# Research Papers — 2026-03 · bundle page 199 of 243

> Full-text markdown of papers #9901–9950 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/199
[← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/198.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-03/page/200.md)

### Random Quadratic Form on a Sphere: Synchronization by Common Noise

Authors: Maximilian Engel, Anna Shalova
Published: 2026-03-06
Categories: math.PR, cs.LG, math.DS
arXiv: https://arxiv.org/abs/2603.06187v1

We introduce the Random Quadratic Form (RQF): a stochastic differential equation which formally corresponds to the gradient flow of a random quadratic functional on a sphere. While the one-point dynamics of the system is a Brownian motion and thus has no preferred direction, the two-point motion exhibits nontrivial synchronizing behaviour. In this work we study synchronization of the RQF, namely we give both distributional and path-wise characterizations of the solutions by studying invariant measures and random attractors of the system. The RQF model is motivated by the study of the role of linear layers in transformers and illustrates the synchronization by common noise phenomena arising in the simplified models of transformers. In particular, we provide an alternative (independent of self-attention) explanation of the clustering behaviour in deep transformers and show that tokens cluster even in the absence of the self-attention mechanism.

---

### SpaCRD: Multimodal Deep Fusion of Histology and Spatial Transcriptomics for Cancer Region Detection

Authors: Shuailin Xue, Jun Wan, Lihua Zhang, Wenwen Min
Published: 2026-03-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.06186v1

Accurate detection of cancer tissue regions (CTR) enables deeper analysis of the tumor microenvironment and offers crucial insights into treatment response. Traditional CTR detection methods, which typically rely on the rich cellular morphology in histology images, are susceptible to a high rate of false positives due to morphological similarities across different tissue regions. The groundbreaking advances in spatial transcriptomics (ST) provide detailed cellular phenotypes and spatial localization information, offering new opportunities for more accurate cancer region detection. However, current methods are unable to effectively integrate histology images with ST data, especially in the context of cross-sample and cross-platform/batch settings for accomplishing the CTR detection. To address this challenge, we propose SpaCRD, a transfer learning-based method that deeply integrates histology images and ST data to enable reliable CTR detection across diverse samples, platforms, and batches. Once trained on source data, SpaCRD can be readily generalized to accurately detect cancerous regions across samples from different platforms and batches. The core of SpaCRD is a category-regularized variational reconstruction-guided bidirectional cross-attention fusion network, which enables the model to adaptively capture latent co-expression patterns between histological features and gene expression from multiple perspectives. Extensive benchmark analysis on 23 matched histology-ST datasets spanning various disease types, platforms, and batches demonstrates that SpaCRD consistently outperforms existing eight state-of-the-art methods in CTR detection.

---

### CRIMSON: A Clinically-Grounded LLM-Based Metric for Generative Radiology Report Evaluation

Authors: Mohammed Baharoon, Thibault Heintz, Siavash Raissi, Mahmoud Alabbad, Mona Alhammad, Hassan AlOmaish, Sung Eun Kim, Oishi Banerjee, Pranav Rajpurkar
Published: 2026-03-06
Categories: cs.CL, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2603.06183v2

We introduce CRIMSON, a clinically grounded evaluation framework for chest X-ray report generation that assesses reports based on diagnostic correctness, contextual relevance, and patient safety. Unlike prior metrics, CRIMSON incorporates full clinical context, including patient age, indication, and guideline-based decision rules, and prevents normal or clinically insignificant findings from exerting disproportionate influence on the overall score. The framework categorizes errors into a comprehensive taxonomy covering false findings, missing findings, and eight attribute-level errors (e.g., location, severity, measurement, and diagnostic overinterpretation). Each finding is assigned a clinical significance level (urgent, actionable non-urgent, non-actionable, or expected/benign), based on a guideline developed in collaboration with attending cardiothoracic radiologists, enabling severity-aware weighting that prioritizes clinically consequential mistakes over benign discrepancies. CRIMSON is validated through strong alignment with clinically significant error counts annotated by six board-certified radiologists in ReXVal (Kendalls tau = 0.61-0.71; Pearsons r = 0.71-0.84), and through two additional benchmarks that we introduce. In RadJudge, a targeted suite of clinically challenging pass-fail scenarios, CRIMSON shows consistent agreement with expert judgment. In RadPref, a larger radiologist preference benchmark of over 100 pairwise cases with structured error categorization, severity modeling, and 1-5 overall quality ratings from three cardiothoracic radiologists, CRIMSON achieves the strongest alignment with radiologist preferences. We release the metric, the evaluation benchmarks, RadJudge and RadPref, and a fine-tuned MedGemma model to enable reproducible evaluation of report generation, all available at https://github.com/rajpurkarlab/CRIMSON.

---

### Towards Motion Turing Test: Evaluating Human-Likeness in Humanoid Robots

Authors: Mingzhe Li, Mengyin Liu, Zekai Wu, Xincheng Lin, Junsheng Zhang, Ming Yan, Zengye Xie, Changwang Zhang, Chenglu Wen, Lan Xu, Siqi Shen, Cheng Wang
Published: 2026-03-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.06181v1

Humanoid robots have achieved significant progress in motion generation and control, exhibiting movements that appear increasingly natural and human-like. Inspired by the Turing Test, we propose the Motion Turing Test, a framework that evaluates whether human observers can discriminate between humanoid robot and human poses using only kinematic information. To facilitate this evaluation, we present the Human-Humanoid Motion (HHMotion) dataset, which consists of 1,000 motion sequences spanning 15 action categories, performed by 11 humanoid models and 10 human subjects. All motion sequences are converted into SMPL-X representations to eliminate the influence of visual appearance. We recruited 30 annotators to rate the human-likeness of each pose on a 0-5 scale, resulting in over 500 hours of annotation. Analysis of the collected data reveals that humanoid motions still exhibit noticeable deviations from human movements, particularly in dynamic actions such as jumping, boxing, and running. Building on HHMotion, we formulate a human-likeness evaluation task that aims to automatically predict human-likeness scores from motion data. Despite recent progress in multimodal large language models, we find that they remain inadequate for assessing motion human-likeness. To address this, we propose a simple baseline model and demonstrate that it outperforms several contemporary LLM-based methods. The dataset, code, and benchmark will be publicly released to support future research in the community.

---

### Contrastive-to-Self-Supervised: A Two-Stage Framework for Script Similarity Learning

Authors: Claire Roman, Philippe Meyer
Published: 2026-03-06
Categories: cs.CV, cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2603.06180v1

Learning similarity metrics for glyphs and writing systems faces a fundamental challenge: while individual graphemes within invented alphabets can be reliably labeled, the historical relationships between different scripts remain uncertain and contested. We propose a two-stage framework that addresses this epistemological constraint. First, we train an encoder with contrastive loss on labeled invented alphabets, establishing a teacher model with robust discriminative features. Second, we extend to historically attested scripts through teacher-student distillation, where the student learns unsupervised representations guided by the teacher's knowledge but free to discover latent cross-script similarities. The asymmetric setup enables the student to learn deformation-invariant embeddings while inheriting discriminative structure from clean examples. Our approach bridges supervised contrastive learning and unsupervised discovery, enabling both hard boundaries between distinct systems and soft similarities reflecting potential historical influences. Experiments on diverse writing systems demonstrate effective few-shot glyph recognition and meaningful script clustering without requiring ground-truth evolutionary relationships.

---

### Making Training-Free Diffusion Segmentors Scale with the Generative Power

Authors: Benyuan Meng, Qianqian Xu, Zitai Wang, Xiaochun Cao, Longtao Huang, Qingming Huang
Published: 2026-03-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.06178v3

As powerful generative models, text-to-image diffusion models have recently been explored for discriminative tasks. A line of research focuses on adapting a pre-trained diffusion model to semantic segmentation without any further training, leading to training-free diffusion segmentors. These methods typically rely on cross-attention maps from the model's attention layers, which are assumed to capture semantic relationships between image pixels and text tokens. Ideally, such approaches should benefit from more powerful diffusion models, i.e., stronger generative capability should lead to better segmentation. However, we observe that existing methods often fail to scale accordingly. To understand this issue, we identify two underlying gaps: (i) cross-attention is computed across multiple heads and layers, but there exists a discrepancy between these individual attention maps and a unified global representation. (ii) Even when a global map is available, it does not directly translate to accurate semantic correlation for segmentation, due to score imbalances among different text tokens. To bridge these gaps, we propose two techniques: auto aggregation and per-pixel rescaling, which together enable training-free segmentation to better leverage generative capability. We evaluate our approach on standard semantic segmentation benchmarks and further integrate it into a generative technique, demonstrating both improved performance broad applicability. Codes are at https://github.com/Darkbblue/goca.

---

### Optimizing 3D Diffusion Models for Medical Imaging via Multi-Scale Reward Learning

Authors: Yueying Tian, Xudong Han, Meng Zhou, Rodrigo Aviles-Espinosa, Rupert Young, Philip Birch
Published: 2026-03-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.06173v1

Diffusion models have emerged as powerful tools for 3D medical image generation, yet bridging the gap between standard training objectives and clinical relevance remains a challenge. This paper presents a method to enhance 3D diffusion models using Reinforcement Learning (RL) with multi-scale feedback. We first pretrain a 3D diffusion model on MRI volumes to establish a robust generative prior. Subsequently, we fine-tune the model using Proximal Policy Optimization (PPO), guided by a novel reward system that integrates both 2D slice-wise assessments and 3D volumetric analysis. This combination allows the model to simultaneously optimize for local texture details and global structural coherence. We validate our framework on the BraTS 2019 and OASIS-1 datasets. Our results indicate that incorporating RL feedback effectively steers the generation process toward higher quality distributions. Quantitative analysis reveals significant improvements in Fréchet Inception Distance (FID) and, crucially, the synthetic data demonstrates enhanced utility in downstream tumor and disease classification tasks compared to non-optimized baselines.

---

### JOPP-3D: Joint Open Vocabulary Semantic Segmentation on Point Clouds and Panoramas

Authors: Sandeep Inuganti, Hideaki Kanayama, Kanta Shimizu, Mahdi Chamseddine, Soichiro Yokota, Didier Stricker, Jason Rambach
Published: 2026-03-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.06168v3

Semantic segmentation across visual modalities such as 3D point clouds and panoramic images remains a challenging task, primarily due to the scarcity of annotated data and the limited adaptability of fixed-label models. In this paper, we present JOPP-3D, an open-vocabulary segmentation framework that jointly leverages panoramic and point cloud data to enable language-driven scene understanding. We convert RGB-D panoramic images into their corresponding wide field-of-view tangential perspectives and 3D point clouds, then use these modalities to extract and align foundational vision-language features. This allows natural language querying to generate semantic masks on both input modalities. Experimental evaluation on the Stanford-2D-3D-s and ToF-360 datasets demonstrates the capability of JOPP-3D to produce coherent and semantically meaningful segmentations across panoramic and 3D domains. Our proposed method achieves a significant improvement compared to the SOTA in open and closed vocabulary 2D and 3D semantic segmentation.

---

### A Semi-Supervised Framework for Breast Ultrasound Segmentation with Training-Free Pseudo-Label Generation and Label Refinement

Authors: Ruili Li, Jiayi Ding, Ruiyu Li, Yilun Jin, Shiwen Ge, Yuwen Zeng, Xiaoyong Zhang, Eichi Takaya, Jan Vrba, Noriyasu Homma
Published: 2026-03-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.06167v1

Semi-supervised learning (SSL) has emerged as a promising paradigm for breast ultrasound (BUS) image segmentation, but it often suffers from unstable pseudo labels under extremely limited annotations, leading to inaccurate supervision and degraded performance. Recent vision-language models (VLMs) provide a new opportunity for pseudo-label generation, yet their effectiveness on BUS images remains limited because domain-specific prompts are difficult to transfer. To address this issue, we propose a semi-supervised framework with training-free pseudo-label generation and label refinement. By leveraging simple appearance-based descriptions (e.g., dark oval), our method enables cross-domain structural transfer between natural and medical images, allowing VLMs to generate structurally consistent pseudo labels. These pseudo labels are used to warm up a static teacher that captures global structural priors of breast lesions. Combined with an exponential moving average teacher, we further introduce uncertainty entropy weighted fusion and adaptive uncertainty-guided reverse contrastive learning to improve boundary discrimination. Experiments on four BUS datasets demonstrate that our method achieves performance comparable to fully supervised models even with only 2.5% labeled data, significantly outperforming existing SSL approaches. Moreover, the proposed paradigm is readily extensible: for other imaging modalities or diseases, only a global appearance description is required to obtain reliable pseudo supervision, enabling scalable semi-supervised medical image segmentation under limited annotations.

---

### FreeOcc: Training-free Panoptic Occupancy Prediction via Foundation Models

Authors: Andrew Caunes, Thierry Chateau, Vincent Fremont
Published: 2026-03-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.06166v1

Semantic and panoptic occupancy prediction for road scene analysis provides a dense 3D representation of the ego vehicle's surroundings. Current camera-only approaches typically rely on costly dense 3D supervision or require training models on data from the target domain, limiting deployment in unseen environments. We propose FreeOcc, a training-free pipeline that leverages pretrained foundation models to recover both semantics and geometry from multi-view images. FreeOcc extracts per-view panoptic priors with a promptable foundation segmentation model and prompt-to-taxonomy rules, and reconstructs metric 3D points with a reconstruction foundation model. Depth- and confidence- aware filtering lifts reliable labels into 3D, which are fused over time and voxelized with a deterministic refinement stack. For panoptic occupancy, instances are recovered by fitting and merging robust current-view 3D box candidates, enabling instance-aware occupancy without any learned 3D model. On Occ3D-nuScenes, FreeOcc achieves 16.9 mIoU and 16.5 RayIoU train-free, on par with state-of-the-art weakly supervised methods. When employed as a pseudo-label generation pipeline for training downstream models, it achieves 21.1 RayIoU, surpassing the previous state-of-the-art weakly supervised baseline. Furthermore, FreeOcc sets new baselines for both train-free and weakly supervised panoptic occupancy prediction, achieving 3.1 RayPQ and 3.9 RayPQ, respectively. These results highlight foundation-model-driven perception as a practical route to training-free 3D scene understanding.

---

### Reflective Flow Sampling Enhancement

Authors: Zikai Zhou, Muyao Wang, Shitong Shao, Lichen Bai, Haoyi Xiong, Bo Han, Zeke Xie
Published: 2026-03-06
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.06165v2

The growing demand for text-to-image generation has led to rapid advances in generative modeling. Recently, text-to-image diffusion models trained with flow matching algorithms, such as FLUX, have achieved remarkable progress and emerged as strong alternatives to conventional diffusion models. At the same time, inference-time enhancement strategies have been shown to improve the generation quality and text-prompt alignment of text-to-image diffusion models. However, these techniques are mainly applicable to conventional diffusion models and usually fail to perform well on flow models. To bridge this gap, we propose Reflective Flow Sampling (RF-Sampling), a theoretically-grounded and training-free inference enhancement framework explicitly designed for flow models, especially for the CFG-distilled variants (i.e., models distilled from CFG guidance techniques), like FLUX. Departing from heuristic interpretations, we provide a formal derivation proving that RF-Sampling implicitly performs gradient ascent on the text-image alignment score. By leveraging a linear combination of textual representations and integrating them with flow inversion, RF-Sampling allows the model to explore noise spaces that are more consistent with the input prompt. Extensive experiments across multiple benchmarks demonstrate that RF-Sampling consistently improves both generation quality and prompt alignment. Moreover, RF-Sampling is also the first inference enhancement method that can exhibit test-time scaling ability to some extent on FLUX.

---

### Do Compact SSL Backbones Matter for Audio Deepfake Detection? A Controlled Study with RAPTOR

Authors: Ajinkya Kulkarni, Sandipana Dowerah, Atharva Kulkarni, Tanel Alumäe, Mathew Magimai Doss
Published: 2026-03-06
Categories: cs.SD, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2603.06164v1

Self-supervised learning (SSL) underpins modern audio deepfake detection, yet most prior work centers on a single large wav2vec2-XLSR backbone, leaving compact under studied. We present RAPTOR, Representation Aware Pairwise-gated Transformer for Out-of-domain Recognition a controlled study of compact SSL backbones from the HuBERT and WavLM within a unified pairwise-gated fusion detector, evaluated across 14 cross-domain benchmarks. We show that multilingual HuBERT pre-training is the primary driver of cross-domain robustness, enabling 100M models to match larger and commercial systems. Beyond EER, we introduce a test-time augmentation protocol with perturbation-based aleatoric uncertainty to expose calibration differences invisible to standard metrics: WavLM variants exhibit overconfident miscalibration under perturbation, whereas iterative mHuBERT remains stable. These findings indicate that SSL pre-training trajectory, not model scale, drives reliable audio deepfake detection.

---

### Efficient K-generalizable Learned Search

Authors: Yifan Peng, Jiafei Fan, Xingda Wei, Sijie Shen, Rong Chen, Jianning Wang, Xiaojian Luo, Wenyuan Yu, Jingren Zhou, Haibo Chen
Published: 2026-03-06
Categories: cs.DB, cs.IR, cs.LG
arXiv: https://arxiv.org/abs/2603.06159v2

Learned top-K search improves the accuracy-latency trade-off of graph-based vector search, but existing methods are designed for a fixed K: serving production workloads with varying K values requires preprocessing cost proportional to the number of distinct Ks served - prohibitive in practice. This paper shows that learned search can support arbitrary K with the preprocessing cost of a single top-1 model. The key idea is to reduce top-K learned search to repeated masked top-1 refinement, which works because the distance-reduction trajectory for discovering the next top-1 vector is largely invariant to the number of results already found. We therefore train the model on trajectory features that remain effective under masking. To make repeated refinement robust and efficient, OMEGA counters error accumulation across iterations with rank-wise confidence allocation, and skips unnecessary model invocations with a statistical forecast of recall from partial results. Across nine dataset-scale configurations, OMEGA meets the 0.95 recall target with one K-independent model. Under the lowest-preprocessing configuration of each learned baseline,it reduces mean latency by 7-36% versus DARTH, 3-25% versus MultiK-DARTH, and 8-21% versus LAET on BIGANN, BIGANN-1B, DEEP, and three production workloads. On GIST, Text2Image, and MS MARCO, its latency remains within 9% of DARTH and MultiK-DARTH. On production traces, OMEGA further reduces total serving and preprocessing computation by up to 28%.

---

### Efficient Vector Search in the Wild: One Model for Multi-K Queries

Authors: Yifan Peng, Jiafei Fan, Xingda Wei, Sijie Shen, Rong Chen, Jianning Wang, Xiaojian Luo, Wenyuan Yu, Jingren Zhou, Haibo Chen
Published: 2026-03-06
Categories: cs.DB, cs.IR, cs.LG
arXiv: https://arxiv.org/abs/2603.06159v1

Learned top-K search is a promising approach for serving vector queries with both high accuracy and performance. However, current models trained for a specific K value fail to generalize to real-world multi-K queries: they suffer from accuracy degradation (for larger Ks) and performance loss (for smaller Ks). Training the model to generalize on different Ks requires orders of magnitude more preprocessing time and is not suitable for serving vector queries in the wild. We present OMEGA, a K-generalizable learned top-K search method that simultaneously achieves high accuracy, high performance, and low preprocessing cost for multi-K vector queries. The key idea is that a base model properly trained on K=1 with our trajectory-based features can be used to accurately predict larger Ks with a dynamic refinement procedure and smaller Ks with minimal performance loss. To make our refinements efficient, we further leverage the statistical properties of top-K searches to reduce excessive model invocations. Extensive evaluations on multiple public and production datasets show that, under the same preprocessing budgets, OMEGA achieves 6-33% lower average latency compared to state-of-the-art learned search methods, while all systems achieve the same recall target. With only 16-30% of the preprocessing time, OMEGA attains 1.01-1.28x of the optimal average latency of these baselines.

---

### Ensemble Graph Neural Networks for Probabilistic Sea Surface Temperature Forecasting via Input Perturbations

Authors: Alejandro J. González-Santana, Giovanny A. Cuervo-Londoño, Javier Sánchez
Published: 2026-03-06
Categories: cs.LG, cs.AI, physics.geo-ph
arXiv: https://arxiv.org/abs/2603.06153v1

Accurate regional ocean forecasting requires models that are both computationally efficient and capable of representing predictive uncertainty. This work investigates ensemble learning strategies for sea surface temperature (SST) forecasting using Graph Neural Networks (GNNs), with a focus on how input perturbation design affects forecast skill and uncertainty representation. We adapt a GNN architecture to the Canary Islands region in the North Atlantic and implement a homogeneous ensemble approach inspired by bagging, where diversity is introduced during inference by perturbing initial ocean states rather than retraining multiple models. Several noise-based ensemble generation strategies are evaluated, including Gaussian noise, Perlin noise, and fractal Perlin noise, with systematic variation of noise intensity and spatial structure. Ensemble forecasts are assessed over a 15-day horizon using deterministic metrics (RMSE and bias) and probabilistic metrics, including the Continuous Ranked Probability Score (CRPS) and the Spread-skill ratio. Results show that, while deterministic skill remains comparable to the single-model forecast, the type and structure of input perturbations strongly influence uncertainty representation, particularly at longer lead times. Ensembles generated with spatially coherent perturbations, such as low-resolution Perlin noise, achieve better calibration and lower CRPS than purely random Gaussian perturbations. These findings highlight the critical role of noise structure and scale in ensemble GNN design and demonstrate that carefully constructed input perturbations can yield well-calibrated probabilistic forecasts without additional training cost, supporting the feasibility of ensemble GNNs for operational regional ocean prediction.

---

### VLM-RobustBench: A Comprehensive Benchmark for Robustness of Vision-Language Models

Authors: Rohit Saxena, Alessandro Suglia, Pasquale Minervini
Published: 2026-03-06
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.06148v1

Vision-language models (VLMs) achieve strong performance on standard, high-quality datasets, but we still do not fully understand how they perform under real-world image distortions. We present VLM-RobustBench, a benchmark spanning 49 augmentation types across noise, blur, weather, digital, and geometric perturbations, evaluated under graded severities (low/mid/high) and binary transforms, yielding 133 corrupted settings. We evaluate VLMs from four families (Qwen, InternVL, Molmo, Gemma) on two complementary benchmarks: MMBench (visually grounded) and MMMU-Pro (reasoning-oriented). Our results reveal that visual severity is a weak predictor of difficulty: low-severity spatial perturbations often degrade performance more than visually severe photometric corruptions. In particular, low-severity glass_blur reduces MMBench accuracy by about 8 pp on average across models, while the largest drops arise from resampling and geometric distortions (e.g., upsample, elastic_transform), reaching up to 34 pp. Overall, our findings suggest current VLMs are semantically strong but spatially fragile, motivating the definition of novel robustness evaluation protocols and training regimes that emphasize resampling and geometric invariances.

---

### Longitudinal NSCLC Treatment Progression via Multimodal Generative Models

Authors: Massimiliano Mantegna, Elena Mulero Ayllón, Alice Natalina Caragliano, Francesco Di Feola, Claudia Tacconi, Michele Fiore, Edy Ippolito, Carlo Greco, Sara Ramella, Philippe C. Cattin, Paolo Soda, Matteo Tortora et al.
Published: 2026-03-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.06147v1

Predicting tumor evolution during radiotherapy is a clinically critical challenge, particularly when longitudinal changes are driven by both anatomy and treatment. In this work, we introduce a Virtual Treatment (VT) framework that formulates non-small cell lung cancer (NSCLC) progression as a dose-aware multimodal conditional image-to-image translation problem. Given a CT scan, baseline clinical variables, and a specified radiation dose increment, VT aims to synthesize plausible follow-up CT images reflecting treatment-induced anatomical changes. We evaluate the proposed framework on a longitudinal dataset of 222 stage III NSCLC patients, comprising 895 CT scans acquired during radiotherapy under irregular clinical schedules. The generative process is conditioned on delivered dose increments together with demographic and tumor-related clinical variables. Representative GAN-based and diffusion-based models are benchmarked across 2D and 2.5D configurations. Quantitative and qualitative results indicate that diffusion-based models benefit more consistently from multimodal, dose-aware conditioning and produce more stable and anatomically plausible tumor evolution trajectories than GAN-based baselines, supporting the potential of VT as a tool for in-silico treatment monitoring and adaptive radiotherapy research in NSCLC.

---

### Predictive Coding Graphs are a Superset of Feedforward Neural Networks

Authors: Björn van Zwol
Published: 2026-03-06
Categories: cs.LG, cond-mat.dis-nn, cs.AI, cs.NE, stat.ML
arXiv: https://arxiv.org/abs/2603.06142v1

Predictive coding graphs (PCGs) are a recently introduced generalization to predictive coding networks, a neuroscience-inspired probabilistic latent variable model. Here, we prove how PCGs define a mathematical superset of feedforward artificial neural networks (multilayer perceptrons). This positions PCNs more strongly within contemporary machine learning (ML), and reinforces earlier proposals to study the use of non-hierarchical neural networks for ML tasks, and more generally the notion of topology in neural networks.

---

### Spatial Colour Mixing Illusions as a Perception Stress Test for Vision-Language Models

Authors: Nicoleta-Nina Basoc, Adrian Cosma, Emilian Radoi
Published: 2026-03-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.06141v1

Vision-language models (VLMs) achieve strong benchmark results, yet can exhibit systematic perceptual weaknesses: structured, large changes to pixel values can cause confident yet nonsensical predictions, even when the underlying scene remains easily recognizable to humans. We study this gap using Spatial Colour Mixing, a programmatic family of colour distortions that overlays structured patterns (in both RGB and Ostwald colour systems) onto natural images. We introduce a framework of eight spatial colour mixing variants and evaluate nine VLMs across three model families on four datasets. Across models and datasets, accuracy degrades sharply with increasing distortion, and scaling the language model does not reliably mitigate the failure. In a human study with 61 participants on an animal recognition dataset, humans substantially outperform VLMs under the same distortions. Finally, we show that a simple human-inspired preprocessing step recovers a meaningful portion of performance for several distortion types, motivating perception-aware preprocessing and tool-use as practical strategies for improving VLM robustness.

---

### Place-it-R1: Unlocking Environment-aware Reasoning Potential of MLLM for Video Object Insertion

Authors: Bohai Gu, Taiyi Wu, Dazhao Du, Jian Liu, Shuai Yang, Xiaotong Zhao, Alan Zhao, Song Guo
Published: 2026-03-06
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.06140v2

Video object insertion is fundamental to video editing, yet existing diffusion methods often produce visually plausible but physically inconsistent results. We present Place-it-R1, an end-to-end framework for physically plausible video object insertion driven by environment-aware MLLM reasoning. Rather than treating reasoning as a generic text prompt, Place-it-R1 uses the MLLM to analyze the target environment, infer object-scene interactions, and determine where an insertion is physically valid. The resulting reasoning is translated into two complementary forms of guidance for video diffusion: semantic guidance that describes the intended physical interaction and spatial guidance that provides a valid insertion region in each frame. To further align generation with local physical realism, we introduce Spatial Direct Preference Optimization, which leverages an MLLM to rank generated candidates, and introduces a region-aware preference objective that explicitly localizes physical-violation penalties to the inserted-object region. Place-it-R1 further offers flexible and standard modes to trade off environment adaptation and scene preservation. Extensive experiments show that Place-it-R1 produces more physically coherent and visually natural insertions than state-of-the-art methods and achieves competitive results against commercial systems.

---

### Partial Policy Gradients for RL in LLMs

Authors: Puneet Mathur, Branislav Kveton, Subhojyoti Mukherjee, Viet Dac Lai
Published: 2026-03-06
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.06138v1

Reinforcement learning is a framework for learning to act sequentially in an unknown environment. We propose a natural approach for modeling policy structure in policy gradients. The key idea is to optimize for a subset of future rewards: smaller subsets represent simpler policies, which can be learned more reliably because their empirical gradient estimates are more accurate. Our approach allows for modeling and comparison of different policy classes, including full planning, greedy, K-step lookahead, and segment policies. We evaluate the policies empirically on multiple persona-alignment conversational problems. Different policies excel in different problems, reflecting their different characteristics and highlighting the importance of our studied policy class.

---

### Cross-Resolution Distribution Matching for Diffusion Distillation

Authors: Feiyang Chen, Hongpeng Pan, Haonan Xu, Xinyu Duan, Zhefeng Wang, Yang Yang
Published: 2026-03-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.06136v2

Diffusion distillation is central to accelerating image and video generation, yet existing methods are fundamentally limited by the denoising process, where step reduction has largely saturated. Partial timestep low-resolution generation can further accelerate inference, but it suffers noticeable quality degradation due to cross-resolution distribution gaps. We propose Cross-Resolution Distribution Matching Distillation (RMD), a novel distillation framework that bridges cross-resolution distribution gaps for high-fidelity, few-step multi-resolution cascaded inference. Specifically, RMD divides the timestep intervals for each resolution using logarithmic signal-to-noise ratio (logSNR) curves, and introduces logSNR-based mapping to compensate for resolution-induced shifts. Distribution matching is conducted along resolution trajectories to reduce the gap between low-resolution generator distributions and the teacher's high-resolution distribution. In addition, a predicted-noise re-injection mechanism is incorporated during upsampling to stabilize training and improve synthesis quality. Quantitative and qualitative results show that RMD preserves high-fidelity generation while accelerating inference across various backbones. Notably, RMD achieves up to 33.4X speedup on SDXL and 25.6X on Wan2.1-14B, while preserving high visual fidelity.

---

### A Causal Graph Approach to Oppositional Narrative Analysis

Authors: Diego Revilla, Martin Fernandez-de-Retana, Lingfeng Chen, Aritz Bilbao-Jayo, Miguel Fernandez-de-Retana
Published: 2026-03-06
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2603.06135v2

Current methods for textual analysis rely on data annotated within predefined ontologies, often embedding human bias within black-box models. Despite achieving near-perfect performance, these approaches exploit unstructured, linear pattern recognition rather than modeling the structured interactions between entities that naturally emerge in discourse. In this work, we propose a graph-based framework for the detection, analysis, and classification of oppositional narratives and their underlying entities by representing narratives as entity-interaction graphs. Moreover, by incorporating causal estimation at the node level, our approach derives a causal representation of each contribution to the final classification by distilling the constructed sentence graph into a minimal causal subgraph. Building upon this representation, we introduce a classification pipeline that outperforms existing approaches to oppositional thinking classification task.

---

### DQE: A Semantic-Aware Evaluation Metric for Time Series Anomaly Detection

Authors: Yuewei Li, Dalin Zhang, Huan Li, Xinyi Gong, Hongjun Chu, Zhaohui Song
Published: 2026-03-06
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.06131v1

Time series anomaly detection has achieved remarkable progress in recent years. However, evaluation practices have received comparatively less attention, despite their critical importance. Existing metrics exhibit several limitations: (1) bias toward point-level coverage, (2) insensitivity or inconsistency in near-miss detections, (3) inadequate penalization of false alarms, and (4) inconsistency caused by threshold or threshold-interval selection. These limitations can produce unreliable or counterintuitive results, hindering objective progress. In this work, we revisit the evaluation of time series anomaly detection from the perspective of detection semantics and propose a novel metric for more comprehensive assessment. We first introduce a partitioning strategy grounded in detection semantics, which decomposes the local temporal region of each anomaly into three functionally distinct subregions. Using this partitioning, we evaluate overall detection behavior across events and design finer-grained scoring mechanisms for each subregion, enabling more reliable and interpretable assessment. Through a systematic study of existing metrics, we identify an evaluation bias associated with threshold-interval selection and adopt an approach that aggregates detection qualities across the full threshold spectrum, thereby eliminating evaluation inconsistency. Extensive experiments on synthetic and real-world data demonstrate that our metric provides stable, discriminative, and interpretable evaluation, while achieving robust assessment compared with ten widely used metrics.

---

### A Hazard-Informed Data Pipeline for Robotics Physical Safety

Authors: Alexei Odinokov, Rostislav Yavorskiy
Published: 2026-03-06
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2603.06130v1

This report presents a structured Robotics Physical Safety Framework based on explicit asset declaration, systematic vulnerability enumeration, and hazard-driven synthetic data generation. The approach bridges classical risk engineering with modern machine learning pipelines, enabling safety envelope learning grounded in a formalized hazard ontology. The key contribution of this framework is the alignment between classical safety engineering, digital twin simulation, synthetic data generation, and machine learning model training.

---

### Diffusion Language Models Are Natively Length-Aware

Authors: Vittorio Rossi, Giacomo Cirò, Davide Beltrame, Luca Gandolfi, Paul Röttger, Dirk Hovy
Published: 2026-03-06
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2603.06123v1

Unlike autoregressive language models, which terminate variable-length generation upon predicting an End-of-Sequence (EoS) token, Diffusion Language Models (DLMs) operate over a fixed maximum-length context window for a predetermined number of denoising steps. However, this process is independent of the required response length, resulting in computational waste for the majority of short responses common in reasoning and chat tasks. To address this problem, we conjecture that the latent prompt representation contains sufficient information to estimate the required output length. We provide empirical evidence for this phenomenon and propose a zero-shot mechanism to dynamically crop the context window before generation begins, leading to fewer diffusion steps and substantial computational savings. We evaluate our approach on four benchmarks with diverse tasks -- GSM8K (reasoning), HumanEval (code generation), IfEval (instruction following), and LongFormQA (question answering) -- revealing massive efficiency gains at minimal performance impact. We report significant reductions in FLOPs across all tasks, with no statistically significant performance degradation, and significant performance improvements in 2 out of 4 tasks.

---

### FedARKS: Federated Aggregation via Robust and Discriminative Knowledge Selection and Integration for Person Re-identification

Authors: Xin Xu, Binchang Ma, Zhixi Yu, Wei Liu
Published: 2026-03-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.06122v1

The application of federated domain generalization in person re-identification (FedDG-ReID) aims to enhance the model's generalization ability in unseen domains while protecting client data privacy. However, existing mainstream methods typically rely on global feature representations and simple averaging operations for model aggregation, leading to two limitations in domain generalization: (1) Using only global features makes it difficult to capture subtle, domain-invariant local details (such as accessories or textures); (2) Uniform parameter averaging treats all clients as equivalent, ignoring their differences in robust feature extraction capabilities, thereby diluting the contributions of high quality clients. To address these issues, we propose a novel federated learning framework, Federated Aggregation via Robust and Discriminative Knowledge Selection and Integration (FedARKS), comprising two mechanisms: RK (Robust Knowledge) and KS (Knowledge Selection).

---

### Dynamic Momentum Recalibration in Online Gradient Learning

Authors: Zhipeng Yao, Rui Yu, Guisong Chang, Ying Li, Yu Zhang, Dazhou Li
Published: 2026-03-06
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.06120v1

Stochastic Gradient Descent (SGD) and its momentum variants form the backbone of deep learning optimization, yet the underlying dynamics of their gradient behavior remain insufficiently understood. In this work, we reinterpret gradient updates through the lens of signal processing and reveal that fixed momentum coefficients inherently distort the balance between bias and variance, leading to skewed or suboptimal parameter updates. To address this, we propose SGDF (SGD with Filter), an optimizer inspired by the principles of Optimal Linear Filtering. SGDF computes an online, time-varying gain to dynamically refine gradient estimation by minimizing the mean-squared error, thereby achieving an optimal trade-off between noise suppression and signal preservation. Furthermore, our approach could extend to other optimizers, showcasing its broad applicability to optimization frameworks. Extensive experiments across diverse architectures and benchmarks demonstrate SGDF surpasses conventional momentum methods and achieves performance on par with or surpassing state-of-the-art optimizers.

---

### Making Implicit Premises Explicit in Logical Understanding of Enthymemes

Authors: Xuyao Feng, Anthony Hunter
Published: 2026-03-06
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2603.06114v3

Real-world arguments in text and dialogues are normally enthymemes (i.e. some of their premises and/or claims are implicit). Natural language processing (NLP) methods for handling enthymemes can potentially identify enthymemes in text but they do not decode their underlying logic, whereas logic-based approaches for handling them assume a knowledgebase with sufficient formulae that can be used to decode them via abduction. There is therefore a lack of a systematic method for translating textual components of an enthymeme into a logical argument and generating the logical formulae required for their decoding, and thereby showing logical entailment. To address this, we propose a pipeline that integrates: (1) a large language model (LLM) to generate intermediate implicit premises based on the explicit premise and claim; (2) another LLM to translate the natural language into logical formulas; and (3) a neuro-symbolic reasoner based on a SAT solver to determine entailment. We evaluate our pipeline on two enthymeme datasets, demonstrating promising performance in selecting the correct implicit premise, as measured by precision, recall, F1-score, and accuracy.

---

### Making Implicit Premises Explicit in Logical Understanding of Enthymemes

Authors: Xuyao Feng, Anthony Hunter
Published: 2026-03-06
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2603.06114v2

Real-world arguments in text and dialogues are normally enthymemes (i.e. some of their premises and/or claims are implicit). Natural language processing (NLP) methods for handling enthymemes can potentially identify enthymemes in text but they do not decode their underlying logic, whereas logic-based approaches for handling them assume a knowledgebase with sufficient formulae that can be used to decode them via abduction. There is therefore a lack of a systematic method for translating textual components of an enthymeme into a logical argument and generating the logical formulae required for their decoding, and thereby showing logical entailment. To address this, we propose a pipeline that integrates: (1) a large language model (LLM) to generate intermediate implicit premises based on the explicit premise and claim; (2) another LLM to translate the natural language into logical formulas; and (3) a neuro-symbolic reasoner based on a SAT solver to determine entailment. We evaluate our pipeline on two enthymeme datasets, demonstrating promising performance in selecting the correct implicit premise, as measured by precision, recall, F1-score, and accuracy.

---

### Latent Diffusion-Based 3D Molecular Recovery from Vibrational Spectra

Authors: Wenjin Wu, Aleš Leonardis, Linjiang Chen, Jianbo Jiao
Published: 2026-03-06
Categories: cs.LG, physics.chem-ph
arXiv: https://arxiv.org/abs/2603.06113v1

Infrared (IR) spectroscopy, a type of vibrational spectroscopy, is widely used for molecular structure determination and provides critical structural information for chemists. However, existing approaches for recovering molecular structures from IR spectra typically rely on one-dimensional SMILES strings or two-dimensional molecular graphs, which fail to capture the intricate relationship between spectral features and three-dimensional molecular geometry. Recent advances in diffusion models have greatly enhanced the ability to generate molecular structures in 3D space. Yet, no existing model has explored the distribution of 3D molecular geometries corresponding to a single IR spectrum. In this work, we introduce IR-GeoDiff, a latent diffusion model that recovers 3D molecular geometries from IR spectra by integrating spectral information into both node and edge representations of molecular structures. We evaluate IR-GeoDiff from both spectral and structural perspectives, demonstrating its ability to recover the molecular distribution corresponding to a given IR spectrum. Furthermore, an attention-based analysis reveals that the model is able to focus on characteristic functional group regions in IR spectra, qualitatively consistent with common chemical interpretation practices.

---

### Enhancing Neural Video Compression of Static Scenes with Positive-Incentive Noise

Authors: Cheng Yuan, Zhenyu Jia, Jiawei Shao, Xuelong Li
Published: 2026-03-06
Categories: eess.IV, cs.CV
arXiv: https://arxiv.org/abs/2603.06095v2

Static scene videos, such as surveillance feeds and videotelephony streams, constitute a dominant share of storage consumption and network traffic. However, both traditional standardized codecs and neural video compression (NVC) methods struggle to encode these videos efficiently due to inadequate usage of temporal redundancy and severe distribution gaps between training and test data, respectively. While recent generative compression methods improve perceptual quality, they introduce hallucinated details that are unacceptable in authenticity-critical applications. To overcome these limitations, we propose a positive-incentive camera (PIC) framework for static scene videos, where short-term temporal changes are reinterpreted as positive-incentive noise to facilitate NVC model finetuning. By disentangling transient variations from the persistent background, structured prior information is internalized in the compression model. During inference, the invariant component requires minimal signaling, thus reducing data transmission while maintaining pixel-level fidelity. Experiment results show that PIC achieves visually lossless reconstruction for static scenes at an extremely low compression rate of 0.009%, while the DCVC-FM baseline requires 20.5% higher Bjøntegaard delta (BD) rate. Our method provides an effective solution to trade computation for bandwidth, enabling robust video transmission under adverse network conditions and economic long-term retention of surveillance footage.

---

### DeepSight: Bridging Depth Maps and Language with a Depth-Driven Multimodal Model

Authors: Hao Yang, Hongbo Zhang, Yanyan Zhao, Bing Qin
Published: 2026-03-06
Categories: cs.CV, cs.CL
arXiv: https://arxiv.org/abs/2603.06090v1

Multimodal large language models (MLLMs) have achieved impressive performance across various tasks such as image captioning and visual question answer(VQA); however, they often struggle to accurately interpret depth information inherent in visual data. In this work, we introduce DeepSight, the first dedicated depth MLLM designed to enhance three-dimensional scene understanding. Unlike conventional methods that align RGB image encodings with text, our approach takes advantage of the unique characteristics of depth images: single-channel grayscale images where the pixel values directly reflect depth cues to improve spatial reasoning. To address challenges associated with limited depth data and the inadequacy of simple channel replication, we construct a novel depth image-text pair dataset and a depth instruction dataset. Depth maps are generated from visual images using the GLPN model, and GPT-4 is employed to curate corresponding depth instructions, an approach validated by LLaVA. Additionally, we modify the ViT encoder in CLIP to incorporate local object information, thereby capturing the subtle continuous variations of depth more effectively. To evaluate the performance of our model, we develop a comprehensive depth question answer benchmark based on existing depth image datasets, which rigorously assesses understanding in typical depth map scenarios. Experimental results demonstrate that DeepSight significantly enhances depth perception and downstream task performance, marking a substantial step forward in multimodal three-dimensional understanding.

---

### Experiences Build Characters: The Linguistic Origins and Functional Impact of LLM Personality

Authors: Xi Wang, Mengdie Zhuang, Jiqun Liu
Published: 2026-03-06
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2603.06088v1

Human problem-solving is enriched by a diversity of styles and personality traits, yet the development of Large Language Models (LLMs) has largely prioritized uniform performance benchmarks that favour specific behavioural tendencies such as assertiveness. To investigate how diverse experiences shape machine personality and influence problem-solving, this study employs continued pre-training to expose models to domain-specific texts in an unsupervised manner, simulating the accumulation of experience. By adapting the Big Five framework via the Machine Personality Inventory (MPI), we quantify the personality traits of these model variants and analyse their relationship to linguistic style and reasoning behaviour. The findings reveal that model competence is bimodal, peaking at "Expressive Generalists" and "Suppressed Specialists," while identifying a "Suppression Advantage" where reduced social traits enhance complex reasoning performance. This study further establishes a causal link between training data linguistics, such as imperative frequency, and lexical diversity, providing a roadmap for "Personality Engineering".

---

### Offline Materials Optimization with CliqueFlowmer

Authors: Jakub Grudzien Kuba, Benjamin Kurt Miller, Sergey Levine, Pieter Abbeel
Published: 2026-03-06
Categories: cs.AI, cs.CE
arXiv: https://arxiv.org/abs/2603.06082v4

Recent advances in deep learning inspired neural network-based approaches to computational materials discovery (CMD). A plethora of problems in this field involve finding materials that optimize a target property. Nevertheless, the increasingly popular generative modeling methods are ineffective at boldly exploring attractive regions of the materials space due to their maximum likelihood training. In this work, we offer an alternative CMD technique based on offline model-based optimization (MBO) that fuses direct optimization of a target material property into generation. To that end, we introduce a domain-specific model, dubbed CliqueFlowmer, that incorporates recent advances of clique-based MBO into transformer and flow generation. We validate this model's optimization abilities and show that materials it produces strongly outperform those from generative baselines. To support specialized materials discovery applications and broader interdisciplinary research, we release our code, model weights, and additional project resources at https://github.com/znowu/CliqueFlowmer, https://colab.research.google.com/drive/1usUg7zezFkcYHlm2MdYwZUNJXf_YkWnY?usp=sharing, and https://x.com/kuba_AI/status/2033382617442345321.

---

### Lyapunov Probes for Hallucination Detection in Large Foundation Models

Authors: Bozhi Luan, Gen Li, Yalan Qin, Jifeng Guo, Yun Zhou, Faguo Wu, Hongwei Zheng, Wenjun Wu, Zhaoxin Fan
Published: 2026-03-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.06081v1

We address hallucination detection in Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) by framing the problem through the lens of dynamical systems stability theory. Rather than treating hallucination as a straightforward classification task, we conceptualize (M)LLMs as dynamical systems, where factual knowledge is represented by stable equilibrium points within the representation space. Our main insight is that hallucinations tend to arise at the boundaries of knowledge-transition regions separating stable and unstable zones. To capture this phenomenon, we propose Lyapunov Probes: lightweight networks trained with derivative-based stability constraints that enforce a monotonic decay in confidence under input perturbations. By performing systematic perturbation analysis and applying a two-stage training process, these probes reliably distinguish between stable factual regions and unstable, hallucination-prone regions. Experiments on diverse datasets and models demonstrate consistent improvements over existing baselines.

---

### StreamVoiceAnon+: Emotion-Preserving Streaming Speaker Anonymization via Frame-Level Acoustic Distillation

Authors: Nikita Kuzmin, Kong Aik Lee, Eng Siong Chng
Published: 2026-03-06
Categories: eess.AS, cs.AI, eess.SP
arXiv: https://arxiv.org/abs/2603.06079v1

We address the challenge of preserving emotional content in streaming speaker anonymization (SA). Neural audio codec language models trained for audio continuation tend to degrade source emotion: content tokens discard emotional information, and the model defaults to dominant acoustic patterns rather than preserving paralinguistic attributes. We propose supervised finetuning with neutral-emotion utterance pairs from the same speaker, combined with frame-level emotion distillation on acoustic token hidden states. All modifications are confined to finetuning, which takes less than 2 hours on 4 GPUs and adds zero inference latency overhead, while maintaining a competitive 180ms streaming latency. On the VoicePrivacy 2024 protocol, our approach achieves a 49.2% UAR (emotion preservation) with 5.77% WER (intelligibility), a +24% relative UAR improvement over the baseline (39.7%->49.2%) and +10% over the emotion-prompt variant (44.6% UAR), while maintaining strong privacy (EER 49.0%). Demo and code are available: https://anonymous3842031239.github.io/

---

### Lifelong Embodied Navigation Learning

Authors: Xudong Wang, Jiahua Dong, Baichen Liu, Qi Lyu, Lianqing Liu, Zhi Han
Published: 2026-03-06
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2603.06073v1

Embodied navigation agents powered by large language models have shown strong performance on individual tasks but struggle to continually acquire new navigation skills, which suffer from catastrophic forgetting. We formalize this challenge as lifelong embodied navigation learning (LENL), where an agent is required to adapt to a sequence of navigation tasks spanning multiple scenes and diverse user instruction styles, while retaining previously learned knowledge. To tackle this problem, we propose Uni-Walker, a lifelong embodied navigation framework that decouples navigation knowledge into task-shared and task-specific components with Decoder Extension LoRA (DE-LoRA). To learn the shared knowledge, we design a knowledge inheritance strategy and an experts co-activation strategy to facilitate shared knowledge transfer and refinement across multiple navigation tasks. To learn the specific knowledge, we propose an expert subspace orthogonality constraint together and a navigation-specific chain-of-thought reasoning mechanism to capture specific knowledge and enhance instruction-style understanding. Extensive experiments demonstrate the superiority of Uni-Walker for building universal navigation agents with lifelong learning.

---

### Text-Driven Emotionally Continuous Talking Face Generation

Authors: Hao Yang, Yanyan Zhao, Tian Zheng, Hongbo Zhang, Bichen Wang, Di Wu, Xing Fu, Xuda Zhi, Yongbo Huang, Hao He
Published: 2026-03-06
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.06071v1

Talking Face Generation (TFG) strives to create realistic and emotionally expressive digital faces. While previous TFG works have mastered the creation of naturalistic facial movements, they typically express a fixed target emotion in synthetic videos and lack the ability to exhibit continuously changing and natural expressions like humans do when conveying information. To synthesize realistic videos, we propose a novel task called Emotionally Continuous Talking Face Generation (EC-TFG), which takes a text segment and an emotion description with varying emotions as driving data, aiming to generate a video where the person speaks the text while reflecting the emotional changes within the description. Alongside this, we introduce a customized model, i.e., Temporal-Intensive Emotion Modulated Talking Face Generation (TIE-TFG), which innovatively manages dynamic emotional variations by employing Temporal-Intensive Emotion Fluctuation Modeling, allowing it to provide emotion variation sequences corresponding to the input text to drive continuous facial expression changes in synthesized videos. Extensive evaluations demonstrate our method's exceptional ability to produce smooth emotion transitions and uphold high-quality visuals and motion authenticity across diverse emotional states.

---

### Aggregative Semantics for Quantitative Bipolar Argumentation Frameworks

Authors: Yann Munro, Isabelle Bloch, Marie-Jeanne Lesot
Published: 2026-03-06
Categories: cs.AI
arXiv: https://arxiv.org/abs/2603.06067v1

Formal argumentation is being used increasingly in artificial intelligence as an effective and understandable way to model potentially conflicting pieces of information, called arguments, and identify so-called acceptable arguments depending on a chosen semantics. This paper deals with the specific context of Quantitative Bipolar Argumentation Frameworks (QBAF), where arguments have intrinsic weights and can attack or support each other. In this context, we introduce a novel family of gradual semantics, called aggregative semantics. In order to deal with situations in which attackers and supporters do not play a symmetric role, and in contrast to modular semantics, we propose to aggregate attackers and supporters separately. This leads to a three-stage computation, which consists in computing a global weight for attackers and another for supporters, before aggregating these two values with the intrinsic weight of the argument. We discuss the properties that the three aggregation functions should satisfy depending on the context, as well as their relationships with the classical principles for gradual semantics. This discussion is supported by various simple examples, as well as a final example on which five hundred aggregative semantics are tested and compared, illustrating the range of possible behaviours with aggregative semantics. Decomposing the computation into three distinct and interpretable steps leads to a more parametrisable computation: it keeps the bipolarity one step further than what is done in the literature, and it leads to more understandable gradual semantics.

---

### Evaluating Austrian A-Level German Essays with Large Language Models for Automated Essay Scoring

Authors: Jonas Kubesch, Lena Huber, Clemens Havas
Published: 2026-03-06
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2603.06066v1

Automated Essay Scoring (AES) has been explored for decades with the goal to support teachers by reducing grading workload and mitigating subjective biases. While early systems relied on handcrafted features and statistical models, recent advances in Large Language Models (LLMs) have made it possible to evaluate student writing with unprecedented flexibility. This paper investigates the application of state-of-the-art open-weight LLMs for the grading of Austrian A-level German texts, with a particular focus on rubric-based evaluation. A dataset of 101 anonymised student exams across three text types was processed and evaluated. Four LLMs, DeepSeek-R1 32b, Qwen3 30b, Mixtral 8x7b and LLama3.3 70b, were evaluated with different contexts and prompting strategies. The LLMs were able to reach a maximum of 40.6% agreement with the human rater in the rubric-provided sub-dimensions, and only 32.8% of final grades matched the ones given by a human expert. The results indicate that even though smaller models are able to use standardised rubrics for German essay grading, they are not accurate enough to be used in a real-world grading environment.

---

### Agentic LLM Planning via Step-Wise PDDL Simulation: An Empirical Characterisation

Authors: Kai Göbel, Pierrick Lorang, Patrik Zips, Tobias Glück
Published: 2026-03-06
Categories: cs.AI
arXiv: https://arxiv.org/abs/2603.06064v1

Task planning, the problem of sequencing actions to reach a goal from an initial state, is a core capability requirement for autonomous robotic systems. Whether large language models (LLMs) can serve as viable planners alongside classical symbolic methods remains an open question. We present PyPDDLEngine, an open-source Planning Domain Definition Language (PDDL) simulation engine that exposes planning operations as LLM tool calls through a Model Context Protocol (MCP) interface. Rather than committing to a complete action sequence upfront, the LLM acts as an interactive search policy that selects one action at a time, observes each resulting state, and can reset and retry. We evaluate four approaches on 102 International Planning Competition (IPC) Blocksworld instances under a uniform 180-second budget: Fast Downward lama-first and seq-sat-lama-2011 as classical baselines, direct LLM planning (Claude Haiku 4.5), and agentic LLM planning via PyPDDLEngine. Fast Downward achieves 85.3% success. The direct and agentic LLM approaches achieve 63.7% and 66.7%, respectively, a consistent but modest three-percentage-point advantage for the agentic approach at $5.7\times$ higher token cost per solution. Across most co-solved difficulty blocks, both LLM approaches produce shorter plans than seq-sat-lama-2011 despite its iterative quality improvement, a result consistent with training-data recall rather than generalisable planning. These results suggest that agentic gains depend on the nature of environmental feedback. Coding agents benefit from externally grounded signals such as compiler errors and test failures, whereas PDDL step feedback is self-assessed, leaving the agent to evaluate its own progress without external verification.

---

### Transforming Omnidirectional RGB-LiDAR data into 3D Gaussian Splatting

Authors: Semin Bae, Hansol Lim, Jongseong Brad Choi
Published: 2026-03-06
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2603.06061v1

The demand for large-scale digital twins is rapidly growing in robotics and autonomous driving. However, constructing these environments with 3D Gaussian Splatting (3DGS) usually requires expensive, purpose-built data collection. Meanwhile, deployed platforms routinely collect extensive omnidirectional RGB and LiDAR logs, but a significant portion of these sensor data is directly discarded or strictly underutilized due to transmission constraints and the lack of scalable reuse pipeline. In this paper, we present an omnidirectional RGB-LiDAR reuse pipeline that transforms these archived logs into robust initialization assets for 3DGS. Direct conversion of such raw logs introduces practical bottlenecks: inherent non-linear distortion leads to unreliable Structure-from-Motion (SfM) tracking, and dense, unorganized LiDAR clouds cause computational overhead during 3DGS optimization. To overcome these challenges, our pipeline strategically integrates an ERP-to-cubemap conversion module for deterministic spatial anchoring, alongside PRISM-a color stratified downsampling strategy. By bridging these multi-modal inputs via Fast Point Feature Histograms (FPFH) based global registration and Iterative Closest Point (ICP), our pipeline successfully repurposes a considerable fraction of discarded data into usable SfM geometry. Furthermore, our LiDAR-reinforced initialization consistently enhances the final 3DGS rendering fidelity in structurally complex scenes compared to vision-only baselines. Ultimately, this work provides a deterministic workflow for creating simulation-grade digital twins from standard archived sensor logs.

---

### TempoSyncDiff: Distilled Temporally-Consistent Diffusion for Low-Latency Audio-Driven Talking Head Generation

Authors: Soumya Mazumdar, Vineet Kumar Rakesh
Published: 2026-03-06
Categories: cs.CV, cs.AI, cs.LG, cs.SD
arXiv: https://arxiv.org/abs/2603.06057v1

Diffusion models have recently advanced photorealistic human synthesis, although practical talking-head generation (THG) remains constrained by high inference latency, temporal instability such as flicker and identity drift, and imperfect audio-visual alignment under challenging speech conditions. This paper introduces TempoSyncDiff, a reference-conditioned latent diffusion framework that explores few-step inference for efficient audio-driven talking-head generation. The approach adopts a teacher-student distillation formulation in which a diffusion teacher trained with a standard noise prediction objective guides a lightweight student denoiser capable of operating with significantly fewer inference steps to improve generation stability. The framework incorporates identity anchoring and temporal regularization designed to mitigate identity drift and frame-to-frame flicker during synthesis, while viseme-based audio conditioning provides coarse lip motion control. Experiments on the LRS3 dataset report denoising-stage component-level metrics relative to VAE reconstructions and preliminary latency characterization, including CPU-only and edge computing measurements and feasibility estimates for edge deployment. The results suggest that distilled diffusion models can retain much of the reconstruction behaviour of a stronger teacher while enabling substantially lower latency inference. The study is positioned as an initial step toward practical diffusion-based talking-head generation under constrained computational settings. GitHub: https://mazumdarsoumya.github.io/TempoSyncDiff

---

### Probing Visual Concepts in Lightweight Vision-Language Models for Automated Driving

Authors: Nikos Theodoridis, Reenu Mohandas, Ganesh Sistu, Anthony Scanlan, Ciarán Eising, Tim Brophy
Published: 2026-03-06
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.06054v2

The use of Vision-Language Models (VLMs) in automated driving applications is becoming increasingly common, with the aim of leveraging their reasoning and generalisation capabilities to handle long-tail scenarios. However, these models often fail on simple visual questions that are highly relevant to automated driving, and the reasons behind these failures remain poorly understood. In this work, we examine the intermediate activations of VLMs and assess the extent to which specific visual concepts are linearly encoded, with the goal of identifying bottlenecks in the flow of visual information. Specifically, we create counterfactual image sets that differ only in a targeted visual concept and then train linear probes to distinguish between them using the activations of five state-of-the-art (SOTA) VLMs, including two training variants for one model. Our results show that concepts such as the presence of an object or agent in a scene are explicitly and linearly encoded, whereas other spatial visual concepts, such as the orientation of an object or agent, are only implicitly encoded by the spatial structure retained by the vision encoder, or are not linearly encoded at all. In parallel, we observe that in certain cases, even when a concept is linearly encoded in the model's activations, the model still fails to answer correctly. This leads us to identify two failure modes. The first is perceptual failure, where the visual information required to answer a question is not linearly encoded in the model's activations. The second is cognitive failure, where the visual information is present but the model fails to align it correctly with language semantics. Finally, we show that increasing the distance of the object in question quickly degrades the linear separability of the corresponding visual concept...

---

### Probing Visual Concepts in Lightweight Vision-Language Models for Automated Driving

Authors: Nikos Theodoridis, Reenu Mohandas, Ganesh Sistu, Anthony Scanlan, Ciarán Eising, Tim Brophy
Published: 2026-03-06
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.06054v1

The use of Vision-Language Models (VLMs) in automated driving applications is becoming increasingly common, with the aim of leveraging their reasoning and generalisation capabilities to handle long tail scenarios. However, these models often fail on simple visual questions that are highly relevant to automated driving, and the reasons behind these failures remain poorly understood. In this work, we examine the intermediate activations of VLMs and assess the extent to which specific visual concepts are linearly encoded, with the goal of identifying bottlenecks in the flow of visual information. Specifically, we create counterfactual image sets that differ only in a targeted visual concept and then train linear probes to distinguish between them using the activations of four state-of-the-art (SOTA) VLMs. Our results show that concepts such as the presence of an object or agent in a scene are explicitly and linearly encoded, whereas other spatial visual concepts, such as the orientation of an object or agent, are only implicitly encoded by the spatial structure retained by the vision encoder. In parallel, we observe that in certain cases, even when a concept is linearly encoded in the model's activations, the model still fails to answer correctly. This leads us to identify two failure modes. The first is perceptual failure, where the visual information required to answer a question is not linearly encoded in the model's activations. The second is cognitive failure, where the visual information is present but the model fails to align it correctly with language semantics. Finally, we show that increasing the distance of the object in question quickly degrades the linear separability of the corresponding visual concept. Overall, our findings improve our understanding of failure cases in VLMs on simple visual tasks that are highly relevant to automated driving.

---

### Devil is in Narrow Policy: Unleashing Exploration in Driving VLA Models

Authors: Canyu Chen, Yuguang Yang, Zhewen Tan, Yizhi Wang, Ruiyi Zhan, Haiyan Liu, Xuanyao Mao, Jason Bao, Xinyue Tang, Linlin Yang, Bingchuan Sun, Yan Wang et al.
Published: 2026-03-06
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2603.06049v1

We identify a fundamental Narrow Policy limitation undermining the performance of autonomous VLA models, where driving Imitation Learning (IL) tends to collapse exploration and limit the potential of subsequent Reinforcement Learning (RL) stages, which often saturate prematurely due to insufficient feedback diversity. Thereby, we propose Curious-VLA, a framework that alleviates the exploit-explore dilemma through a two-stage design. During IL, we introduce a Feasible Trajectory Expansion (FTE) strategy to generate multiple physically valid trajectories and a step-wise normalized trajectory representation to adapt this diverse data. In the RL stage, we present Adaptive Diversity-Aware Sampling (ADAS) that prioritizes high-diversity samples and introduce Spanning Driving Reward (SDR) with a focal style weighting to amplify reward's value span for improving sensitivity to driving quality. On the Navsim benchmark, Curious-VLA achieves SoTA results (PDMS 90.3, EPDMS 85.4) and a Best-of-N PDMS of 94.8, demonstrating its effectiveness in unlocking the exploratory potential of VLA models. Code: https://github.com/Mashiroln/curious_vla.git.

---

### GenHOI: Towards Object-Consistent Hand-Object Interaction with Temporally Balanced and Spatially Selective Object Injection

Authors: Xuan Huang, Mochu Xiang, Zhelun Shen, Jinbo Wu, Chenming Wu, Chen Zhao, Kaisiyuan Wang, Hang Zhou, Shanshan Liu, Haocheng Feng, Wei He, Jingdong Wang
Published: 2026-03-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.06048v1

Hand-Object Interaction (HOI) remains a core challenge in digital human video synthesis, where models must generate physically plausible contact and preserve object identity across frames. Although recent HOI reenactment approaches have achieved progress, they are typically trained and evaluated in-domain and fail to generalize to complex, in-the-wild scenarios. In contrast, all-in-one video editing models exhibit broader robustness but still struggle with HOI-specific issues such as inconsistent object appearance. In this paper, we present GenHOI, a lightweight augmentation to pretrained video generation models that injects reference-object information in a temporally balanced and spatially selective manner. For temporal balancing, we propose Head-Sliding RoPE, which assigns head-specific temporal offsets to reference tokens, distributing their influence evenly across frames and mitigating the temporal decay of 3D RoPE to improve long-range object consistency. For spatial selectivity, we design a two-level spatial attention gate that concentrates object-conditioned attention on HOI regions and adaptively scales its strength, preserving background realism while enhancing interaction fidelity. Extensive qualitative and quantitative evaluations on unseen, in-the-wild scenes demonstrate that GenHOI significantly outperforms state-of-the-art HOI reenactment and all-in-one video editing methods. Project page: https://xuanhuang0.github.io/GenHOI/

---

### Learning to Generate via Understanding: Understanding-Driven Intrinsic Rewarding for Unified Multimodal Models

Authors: Jiadong Pan, Liang Li, Yuxin Peng, Yu-Ming Tang, Shuohuan Wang, Yu Sun, Hua Wu, Qingming Huang, Haifeng Wang
Published: 2026-03-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.06043v1

Recently, unified multimodal models (UMMs) have made remarkable progress in integrating visual understanding and generation, demonstrating strong potential for complex text-to-image (T2I) tasks. Despite their theoretical promise, a persistent capability gap exists: UMMs typically exhibit superior visual understanding but comparatively weaker generative capabilities. This discrepancy arises largely from the intrinsic decoupling between the understanding and generation processes. While a UMM can accurately interpret fine-grained visual details, it often struggles to produce semantically coherent images from complex textual prompts. To address this challenge, we explore UMMs' internal understanding capability to enhance generation quality. We propose a token-level intrinsic text-image alignment reward mechanism, GvU, enabling the UMM to act simultaneously as teacher and student: it evaluates its own outputs using the understanding branch to guide the generations accordingly. Building upon this, we design a self-supervised reinforcement learning framework, allowing UMMs to iteratively improve their generation quality through understanding-based intrinsic reward signals--without reliance on external supervision. Experimental results show that our method substantially boosts UMMs' generation, which in turn strengthens their fine-grained visual understanding, narrowing the capability gap between UMMs' visual understanding and generation.

---

### FontUse: A Data-Centric Approach to Style- and Use-Case-Conditioned In-Image Typography

Authors: Xia Xin, Yuki Endo, Yoshihiro Kanamori
Published: 2026-03-06
Categories: cs.CV, cs.GR
arXiv: https://arxiv.org/abs/2603.06038v1

Recent text-to-image models can generate high-quality images from natural-language prompts, yet controlling typography remains challenging: requested typographic appearance is often ignored or only weakly followed. We address this limitation with a data-centric approach that trains image generation models using targeted supervision derived from a structured annotation pipeline specialized for typography. Our pipeline constructs a large-scale typography-focused dataset, FontUse, consisting of about 70K images annotated with user-friendly prompts, text-region locations, and OCR-recognized strings. The annotations are automatically produced using segmentation models and multimodal large language models (MLLMs). The prompts explicitly combine font styles (e.g., serif, script, elegant) and use cases (e.g., wedding invitations, coffee-shop menus), enabling intuitive specification even for novice users. Fine-tuning existing generators with these annotations allows them to consistently interpret style and use-case conditions as textual prompts without architectural modification. For evaluation, we introduce a Long-CLIP-based metric that measures alignment between generated typography and requested attributes. Experiments across diverse prompts and layouts show that models trained with our pipeline produce text renderings more consistent with prompts than competitive baselines. The source code for our annotation pipeline is available at https://github.com/xiaxinz/FontUSE.

---