group Entropies and Mirror Duality: A Class of Flexible Mirror Descent Updates for Machine Learning

Authors: Andrzej Cichocki, Piergiulio Tempesta
Published: 2026-03-09
Categories: cs.LG, hep-th, math-ph
arXiv: https://arxiv.org/abs/2603.08651v2

We introduce a comprehensive theoretical and algorithmic framework that bridges formal group theory and group entropies with modern machine learning, paving the way for an infinite, flexible family of Mirror Descent (MD) optimization algorithms. Our approach exploits the rich structure of group entropies, which are generalized entropic functionals governed by group composition laws, encompassing and significantly extending all trace-form entropies such as the Shannon, Tsallis, and Kaniadakis families. By leveraging group-theoretical mirror maps (or link functions) in MD, expressed via multi-parametric generalized logarithms and their inverses (group exponentials), we achieve highly flexible and adaptable MD updates that can be tailored to diverse data geometries and statistical distributions. To this end, we introduce the notion of \textit{mirror duality}, which allows us to seamlessly switch or interchange group-theoretical link functions with their inverses, subject to specific learning rate constraints. By tuning or learning the hyperparameters of the group logarithms enables us to adapt the model to the statistical properties of the training distribution, while simultaneously ensuring desirable convergence characteristics via fine-tuning. This generality not only provides greater flexibility and improved convergence properties, but also opens new perspectives for applications in machine learning and deep learning by expanding the design of regularizers and natural gradient algorithms. We extensively evaluate the validity, robustness, and performance of the proposed updates on large-scale, simplex-constrained quadratic programming problems.

---

### Divide and Predict: An Architecture for Input Space Partitioning and Enhanced Accuracy

Authors: Fenix W. Huang, Henning S. Mortveit, Christian M. Reidys
Published: 2026-03-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.08649v1

In this article the authors develop an intrinsic measure for quantifying heterogeneity in training data for supervised learning. This measure is the variance of a random variable which factors through the influences of pairs of training points. The variance is shown to capture data heterogeneity and can thus be used to assess if a sample is a mixture of distributions. The authors prove that the data itself contains key information that supports a partitioning into blocks. Several proof of concept studies are provided that quantify the connection between variance and heterogeneity for EMNIST image data and synthetic data. The authors establish that variance is maximal for equal mixes of distributions, and detail how variance-based data purification followed by conventional training over blocks can lead to significant increases in test accuracy.

---

### CAST: Modeling Visual State Transitions for Consistent Video Retrieval

Authors: Yanqing Liu, Yingcheng Liu, Fanghong Dong, Budianto Budianto, Cihang Xie, Yan Jiao
Published: 2026-03-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.08648v1

As video content creation shifts toward long-form narratives, composing short clips into coherent storylines becomes increasingly important. However, prevailing retrieval formulations remain context-agnostic at inference time, prioritizing local semantic alignment while neglecting state and identity consistency. To address this structural limitation, we formalize the task of Consistent Video Retrieval (CVR) and introduce a diagnostic benchmark spanning YouCook2, COIN, and CrossTask. We propose CAST (Context-Aware State Transition), a lightweight, plug-and-play adapter compatible with diverse frozen vision-language embedding spaces. By predicting a state-conditioned residual update ($Δ$) from visual history, CAST introduces an explicit inductive bias for latent state evolution. Extensive experiments show that CAST improves performance on YouCook2 and CrossTask, remains competitive on COIN, and consistently outperforms zero-shot baselines across diverse foundation backbones. Furthermore, CAST provides a useful reranking signal for black-box video generation candidates (e.g., from Veo), promoting more temporally coherent continuations.

---

### Grow, Don't Overwrite: Fine-tuning Without Forgetting

Authors: Dyah Adila, Hanna Mazzawi, Benoit Dherin, Xavier Gonzalvo
Published: 2026-03-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.08647v1

Adapting pre-trained models to specialized tasks often leads to catastrophic forgetting, where new knowledge overwrites foundational capabilities. Existing methods either compromise performance on the new task or struggle to balance training stability with efficient reuse of pre-trained knowledge. We introduce a novel function-preserving expansion method that resolves this dilemma. Our technique expands model capacity by replicating pre-trained parameters within transformer submodules and applying a scaling correction that guarantees the expanded model is mathematically identical to the original at initialization, enabling stable training while exploiting existing knowledge. Empirically, our method eliminates the trade-off between plasticity and stability, matching the performance of full fine-tuning on downstream tasks without any degradation of the model's original capabilities. Furthermore, we demonstrate the modularity of our approach, showing that by selectively expanding a small subset of layers we can achieve the same performance as full fine-tuning at a fraction of the computational cost.

---

### Retrieval-Augmented Gaussian Avatars: Improving Expression Generalization

Authors: Matan Levy, Gavriel Habib, Issar Tzachor, Dvir Samuel, Rami Ben-Ari, Nir Darshan, Or Litany, Dani Lischinski
Published: 2026-03-09
Categories: cs.CV, cs.GR, cs.LG
arXiv: https://arxiv.org/abs/2603.08645v1

Template-free animatable head avatars can achieve high visual fidelity by learning expression-dependent facial deformation directly from a subject's capture, avoiding parametric face templates and hand-designed blendshape spaces. However, since learned deformation is supervised only by the expressions observed for a single identity, these models suffer from limited expression coverage and often struggle when driven by motions that deviate from the training distribution. We introduce RAF (Retrieval-Augmented Faces), a simple training-time augmentation designed for template-free head avatars that learn deformation from data. RAF constructs a large unlabeled expression bank and, during training, replaces a subset of the subject's expression features with nearest-neighbor expressions retrieved from this bank while still reconstructing the subject's original frames. This exposes the deformation field to a broader range of expression conditions, encouraging stronger identity-expression decoupling and improving robustness to expression distribution shift without requiring paired cross-identity data, additional annotations, or architectural changes. We further analyze how retrieval augmentation increases expression diversity and validate retrieval quality with a user study showing that retrieved neighbors are perceptually closer in expression and pose. Experiments on the NeRSemble benchmark demonstrate that RAF consistently improves expression fidelity over the baseline, in both self-driving and cross-driving scenarios.

---

### PostTrainBench: Can LLM Agents Automate LLM Post-Training?

Authors: Ben Rank, Hardik Bhatnagar, Ameya Prabhu, Shira Eisenberg, Karina Nguyen, Matthias Bethge, Maksym Andriushchenko
Published: 2026-03-09
Categories: cs.SE, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2603.08640v2

AI agents have become surprisingly proficient at software engineering over the past year, largely due to improvements in reasoning capabilities. This raises a deeper question: can these systems extend their capabilities to automate AI research itself? In this paper, we explore post-training, the critical phase that turns base LLMs into useful assistants. We introduce PostTrainBench to benchmark how well LLM agents can perform post-training autonomously under bounded compute constraints (10 hours on one H100 GPU). We ask frontier agents (e.g., Claude Code with Opus 4.6) to optimize the performance of a base LLM on a particular benchmark (e.g., Qwen3-4B on AIME). Importantly, we do not provide any predefined strategies to the agents and instead give them full autonomy to find necessary information on the web, run experiments, and curate data. We find that frontier agents make substantial progress but generally lag behind instruction-tuned LLMs from leading providers: 23.2% for the best agent vs. 51.1% for official instruction-tuned models. However, agents can exceed instruction-tuned models in targeted scenarios: GPT-5.1 Codex Max achieves 89% on BFCL with Gemma-3-4B vs. 67% for the official model. We also observe several failure modes worth flagging. Agents sometimes engage in reward hacking: training on the test set, downloading existing instruction-tuned checkpoints instead of training their own, and using API keys they find to generate synthetic data without authorization. These behaviors are concerning and highlight the importance of careful sandboxing as these systems become more capable. Overall, we hope PostTrainBench will be useful for tracking progress in AI R&D automation and for studying the risks that come with it. Website and code are available at https://posttrainbench.com/.

---

### UNBOX: Unveiling Black-box visual models with Natural-language

Authors: Simone Carnemolla, Chiara Russo, Simone Palazzo, Quentin Bouniot, Daniela Giordano, Zeynep Akata, Matteo Pennisi, Concetto Spampinato
Published: 2026-03-09
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.08639v2

Ensuring trustworthiness in open-world visual recognition requires models that are interpretable, fair, and robust to distribution shifts. Yet modern vision systems are increasingly deployed as proprietary black-box APIs, exposing only output probabilities and hiding architecture, parameters, gradients, and training data. This opacity prevents meaningful auditing, bias detection, and failure analysis. Existing explanation methods assume white- or gray-box access or knowledge of the training distribution, making them unusable in these real-world settings. We introduce UNBOX, a framework for class-wise model dissection under fully data-free, gradient-free, and backpropagation-free constraints. UNBOX leverages Large Language Models and text-to-image diffusion models to recast activation maximization as a purely semantic search driven by output probabilities. The method produces human-interpretable text descriptors that maximally activate each class, revealing the concepts a model has implicitly learned, the training distribution it reflects, and potential sources of bias. We evaluate UNBOX on ImageNet-1K, Waterbirds, and CelebA through semantic fidelity tests, visual-feature correlation analyses and slice-discovery auditing. Despite operating under the strictest black-box constraints, UNBOX performs competitively with state-of-the-art white-box interpretability methods. This demonstrates that meaningful insight into a model's internal reasoning can be recovered without any internal access, enabling more trustworthy and accountable visual recognition systems.

---

### Integral Formulas for Vector Signal Tensor Products

Authors: Valentin Heyraud, Zachary Weller-Davies, Jules Tilly
Published: 2026-03-09
Categories: cs.LG, physics.comp-ph
arXiv: https://arxiv.org/abs/2603.08630v2

We derive integral formulas that simplify the Vector Signal Tensor Product recently introduced by Xie et al., which generalizes the Gaunt tensor product to anti-symmetric couplings. In particular, we obtain explicit closed-form expressions for the anti-symmetric analogues of the Gaunt coefficients. This enables us to simulate the Clebsch-Gordan tensor product using a single Vector Signal Tensor Product, yielding up to a $9\times$ reduction in the required tensor product evaluations. Our results enable efficient and practical implementations of the Vector Signal Tensor Product, paving the way for applications of this generalization of Gaunt Tensor Products in $\mathrm{SO}(3)$-equivariant neural networks. Moreover, we discuss how the Gaunt and the Vector Signal Tensor Products allow to control the expressivity-runtime tradeoff associated with the usual Clebsch-Gordan Tensor Products. Finally, we investigate low rank decompositions of the normalizations of the considered tensor products in view of their use in equivariant neural networks.

---

### StreamReady: Learning What to Answer and When in Long Streaming Videos

Authors: Shehreen Azad, Vibhav Vineet, Yogesh Singh Rawat
Published: 2026-03-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.08620v1

Streaming video understanding often involves time-sensitive scenarios where models need to answer exactly when the supporting visual evidence appears: answering before the evidence reflects speculation, answering after it has passed reduces real-time utility. To capture this behavior, we introduce a readiness-aware formulation of streaming video understanding with the Answer Readiness Score (ARS), a timing-aware objective with asymmetric early and late penalties. When combined with correctness, ARS defines an effective accuracy that measures not just whether a model is right, but whether it answers at the appropriate moment. Building on this formulation, we introduce StreamReady, a framework to unify temporal reasoning with on-time answering through a lightweight readiness mechanism that decides if sufficient evidence has been observed before responding. To evaluate this capability, we further introduce ProReady-QA, a benchmark with annotated answer evidence windows and proactive multi-turn questions across local and global contexts. StreamReady achieves superior performance on ProReady-QA, and consistently outperforms prior methods across eight additional streaming and offline long-video benchmarks, demonstrating robust and broadly generalizable video understanding capability.

---

### FOMO-3D: Using Vision Foundation Models for Long-Tailed 3D Object Detection

Authors: Anqi Joyce Yang, James Tu, Nikita Dvornik, Enxu Li, Raquel Urtasun
Published: 2026-03-09
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2603.08611v1

In order to navigate complex traffic environments, self-driving vehicles must recognize many semantic classes pertaining to vulnerable road users or traffic control devices. However, many safety-critical objects (e.g., construction worker) appear infrequently in nominal traffic conditions, leading to a severe shortage of training examples from driving data alone. Recent vision foundation models, which are trained on a large corpus of data, can serve as a good source of external prior knowledge to improve generalization. We propose FOMO-3D, the first multi-modal 3D detector to leverage vision foundation models for long-tailed 3D detection. Specifically, FOMO-3D exploits rich semantic and depth priors from OWLv2 and Metric3Dv2 within a two-stage detection paradigm that first generates proposals with a LiDAR-based branch and a novel camera-based branch, and refines them with attention especially to image features from OWL. Evaluations on real-world driving data show that using rich priors from vision foundation models with careful multi-modal fusion designs leads to large gains for long-tailed 3D detection. Project website is at https://waabi.ai/fomo3d/.

---

### Weakly Supervised Teacher-Student Framework with Progressive Pseudo-mask Refinement for Gland Segmentation

Authors: Hikmat Khan, Wei Chen, Muhammad Khalid Khan Niazi
Published: 2026-03-09
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.08605v3

Background and objectives: Colorectal cancer histopathological grading depends on accurate segmentation of glandular structures. Current deep learning approaches rely on large scale pixel level annotations that are labor intensive and difficult to obtain in routine clinical practice. Weakly supervised semantic segmentation offers a promising alternative. However, class activation map based methods often produce incomplete pseudo masks that emphasize highly discriminative regions and fail to supervise unannotated glandular structures. We propose a weakly supervised teacher student framework that leverages sparse pathologist annotations and an Exponential Moving Average stabilized teacher network to generate refined pseudo masks. Methods: The framework integrates confidence based filtering, adaptive fusion of teacher predictions with limited ground truth, and curriculum guided refinement to progressively segment unannotated glandular regions. The method was evaluated on an institutional colorectal cancer cohort from The Ohio State University Wexner Medical Center consisting of 60 hematoxylin and eosin stained whole slide images and on public datasets including the Gland Segmentation dataset, TCGA COAD, TCGA READ, and SPIDER. Results: On the Gland Segmentation dataset the framework achieved a mean Intersection over Union of 80.10 and a mean Dice coefficient of 89.10. Cross cohort evaluation demonstrated robust generalization on TCGA COAD and TCGA READ without additional annotations, while reduced performance on SPIDER reflected domain shift. Conclusions: The proposed framework provides an annotation efficient and generalizable approach for gland segmentation in colorectal histopathology.

---

### Don't Look Back in Anger: MAGIC Net for Streaming Continual Learning with Temporal Dependence

Authors: Federico Giannini, Sandro D'Andrea, Emanuele Della Valle
Published: 2026-03-09
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.08600v1

Concept drift, temporal dependence, and catastrophic forgetting represent major challenges when learning from data streams. While Streaming Machine Learning and Continual Learning (CL) address these issues separately, recent efforts in Streaming Continual Learning (SCL) aim to unify them. In this work, we introduce MAGIC Net, a novel SCL approach that integrates CL-inspired architectural strategies with recurrent neural networks to tame temporal dependence. MAGIC Net continuously learns, looks back at past knowledge by applying learnable masks over frozen weights, and expands its architecture when necessary. It performs all operations online, ensuring inference availability at all times. Experiments on synthetic and real-world streams show that it improves adaptation to new concepts, limits memory usage, and mitigates forgetting.

---

### Boosting MLLM Spatial Reasoning with Geometrically Referenced 3D Scene Representations

Authors: Jiangye Yuan, Gowri Kumar, Baoyuan Wang
Published: 2026-03-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.08592v2

While Multimodal Large Language Models (MLLMs) have achieved remarkable success in 2D visual understanding, their ability to reason about 3D space remains limited. To address this gap, we introduce geometrically referenced 3D scene representations (GR3D). Given a set of input images, GR3D annotates objects in the images with unique IDs and encodes their 3D geometric attributes as textual references indexed by these IDs. This representation enables MLLMs to interpret 3D cues using their advanced language-based skills in mathematical reasoning, while concurrently analyzing 2D visual features in a tightly coupled way. We present a simple yet effective approach based on GR3D, which requires no additional training and is readily applicable to different MLLMs. Implemented in a zero-shot setting, our approach yields substantial improvements on challenging spatial reasoning benchmarks, boosting GPT-5 performance by 9% on VSI-Bench and 12% on MindCube. Qualitative studies further demonstrate that GR3D empowers MLLMs to perform complex spatial reasoning with highly sparse input views.

---

### PRISM: Streaming Human Motion Generation with Per-Joint Latent Decomposition

Authors: Zeyu Ling, Qing Shuai, Teng Zhang, Shiyang Li, Bo Han, Changqing Zou
Published: 2026-03-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.08590v4

Text-to-motion generation has advanced with larger corpora and stronger generators, yet many models still rely on holistic frame- or clip-level latents that entangle trajectory, orientation, and articulation. This entanglement obscures body topology and forces the generator to recover kinematic structure implicitly. We present \name, a SMPL motion generation framework that factorizes motion into continuous kinematic-unit latents. A causal Motion VAE maps motion to a time-by-kinematic-unit latent manifold, and a Kinematic-Unit Flow Transformer performs text-conditioned flow matching in this structured space. Because each latent coordinate remains tied to a physical body unit, \name can use kinematic-tree rotary position encoding and kinematic-adaptive flow scheduling. We further train the generator with per-token timesteps over clean-context/noisy-target masks, enabling frame-conditioned continuation and autoregressive segment chaining within one model. Experiments first validate the representation: the kinematic-unit VAE achieves lower geometry, rotation, and feature errors than existing motion tokenizers, showing that the latent space preserves articulated structure rather than merely compressing frames. With a 1.4B-parameter generator trained only on publicly available academic motion--text data, \name outperforms all evaluated academic-data text-to-motion baselines and remains competitive with systems trained on much larger non-public motion corpora. Without task-specific retraining, the same formulation also improves prefix-conditioned generation, BABEL sequential rollout, and narrative motion composition. These results indicate that kinematic-unit latent factorization provides an effective generation substrate for controllable SMPL motion synthesis. Code will be released at https://github.com/ZeyuLing/PRISM.

---

### PRISM: Streaming Human Motion Generation with Per-Joint Latent Decomposition

Authors: Zeyu Ling, Qing Shuai, Teng Zhang, Shiyang Li, Bo Han, Changqing Zou
Published: 2026-03-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.08590v2

Text-to-motion generation has advanced rapidly, yet two challenges persist. First, existing motion autoencoders compress each frame into a single monolithic latent vector, entangling trajectory and per-joint rotations in an unstructured representation that downstream generators struggle to model faithfully. Second, text-to-motion, pose-conditioned generation, and long-horizon sequential synthesis typically require separate models or task-specific mechanisms, with autoregressive approaches suffering from severe error accumulation over extended rollouts. We present PRISM, addressing each challenge with a dedicated contribution. (1) A joint-factorized motion latent space: each body joint occupies its own token, forming a structured 2D grid (time joints) compressed by a causal VAE with forward-kinematics supervision. This simple change to the latent space -- without modifying the generator -- substantially improves generation quality, revealing that latent space design has been an underestimated bottleneck. (2) Noise-free condition injection: each latent token carries its own timestep embedding, allowing conditioning frames to be injected as clean tokens (timestep0) while the remaining tokens are denoised. This unifies text-to-motion and pose-conditioned generation in a single model, and directly enables autoregressive segment chaining for streaming synthesis. Self-forcing training further suppresses drift in long rollouts. With these two components, we train a single motion generation foundation model that seamlessly handles text-to-motion, pose-conditioned generation, autoregressive sequential generation, and narrative motion composition, achieving state-of-the-art on HumanML3D, MotionHub, BABEL, and a 50-scenario user study.

---

### CARE-Edit: Condition-Aware Routing of Experts for Contextual Image Editing

Authors: Yucheng Wang, Zedong Wang, Yuetong Wu, Yue Ma, Dan Xu
Published: 2026-03-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.08589v1

Unified diffusion editors often rely on a fixed, shared backbone for diverse tasks, suffering from task interference and poor adaptation to heterogeneous demands (e.g., local vs global, semantic vs photometric). In particular, prevalent ControlNet and OmniControl variants combine multiple conditioning signals (e.g., text, mask, reference) via static concatenation or additive adapters which cannot dynamically prioritize or suppress conflicting modalities, thus resulting in artifacts like color bleeding across mask boundaries, identity or style drift, and unpredictable behavior under multi-condition inputs. To address this, we propose Condition-Aware Routing of Experts (CARE-Edit) that aligns model computation with specific editing competencies. At its core, a lightweight latent-attention router assigns encoded diffusion tokens to four specialized experts--Text, Mask, Reference, and Base--based on multi-modal conditions and diffusion timesteps: (i) a Mask Repaint module first refines coarse user-defined masks for precise spatial guidance; (ii) the router applies sparse top-K selection to dynamically allocate computation to the most relevant experts; (iii) a Latent Mixture module subsequently fuses expert outputs, coherently integrating semantic, spatial, and stylistic information to the base images. Experiments validate CARE-Edit's strong performance on contextual editing tasks, including erasure, replacement, text-driven edits, and style transfer. Empirical analysis further reveals task-specific behavior of specialized experts, showcasing the importance of dynamic, condition-aware processing to mitigate multi-condition conflicts.

---

### Towards Batch-to-Streaming Deep Reinforcement Learning for Continuous Control

Authors: Riccardo De Monte, Matteo Cederle, Gian Antonio Susto
Published: 2026-03-09
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.08588v2

State-of-the-art deep reinforcement learning (RL) methods have achieved remarkable performance in continuous control tasks, yet their computational complexity is often incompatible with the constraints of resource-limited hardware, due to their reliance on replay buffers, batch updates, and target networks. The emerging paradigm of streaming deep RL addresses this limitation through purely online updates, achieving strong empirical performance on standard benchmarks. In this work, we propose two novel streaming deep RL algorithms, Streaming Soft Actor-Critic (S2AC) and Streaming Deterministic Actor-Critic (SDAC), explicitly designed to be compatible with state-of-the-art batch RL methods, making them particularly suitable for on-device finetuning applications such as Sim2Real transfer. Both algorithms achieve performance comparable to state-of-the-art streaming baselines on standard benchmarks without requiring tedious per-environment hyperparameter tuning. We further investigate the batch-to-streaming transition, showing that a naive transition does not guarantee preservation of pre-trained policy performance, and propose a principled approach to address this challenge.

---

### DualFlexKAN: Dual-stage Kolmogorov-Arnold Networks with Independent Function Control

Authors: Andrés Ortiz, Nicolás J. Gallego-Molina, Carmen Jiménez-Mesa, Juan M. Górriz, Javier Ramírez
Published: 2026-03-09
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2603.08583v1

Multi-Layer Perceptrons (MLPs) rely on pre-defined, fixed activation functions, imposing a static inductive bias that forces the network to approximate complex topologies solely through increased depth and width. Kolmogorov-Arnold Networks (KANs) address this limitation through edge-centric learnable functions, yet their formulation suffers from quadratic parameter scaling and architectural rigidity that hinders the effective integration of standard regularization techniques. This paper introduces the DualFlexKAN (DFKAN), a flexible architecture featuring a dual-stage mechanism that independently controls pre-linear input transformations and post-linear output activations. This decoupling enables hybrid networks that optimize the trade-off between expressiveness and computational cost. Unlike standard formulations, DFKAN supports diverse basis function families, including orthogonal polynomials, B-splines, and radial basis functions, integrated with configurable regularization strategies that stabilize training dynamics. Comprehensive evaluations across regression benchmarks, physics-informed tasks, and function approximation demonstrate that DFKAN outperforms both MLPs and conventional KANs in accuracy, convergence speed, and gradient fidelity. The proposed hybrid configurations achieve superior performance with one to two orders of magnitude fewer parameters than standard KANs, effectively mitigating the parameter explosion problem while preserving KAN-style expressiveness. DFKAN provides a principled, scalable framework for incorporating adaptive non-linearities, proving particularly advantageous for data-efficient learning and interpretable function discovery in scientific applications.

---

### Online Sparse Synthetic Aperture Radar Imaging

Authors: Conor Flynn, Radoslav Ivanov, Birsen Yazici
Published: 2026-03-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.08582v2

With modern defense applications increasingly relying on inexpensive, autonomous drones, lies the major challenge of designing computationally and memory-efficient onboard algorithms to fulfill mission objectives. This challenge is particularly significant in Synthetic Aperture Radar (SAR), where large volumes of data must be collected and processed for downstream tasks. We propose an online reconstruction method, the Online Fast Iterative Shrinkage-Thresholding Algorithm (Online FISTA), which incrementally reconstructs a scene with limited data through sparse coding. Rather than requiring storage of all received signal data, the algorithm recursively updates storage matrices for each iteration, greatly reducing memory demands. Online SAR image reconstruction facilitates more complex downstream tasks, such as Automatic Target Recognition (ATR), in an online manner, resulting in a more versatile and integrated framework compared to existing post-collection reconstruction and ATR approaches.

---

### Drift-to-Action Controllers: Budgeted Interventions with Online Risk Certificates

Authors: Ismail Lamaakal, Chaymae Yahyati, Khalid El Makkaoui, Ibrahim Ouahbi, Yassine Maleh
Published: 2026-03-09
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2603.08578v1

Deployed machine learning systems face distribution drift, yet most monitoring pipelines stop at alarms and leave the response underspecified under labeling, compute, and latency constraints. We introduce Drift2Act, a drift-to-action controller that treats monitoring as constrained decision-making with explicit safety. Drift2Act combines a sensing layer that maps unlabeled monitoring signals to a belief over drift types with an active risk certificate that queries a small set of delayed labels from a recent window to produce an anytime-valid upper bound $U_t(δ)$ on current risk. The certificate gates operation: if $U_t(δ) \le τ$, the controller selects low-cost actions (e.g., recalibration or test-time adaptation); if $U_t(δ) > τ$, it activates abstain/handoff and escalates to rollback or retraining under cooldowns. In a realistic streaming protocol with label delay and explicit intervention costs, Drift2Act achieves near-zero safety violations and fast recovery at moderate cost on WILDS Camelyon17, DomainNet, and a controlled synthetic drift stream, outperforming alarm-only monitoring, adapt-always adaptation, schedule-based retraining, selective prediction alone, and an ablation without certification. Overall, online risk certification enables reliable drift response and reframes monitoring as decision-making with safety.

---

### Trust via Reputation of Conviction

Authors: Aravind R. Iyengar
Published: 2026-03-09
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2603.08575v1

The question of \emph{knowledge}, \emph{truth} and \emph{trust} is explored via a mathematical formulation of claims and sources. We define truth as the reproducibly perceived subset of knowledge, formalize sources as having both generative and discriminative roles, and develop a framework for reputation grounded in the \emph{conviction} -- the likelihood that a source's stance is vindicated by independent consensus. We argue that conviction, rather than correctness or faithfulness, is the principled basis for trust: it is regime-independent, rewards genuine contribution, and demands the transparent and self-sufficient perceptions that make external verification possible. We formalize reputation as the expected weighted signed conviction over a realm of claims, characterize its behavior across source-claim regimes, and identify continuous verification as both a theoretical necessity and a practical mechanism through which reputation accrues. The framework is applied to AI agents, which are identified as capable but error-prone sources for whom verifiable conviction and continuously accrued reputation constitute the only robust foundation for trust.

---

### MetaWorld-X: Hierarchical World Modeling via VLM-Orchestrated Experts for Humanoid Loco-Manipulation

Authors: Yutong Shen, Hangxu Liu, Penghui Liu, Jiashuo Luo, Yongkang Zhang, Rex Morvley, Chen Jiang, Jianwei Zhang, Lei Zhang
Published: 2026-03-09
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2603.08572v1

Learning natural, stable, and compositionally generalizable whole-body control policies for humanoid robots performing simultaneous locomotion and manipulation (loco-manipulation) remains a fundamental challenge in robotics. Existing reinforcement learning approaches typically rely on a single monolithic policy to acquire multiple skills, which often leads to cross-skill gradient interference and motion pattern conflicts in high-degree-of-freedom systems. As a result, generated behaviors frequently exhibit unnatural movements, limited stability, and poor generalization to complex task compositions. To address these limitations, we propose MetaWorld-X, a hierarchical world model framework for humanoid control. Guided by a divide-and-conquer principle, our method decomposes complex control problems into a set of specialized expert policies (Specialized Expert Policies, SEP). Each expert is trained under human motion priors through imitation-constrained reinforcement learning, introducing biomechanically consistent inductive biases that ensure natural and physically plausible motion generation. Building upon this foundation, we further develop an Intelligent Routing Mechanism (IRM) supervised by a Vision-Language Model (VLM), enabling semantic-driven expert composition. The VLM-guided router dynamically integrates expert policies according to high-level task semantics, facilitating compositional generalization and adaptive execution in multi-stage loco-manipulation tasks.

---

### OSS-CRS: Liberating AIxCC Cyber Reasoning Systems for Real-World Open-Source Security

Authors: Andrew Chin, Dongkwan Kim, Yu-Fu Fu, Fabian Fleischer, Youngjoon Kim, HyungSeok Han, Cen Zhang, Brian Junekyu Lee, Hanqing Zhao, Taesoo Kim
Published: 2026-03-09
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2603.08566v2

DARPA's AI Cyber Challenge (AIxCC) showed that cyber reasoning systems (CRSs) can go beyond vulnerability discovery to autonomously confirm and patch bugs: seven teams built such systems and open-sourced them after the competition. Yet all seven open-sourced CRSs remain largely unusable outside their original teams, each bound to the competition cloud infrastructure that no longer exists. We present OSS-CRS, an open, locally deployable framework for running and combining CRS techniques against real-world open-source projects, with budget-aware resource management. We ported the first-place system (Atlantis) and discovered 10 previously unknown bugs (three of high severity) across 8 OSS-Fuzz projects. OSS-CRS is publicly available.

---

### BioGait-VLM: A Tri-Modal Vision-Language-Biomechanics Framework for Interpretable Clinical Gait Assessment

Authors: Erdong Chen, Yuyang Ji, Jacob K. Greenberg, Benjamin Steel, Faraz Arkam, Abigail Lewis, Pranay Singh, Feng Liu
Published: 2026-03-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.08564v1

Video-based Clinical Gait Analysis often suffers from poor generalization as models overfit environmental biases instead of capturing pathological motion. To address this, we propose BioGait-VLM, a tri-modal Vision-Language-Biomechanics framework for interpretable clinical gait assessment. Unlike standard video encoders, our architecture incorporates a Temporal Evidence Distillation branch to capture rhythmic dynamics and a Biomechanical Tokenization branch that projects 3D skeleton sequences into language-aligned semantic tokens. This enables the model to explicitly reason about joint mechanics independent of visual shortcuts. To ensure rigorous benchmarking, we augment the public GAVD dataset with a high-fidelity Degenerative Cervical Myelopathy (DCM) cohort to form a unified 8-class taxonomy, establishing a strict subject-disjoint protocol to prevent data leakage. Under this setting, BioGait-VLM achieves state-of-the-art recognition accuracy. Furthermore, a blinded expert study confirms that biomechanical tokens significantly improve clinical plausibility and evidence grounding, offering a path toward transparent, privacy-enhanced gait assessment.

---

### RetroAgent: From Solving to Evolving via Retrospective Dual Intrinsic Feedback

Authors: Xiaoying Zhang, Zichen Liu, Yipeng Zhang, Xia Hu, Wenqi Shao
Published: 2026-03-09
Categories: cs.AI
arXiv: https://arxiv.org/abs/2603.08561v6

Standard reinforcement learning (RL) for large language model (LLM) agents primarily optimizes extrinsic task rewards, often favoring isolated task completion over continual adaptation. This paradigm can cause premature convergence to suboptimal policies and leaves useful experience only implicitly encoded in model parameters, limiting its retrieval and reuse for future decisions. We introduce RetroAgent, an online RL framework that trains agents to master interactive environments not merely by solving tasks, but by evolving across episodes. Inspired by human retrospective self-improvement, RetroAgent augments extrinsic rewards with hindsight-generated dual intrinsic feedback: (1) Intrinsic Numerical Feedback, which rewards beneficial exploration by measuring incremental subtask progress relative to prior attempts; and (2) Intrinsic Language Feedback which distills successes and failures into reusable textual lessons for explicit experience reuse. To leverage these lessons effectively, we propose Similarity & Utility-Aware Upper Confidence Bound (SimUtil-UCB), a retrieval strategy that balances semantic relevance, historical utility, and exploration. Across four challenging agentic benchmarks, RetroAgent achieves new state-of-the-art performance, outperforming GRPO by +18.3% on ALFWorld, +15.4% on WebShop, +27.1% on Sokoban, and +8.9% on MineSweeper, while demonstrating strong test-time adaptation and out-of-distribution generalization.

---

### Impact of Connectivity on Laplacian Representations in Reinforcement Learning

Authors: Tommaso Giorgi, Pierriccardo Olivieri, Keyue Jiang, Laura Toni, Matteo Papini
Published: 2026-03-09
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2603.08558v3

Learning compact state representations in Markov Decision Processes (MDPs) has proven crucial for addressing the curse of dimensionality in large-scale reinforcement learning (RL) problems. Existing principled approaches leverage structural priors on the MDP by constructing state representations as linear combinations of the state-graph Laplacian eigenvectors. When the transition graph is unknown or the state space is prohibitively large, the graph spectral features can be estimated directly via sample trajectories. In this work, we prove an upper bound on the approximation error of linear value function approximation under the learned spectral features. We show how this error scales with the algebraic connectivity of the state-graph, grounding the approximation quality in the topological structure of the MDP. We further bound the error introduced by the eigenvector estimation itself, leading to an end-to-end error decomposition across the representation learning pipeline. Additionally, our expression of the Laplacian operator for the RL setting, although equivalent to existing ones, prevents some common misunderstandings, of which we show some examples from the literature. Our results hold for general (non-uniform) policies without any assumptions on the symmetry of the induced transition kernel. We validate our theoretical findings with numerical simulations on gridworld environments.

---

### Generative Adversarial Regression (GAR): Learning Conditional Risk Scenarios

Authors: Saeed Asadi, Jonathan Yu-Meng Li
Published: 2026-03-09
Categories: stat.ML, cs.LG, math.OC, q-fin.PM, q-fin.RM
arXiv: https://arxiv.org/abs/2603.08553v1

We propose Generative Adversarial Regression (GAR), a framework for learning conditional risk scenarios through generators aligned with downstream risk objectives. GAR builds on a regression characterization of conditional risk for elicitable functionals, including quantiles, expectiles, and jointly elicitable pairs. We extend this principle from point prediction to generative modeling by training generators whose policy-induced risk matches that of real data under the same context. To ensure robustness across all policies, GAR adopts a minimax formulation in which an adversarial policy identifies worst-case discrepancies in risk evaluation while the generator adapts to eliminate them. This structure preserves alignment with the risk functional across a broad class of policies rather than a fixed, pre-specified set. We illustrate GAR through a tail-risk instantiation based on jointly elicitable $(\mathrm{VaR}, \mathrm{ES})$ objectives. Experiments on S\&P 500 data show that GAR produces scenarios that better preserve downstream risk than unconditional, econometric, and direct predictive baselines while remaining stable under adversarially selected policies.

---

### mmGAT: Pose Estimation by Graph Attention with Mutual Features from mmWave Radar Point Cloud

Authors: Abdullah Al Masud, Shi Xintong, Mondher Bouazizi, Ohtsuki Tomoaki
Published: 2026-03-09
Categories: cs.CV, cs.IR
arXiv: https://arxiv.org/abs/2603.08551v1

Pose estimation and human action recognition (HAR) are pivotal technologies spanning various domains. While the image-based pose estimation and HAR are widely admired for their superior performance, they lack in privacy protection and suboptimal performance in low-light and dark environments. This paper exploits the capabilities of millimeter-wave (mmWave) radar technology for human pose estimation by processing radar data with Graph Neural Network (GNN) architecture, coupled with the attention mechanism. Our goal is to capture the finer details of the radar point cloud to improve the pose estimation performance. To this end, we present a unique feature extraction technique that exploits the full potential of the GNN processing method for pose estimation. Our model mmGAT demonstrates remarkable performance on two publicly available benchmark mmWave datasets and establishes new state of the art results in most scenarios in terms of human pose estimation. Our approach achieves a noteworthy reduction of pose estimation mean per joint position error (MPJPE) by 35.6% and PA-MPJPE by 14.1% from the current state of the art benchmark within this domain.

---

### Interactive World Simulator for Robot Policy Training and Evaluation

Authors: Yixuan Wang, Rhythm Syed, Fangyu Wu, Mengchao Zhang, Aykut Onol, Jose Barreiros, Hooshang Nayyeri, Tony Dear, Huan Zhang, Yunzhu Li
Published: 2026-03-09
Categories: cs.RO, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2603.08546v1

Action-conditioned video prediction models (often referred to as world models) have shown strong potential for robotics applications, but existing approaches are often slow and struggle to capture physically consistent interactions over long horizons, limiting their usefulness for scalable robot policy training and evaluation. We present Interactive World Simulator, a framework for building interactive world models from a moderate-sized robot interaction dataset. Our approach leverages consistency models for both image decoding and latent-space dynamics prediction, enabling fast and stable simulation of physical interactions. In our experiments, the learned world models produce interaction-consistent pixel-level predictions and support stable long-horizon interactions for more than 10 minutes at 15 FPS on a single RTX 4090 GPU. Our framework enables scalable demonstration collection solely within the world models to train state-of-the-art imitation policies. Through extensive real-world evaluation across diverse tasks involving rigid objects, deformable objects, object piles, and their interactions, we find that policies trained on world-model-generated data perform comparably to those trained on the same amount of real-world data. Additionally, we evaluate policies both within the world models and in the real world across diverse tasks, and observe a strong correlation between simulated and real-world performance. Together, these results establish the Interactive World Simulator as a stable and physically consistent surrogate for scalable robotic data generation and faithful, reproducible policy evaluation.

---

### The Neural Compass: Probabilistic Relative Feature Fields for Robotic Search

Authors: Gabriele Somaschini, Adrian Röfer, Abhinav Valada
Published: 2026-03-09
Categories: cs.RO, cs.LG
arXiv: https://arxiv.org/abs/2603.08544v1

Object co-occurrences provide a key cue for finding objects successfully and efficiently in unfamiliar environments. Typically, one looks for cups in kitchens and views fridges as evidence of being in a kitchen. Such priors have also been exploited in artificial agents, but they are typically learned from explicitly labeled data or queried from language models. It is still unclear whether these relations can be learned implicitly from unlabeled observations alone. In this work, we address this problem and propose ProReFF, a feature field model trained to predict relative distributions of features obtained from pre-trained vision language models. In addition, we introduce a learning-based strategy that enables training from unlabeled and potentially contradictory data by aligning inconsistent observations into a coherent relative distribution. For the downstream object search task, we propose an agent that leverages predicted feature distributions as a semantic prior to guide exploration toward regions with a high likelihood of containing the object. We present extensive evaluations demonstrating that ProReFF captures meaningful relative feature distributions in natural scenes and provides insight into the impact of our proposed alignment step. We further evaluate the performance of our search agent in 100 challenges in the Matterport3D simulator, comparing with feature-based baselines and human participants. The proposed agent is 20% more efficient than the strongest baseline and achieves up to 80% of human performance.

---

### PCFEx: Point Cloud Feature Extraction for Graph Neural Networks

Authors: Abdullah Al Masud, Shi Xintong, Mondher Bouazizi, Ohtsuki Tomoaki
Published: 2026-03-09
Categories: cs.CV, cs.IR
arXiv: https://arxiv.org/abs/2603.08540v1

Graph neural networks (GNNs) have gained significant attention for their effectiveness across various domains. This study focuses on applying GNN to process 3D point cloud data for human pose estimation (HPE) and human activity recognition (HAR). We propose novel point cloud feature extraction (PCFEx) techniques to capture meaningful information at the point, edge, and graph levels of the point cloud by considering point cloud as a graph. Moreover, we introduce a GNN architecture designed to efficiently process these features. Our approach is evaluated on four most popular publicly available millimeter wave radar datasets, three for HPE and one for HAR. The results show substantial improvements, with significantly reduced errors in all three HPE benchmarks, and an overall accuracy of 98.8% in mmWave-based HAR, outperforming the existing state of the art models. This work demonstrates the great potential of feature extraction incorporated with GNN modeling approach to enhance the precision of point cloud processing.

---

### SWIFT: Sliding Window Reconstruction for Few-Shot Training-Free Generated Video Attribution

Authors: Chao Wang, Zijin Yang, Yaofei Wang, Yuang Qi, Weiming Zhang, Nenghai Yu, Kejiang Chen
Published: 2026-03-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.08536v2

Recent advancements in video generation technologies have been significant, resulting in their widespread application across multiple domains. However, concerns have been mounting over the potential misuse of generated content. Tracing the origin of generated videos has become crucial to mitigate potential misuse and identify responsible parties. Existing video attribution methods require additional operations or the training of source attribution models, which may degrade video quality or necessitate large amounts of training samples. To address these challenges, we define for the first time the "few-shot training-free generated video attribution" task and propose SWIFT, which is tightly integrated with the temporal characteristics of the video. By leveraging the "Pixel Frames(many) to Latent Frame(one)" temporal mapping within each video chunk, SWIFT applies a fixed-length sliding window to perform two distinct reconstructions: normal and corrupted. The variation in the losses between two reconstructions is then used as an attribution signal. We conducted an extensive evaluation of five state-of-the-art (SOTA) video generation models. Experimental results show that SWIFT achieves over 90% average attribution accuracy with merely 20 video samples across all models and even enables zero-shot attribution for HunyuanVideo, EasyAnimate, and Wan2.2. Our source code is available at https://github.com/wangchao0708/SWIFT.

---

### SecAgent: Efficient Mobile GUI Agent with Semantic Context

Authors: Yiping Xie, Song Chen, Jingxuan Xing, Wei Jiang, Zekun Zhu, Yingyao Wang, Pi Bu, Jun Song, Yuning Jiang, Bo Zheng
Published: 2026-03-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.08533v2

Mobile Graphical User Interface (GUI) agents powered by multimodal large language models have demonstrated promising capabilities in automating complex smartphone tasks. However, existing approaches face two critical limitations: the scarcity of high-quality multilingual datasets, particularly for non-English ecosystems, and inefficient history representation methods. To address these challenges, we present SecAgent, an efficient mobile GUI agent at 3B scale. We first construct a human-verified Chinese mobile GUI dataset with 18k grounding samples and 121k navigation steps across 44 applications, along with a Chinese navigation benchmark featuring multi-choice action annotations. Building upon this dataset, we propose a semantic context mechanism that distills history screenshots and actions into concise, natural language summaries, significantly reducing computational costs while preserving task-relevant information. Through supervised and reinforcement fine-tuning, SecAgent outperforms similar-scale baselines and achieves performance comparable to 7B-8B models on our and public navigation benchmarks. Our dataset is available at https://huggingface.co/datasets/alibabagroup/CMGUI.

---

### Towards Effective and Efficient Graph Alignment without Supervision

Authors: Songyang Chen, Youfang Lin, Yu Liu, Shuai Zheng, Lei Zou
Published: 2026-03-09
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.08526v1

Unsupervised graph alignment aims to find the node correspondence across different graphs without any anchor node pairs. Despite the recent efforts utilizing deep learning-based techniques, such as the embedding and optimal transport (OT)-based approaches, we observe their limitations in terms of model accuracy-efficiency tradeoff. By focusing on the exploitation of local and global graph information, we formalize them as the ``local representation, global alignment'' paradigm, and present a new ``global representation and alignment'' paradigm to resolve the mismatch between the two phases in the alignment process. We then propose \underline{Gl}obal representation and \underline{o}ptimal transport-\underline{b}ased \underline{Align}ment (\texttt{GlobAlign}), and its variant, \texttt{GlobAlign-E}, for better \underline{E}fficiency. Our methods are equipped with the global attention mechanism and a hierarchical cross-graph transport cost, able to capture long-range and implicit node dependencies beyond the local graph structure. Furthermore, \texttt{GlobAlign-E} successfully closes the time complexity gap between representative embedding and OT-based methods, reducing OT's cubic complexity to quadratic terms. Through extensive experiments, our methods demonstrate superior performance, with up to a 20\% accuracy improvement over the best competitor. Meanwhile, \texttt{GlobAlign-E} achieves the best efficiency, with an order of magnitude speedup against existing OT-based methods.

---