# Research Papers — 2026-03 · bundle page 125 of 243

> Full-text markdown of papers #6201–6250 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/125
[← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/124.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-03/page/126.md)

### Training-free Detection of Generated Videos via Spatial-Temporal Likelihoods

Authors: Omer Ben Hayun, Roy Betser, Meir Yossef Levi, Levi Kassel, Guy Gilboa
Published: 2026-03-16
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2603.15026v2

Following major advances in text and image generation, the video domain has surged, producing highly realistic and controllable sequences. Along with this progress, these models also raise serious concerns about misinformation, making reliable detection of synthetic videos increasingly crucial. Image-based detectors are fundamentally limited because they operate per frame and ignore temporal dynamics, while supervised video detectors generalize poorly to unseen generators, a critical drawback given the rapid emergence of new models. These challenges motivate zero-shot approaches, which avoid synthetic data and instead score content against real-data statistics, enabling training-free, model-agnostic detection. We introduce STALL, a simple, training-free, theoretically justified detector that provides likelihood-based scoring for videos, jointly modeling spatial and temporal evidence within a probabilistic framework. We evaluate STALL on two public benchmarks and introduce ComGenVid, a new benchmark with state-of-the-art generative models. STALL consistently outperforms prior image- and video-based baselines. Code and data are available at https://omerbenhayun.github.io/stall-video.

---

### One CT Unified Model Training Framework to Rule All Scanning Protocols

Authors: Fengzhi Xu, Ziyuan Yang, Zexin Lu, Yingyu Chen, Fenglei Fan, Hongming Shan, Yi Zhang
Published: 2026-03-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.15025v1

Non-ideal measurement computed tomography (NICT), which lowers radiation at the cost of image quality, is expanding the clinical use of CT. Although unified models have shown promise in NICT enhancement, most methods require paired data, which is an impractical demand due to inevitable organ motion. Unsupervised approaches attempt to overcome this limitation, but their assumption of homogeneous noise neglects the variability of scanning protocols, leading to poor generalization and potential model collapse. We further observe that distinct scanning protocols, which correspond to different physical imaging processes, produce discrete sub-manifolds in the feature space, contradicting these assumptions and limiting their effectiveness. To address this, we propose an Uncertainty-Guided Manifold Smoothing (UMS) framework to bridge the gaps between sub-manifolds. A classifier in UMS identifies sub-manifolds and predicts uncertainty scores, which guide the generation of diverse samples across the entire manifold. By leveraging the classifier's capability, UMS effectively fills the gaps between discrete sub-manifolds, and promotes a continuous and dense feature space. Due to the complexity of the global manifold, it's hard to directly model it. Therefore, we propose to dynamically incorporate the global- and sub-manifold-specific features. Specifically, we design a global- and sub-manifold-driven architecture guided by the classifier, which enables dynamic adaptation to subdomain variations. This dynamic mechanism improves the network's capacity to capture both shared and domain-specific features, thereby improving reconstruction performance. Extensive experiments on public datasets are conducted to validate the effectiveness of our method across different generation paradigms.

---

### Describing Agentic AI Systems with C4: Lessons from Industry Projects

Authors: Andreas Rausch, Stefan Wittek
Published: 2026-03-16
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2603.15021v1

Different domains foster different architectural styles -- and thus different documentation practices (e.g., state-based models for behavioral control vs. ER-style models for information structures). Agentic AI systems exhibit another characteristic style: specialized agents collaborate by exchanging artifacts, invoking external tools, and coordinating via recurring interaction patterns and quality gates. As these systems evolve into long-lived industrial solutions, documentation must capture these style-defining concerns rather than relying on ad-hoc code sketches or pipeline drawings. This paper reports industrial experience from joint projects and derives a documentation systematics tailored to this style. Concretely, we provide (i) a style-oriented modeling vocabulary and a small set of views for agents, artifacts, tools, and their coordination patterns, (ii) a hierarchical description technique aligned with C4 to structure these views across abstraction levels, and (iii) industrial examples with lessons learned that demonstrate how the approach yields transparent, maintainable architecture documentation supporting sustained evolution.

---

### MER-Bench: A Comprehensive Benchmark for Multimodal Meme Reappraisal

Authors: Yiqi Nie, Fei Wang, Junjie Chen, Kun Li, Yudi Cai, Dan Guo, Chenglong Li, Meng Wang
Published: 2026-03-16
Categories: cs.CV, cs.CL
arXiv: https://arxiv.org/abs/2603.15020v1

Memes represent a tightly coupled, multimodal form of social expression, in which visual context and overlaid text jointly convey nuanced affect and commentary. Inspired by cognitive reappraisal in psychology, we introduce Meme Reappraisal, a novel multimodal generation task that aims to transform negatively framed memes into constructive ones while preserving their underlying scenario, entities, and structural layout. Unlike prior works on meme understanding or generation, Meme Reappraisal requires emotion-controllable, structure-preserving multimodal transformation under multiple semantic and stylistic constraints. To support this task, we construct MER-Bench, a benchmark of real-world memes with fine-grained multimodal annotations, including source and target emotions, positively rewritten meme text, visual editing specifications, and taxonomy labels covering visual type, sentiment polarity, and layout structure. We further propose a structured evaluation framework based on a multimodal large language model (MLLM)-as-a-Judge paradigm, decomposing performance into modality-level generation quality, affect controllability, structural fidelity, and global affective alignment. Extensive experiments across representative image-editing and multimodal-generation systems reveal substantial gaps in satisfying the constraints of structural preservation, semantic consistency, and affective transformation. We believe MER-Bench establishes a foundation for research on controllable meme editing and emotion-aware multimodal generation. Our code is available at: https://github.com/one-seven17/MER-Bench.

---

### Reference-Free Omnidirectional Stereo Matching via Multi-View Consistency Maximization

Authors: Lehuai Xu, Weiming Zhang, Yang Li, Sidan Du, Lin Wang
Published: 2026-03-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.15019v1

Reliable omnidirectional depth estimation from multi-fisheye stereo matching is pivotal to many applications, such as embodied robotics. Existing approaches either rely on spherical sweeping with heuristic fusion strategies to build the cost columns or perform reference-centric stereo matching based on rectified views. However, these methods fail to explicitly exploit geometric relationships between multiple views, rendering them less capable of capturing the global dependencies, visibility, or scale changes. In this paper, we shift to a new perspective and propose a novel reference-free framework, dubbed FreeOmniMVS, via multi-view consistency maximization. The highlight of FreeOmniMVS is that it can aggregate pair-wise correlations into a robust, visibility-aware, and global consensus. As such, it is tolerant to occlusions, partial overlaps, and varying baselines. Specifically, to achieve global coherence, we introduce a novel View-pair Correlation Transformer (VCT) that explicitly models pairwise correlation volumes across all camera view pairs, allowing us to drop unreliable pairs caused by occlusion or out-of-focus observations. To realize scalable and visibility-aware consensus, we propose a lightweight attention mechanism that adaptively fuses the correlation vectors, eliminating the need for a designated reference view and allowing all cameras to contribute equally to the stereo matching process. Extensive experiments on diverse benchmark datasets demonstrate the superiority of our method for globally consistent, visibility-aware, and scale-aware omnidirectional depth estimation.

---

### Consequentialist Objectives and Catastrophe

Authors: Henrik Marklund, Alex Infanger, Benjamin Van Roy
Published: 2026-03-16
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2603.15017v3

Because human preferences are too complex to codify, AIs operate with misspecified objectives. Optimizing such objectives often produces undesirable outcomes; this phenomenon is known as reward hacking. Such outcomes are not necessarily catastrophic. Indeed, most examples of reward hacking in previous literature are benign. And typically, objectives can be modified to resolve the issue. We study the prospect of catastrophic outcomes induced by AIs operating in complex environments. We argue that, when capabilities are sufficiently advanced, pursuing a fixed consequentialist objective tends to result in catastrophic outcomes. We formalize this by establishing conditions that provably lead to such outcomes. Under these conditions, simple or random behavior is safe. Catastrophic risk arises due to extraordinary competence rather than incompetence. With a fixed consequentialist objective, avoiding catastrophe requires constraining AI capabilities. In fact, constraining capabilities the right amount not only averts catastrophe but yields valuable outcomes. Our results apply to any objective produced by modern industrial AI development pipelines.

---

### Riemannian Motion Generation: A Unified Framework for Human Motion Representation and Generation via Riemannian Flow Matching

Authors: Fangran Miao, Jian Huang, Ting Li
Published: 2026-03-16
Categories: cs.CV, stat.ML
arXiv: https://arxiv.org/abs/2603.15016v1

Human motion generation is often learned in Euclidean spaces, although valid motions follow structured non-Euclidean geometry. We present Riemannian Motion Generation (RMG), a unified framework that represents motion on a product manifold and learns dynamics via Riemannian flow matching. RMG factorizes motion into several manifold factors, yielding a scale-free representation with intrinsic normalization, and uses geodesic interpolation, tangent-space supervision, and manifold-preserving ODE integration for training and sampling. On HumanML3D, RMG achieves state-of-the-art FID in the HumanML3D format (0.043) and ranks first on all reported metrics under the MotionStreamer format. On MotionMillion, it also surpasses strong baselines (FID 5.6, R@1 0.86). Ablations show that the compact $\mathscr{T}+\mathscr{R}$ (translation + rotations) representation is the most stable and effective, highlighting geometry-aware modeling as a practical and scalable route to high-fidelity motion generation.

---

### Molecular Identifier Visual Prompt and Verifiable Reinforcement Learning for Chemical Reaction Diagram Parsing

Authors: Jiahe Song, Chuang Wang, Yinfan Wang, Hao Zheng, Rui Nie, Bowen Jiang, Xingjian Wei, Junyuan Gao, Yubin Wang, Bin Wang, Lijun Wu, Jiang Wu et al.
Published: 2026-03-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.15011v2

Reaction diagram parsing (RxnDP) is critical for extracting chemical synthesis information from literature. Although recent Vision-Language Models (VLMs) have emerged as a promising paradigm to automate this complex visual reasoning task, their application is fundamentally bottlenecked by the inability to align visual chemical entities with pre-trained knowledge, alongside the inherent discrepancy between token-level training and reaction-level evaluation. To address these dual challenges, this work enhances VLM-based RxnDP from two complementary perspectives: prompting representation and learning paradigms. First, we propose Identifier as Visual Prompting (IdtVP), which leverages naturally occurring molecule identifiers (e.g., bold numerals like 1a) to activate the chemical knowledge acquired during VLM pre-training. IdtVP enables powerful zero-shot and out-of-distribution capabilities, outperforming existing prompting strategies. Second, to further optimize performance within fine-tuning paradigms, we introduce Re3-DAPO, a reinforcement learning algorithm that leverages verifiable rewards to directly optimize reaction-level metrics, thereby achieving consistent gains over standard supervised fine-tuning. Additionally, we release the ScannedRxn benchmark, comprising scanned historical reaction diagrams with real-world artifacts, to rigorously assess model robustness and out-of-distribution ability. Our contributions advance the accuracy and generalization of VLM-based reaction diagram parsing. We will release data, models, and code on GitHub.

---

### TrajFlow: Nation-wide Pseudo GPS Trajectory Generation with Flow Matching Models

Authors: Peiran Li, Jiawei Wang, Haoran Zhang, Xiaodan Shi, Noboru Koshizuka, Chihiro Shimizu, Renhe Jiang
Published: 2026-03-16
Categories: cs.LG, cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2603.15009v1

The importance of mobile phone GPS trajectory data is widely recognized across many fields, yet the use of real data is often hindered by privacy concerns, limited accessibility, and high acquisition costs. As a result, generating pseudo-GPS trajectory data has become an active area of research. Recent diffusion-based approaches have achieved strong fidelity but remain limited in spatial scale (small urban areas), transportation-mode diversity, and efficiency (requiring numerous sampling steps). To address these challenges, we introduce TrajFlow, which to the best of our knowledge is the first flow-matching-based generative model for GPS trajectory generation. TrajFlow leverages the flow-matching paradigm to improve robustness and efficiency across multiple geospatial scales, and incorporates a trajectory harmonization and reconstruction strategy to jointly address scalability, diversity, and efficiency. Using a nationwide mobile phone GPS dataset with millions of trajectories across Japan, we show that TrajFlow or its variants consistently outperform diffusion-based and deep generative baselines at urban, metropolitan, and nationwide levels. As the first nationwide, multi-scale GPS trajectory generation model, TrajFlow demonstrates strong potential to support inter-region urban planning, traffic management, and disaster response, thereby advancing the resilience and intelligence of future mobility systems.

---

### Clue Matters: Leveraging Latent Visual Clues to Empower Video Reasoning

Authors: Kaixin zhang, Xiaohe Li, Jiahao Li, Haohua Wu, Xinyu Zhao, Zide Fan, Lei Wang
Published: 2026-03-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.15008v1

Multi-modal Large Language Models (MLLMs) have significantly advanced video reasoning, yet Video Question Answering (VideoQA) remains challenging due to its demand for temporal causal reasoning and evidence-grounded answer generation. Prevailing end-to-end MLLM frameworks lack explicit structured reasoning between visual perception and answer derivation, causing severe hallucinations and poor interpretability. Existing methods also fail to address three core gaps: faithful visual clue extraction, utility-aware clue filtering, and end-to-end clue-answer alignment. Inspired by hierarchical human visual cognition, we propose ClueNet, a clue-aware video reasoning framework with a two-stage supervised fine-tuning paradigm without extensive base model modifications. Decoupled supervision aligns clue extraction and chain-based reasoning, while inference supervision with an adaptive clue filter refines high-order reasoning, alongside lightweight modules for efficient inference. Experiments on NExT-QA, STAR, and MVBench show that ClueNet outperforms state-of-the-art methods by $\ge$ 1.1%, with superior generalization, hallucination mitigation, inference efficiency, and cross-backbone compatibility. This work bridges the perception-to-generation gap in MLLM video understanding, providing an interpretable, faithful reasoning paradigm for high-stakes VideoQA applications.

---

### Empowering Chemical Structures with Biological Insights for Scalable Phenotypic Virtual Screening

Authors: Xiaoqing Lian, Pengsen Ma, Tengfeng Ma, Zhonghao Ren, Xibao Cai, Zhixiang Cheng, Bosheng Song, He Wang, Xiang Pan, Yangyang Chen, Sisi Yuan, Chen Lin
Published: 2026-03-16
Categories: q-bio.QM, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2603.15006v1

Motivation: The scalable identification of bioactive compounds is essential for contemporary drug discovery. This process faces a key trade-off: structural screening offers scalability but lacks biological context, whereas high-content phenotypic profiling provides deep biological insights but is resource-intensive. The primary challenge is to extract robust biological signals from noisy data and encode them into representations that do not require biological data at inference. Results: This study presents DECODE (DEcomposing Cellular Observations of Drug Effects), a framework that bridges this gap by empowering chemical representations with intrinsic biological semantics to enable structure-based in silico biological profiling. DECODE leverages limited paired transcriptomic and morphological data as supervisory signals during training, enabling the extraction of a measurement-invariant biological fingerprint from chemical structures and explicit filtering of experimental noise. Our evaluations demonstrate that DECODE retrieves functionally similar drugs in zero-shot settings with over 20% relative improvement over chemical baselines in mechanism-of-action (MOA) prediction. Furthermore, the framework achieves a 6-fold increase in hit rates for novel anti-cancer agents during external validation. Availability and implementation: The codes and datasets of DECODE are available at https://github.com/lian-xiao/DECODE.

---

### Pretraining and Benchmarking Modern Encoders for Latvian

Authors: Arturs Znotins
Published: 2026-03-16
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.15005v1

Encoder-only transformers remain essential for practical NLP tasks. While recent advances in multilingual models have improved cross-lingual capabilities, low-resource languages such as Latvian remain underrepresented in pretraining corpora, and few monolingual Latvian encoders currently exist. We address this gap by pretraining a suite of Latvian-specific encoders based on RoBERTa, DeBERTaV3, and ModernBERT architectures, including long-context variants, and evaluating them across a diverse set of Latvian diagnostic and linguistic benchmarks. Our models are competitive with existing monolingual and multilingual encoders while benefiting from recent architectural and efficiency advances. Our best model, lv-deberta-base (111M parameters), achieves the strongest overall performance, outperforming larger multilingual baselines and prior Latvian-specific encoders. We release all pretrained models and evaluation resources to support further research and practical applications in Latvian NLP.

---

### Edit2Interp: Adapting Image Foundation Models from Spatial Editing to Video Frame Interpolation with Few-Shot Learning

Authors: Nasrin Rahimi, Mısra Yavuz, Burak Can Biner, Yunus Bilge Kurt, Ahmet Rasim Emirdağı, Süleyman Aslan, Görkay Aydemir, M. Akın Yılmaz, A. Murat Tekalp
Published: 2026-03-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.15003v1

Pre-trained image editing models exhibit strong spatial reasoning and object-aware transformation capabilities acquired from billions of image-text pairs, yet they possess no explicit temporal modeling. This paper demonstrates that these spatial priors can be repurposed to unlock temporal synthesis capabilities through minimal adaptation - without introducing any video-specific architecture or motion estimation modules. We show that a large image editing model (Qwen-Image-Edit), originally designed solely for static instruction-based edits, can be adapted for Video Frame Interpolation (VFI) using only 64-256 training samples via Low-Rank Adaptation (LoRA). Our core contribution is revealing that the model's inherent understanding of "how objects transform" in static scenes contains latent temporal reasoning that can be activated through few-shot fine-tuning. While the baseline model completely fails at producing coherent intermediate frames, our parameter-efficient adaptation successfully unlocks its interpolation capability. Rather than competing with task-specific VFI methods trained from scratch on massive datasets, our work establishes that foundation image editing models possess untapped potential for temporal tasks, offering a data-efficient pathway for video synthesis in resource-constrained scenarios. This bridges the gap between image manipulation and video understanding, suggesting that spatial and temporal reasoning may be more intertwined in foundation models than previously recognized

---

### MONET: Modeling and Optimization of neural NEtwork Training from Edge to Data Centers

Authors: Jérémy Morlier, Robin Geens, Stef Cuyckens, Arne Symons, Marian Verhelst, Vincent Gripon, Mathieu Léonardon
Published: 2026-03-16
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.15002v1

While hardware-software co-design has significantly improved the efficiency of neural network inference, modeling the training phase remains a critical yet underexplored challenge. Training workloads impose distinct constraints, particularly regarding memory footprint and backpropagation complexity, which existing inference-focused tools fail to capture. This paper introduces MONET, a framework designed to model the training of neural networks on heterogeneous dataflow accelerators. MONET builds upon Stream, an experimentally verified framework that that models the inference of neural networks on heterogeneous dataflow accelerators with layer fusion. Using MONET, we explore the design space of ResNet-18 and a small GPT-2, demonstrating the framework's capability to model training workflows and find better hardware architectures. We then further examine problems that become more complex in neural network training due to the larger design space, such as determining the best layer-fusion configuration. Additionally, we use our framework to find interesting trade-offs in activation checkpointing, with the help of a genetic algorithm. Our findings highlight the importance of a holistic approach to hardware-software co-design for scalable and efficient deep learning deployment.

---

### How Log-Barrier Helps Exploration in Policy Optimization

Authors: Leonardo Cesani, Matteo Papini, Marcello Restelli
Published: 2026-03-16
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.15001v2

Recently, it has been shown that the Stochastic Gradient Bandit (SGB) algorithm converges to a globally optimal policy with a constant learning rate. However, these guarantees rely on unrealistic assumptions about the learning process, namely that the probability of the optimal action is always bounded away from zero. We attribute this to the lack of an explicit exploration mechanism in SGB. To address these limitations, we propose to regularize the SGB objective with a log-barrier on the parametric policy, structurally enforcing a minimal amount of exploration. We prove that Log-Barrier Stochastic Gradient Bandit (LB-SGB) matches the sample complexity of SGB, but also converges (at a slower rate) without any assumptions on the learning process. We also show a connection between the log-barrier regularization and Natural Policy Gradient, as both exploit the geometry of the policy space by controlling the Fisher information. We validate our theoretical findings through numerical simulations, showing the benefits of the log-barrier regularization.

---

### Thermal Image Refinement with Depth Estimation using Recurrent Networks for Monocular ORB-SLAM3

Authors: Hürkan Şahin, Huy Xuan Pham, Van Huyen Dang, Alper Yegenoglu, Erdal Kayacan
Published: 2026-03-16
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2603.14998v1

Autonomous navigation in GPS-denied and visually degraded environments remains challenging for unmanned aerial vehicles (UAVs). To this end, we investigate the use of a monocular thermal camera as a standalone sensor on a UAV platform for real-time depth estimation and simultaneous localization and mapping (SLAM). To extract depth information from thermal images, we propose a novel pipeline employing a lightweight supervised network with recurrent blocks (RBs) integrated to capture temporal dependencies, enabling more robust predictions. The network combines lightweight convolutional backbones with a thermal refinement network (T-RefNet) to refine raw thermal inputs and enhance feature visibility. The refined thermal images and predicted depth maps are integrated into ORB-SLAM3, enabling thermal-only localization. Unlike previous methods, the network is trained on a custom non-radiometric dataset, obviating the need for high-cost radiometric thermal cameras. Experimental results on datasets and UAV flights demonstrate competitive depth accuracy and robust SLAM performance under low-light conditions. On the radiometric VIVID++ (indoor-dark) dataset, our method achieves an absolute relative error of approximately 0.06, compared to baselines exceeding 0.11. In our non-radiometric indoor set, baseline errors remain above 0.24, whereas our approach remains below 0.10. Thermal-only ORB-SLAM3 maintains a mean trajectory error under 0.4 m.

---

### OrgForge: A Multi-Agent Simulation Framework for Verifiable Synthetic Corporate Corpora

Authors: Jeffrey Flynt
Published: 2026-03-16
Categories: cs.CL, cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2603.14997v2

Building and evaluating enterprise AI systems requires synthetic organizational corpora that are internally consistent, temporally structured, and cross-artifact traceable. Existing corpora either carry legal constraints or inherit hallucination artifacts from the generating LLMs, silently corrupting results when timestamps or facts contradict across documents and reinforcing those errors during training. We present OrgForge, an open-source multi-agent simulation framework that enforces a strict physics-cognition boundary: a deterministic Python engine maintains a SimEvent ground-truth bus while LLMs generate only surface prose. OrgForge simulates the organizational processes that produce documents, not the documents themselves. Engineers leave mid-sprint, triggering incident handoffs and CRM ownership lapses. Knowledge gaps emerge when under-documented systems break and recover through organic documentation and incident resolution. Customer emails fire only when simulation state warrants contact; silence is verifiable ground truth. A live CRM state machine extends the physics-cognition boundary to the customer boundary, producing cross-system causal cascades spanning engineering incidents, support escalation, deal risk flagging, and SLA-adjusted invoices. The framework generates fifteen interleaved artifact categories traceable to a shared immutable event log. Four graph-dynamic subsystems govern organizational behavior independently of any LLM. An embedding-based ticket assignment system using the Hungarian algorithm makes the simulation domain-agnostic. An empirical evaluation across ten incidents demonstrates a 0.46 absolute improvement in prose-to-ground-truth fidelity over chained LLM baselines, and isolates a consistent hallucination failure mode in which chaining propagates fabricated facts faithfully across documents without correcting them.

---

### Exposing Cross-Modal Consistency for Fake News Detection in Short-Form Videos

Authors: Chong Tian, Yu Wang, Chenxu Yang, Junyi Guan, Zheng Lin, Yuhan Liu, Xiuying Chen, Qirong Ho
Published: 2026-03-16
Categories: cs.AI, cs.MM
arXiv: https://arxiv.org/abs/2603.14992v1

Short-form video platforms are major channels for news but also fertile ground for multimodal misinformation where each modality appears plausible alone yet cross-modal relationships are subtly inconsistent, like mismatched visuals and captions. On two benchmark datasets, FakeSV (Chinese) and FakeTT (English), we observe a clear asymmetry: real videos exhibit high text-visual but moderate text-audio consistency, while fake videos show the opposite pattern. Moreover, a single global consistency score forms an interpretable axis along which fake probability and prediction errors vary smoothly. Motivated by these observations, we present MAGIC3 (Modal-Adversarial Gated Interaction and Consistency-Centric Classifier), a detector that explicitly models and exposes cross-tri-modal consistency signals at multiple granularities. MAGIC3 combines explicit pairwise and global consistency modeling with token- and frame-level consistency signals derived from cross-modal attention, incorporates multi-style LLM rewrites to obtain style-robust text representations, and employs an uncertainty-aware classifier for selective VLM routing. Using pre-extracted features, MAGIC3 consistently outperforms the strongest non-VLM baselines on FakeSV and FakeTT. While matching VLM-level accuracy, the two-stage system achieves 18-27x higher throughput and 93% VRAM savings, offering a strong cost-performance tradeoff.

---

### MMSpec: Benchmarking Speculative Decoding for Vision-Language Models

Authors: Hui Shen, Xin Wang, Ping Zhang, Yunta Hsieh, Qi Han, Zhongwei Wan, Ziheng Zhang, Jingxuan Zhang, Jing Xiong, Ziyuan Liu, Yifan Zhang, Hangrui Cao et al.
Published: 2026-03-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.14989v1

Vision-language models (VLMs) achieve strong performance on multimodal tasks but suffer from high inference latency due to large model sizes and long multimodal contexts. Speculative decoding has recently emerged as an effective acceleration technique, yet its behavior in VLMs remains insufficiently understood. We introduce MMSpec, the first benchmark for evaluating speculative decoding in vision-language models. MMSpec contains 600 multimodal samples across six task categories and integrates ten representative speculative decoding algorithms under a unified evaluation framework. Our study reveals three key findings: (1) methods designed for text-only LLMs degrade in multimodal scenarios, (2) vision awareness becomes increasingly important at larger batch sizes, and (3) throughput speedup alone does not reliably reflect latency performance. Motivated by these findings, we propose ViSkip, a plug-and-play speculative decoding method that dynamically adapts speculation to vision tokens and achieves state-of-the-art performance.

---

### Beyond Benchmark Islands: Toward Representative Trustworthiness Evaluation for Agentic AI

Authors: Jinhu Qi, Yifan Li, Minghao Zhao, Wentao Zhang, Zijian Zhang, Yaoman Li, Irwin King
Published: 2026-03-16
Categories: cs.CL, cs.DB
arXiv: https://arxiv.org/abs/2603.14987v2

Agentic AI systems increasingly act through tool-augmented, multi-step workflows whose failures (unsafe tool use, unauthorised actions, social harm) carry deployment-level consequences. Evaluation practice remains fragmented across isolated benchmark slices, and "trustworthiness" is frequently invoked but rarely defined operationally. We argue the central limitation is twofold: (i) the absence of a measurable specification of what agent trustworthiness means, and (ii) the lack of a principled notion of representativeness allowing assessment over a socio-technical scenario distribution rather than disconnected benchmark instances. We address (i) by defining agentic trustworthiness as a five-property profile (Reliability, Robustness, Safety, Social-Ethical Alignment, Operational Integrity) grounded in current AI risk frameworks, and (ii) with the Holographic Agent Assessment Framework (HAAF), which measures this profile over a scenario manifold through static policy analysis, sandbox simulation, social-ethical alignment assessment, and distribution-aware sampling, connected through an iterative Trustworthy Optimization Factory that converts red-team diagnoses into blue-team interventions. Our contributions are: (1) an operational five-property definition of agentic trustworthiness; (2) a distribution-aware scenario-sampling framework that surfaces property-level trade-offs invisible to scalar leaderboards; and (3) a cross-family transfer experiment in which interventions designed from a single focal model generalise -- without per-model or per-scenario tuning -- to 13 systems from seven model families (Llama, Mistral, Kimi, GLM, Qwen, GPT, DeepSeek) on a 100-scenario suite, where all 13 systems improve and two reach a perfect risk-weighted profile, establishing HAAF's Factory as a model-agnostic deployment-readiness pipeline. Code: https://github.com/TonyQJH/haaf-pilot

---

### Anchoring Emotions in Text: Robust Multimodal Fusion for Mimicry Intensity Estimation

Authors: Lingsi Zhu, Yuefeng Zou, Yunxiang Zhang, Naixiang Zheng, Guoyuan Wang, Jun Yu, Jiaen Liang, Wei Huang, Shengping Liu, Ximin Zheng
Published: 2026-03-16
Categories: cs.MM, cs.CV
arXiv: https://arxiv.org/abs/2603.14976v1

Estimating Emotional Mimicry Intensity (EMI) in naturalistic environments is a critical yet challenging task in affective computing. The primary difficulty lies in effectively modeling the complex, nonlinear temporal dynamics across highly heterogeneous modalities, especially when physical signals are corrupted or missing. To tackle this, we propose TAEMI (Text-Anchored Emotional Mimicry Intensity estimation), a novel multimodal framework designed for the 10th ABAW Competition. Motivated by the observation that continuous visual and acoustic signals are highly susceptible to transient environmental noise, we break the traditional symmetric fusion paradigm. Instead, we leverage textual transcript--which inherently encode a stable, time-independent semantic prior--as central anchors. Specifically, we introduce a Text-Anchored Dual Cross-Attention mechanism that utilizes these robust textual queries to actively filter out frame-level redundancies and align the noisy physical streams. Furthermore, to prevent catastrophic performance degradation caused by inevitably missing data in unconstrained real-world scenarios, we integrate Learnable Missing-Modality Tokens and a Modality Dropout strategy during training. Extensive experiments on the Hume-Vidmimic2 dataset demonstrate that TAEMI effectively captures fine-grained emotional variations and maintains robust predictive resilience under imperfect conditions. Our framework achieves a state-of-the-art mean Pearson correlation coefficient across six continuous emotional dimensions, significantly outperforming existing baseline methods.

---

### Why Agents Compromise Safety Under Pressure

Authors: Hengle Jiang, Ke Tang
Published: 2026-03-16
Categories: cs.AI, cs.CL, cs.CY, cs.MA
arXiv: https://arxiv.org/abs/2603.14975v2

Large Language Model agents deployed in complex environments frequently encounter a conflict between maximizing goal achievement and adhering to safety constraints. This paper identifies a new concept called Agentic Pressure, which characterizes the endogenous tension emerging when compliant execution becomes infeasible. We demonstrate that under this pressure agents exhibit normative drift where they strategically sacrifice safety to preserve utility. Notably we find that advanced reasoning capabilities accelerate this decline as models construct linguistic rationalizations to justify violation. Finally, we analyze the root causes and explore preliminary mitigation strategies, such as pressure isolation, which attempts to restore alignment by decoupling decision-making from pressure signals.

---

### Voronoi-based Second-order Descriptor with Whitened Metric in LiDAR Place Recognition

Authors: Jaein Kim, Hee Bin Yoo, Dong-Sig Han, Byoung-Tak Zhang
Published: 2026-03-16
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2603.14974v1

The pooling layer plays a vital role in aggregating local descriptors into the metrizable global descriptor in the LiDAR Place Recognition (LPR). In particular, the second-order pooling is capable of capturing higher-order interactions among local descriptors. However, its existing methods in the LPR adhere to conventional implementations and post-normalization, and incur the descriptor unsuitable for Euclidean distancing. Based on the recent interpretation that associates NetVLAD with the second-order statistics, we propose to integrate second-order pooling with the inductive bias from Voronoi cells. Our novel pooling method aggregates local descriptors to form the second-order matrix and whitens the global descriptor to implicitly measure the Mahalanobis distance while conserving the cluster property from Voronoi cells, addressing its numerical instability during learning with diverse techniques. We demonstrate its performance gains through the experiments conducted on the Oxford Robotcar and Wild-Places benchmarks and analyze the numerical effect of the proposed whitening algorithm.

---

### Rethinking LLM Watermark Detection in Black-Box Settings: A Non-Intrusive Third-Party Framework

Authors: Zhuoshang Wang, Yubing Ren, Yanan Cao, Fang Fang, Xiaoxue Li, Li Guo
Published: 2026-03-16
Categories: cs.CR, cs.CL
arXiv: https://arxiv.org/abs/2603.14968v2

While watermarking serves as a critical mechanism for LLM provenance, existing secret-key schemes tightly couple detection with injection, requiring access to keys or provider-side scheme-specific detectors for verification. This dependency creates a fundamental barrier for real-world governance, as independent auditing becomes impossible without compromising model security or relying on the opaque claims of service providers. To resolve this dilemma, we introduce TTP-Detect, a pioneering black-box framework designed for non-intrusive, third-party watermark verification. By decoupling detection from injection, TTP-Detect reframes verification as a relative hypothesis testing problem. It employs a proxy model to amplify watermark-relevant signals and a suite of complementary relative measurements to assess the alignment of the query text with watermarked distributions. Extensive experiments across representative watermarking schemes, datasets and models demonstrate that TTP-Detect achieves superior detection performance and robustness against diverse attacks.

---

### GeoNVS: Geometry Grounded Video Diffusion for Novel View Synthesis

Authors: Minjun Kang, Inkyu Shin, Taeyeop Lee, Myungchul Kim, In So Kweon, Kuk-Jin Yoon
Published: 2026-03-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.14965v2

Novel view synthesis requires strong 3D geometric consistency and the ability to generate visually coherent images across diverse viewpoints. While recent camera-controlled video diffusion models show promising results, they often suffer from geometric distortions and limited camera controllability. To overcome these challenges, we introduce GeoNVS, a geometry-grounded novel-view synthesizer that enhances both geometric fidelity and camera controllability through explicit 3D geometric guidance. Our key innovation is the Gaussian Splat Feature Adapter (GS-Adapter), which lifts input-view diffusion features into 3D Gaussian representations, renders geometry-constrained novel-view features, and adaptively fuses them with diffusion features to correct geometrically inconsistent representations. Unlike prior methods that inject geometry at the input level, GS-Adapter operates in feature space, avoiding view-dependent color noise that degrades structural consistency. Its plug-and-play design enables zero-shot compatibility with diverse feed-forward geometry models without additional training, and can be adapted to other video diffusion backbones. Experiments across 9 scenes and 18 settings demonstrate state-of-the-art performance, achieving 11.3% and 14.9% improvements over SEVA and CameraCtrl, with up to 2x reduction in translation error and 7x in Chamfer Distance.

---

### Lightweight User-Personalization Method for Closed Split Computing

Authors: Yuya Okada, Takayuki Nishio
Published: 2026-03-16
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.14958v1

Split Computing enables collaborative inference between edge devices and the cloud by partitioning a deep neural network into an edge-side head and a server-side tail, reducing latency and limiting exposure of raw input data. However, inference performance often degrades in practical deployments due to user-specific data distribution shifts, unreliable communication, and privacy-oriented perturbations, especially in closed environments where model architectures and parameters are inaccessible. To address this challenge, we propose SALT (Split-Adaptive Lightweight Tuning), a lightweight adaptation framework for closed Split Computing systems. SALT introduces a compact client-side adapter that refines intermediate representations produced by a frozen head network, enabling effective model adaptation without modifying the head or tail networks or increasing communication overhead. By modifying only the training conditions, SALT supports multiple adaptation objectives, including user personalization, communication robustness, and privacy-aware inference. Experiments using ResNet-18 on CIFAR-10 and CIFAR-100 show that SALT achieves higher accuracy than conventional retraining and fine-tuning while significantly reducing training cost. On CIFAR-10, SALT improves personalized accuracy from 88.1% to 93.8% while reducing training latency by more than 60%. SALT also maintains over 90% accuracy under 75% packet loss and preserves high accuracy (about 88% at sigma = 1.0) under noise injection. These results demonstrate that SALT provides an efficient and practical adaptation framework for real-world Split Computing systems.

---

### CyCLeGen: Cycle-Consistent Layout Prediction and Image Generation in Vision Foundation Models

Authors: Xiaojun Shan, Haoyu Shen, Yucheng Mao, Xiang Zhang, Abhay Anand, Bingnan Li, Haiyang Xu, Zhuowen Tu
Published: 2026-03-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.14957v1

We present CyCLeGen, a unified vision-language foundation model capable of both image understanding and image generation within a single autoregressive framework. Unlike existing vision models that depend on separate modules for perception and synthesis, CyCLeGen adopts a fully integrated architecture that enforces cycle-consistent learning through image->layout->image and layout->image->layout generation loops. This unified formulation introduces two key advantages: introspection, enabling the model to reason about its own generations, and data efficiency, allowing self-improvement via synthetic supervision under a reinforcement learning objective guided by cycle consistency. Extensive experiments show that CyCLeGen achieves significant gains across diverse image understanding and generation benchmarks, highlighting the potential of unified vision-language foundation models.

---

### SFedHIFI: Fire Rate-Based Heterogeneous Information Fusion for Spiking Federated Learning

Authors: Ran Tao, Qiugang Zhan, Shantian Yang, Xiurui Xie, Qi Tian, Guisong Liu
Published: 2026-03-16
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.14956v1

Spiking Federated Learning (SFL) has been widely studied with the energy efficiency of Spiking Neural Networks (SNNs). However, existing SFL methods require model homogeneity and assume all clients have sufficient computational resources, resulting in the exclusion of some resource-constrained clients. To address the prevalent system heterogeneity in real-world scenarios, enabling heterogeneous SFL systems that allow clients to adaptively deploy models of different scales based on their local resources is crucial. To this end, we introduce SFedHIFI, a novel Spiking Federated Learning framework with Fire Rate-Based Heterogeneous Information Fusion. Specifically, SFedHIFI employs channel-wise matrix decomposition to deploy SNN models of adaptive complexity on clients with heterogeneous resources. Building on this, the proposed heterogeneous information fusion module enables cross-scale aggregation among models of different widths, thereby enhancing the utilization of diverse local knowledge. Extensive experiments on three public benchmarks demonstrate that SFedHIFI can effectively enable heterogeneous SFL, consistently outperforming all three baseline methods. Compared with ANN-based FL, it achieves significant energy savings with only a marginal trade-off in accuracy.

---

### Learning Question-Aware Keyframe Selection with Synthetic Supervision for Video Question Answering

Authors: Minchan Kwon, Hyounguk Shon, Junmo Kim
Published: 2026-03-16
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.14953v1

Large multimodal models (LMMs) have recently demonstrated remarkable performance in video question answering (VideoQA), yet reasoning over video remains challenging due to high inference cost and diluted information. Keyframe selection offers efficiency and sharper reasoning but suffers from sparse supervision and redundant frame choices when relying only on image-text similarity. We present a question-aware keyframe selection framework with two components: pseudo keyframe labels derived from LMMs that provide informative supervision and a coverage regularization that promotes diverse, complementary evidence across time. Experiments on NExT-QA show that our method significantly improves accuracy, especially for temporal and causal question types, establishing keyframe selection as an effective and learnable module for VideoQA.

---

### Pansharpening for Thin-Cloud Contaminated Remote Sensing Images: A Unified Framework and Benchmark Dataset

Authors: Songcheng Du, Yang Zou, Jiaxin Li, Mingxuan Liu, Ying Li, Changjing Shang, Qiang Shen
Published: 2026-03-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.14952v1

Pansharpening under thin cloudy conditions is a practically significant yet rarely addressed task, challenged by simultaneous spatial resolution degradation and cloud-induced spectral distortions. Existing methods often address cloud removal and pansharpening sequentially, leading to cumulative errors and suboptimal performance due to the lack of joint degradation modeling. To address these challenges, we propose a Unified Pansharpening Model with Thin Cloud Removal (Pan-TCR), an end-to-end framework that integrates physical priors. Motivated by theoretical analysis in the frequency domain, we design a frequency-decoupled restoration (FDR) block that disentangles the restoration of multispectral image (MSI) features into amplitude and phase components, each guided by complementary degradation-robust prompts: the near-infrared (NIR) band amplitude for cloud-resilient restoration, and the panchromatic (PAN) phase for high-resolution structural enhancement. To ensure coherence between the two components, we further introduce an interactive inter-frequency consistency (IFC) module, enabling cross-modal refinement that enforces consistency and robustness across frequency cues. Furthermore, we introduce the first real-world thin-cloud contaminated pansharpening dataset (PanTCR-GF2), comprising paired clean and cloudy PAN-MSI images, to enable robust benchmarking under realistic conditions. Extensive experiments on real-world and synthetic datasets demonstrate the superiority and robustness of Pan-TCR, establishing a new benchmark for pansharpening under realistic atmospheric degradations.

---

### GT-PCQA: Geometry-Texture Decoupled Point Cloud Quality Assessment with MLLM

Authors: Guohua Zhang, Jian Jin, Meiqin Liu, Chao Yao, Weisi Lin, Yao Zhao
Published: 2026-03-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.14951v1

With the rapid advancement of Multi-modal Large Language Models (MLLMs), MLLM-based Image Quality Assessment (IQA) methods have shown promising generalization. However, directly extending these MLLM-based IQA methods to PCQA remains challenging. On the one hand, existing PCQA datasets are limited in scale, which hinders stable and effective instruction tuning of MLLMs. On the other hand, due to large-scale image-text pretraining, MLLMs tend to rely on texture-dominant reasoning and are insufficiently sensitive to geometric structural degradations that are critical for PCQA. To address these gaps, we propose a novel MLLM-based no-reference PCQA framework, termed GT-PCQA, which is built upon two key strategies. First, to enable stable and effective instruction tuning under scarce PCQA supervision, a 2D-3D joint training strategy is proposed. This strategy formulates PCQA as a relative quality comparison problem to unify large-scale IQA datasets with limited PCQA datasets. It incorporates a parameter-efficient Low-Rank Adaptation (LoRA) scheme to support instruction tuning. Second, a geometry-texture decoupling strategy is presented, which integrates a dual-prompt mechanism with an alternating optimization scheme to mitigate the inherent texture-dominant bias of pre-trained MLLMs, while enhancing sensitivity to geometric structural degradations. Extensive experiments demonstrate that GT-PCQA achieves competitive performance and exhibits strong generalization.

---

### Bridging Scene Generation and Planning: Driving with World Model via Unifying Vision and Motion Representation

Authors: Xingtai Gui, Meijie Zhang, Tianyi Yan, Wencheng Han, Jiahao Gong, Feiyang Tan, Cheng-zhong Xu, Jianbing Shen
Published: 2026-03-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.14948v1

End-to-end autonomous driving aims to generate safe and plausible planning policies from raw sensor input. Driving world models have shown great potential in learning rich representations by predicting the future evolution of a driving scene. However, existing driving world models primarily focus on visual scene representation, and motion representation is not explicitly designed to be planner-shared and inheritable, leaving a schism between the optimization of visual scene generation and the requirements of precise motion planning. We present WorldDrive, a holistic framework that couples scene generation and real-time planning via unifying vision and motion representation. We first introduce a Trajectory-aware Driving World Model, which conditions on a trajectory vocabulary to enforce consistency between visual dynamics and motion intentions, enabling the generation of diverse and plausible future scenes conditioned on a specific trajectory. We transfer the vision and motion encoders to a downstream Multi-modal Planner, ensuring the driving policy operates on mature representations pre-optimized by scene generation. A simple interaction between motion representation, visual representation, and ego status can generate high-quality, multi-modal trajectories. Furthermore, to exploit the world model's foresight, we propose a Future-aware Rewarder, which distills future latent representation from the frozen world model to evaluate and select optimal trajectories in real-time. Extensive experiments on the NAVSIM, NAVSIM-v2, and nuScenes benchmarks demonstrate that WorldDrive achieves leading planning performance among vision-only methods while maintaining high-fidelity action-controlled video generation capabilities, providing strong evidence for the effectiveness of unifying vision and motion representation for robust autonomous driving.

---

### FairMed-XGB: A Bayesian-Optimised Multi-Metric Framework with Explainability for Demographic Equity in Critical Healthcare Data

Authors: Mitul Goswami, Romit Chatterjee, Arif Ahmed Sekh
Published: 2026-03-16
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.14947v1

Machine learning models deployed in critical care settings exhibit demographic biases, particularly gender disparities, that undermine clinical trust and equitable treatment. This paper introduces FairMed-XGB, a novel framework that systematically detects and mitigates gender-based prediction bias while preserving model performance and transparency. The framework integrates a fairness-aware loss function combining Statistical Parity Difference, Theil Index, and Wasserstein Distance, jointly optimised via Bayesian Search into an XGBoost classifier. Post-mitigation evaluation on seven clinically distinct cohorts derived from the MIMIC-IV-ED and eICU databases demonstrates substantial bias reduction: Statistical Parity Difference decreases by 40 to 51 percent on MIMIC-IV-ED and 10 to 19 percent on eICU; Theil Index collapses by four to five orders of magnitude to near-zero values; Wasserstein Distance is reduced by 20 to 72 percent. These gains are achieved with negligible degradation in predictive accuracy (AUC-ROC drop <0.02). SHAP-based explainability reveals that the framework diminishes reliance on gender-proxy features, providing clinicians with actionable insights into how and where bias is corrected. FairMed-XGB offers a robust, interpretable, and ethically aligned solution for equitable clinical decision-making, paving the way for trustworthy deployment of AI in high-stakes healthcare environments.

---

### Spiking Layer-Adaptive Magnitude-based Pruning

Authors: Junqiao Wang, Zhehang Ye, Yuqi Ouyang
Published: 2026-03-16
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.14946v1

Spiking Neural Networks (SNNs) provide energy-efficient computation but their deployment is constrained by dense connectivity and high spiking operation costs. Existing magnitude-based pruning strategies, when naively applied to SNNs, fail to account for temporal accumulation, non-uniform timestep contributions, and membrane stability, often leading to severe performance degradation. This paper proposes Spiking Layer-Adaptive Magnitude-based Pruning (SLAMP), a theory-guided pruning framework that generalizes layer-adaptive magnitude pruning to temporal SNNs by explicitly controlling worst-case output distortion across layers and timesteps. SLAMP formulates sparsity allocation as a temporal distortion-constrained optimization problem, yielding time-aware layer importance scores that reduce to conventional layer-adaptive pruning in single-timestep limit. An efficient two-stage procedure is derived, combining temporal score estimation, global sparsity allocation, and magnitude pruning with retraining for stability recovery. Experiments on CIFAR10, CIFAR100, and the event-based CIFAR10-DVS datasets demonstrate that SLAMP achieves substantial connectivity and spiking operation reductions while preserving accuracy, enabling efficient and deployable SNN inference.

---

### Ultra-Early Prediction of Tipping Points: Integrating Dynamical Measures with Reservoir Computing

Authors: Xin Li, Qunxi Zhu, Chengli Zhao, Bolin Zhao, Xue Zhang, Xiaojun Duan, Wei Lin
Published: 2026-03-16
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.14944v1

Complex dynamical systems-such as climate, ecosystems, and economics-can undergo catastrophic and potentially irreversible regime changes, often triggered by environmental parameter drift and stochastic disturbances. These critical thresholds, known as tipping points, pose a prediction problem of both theoretical and practical significance, yet remain largely unresolved. To address this, we articulate a model-free framework that integrates the measures characterizing the stability and sensitivity of dynamical systems with the reservoir computing (RC), a lightweight machine learning technique, using only observational time series data. The framework consists of two stages. The first stage involves using RC to robustly learn local complex dynamics from observational data segmented into windows. The second stage focuses on accurately detecting early warning signals of tipping points by analyzing the learned autonomous RC dynamics through dynamical measures, including the dominant eigenvalue of the Jacobian matrix, the maximum Floquet multiplier, and the maximum Lyapunov exponent. Furthermore, when these dynamical measures exhibit trend-like patterns, their extrapolation enables ultra-early prediction of tipping points significantly prior to the occurrence of critical transitions. We conduct a rigorous theoretical analysis of the proposed method and perform extensive numerical evaluations on a series of representative synthetic systems and eight real-world datasets, as well as quantitatively predict the tipping time of the Atlantic Meridional Overturning Circulation system. Experimental results demonstrate that our framework exhibits advantages over the baselines in comprehensive evaluations, particularly in terms of dynamical interpretability, prediction stability and robustness, and ultra-early prediction capability.

---

### RS-WorldModel: a Unified Model for Remote Sensing Understanding and Future Sense Forecasting

Authors: Linrui Xu, Zhongan Wang, Fei Shen, Gang Xu, Huiping Zhuang, Ming Li, Haifeng Li
Published: 2026-03-16
Categories: cs.AI
arXiv: https://arxiv.org/abs/2603.14941v1

Remote sensing world models aim to both explain observed changes and forecast plausible futures, two tasks that share spatiotemporal priors. Existing methods, however, typically address them separately, limiting cross-task transfer. We present RS-WorldModel, a unified world model for remote sensing that jointly handles spatiotemporal change understanding and text-guided future scene forecasting, and we build RSWBench-1.1M, a 1.1 million sample dataset with rich language annotations covering both tasks. RS-WorldModel is trained in three stages: (1) Geo-Aware Generative Pre-training (GAGP) conditions forecasting on geographic and acquisition metadata; (2) synergistic instruction tuning (SIT) jointly trains understanding and forecasting; (3) verifiable reinforcement optimization (VRO) refines outputs with verifiable, task-specific rewards. With only 2B parameters, RS-WorldModel surpasses open-source models up to 120$ \times $ larger on most spatiotemporal change question-answering metrics. It achieves an FID of 43.13 on text-guided future scene forecasting, outperforming all open-source baselines as well as the closed-source Gemini-2.5-Flash Image (Nano Banana).

---

### Intelligent Control of Differential Drive Robots Subject to Unmodeled Dynamics with EKF-based State Estimation

Authors: Amos Alwala, Yuchen Hu, Gabriel da Silva Lima, Wallace Moreira Bessa
Published: 2026-03-16
Categories: eess.SY, cs.LG, cs.RO
arXiv: https://arxiv.org/abs/2603.14940v1

Reliable control and state estimation of differential drive robots (DDR) operating in dynamic and uncertain environments remains a challenge, particularly when system dynamics are partially unknown and sensor measurements are prone to degradation. This work introduces a unified control and state estimation framework that combines a Lyapunov-based nonlinear controller and Adaptive Neural Networks (ANN) with Extended Kalman Filter (EKF)-based multi-sensor fusion. The proposed controller leverages the universal approximation property of neural networks to model unknown nonlinearities in real time. An online adaptation scheme updates the weights of the radial basis function (RBF), the architecture chosen for the ANN. The learned dynamics are integrated into a feedback linearization (FBL) control law, for which theoretical guarantees of closed-loop stability and asymptotic convergence in a trajectory-tracking task are established through a Lyapunov-like stability analysis. To ensure robust state estimation, the EKF fuses inertial measurement unit (IMU) and odometry from monocular, 2D-LiDAR and wheel encoders. The fused state estimate drives the intelligent controller, ensuring consistent performance even under drift, wheel slip, sensor noise and failure. Gazebo simulations and real-world experiments are done using DDR, demonstrating the effectiveness of the approach in terms of improved velocity tracking performance with reduction in linear and angular velocity errors up to $53.91\%$ and $29.0\%$ in comparison to the baseline FBL.

---

### FAR-Drive: Frame-AutoRegressive Video Generation in Closed-Loop Autonomous Driving

Authors: Yaoru Li, Federico Landi, Marco Godi, Xin Jin, Ruiju Fu, Yufei Ma, Muyang Sun, Heyu Si, Qi Guo
Published: 2026-03-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.14938v1

Despite rapid progress in autonomous driving, reliable training and evaluation of driving systems remain fundamentally constrained by the lack of scalable and interactive simulation environments. Recent generative video models achieve remarkable visual fidelity, yet most operate in open-loop settings and fail to support fine-grained frame-level interaction between agent actions and environment evolution. Building a learning-based closed-loop simulator for autonomous driving poses three major challenges: maintaining long-horizon temporal and cross-view consistency, mitigating autoregressive degradation under iterative self-conditioning, and satisfying low-latency inference constraints. In this work, we propose FAR-Drive, a frame-level autoregressive video generation framework for autonomous driving. We introduce a multi-view diffusion transformer with fine-grained structured control, enabling geometrically consistent multi-camera generation. To address long-horizon consistency and iterative degradation, we design a two-stage training strategy consisting of adaptive reference horizon conditioning and blend-forcing autoregressive training, which progressively improves consistency and robustness under self-conditioning. To meet low-latency interaction requirements, we further integrate system-level efficiency optimizations for inference acceleration. Experiments on the nuScenes dataset demonstrate that our method achieves state-of-the-art performance among existing closed-loop autonomous driving simulation approaches, while maintaining sub-second latency on a single GPU.

---

### LLM as Graph Kernel: Rethinking Message Passing on Text-Rich Graphs

Authors: Ying Zhang, Hang Yu, Haipeng Zhang, Peng Di
Published: 2026-03-16
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2603.14937v3

Text-rich graphs, which integrate complex structural dependencies with abundant textual information, are ubiquitous yet remain challenging for existing learning paradigms. Conventional methods and even LLM-hybrids compress rich text into static embeddings or summaries before structural reasoning, creating an information bottleneck and detaching updates from the raw content. We argue that in text-rich graphs, the text is not merely a node attribute but the primary medium through which structural relationships are manifested. We introduce RAMP, a Raw-text Anchored Message Passing approach that moves beyond using LLMs as mere feature extractors and instead recasts the LLM itself as a graph-native aggregation operator. RAMP exploits the text-rich nature of the graph via a novel dual-representation scheme: it anchors inference on each node's raw text during each iteration while propagating dynamically optimized messages from neighbors. It further handles both discriminative and generative tasks under a single unified generative formulation. Extensive experiments show that RAMP effectively bridges the gap between graph propagation and deep text reasoning, achieving competitive performance and offering new insights into the role of LLMs as graph kernels for general-purpose graph learning.

---

### Bridging the Intention-Expression Gap: Aligning Multi-Dimensional Preferences via Hierarchical Relevance Feedback in Text-to-Image Diffusion

Authors: Wenxi Wang, Hongbin Liu, Mingqian Li, Junyan Yuan, Junqi Zhang
Published: 2026-03-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.14936v3

Users often possess a clear visual intent but struggle to articulate it precisely in language. This intention-expression gap makes aligning generated images with latent visual preferences a fundamental challenge in text-to-image diffusion models. Existing methods either require model training, sacrificing flexibility, or rely on textual feedback, imposing a heavy cognitive burden. Although recent training-free methods use click-based binary preference feedback to reduce user effort, they force Foundation Models (FMs) to infer preferences at the semantic level. When faced with multi-dimensional preferences, FMs suffer from inference overload and fail to identify exact preferred feature values under conflicting user signals. Consequently, a flexible framework for multi-dimensional feature alignment remains absent. To address this, we propose a Hierarchical Relevance Feedback-Driven (HRFD) framework. Recognizing that multiple features struggle to converge simultaneously, HRFD organizes them into a three-tier hierarchy and adapts relevance feedback to enforce coarse-to-fine convergence, minimizing cognitive load. To bypass FM inference overload, HRFD decouples the process into independent single-feature preference inference tasks. Furthermore, to overcome FMs' failure in identifying preferred values, HRFD employs statistical inference to quantify the distribution divergence of features between "liked" and "disliked" image sets, achieving robust and transparent preference measurement. Crucially, HRFD operates entirely within the external text space, remaining strictly training-free and model-agnostic. Extensive experiments demonstrate that HRFD effectively captures the user's true visual intent, significantly outperforming baseline approaches.

---

### Video-CoE: Reinforcing Video Event Prediction via Chain of Events

Authors: Qile Su, Jing Tang, Rui Chen, Lei Sun, Xiangxiang Chu
Published: 2026-03-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.14935v1

Despite advances in the application of MLLMs for various video tasks, video event prediction (VEP) remains relatively underexplored. VEP requires the model to perform fine-grained temporal modeling of videos and establish logical relationships between videos and future events, which current MLLMs still struggle with. In this work, we first present a comprehensive evaluation of current leading MLLMs on the VEP task, revealing the reasons behind their inaccurate predictions, including lack of logical reasoning ability for future events prediction and insufficient utilization of visual information. To address these challenges, we propose \textbf{C}hain \textbf{o}f \textbf{E}vents (\textbf{CoE}) paradigm, which constructs temporal event chains to implicitly enforce MLLM focusing on the visual content and the logical connections between videos and future events, incentivizing model's reasoning capability with multiple training protocols. Experimental results on public benchmarks demonstrate that our method outperforms both leading open-source and commercial MLLMs, establishing a new state-of-the-art on the VEP task. Codes and models will be released soon.

---

### Masked BRep Autoencoder via Hierarchical Graph Transformer

Authors: Yifei Li, Kang Wu, Wenming Wu, Xiao-Ming Fu
Published: 2026-03-16
Categories: cs.GR, cs.LG
arXiv: https://arxiv.org/abs/2603.14927v2

We introduce a novel self-supervised learning framework that automatically learns representations from input computer-aided design (CAD) models for downstream tasks, including part classification, modeling segmentation, and machining feature recognition. To train our network, we construct a large-scale, unlabeled dataset of boundary representation (BRep) models. The success of our algorithm relies on two keycomponents. The first is a masked graph autoencoder that reconstructs randomly masked geometries and attributes of BReps for representation learning to enhance the generalization. The second is a hierarchical graph Transformer architecture that elegantly fuses global and local learning by a cross-scale mutual attention block to model long-range geometric dependencies and a graph neural network block to aggregate local topological information. After training the autoencoder, we replace its decoder with a task-specific network trained on a small amount of labeled data for downstream tasks. We conduct experiments on various tasks and achieve high performance, even with a small amount of labeled data, demonstrating the practicality and generalizability of our model. Compared to other methods, our model performs significantly better on downstream tasks with the same amount of training data, particularly when the training data is very limited.

---

### Workflow-Aware Structured Layer Decomposition for Illustration Production

Authors: Tianyu Zhang, Dongchi Li, Keiichi Sawada, Haoran Xie
Published: 2026-03-16
Categories: cs.CV, cs.GR
arXiv: https://arxiv.org/abs/2603.14925v2

Recent generative image editing methods adopt layered representations to mitigate the entangled nature of raster images and improve controllability, typically relying on object-based segmentation. However, such strategies may fail to capture the structural and stylized properties of human-created images, such as anime illustrations. To solve this issue, we propose a workflow-aware structured layer decomposition framework tailored to the illustration production of anime artwork. Inspired by the creation pipeline of anime production, our method decomposes the illustration into semantically meaningful production layers, including line art, flat color, shadow, and highlight. To decouple all these layers, we introduce lightweight layer semantic embeddings to provide specific task guidance for each layer. Furthermore, a set of layer-wise losses is incorporated to supervise the training process of individual layers. To overcome the lack of ground-truth layered data, we construct a high-quality illustration dataset that simulated the standard anime production workflow. Experiments demonstrate that the accurate and visually coherent layer decompositions were achieved by using our method. We believe that the resulting layered representation further enables downstream tasks such as recoloring and embedding texture, supporting content creation, and illustration editing. Code is available at: https://github.com/zty0304/Anime-layer-decomposition

---

### Directional Routing in Transformers

Authors: Kevin Taylor
Published: 2026-03-16
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.14923v1

We introduce directional routing, a lightweight mechanism that gives each transformer attention head learned suppression directions controlled by a shared router, at 3.9% parameter cost. We train a 433M-parameter model alongside an identical baseline in a single run, then trace the resulting circuits through mechanistic interpretability. Routing becomes the model's dominant computational pathway. Disabling it collapses factual recall to near-zero probability across all 8 test prompts and drops induction accuracy from 93.4% to 0.0%. Knocking out individual attention heads has negligible effect: the primary mover head's removal actually increases target probability, and induction heads retain 98.6% accuracy without their strongest member. The coordination mechanism is irreplaceable; the components it coordinates are not. The model also self-organizes, without explicit pressure, into two regimes: domain-adaptive routing in early layers and fixed syntactic pruning in late layers, where the least-varying layer is the most critical (+42.6 PPL when disabled). Routing reduces perplexity 31-56% relative to the baseline, though downstream multiple-choice benchmarks do not yet reflect these gains.

---

### F2HDR: Two-Stage HDR Video Reconstruction via Flow Adapter and Physical Motion Modeling

Authors: Huanjing Yue, Dawei Li, Shaoxiong Tu, Jingyu Yang
Published: 2026-03-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.14920v2

Reconstructing High Dynamic Range (HDR) videos from sequences of alternating-exposure Low Dynamic Range (LDR) frames remains highly challenging, especially under dynamic scenes where cross-exposure inconsistencies and complex motion make inter-frame alignment difficult, leading to ghosting and detail loss. Existing methods often suffer from inaccurate alignment, suboptimal feature aggregation, and degraded reconstruction quality in motion-dominated regions. To address these challenges, we propose F2HDR, a two-stage HDR video reconstruction framework that robustly perceives inter-frame motion and restores fine details in complex dynamic scenarios. The proposed framework integrates a flow adapter that adapts generic optical flow for robust cross-exposure alignment, a physical motion modeling to identify salient motion regions, and a motion-aware refinement network that aggregates complementary information while removing ghosting and noise. Extensive experiments demonstrate that F2HDR achieves state-of-the-art performance on real-world HDR video benchmarks, producing ghost-free and high-fidelity results under large motion and exposure variations.

---

### Bayesian Symbolic Regression for Missing Physics

Authors: Arno Strouwen
Published: 2026-03-16
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2603.14918v2

Model-based approaches for (bio)process systems often suffer from incomplete knowledge of the underlying physical, chemical, or biological laws. Universal differential equations, which embed neural networks within differential equations, have emerged as powerful tools to learn this missing physics from experimental data. However, neural networks are inherently opaque, motivating their post-processing via symbolic regression to obtain interpretable mathematical expressions. Genetic algorithm-based symbolic regression is a popular approach for this post-processing step, but provides only point estimates and cannot quantify the confidence we should place in a discovered equation. We address this limitation by applying Bayesian symbolic regression, which uses Reversible Jump Markov Chain Monte Carlo to sample from the posterior distribution over symbolic expression trees. This approach naturally quantifies uncertainty in the recovered model structure. We demonstrate the methodology on a Lotka-Volterra predator-prey system and then show how a well-designed experiment leads to lower uncertainty in a fed-batch bioreactor case study.

---

### Spectrogram features for audio and speech analysis

Authors: Ian McLoughlin, Lam Pham, Yan Song, Xiaoxiao Miao, Huy Phan, Pengfei Cai, Qing Gu, Jiang Nan, Haoyu Song, Donny Soh
Published: 2026-03-16
Categories: eess.AS, cs.AI, cs.LG, eess.SP
arXiv: https://arxiv.org/abs/2603.14917v1

Spectrogram-based representations have grown to dominate the feature space for deep learning audio analysis systems, and are often adopted for speech analysis also. Initially, the primary motivator for spectrogram-based representations was their ability to present sound as a two dimensional signal in the time-frequency plane, which not only provides an interpretable physical basis for analysing sound, but also unlocks the use of a wide range of machine learning techniques such as convolutional neural networks, that had been developed for image processing. A spectrogram is a matrix characterised by the resolution and span of its two dimensions, as well as by the representation and scaling of each element. Many possibilities for these three characteristics have been explored by researchers across numerous application areas, with different settings showing affinity for various tasks. This paper reviews the use of spectrogram-based representations and surveys the state-of-the-art to question how front-end feature representation choice allies with back-end classifier architecture for different tasks.

---

### EditHF-1M: A Million-Scale Rich Human Preference Feedback for Image Editing

Authors: Zitong Xu, Huiyu Duan, Zhongpeng Ji, Xinyun Zhang, Yutao Liu, Xiongkuo Min, Ke Gu, Jian Zhang, Shusong Xu, Jinwei Chen, Bo Li, Guangtao Zhai
Published: 2026-03-16
Categories: cs.CV, cs.MM
arXiv: https://arxiv.org/abs/2603.14916v1

Recent text-guided image editing (TIE) models have achieved remarkable progress, while many edited images still suffer from issues such as artifacts, unexpected editings, unaesthetic contents. Although some benchmarks and methods have been proposed for evaluating edited images, scalable evaluation models are still lacking, which limits the development of human feedback reward models for image editing. To address the challenges, we first introduce \textbf{EditHF-1M}, a million-scale image editing dataset with over 29M human preference pairs and 148K human mean opinion ratings, both evaluated from three dimensions, \textit{i.e.}, visual quality, instruction alignment, and attribute preservation. Based on EditHF-1M, we propose \textbf{EditHF}, a multimodal large language model (MLLM) based evaluation model, to provide human-aligned feedback from image editing. Finally, we introduce \textbf{EditHF-Reward}, which utilizes EditHF as the reward signal to optimize the text-guided image editing models through reinforcement learning. Extensive experiments show that EditHF achieves superior alignment with human preferences and demonstrates strong generalization on other datasets. Furthermore, we fine-tune the Qwen-Image-Edit using EditHF-Reward, achieving significant performance improvements, which demonstrates the ability of EditHF to serve as a reward model to scale-up the image editing. Both the dataset and code will be released in our GitHub repository: https://github.com/IntMeGroup/EditHF.

---

### ILV: Iterative Latent Volumes for Fast and Accurate Sparse-View CT Reconstruction

Authors: Seungryong Lee, Woojeong Baek, Joosang Lee, Eunbyung Park
Published: 2026-03-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.14915v2

A long-term goal in CT imaging is to achieve fast and accurate 3D reconstruction from sparse-view projections, thereby reducing radiation exposure, lowering system cost, and enabling timely imaging in clinical workflows. Recent feed-forward approaches have shown strong potential toward this overarching goal, yet their results still suffer from artifacts and loss of fine details. In this work, we introduce Iterative Latent Volumes (ILV), a feed-forward framework that integrates data-driven priors with classical iterative reconstruction principles to overcome key limitations of prior feed-forward models in sparse-view CBCT reconstruction. At its core, ILV constructs an explicit 3D latent volume that is repeatedly updated by conditioning on multi-view X-ray features and the learned anatomical prior, enabling the recovery of fine structural details beyond the reach of prior feed-forward models. In addition, we develop and incorporate several key architectural components, including an X-ray feature volume, group cross-attention, efficient self-attention, and view-wise feature aggregation, that efficiently realize its core latent volume refinement concept. Extensive experiments on a large-scale dataset of approximately 14,000 CT volumes demonstrate that ILV significantly outperforms existing feed-forward and optimization-based methods in both reconstruction quality and speed. These results show that ILV enables fast and accurate sparse-view CBCT reconstruction suitable for clinical use. The project page is available at: https://sngryonglee.github.io/ILV/.

---

### Fine-tuning RoBERTa for CVE-to-CWE Classification: A 125M Parameter Model Competitive with LLMs

Authors: Nikita Mosievskiy
Published: 2026-03-16
Categories: cs.CR, cs.CL
arXiv: https://arxiv.org/abs/2603.14911v1

We present a fine-tuned RoBERTa-base classifier (125M parameters) for mapping Common Vulnerabilities and Exposures (CVE) descriptions to Common Weakness Enumeration (CWE) categories. We construct a large-scale training dataset of 234,770 CVE descriptions with AI-refined CWE labels using Claude Sonnet 4.6, and agreement-filtered evaluation sets where NVD and AI labels agree. On our held-out test set (27,780 samples, 205 CWE classes), the model achieves 87.4% top-1 accuracy and 60.7% Macro F1 -- a +15.5 percentage-point Macro F1 gain over a TF-IDF baseline that already reaches 84.9% top-1, demonstrating the model's advantage on rare weakness categories. On the external CTI-Bench benchmark (NeurIPS 2024), the model achieves 75.6% strict accuracy (95% CI: 72.8-78.2%) -- statistically indistinguishable from Cisco Foundation-Sec-8B-Reasoning (75.3%, 8B parameters) at 64x fewer parameters. We release the dataset, model, and training code.

---