# Research Papers — 2026-03 · bundle page 109 of 243 > Full-text markdown of papers #5401–5450 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/109 [← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/108.md) [Next bundle →](https://aipod.dev/papers/archive/2026-03/page/110.md) ### Transformers Can Learn Rules They've Never Seen: Proof of Computation Beyond Interpolation Authors: Andy Gray Published: 2026-03-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.17019v2 A central question in the debate over large language models is whether transformers can learn rules they have never seen, or whether they can only interpolate: predict new cases from their similarity to training examples. We test this in a controlled setting where interpolation provably fails, so success can only come from computation beyond interpolation. We train small transformers to predict the rollout of a cellular automaton whose update rule is pure XOR, and remove one entry of the rule's truth table from all direct supervision. The missing entry's output is never shown to the model; its only trace is indirect, as wrong values corrupt visible predictions at later timesteps. Because XOR parity flips whenever one input bit is changed, every one-bit neighbour of the missing entry carries the opposite label, and we prove that similarity-based predictors, including nearest-neighbour, kernel, and Gaussian-process methods, are forced to the wrong answer. A two-layer transformer can nevertheless recover the missing entry, and circuit extraction confirms it computes XOR exactly. Ablations show the recovery depends on gradient signal propagating through multi-step prediction, and a second, structurally unrelated benchmark on symbolic operator chains exhibits the same capacity under ordinary autoregressive training. Together with a constructive proof that a standard transformer block can implement exact local Boolean rules, these results provide an existence proof that transformers can learn rule structure not directly observed in training and express it explicitly. This rules out the strongest architectural form of the interpolation-only account, the claim that transformers cannot in principle discover and communicate unseen rules, while leaving open when such behaviour arises in large-scale language training. --- ### LLM NL2SQL Robustness: Surface Noise vs. Linguistic Variation in Traditional and Agentic Settings Authors: Lifu Tu, Rongguang Wang, Tao Sheng, Sujjith Ravi, Dan Roth Published: 2026-03-17 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.17017v1 Robustness evaluation for Natural Language to SQL (NL2SQL) systems is essential because real-world database environments are dynamic, noisy, and continuously evolving, whereas conventional benchmark evaluations typically assume static schemas and well-formed user inputs. In this work, we introduce a robustness evaluation benchmark containing approximately ten types of perturbations and conduct evaluations under both traditional and agentic settings. We assess multiple state-of-the-art large language models (LLMs), including Grok-4.1, Gemini-3-Pro, Claude-Opus-4.6, and GPT-5.2. Our results show that these models generally maintain strong performance under several perturbations; however, notable performance degradation is observed for surface-level noise (e.g., character-level corruption) and linguistic variation that preserves semantics while altering lexical or syntactic forms. Furthermore, we observe that surface-level noise causes larger performance drops in traditional pipelines, whereas linguistic variation presents greater challenges in agentic settings. These findings highlight the remaining challenges in achieving robust NL2SQL systems, particularly in handling linguistic variability. --- ### Empirical Recipes for Efficient and Compact Vision-Language Models Authors: Jiabo Huang, Zhizhong Li, Sina Sajadmanesh, Weiming Zhuang, Lingjuan Lyu Published: 2026-03-17 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.16987v1 Deploying vision-language models (VLMs) in resource-constrained settings demands low latency and high throughput, yet existing compact VLMs often fall short of the inference speedups their smaller parameter counts suggest. To explain this discrepancy, we conduct an empirical end-to-end efficiency analysis and systematically profile inference to identify the dominant bottlenecks. Based on these findings, we develop optimization recipes tailored to compact VLMs that substantially reduce latency while preserving accuracy. These techniques cut time to first token (TTFT) by 53% on InternVL3-2B and by 93% on SmolVLM-256M. Our recipes are broadly applicable across both VLM architectures and common serving frameworks, providing practical guidance for building efficient VLM systems. Beyond efficiency, we study how to extend compact VLMs with structured perception outputs and introduce the resulting model family, ArgusVLM. Across diverse benchmarks, ArgusVLM achieves strong performance while maintaining a compact and efficient design. --- ### Integrating Inductive Biases in Transformers via Distillation for Financial Time Series Forecasting Authors: Yu-Chen Den, Kuan-Yu Chen, Kendro Vincent, Darby Tien-Hao Chang Published: 2026-03-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.16985v2 Transformer-based models have been widely adopted for time-series forecasting due to their high representational capacity and architectural flexibility. However, many Transformer variants implicitly assume stationarity and stable temporal dynamics -- assumptions routinely violated in financial markets characterized by regime shifts and non-stationarity. Empirically, state-of-the-art time-series Transformers often underperform even vanilla Transformers on financial tasks, while simpler architectures with distinct inductive biases, such as CNNs and RNNs, can achieve stronger performance with substantially lower complexity. At the same time, no single inductive bias dominates across markets or regimes, suggesting that robust financial forecasting requires integrating complementary temporal priors. We propose TIPS (Transformer with Inductive Prior Synthesis), a knowledge distillation framework that synthesizes diverse inductive biases -- causality, locality, and periodicity -- within a unified Transformer. TIPS trains bias-specialized Transformer teachers via attention masking, then distills their knowledge into a single student model with regime-dependent alignment across inductive biases. Across four major equity markets, TIPS achieves state-of-the-art performance, outperforming strong ensemble baselines by 55%, 9%, and 16% in annual return, Sharpe ratio, and Calmar ratio, while requiring only 38% of the inference-time computation. Further analyses show that TIPS generates statistically significant excess returns beyond both vanilla Transformers and its teacher ensembles, and exhibits regime-dependent behavioral alignment with classical architectures during their profitable periods. These results highlight the importance of regime-dependent inductive bias utilization for robust generalization in non-stationary financial time series. --- ### Formal verification of tree-based machine learning models for lateral spreading Authors: Krishna Kumar Published: 2026-03-17 Categories: cs.LG, cs.LO arXiv: https://arxiv.org/abs/2603.16983v1 Machine learning models for geotechnical hazard prediction can achieve high accuracy while learning physically inconsistent relationships from sparse or biased training data. Current remedies (post-hoc explainability, such as SHAP and LIME, and training-time constraints) either diagnose individual predictions approximately or restrict model capacity without providing exhaustive guarantees. This paper encodes trained tree ensembles as logical formulas in a Satisfiability Modulo Theories (SMT) solver and checks physical specifications across the entire input domain, not just sampled points. Four geotechnical specifications (water table depth, PGA monotonicity, distance safety, and flat-ground safety) are formalized as decidable logical formulas and verified via SMT against both XGBoost ensembles and Explainable Boosting Machines (EBMs) trained on the 2011 Christchurch earthquake lateral spreading dataset (7,291 sites, four features). The SMT solver either produces a concrete counterexample where a specification fails or proves that no violation exists. The unconstrained EBM (80.1% accuracy) violates all four specifications. A fully constrained EBM (67.2%) satisfies three of four specifications, demonstrating that iterative constraint application guided by verification can progressively improve physical consistency. A Pareto analysis of 33 model variants reveals a persistent trade-off, as none of the variants studied achieve both greater than 80% accuracy and full compliance with the specified set. SHAP analysis of specification counterexamples shows that the offending feature can rank last, demonstrating that post-hoc explanations do not substitute for formal verification. These results establish a verify-fix-verify engineering loop and a formal certification for deploying physically consistent ML models in safety-critical geotechnical applications. --- ### Interpretable AI-Assisted Early Reliability Prediction for a Two-Parameter Parallel Root-Finding Scheme Authors: Bruno Carpentieri, Andrei Velichko, Mudassir Shams, Paola Lecca Published: 2026-03-17 Categories: math.NA, cs.LG arXiv: https://arxiv.org/abs/2603.16980v1 We propose an interpretable AI-assisted reliability diagnostic framework for parameterized root-finding schemes based on kNN-LLE proxy stability profiling and multi-horizon early prediction. The approach augments a numerical solver with a lightweight predictive layer that estimates solver reliability from short prefixes of iteration dynamics, enabling early identification of stable and unstable parameter regimes. For each configuration in the parameter space, raw and smoothed proxy profiles of a largest Lyapunov exponent (LLE) estimator are constructed, from which contractivity-based reliability scores summarizing finite-time convergence are derived. Machine learning models predict the reliability score from early segments of the proxy profile, allowing the framework to determine when solver dynamics become diagnostically informative. Experiments on a two-parameter parallel root-finding scheme show reliable prediction after only a few iterations: the best models achieve R^2=0.48 at horizon T=1, improve to R^2=0.67 by T=3, and exceed R^2=0.89 before the characteristic minimum-location scale of the stability profile. Prediction accuracy increases to R^2=0.96 at larger horizons, with mean absolute errors around 0.03, while inference costs remain negligible (microseconds per sample). The framework provides interpretable stability indicators and supports early decisions during solver execution, such as continuing, restarting, or adjusting parameters. --- ### Rewarding DINO: Predicting Dense Rewards with Vision Foundation Models Authors: Pierre Krack, Tobias Jülg, Wolfram Burgard, Florian Walter Published: 2026-03-17 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2603.16978v1 Well-designed dense reward functions in robot manipulation not only indicate whether a task is completed but also encode progress along the way. Generally, designing dense rewards is challenging and usually requires access to privileged state information available only in simulation, not in real-world experiments. This makes reward prediction models that infer task state information from camera images attractive. A common approach is to predict rewards from expert demonstrations based on visual similarity or sequential frame ordering. However, this biases the resulting reward function towards a specific solution and leaves it undefined in states not covered by the demonstrations. In this work, we introduce Rewarding DINO, a method for language-conditioned reward modeling that learns actual reward functions rather than specific trajectories. The model's compact size allows it to serve as a direct replacement for analytical reward functions with comparatively low computational overhead. We train our model on data sampled from 24 Meta-World+ tasks using a rank-based loss and evaluate pairwise accuracy, rank correlation, and calibration. Rewarding DINO achieves competitive performance in tasks from the training set and generalizes to new settings in simulation and the real world, indicating that it learns task semantics. We also test the model with off-the-shelf reinforcement learning algorithms to solve tasks from our Meta-World+ training set. --- ### Implementation of tangent linear and adjoint models for neural networks based on a compiler library tool Authors: Sa Xiao, Hao Jing, Honglu Sun, Haoyu Li Published: 2026-03-17 Categories: cs.MS, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.16976v1 This paper presents TorchNWP, a compilation library tool for the efficient coupling of artificial intelligence components and traditional numerical models. It aims to address the issues of poor cross-language compatibility, insufficient coupling flexibility, and low data transfer efficiency between operational numerical models developed in Fortran and Python-based deep learning frameworks. Based on LibTorch, it optimizes and designs a unified application-layer calling interface, converts deep learning models under the PyTorch framework into a static binary format, and provides C/C++ interfaces. Then, using hybrid Fortran/C/C++ programming, it enables the deployment of deep learning models within numerical models. Integrating TorchNWP into a numerical model only requires compiling it into a callable link library and linking it during the compilation and linking phase to generate the executable. On this basis, tangent linear and adjoint model based on neural networks are implemented at the C/C++ level, which can shield the internal structure of neural network models and simplify the construction process of four-dimensional variational data assimilation systems. Meanwhile, it supports deployment on heterogeneous platforms, is compatible with mainstream neural network models, and enables mapping of different parallel granularities and efficient parallel execution. Using this tool requires minimal code modifications to the original numerical model, thus reducing coupling costs. It can be efficiently integrated into numerical weather prediction models such as CMA-GFS and MCV, and has been applied to the coupling of deep learning-based physical parameterization schemes (e.g., radiation, non-orographic gravity wave drag) and the development of their tangent linear and adjoint models, significantly improving the accuracy and efficiency of numerical weather prediction. --- ### The State of Generative AI in Software Development: Insights from Literature and a Developer Survey Authors: Vincent Gurgul, Robin Gubela, Stefan Lessmann Published: 2026-03-17 Categories: cs.SE, cs.AI, cs.CY, cs.ET, cs.HC arXiv: https://arxiv.org/abs/2603.16975v1 Generative Artificial Intelligence (GenAI) rapidly transforms software engineering, yet existing research remains fragmented across individual tasks in the Software Development Lifecycle. This study integrates a systematic literature review with a survey of 65 software developers. The results show that GenAI exerts its highest impact in design, implementation, testing, and documentation, where over 70 % of developers report at least halving the time for boilerplate and documentation tasks. 79 % of survey respondents use GenAI daily, preferring browser-based Large Language Models over alternatives integrated directly in their development environment. Governance is maturing, with two-thirds of organizations maintaining formal or informal guidelines. In contrast, early SDLC phases such as planning and requirements analysis show markedly lower reported benefits. In a nutshell, GenAI shifts value creation from routine coding toward specification quality, architectural reasoning, and oversight, while risks such as uncritical adoption, skill erosion, and technical debt require robust governance and human-in-the-loop mechanisms. --- ### Are a Thousand Words Better Than a Single Picture? Beyond Images -- A Framework for Multi-Modal Knowledge Graph Dataset Enrichment Authors: Pengyu Zhang, Klim Zaporojets, Jie Liu, Jia-Hong Huang, Paul Groth Published: 2026-03-17 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.16974v1 Multi-Modal Knowledge Graphs (MMKGs) benefit from visual information, yet large-scale image collection is hard to curate and often excludes ambiguous but relevant visuals (e.g., logos, symbols, abstract scenes). We present Beyond Images, an automatic data-centric enrichment pipeline with optional human auditing. This pipeline operates in three stages: (1) large-scale retrieval of additional entity-related images, (2) conversion of all visual inputs into textual descriptions to ensure that ambiguous images contribute usable semantics rather than noise, and (3) fusion of multi-source descriptions using a large language model (LLM) to generate concise, entity-aligned summaries. These summaries replace or augment the text modality in standard MMKG models without changing their architectures or loss functions. Across three public MMKG datasets and multiple baseline models, we observe consistent gains (up to 7% Hits@1 overall). Furthermore, on a challenging subset of entities with visually ambiguous logos and symbols, converting images into text yields large improvements (201.35% MRR and 333.33% Hits@1). Additionally, we release a lightweight Text-Image Consistency Check Interface for optional targeted audits, improving description quality and dataset reliability. Our results show that scaling image coverage and converting ambiguous visuals into text is a practical path to stronger MMKG completion. Code, datasets, and supplementary materials are available at https://github.com/pengyu-zhang/Beyond-Images. --- ### Hybrid Classical-Quantum Transfer Learning with Noisy Quantum Circuits Authors: D. Martín-Pérez, F. Rodríguez-Díaz, D. Gutiérrez-Avilés, A. Troncoso, F. Martínez-Álvarez Published: 2026-03-17 Categories: quant-ph, cs.LG arXiv: https://arxiv.org/abs/2603.16973v1 Quantum transfer learning combines pretrained classical deep learning models with quantum circuits to reuse expressive feature representations while limiting the number of trainable parameters. In this work, we introduce a family of compact quantum transfer learning architectures that attach variational quantum classifiers to frozen convolutional backbones for image classification. We instantiate and evaluate several classical-quantum hybrid models implemented in PennyLane and Qiskit, and systematically compare them with a classical transfer-learning baseline across heterogeneous image datasets. To ensure a realistic assessment, we evaluate all approaches under both ideal simulation and noisy emulation using noise models calibrated from IBM quantum hardware specifications, as well as on real IBM quantum hardware. Experimental results show that the proposed quantum transfer learning architectures achieve competitive and, in several cases, superior accuracy while consistently reducing training time and energy consumption relative to the classical baseline. Among the evaluated approaches, PennyLane-based implementations provide the most favorable trade-off between accuracy and computational efficiency, suggesting that hybrid quantum transfer learning can offer practical benefits in realistic NISQ era settings when feature extraction remains classical. --- ### Over-the-air White-box Attack on the Wav2Vec Speech Recognition Neural Network Authors: Protopopov Alexey Published: 2026-03-17 Categories: eess.AS, cs.LG, cs.SD arXiv: https://arxiv.org/abs/2603.16972v1 Automatic speech recognition systems based on neural networks are vulnerable to adversarial attacks that alter transcriptions in a malicious way. Recent works in this field have focused on making attacks work in over-the-air scenarios, however such attacks are typically detectable by human hearing, limiting their potential applications. In the present work we explore different approaches of making over-the-air attacks less detectable, as well as the impact these approaches have on the attacks' effectiveness. --- ### MAND: Modality-Aware Novelty Detection for Open-World Egocentric Activity Recognition Authors: Hyejeong Im, Wonseon Lim, Dae-Won Kim Published: 2026-03-17 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.16970v2 Multimodal egocentric activity recognition integrates visual and inertial cues for robust first-person behavior understanding. However, deploying such systems in open-world environments requires detecting novel activities while continuously learning from non-stationary data streams. Existing methods rely on the main fused logits for novelty scoring, without fully exploiting the complementary evidence available from individual modalities. Because these logits are often dominated by RGB, cues from other modalities, particularly IMU, remain underutilized, and this imbalance worsens as catastrophic forgetting accumulates. To address this, we propose MAND, a modality-aware framework for multimodal egocentric open-world continual learning. At inference, Modality-aware Adaptive Scoring (MoAS) adaptively adjusts modality contributions using sample-wise reliability and refines novelty scoring with deviation and disagreement penalties. During training, Modality-aware Representation Stabilization Training (MoRST) preserves the discriminative capacity of each modality across tasks through modality-specific heads and modality-wise logit distillation. Experiments on a public multimodal egocentric benchmark show that MAND consistently improves novel activity detection and known-class accuracy while substantially reducing FPR95, indicating more reliable open-world recognition. The source code is available at \href{https://github.com/HyeJeongIm/MAND}{github.com/HyeJeongIm/MAND}. --- ### DeepStage: Learning Autonomous Defense Policies Against Multi-Stage APT Campaigns Authors: Trung V. Phan, Tri Gia Nguyen, Thomas Bauschert Published: 2026-03-17 Categories: cs.CR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.16969v2 This paper presents DeepStage, a deep reinforcement learning (DRL) framework for adaptive and stage-aware defense against Advanced Persistent Threats (APTs). The enterprise environment is formulated as a partially observable Markov decision process (POMDP), in which host provenance and network telemetry are fused into unified provenance graphs. Building on our prior work (StageFinder), DeepStage employs a graph neural network encoder and an LSTM-based stage estimator to infer probabilistic attacker stages aligned with the MITRE ATT&CK framework. The resulting stage beliefs, together with graph embeddings, are used to guide a hierarchical Proximal Policy Optimization (PPO) agent that selects defense actions across monitoring, access control, containment, and remediation. Experiments in a realistic enterprise testbed with CALDERA-driven APT playbooks show that DeepStage achieves an average F1-score of 0.887 and a mitigation success rate of 84.7%, outperforming a risk-aware DRL baseline by 21.8% in F1-score and 16.2% in mitigation success. The results demonstrate effective stage-aware and cost-efficient autonomous cyber defense. --- ### MSRAMIE: Multimodal Structured Reasoning Agent for Multi-instruction Image Editing Authors: Zhaoyuan Qiu, Ken Chen, Xiangwei Wang, Yu Xia, Sachith Seneviratne, Saman Halgamuge Published: 2026-03-17 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.16967v1 Existing instruction-based image editing models perform well with simple, single-step instructions but degrade in realistic scenarios that involve multiple, lengthy, and interdependent directives. A main cause is the scarcity of training data with complex multi-instruction annotations. However, it is costly to collect such data and retrain these models. To address this challenge, we propose MSRAMIE, a training-free agent framework built on Multimodal Large Language Model (MLLM). MSRAMIE takes existing editing models as plug-in components and handle multi-instruction tasks via structured multimodal reasoning. It orchestrates iterative interactions between an MLLM-based Instructor and an image editing Actor, introducing a novel reasoning topology that comprises the proposed Tree-of-States and Graph-of-References. During inference, complex instructions are decomposed into multiple editing steps which enable state transitions, cross-step information aggregation, and original input recall, which enables systematic exploration of the image editing space and flexible progressive output refinement. The visualizable inference topology further provides interpretable and controllable decision pathways. Experiments show that as the instruction complexity increases, MSRAMIE can improve instruction following over 15% and increases the probability of finishing all modifications in a single run over 100%, while preserving perceptual quality and maintaining visual consistency. --- ### CineSRD: Leveraging Visual, Acoustic, and Linguistic Cues for Open-World Visual Media Speaker Diarization Authors: Liangbin Huang, Xiaohua Liao, Chaoqun Cui, Shijing Wang, Zhaolong Huang, Yanlong Du, Wenji Mao Published: 2026-03-17 Categories: cs.CV, cs.AI, cs.MM, cs.SD, eess.AS arXiv: https://arxiv.org/abs/2603.16966v1 Traditional speaker diarization systems have primarily focused on constrained scenarios such as meetings and interviews, where the number of speakers is limited and acoustic conditions are relatively clean. To explore open-world speaker diarization, we extend this task to the visual media domain, encompassing complex audiovisual programs such as films and TV series. This new setting introduces several challenges, including long-form video understanding, a large number of speakers, cross-modal asynchrony between audio and visual cues, and uncontrolled in-the-wild variability. To address these challenges, we propose Cinematic Speaker Registration & Diarization (CineSRD), a unified multimodal framework that leverages visual, acoustic, and linguistic cues from video, speech, and subtitles for speaker annotation. CineSRD first performs visual anchor clustering to register initial speakers and then integrates an audio language model for speaker turn detection, refining annotations and supplementing unregistered off-screen speakers. Furthermore, we construct and release a dedicated speaker diarization benchmark for visual media that includes Chinese and English programs. Experimental results demonstrate that CineSRD achieves superior performance on the proposed benchmark and competitive results on conventional datasets, validating its robustness and generalizability in open-world visual media settings. --- ### Behavior-Centric Extraction of Scenarios from Highway Traffic Data and their Domain-Knowledge-Guided Clustering using CVQ-VAE Authors: Niklas Roßberg, Sinan Hasirlioglu, Mohamed Essayed Bouzouraa, Wolfgang Utschick, Michael Botsch Published: 2026-03-17 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.16964v2 Approval of ADS depends on evaluating its behavior within representative real-world traffic scenarios. A common way to obtain such scenarios is to extract them from real-world data recordings. These can then be grouped and serve as basis on which the ADS is subsequently tested. This poses two central challenges: how scenarios are extracted and how they are grouped. Existing extraction methods rely on heterogeneous definitions, hindering scenario comparability. For the grouping of scenarios, rule-based or ML-based methods can be utilized. However, while modern ML-based approaches can handle the complexity of traffic scenarios, unlike rule-based approaches, they lack interpretability and may not align with domain-knowledge. This work contributes to a standardized scenario extraction based on the Scenario-as-Specification concept, as well as a domain-knowledge-guided scenario clustering process. Experiments on the highD dataset demonstrate that scenarios can be extracted reliably and that domain-knowledge can be effectively integrated into the clustering process. As a result, the proposed methodology supports a more standardized process for deriving scenario categories from highway data recordings and thus enables a more efficient validation process of automated vehicles. --- ### Topology-Guided Biomechanical Profiling: A White-Box Framework for Opportunistic Screening of Spinal Instability on Routine CT Authors: Zanting Ye, Xuanbin Wu, Guoqing Zhong, Shengyuan Liu, Jiashuai Liu, Ge Song, Zhisong Wang, Jing Hao, Xiaolong Niu, Yefeng Zheng, Yu Zhang, Lijun Lu Published: 2026-03-17 Categories: q-bio.QM, cs.CV arXiv: https://arxiv.org/abs/2603.16963v1 Routine oncologic computed tomography (CT) presents an ideal opportunity for screening spinal instability, yet prophylactic stabilization windows are frequently missed due to the complex geometric reasoning required by the Spinal Instability Neoplastic Score (SINS). Automating SINS is fundamentally hindered by metastatic osteolysis, which induces topological ambiguity that confounds standard segmentation and black-box AI. We propose Topology-Guided Biomechanical Profiling (TGBP), an auditable white-box framework decoupling anatomical perception from structural reasoning. TGBP anchors SINS assessment on two deterministic geometric innovations: (i) canal-referenced partitioning to resolve posterolateral boundary ambiguity, and (ii) context-aware morphometric normalization via covariance-based oriented bounding boxes (OBB) to quantify vertebral collapse. Integrated with auxiliary radiomic and large language model (LLM) modules, TGBP provides an end-to-end, interpretable SINS evaluation. Validated on a multi-center, multi-cancer cohort ($N=482$), TGBP achieved 90.2\% accuracy in 3-tier stability triage. In a blinded reader study ($N=30$), TGBP significantly outperformed medical oncologists on complex structural features ($κ=0.857$ vs.\ $0.570$) and prevented compounding errors in Total Score estimation ($κ=0.625$ vs.\ $0.207$), democratizing expert-level opportunistic screening. --- ### Adversarial attacks against Modern Vision-Language Models Authors: Alejandro Paredes La Torre Published: 2026-03-17 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2603.16960v2 We study adversarial robustness of open-source vision-language model (VLM) agents deployed in a self-contained e-commerce environment built to simulate realistic pre-deployment conditions. We evaluate two agents, LLaVA-v1.5-7B and Qwen2.5-VL-7B, under three gradient-based attacks: the Basic Iterative Method (BIM), Projected Gradient Descent (PGD), and a CLIP-based spectral attack. Against LLaVA, all three attacks achieve substantial attack success rates (52.6%, 53.8%, and 66.9% respectively), demonstrating that simple gradient-based methods pose a practical threat to open-source VLM agents. Qwen2.5-VL proves significantly more robust across all attacks (6.5%, 7.7%, and 15.5%), suggesting meaningful architectural differences in adversarial resilience between open-source VLM families. These findings have direct implications for the security evaluation of VLM agents prior to commercial deployment. --- ### Data-knowledge dual-driven intelligent framework for full-chain, experiment-efficient synthesis of 2D dendrites Authors: Wenqiang Huang, Xuhang Gu, Susu Fang, Shen'ao Xue, Huanhuan Xing, Junjie Jiang, Junying Zhang, Shen Zhou, Zheng Luo, Jin Zhang, Fangping Ouyang, Shanshan Wang Published: 2026-03-17 Categories: cond-mat.mtrl-sci, cs.AI arXiv: https://arxiv.org/abs/2603.16959v2 Exemplified by the chemical vapor deposition growth of two-dimensional dendrites, which has potential applications in catalysis and presents a parameter-intensive, data-scarce and reaction process-complex model problem, we devise a machine intelligence-empowered framework for the full chain support of material synthesis, encompassing rapid process optimization, accurate customized synthesis, and comprehensive mechanism deciphering.First, active learning is integrated into the experimental workflow, identifying an optimal recipe for the growth of highly-branched, electrocatalytically-active ReSe2 dendrites through 60 experiments (4 iterations), which account for less than 1.3% of the numerous possible parameter combinations.Then, a prediction accuracy-guided data augmentation strategy is developed combined with a tree-based machine learning (ML) algorithm, unveiling a non-linear correlation between 5 process variables and fractal dimension (DF) of ReSe2 dendrites with only 9 experiment additions, which guides the synthesis of various user-defined DF. Finally, we construct a data-knowledge dual-driven mechanism model by integration of cross-scale characterizations, interpretable ML models, and domain knowledge in thermodynamics and kinetics, unraveling synergistic contributions of multiple process parameters to the product morphology. This work demonstrates the ML potential to transform the research paradigm and is adaptable to broader material synthesis. --- ### Machine intelligence supports the full chain of 2D dendrite synthesis Authors: Wenqiang Huang, Susu Fang, Xuhang Gu, Shen'ao Xue, Huanhuan Xing, Junjie Jiang, Junying Zhang, Shen Zhou, Zheng Luo, Jin Zhang, Fangping Ouyang, Shanshan Wang Published: 2026-03-17 Categories: cond-mat.mtrl-sci, cs.AI arXiv: https://arxiv.org/abs/2603.16959v1 Exemplified by the chemical vapor deposition growth of two-dimensional dendrites, which has potential applications in catalysis and presents a parameter-intensive, data-scarce and reaction process-complex model problem, we devise a machine intelligence-empowered framework for the full chain support of material synthesis, encompassing rapid process optimization, accurate customized synthesis, and comprehensive mechanism deciphering.First, active learning is integrated into the experimental workflow, identifying an optimal recipe for the growth of highly-branched, electrocatalytically-active ReSe2 dendrites through 60 experiments (4 iterations), which account for less than 1.3% of the numerous possible parameter combinations.Then, a prediction accuracy-guided data augmentation strategy is developed combined with a tree-based machine learning (ML) algorithm, unveiling a non-linear correlation between 5 process variables and fractal dimension (DF) of ReSe2 dendrites with only 9 experiment additions, which guides the synthesis of various user-defined DF. Finally, we construct a data-knowledge dual-driven mechanism model by integration of cross-scale characterizations, interpretable ML models, and domain knowledge in thermodynamics and kinetics, unraveling synergistic contributions of multiple process parameters to the product morphology. This work demonstrates the ML potential to transform the research paradigm and is adaptable to broader material synthesis. --- ### PhysQuantAgent: An Inference Pipeline of Mass Estimation for Vision-Language Models Authors: Hisayuki Yokomizo, Taiki Miyanishi, Yan Gang, Shuhei Kurita, Nakamasa Inoue, Yusuke Iwasawa Published: 2026-03-17 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.16958v1 Vision-Language Models (VLMs) are increasingly applied to robotic perception and manipulation, yet their ability to infer physical properties required for manipulation remains limited. In particular, estimating the mass of real-world objects is essential for determining appropriate grasp force and ensuring safe interaction. However, current VLMs lack reliable mass reasoning capabilities, and most existing benchmarks do not explicitly evaluate physical quantity estimation under realistic sensing conditions. In this work, we propose PhysQuantAgent, a framework for real-world object mass estimation using VLMs, together with VisPhysQuant, a new benchmark dataset for evaluation. VisPhysQuant consists of RGB-D videos of real objects captured from multiple viewpoints, annotated with precise mass measurements. To improve estimation accuracy, we introduce three visual prompting methods that enhance the input image with object detection, scale estimation, and cross-sectional image generation to help the model comprehend the size and internal structure of the target object. Experiments show that visual prompting significantly improves mass estimation accuracy on real-world data, suggesting the efficacy of integrating spatial reasoning with VLM knowledge for physical inference. --- ### WorldCam: Interactive Autoregressive 3D Gaming Worlds with Camera Pose as a Unifying Geometric Representation Authors: Jisu Nam, Yicong Hong, Chun-Hao Paul Huang, Feng Liu, JoungBin Lee, Jiyoung Kim, Siyoon Jin, Yunsung Lee, Jaeyoon Jung, Suhwan Choi, Seungryong Kim, Yang Zhou Published: 2026-03-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.16871v1 Recent advances in video diffusion transformers have enabled interactive gaming world models that allow users to explore generated environments over extended horizons. However, existing approaches struggle with precise action control and long-horizon 3D consistency. Most prior works treat user actions as abstract conditioning signals, overlooking the fundamental geometric coupling between actions and the 3D world, whereby actions induce relative camera motions that accumulate into a global camera pose within a 3D world. In this paper, we establish camera pose as a unifying geometric representation to jointly ground immediate action control and long-term 3D consistency. First, we define a physics-based continuous action space and represent user inputs in the Lie algebra to derive precise 6-DoF camera poses, which are injected into the generative model via a camera embedder to ensure accurate action alignment. Second, we use global camera poses as spatial indices to retrieve relevant past observations, enabling geometrically consistent revisiting of locations during long-horizon navigation. To support this research, we introduce a large-scale dataset comprising 3,000 minutes of authentic human gameplay annotated with camera trajectories and textual descriptions. Extensive experiments show that our approach substantially outperforms state-of-the-art interactive gaming world models in action controllability, long-horizon visual quality, and 3D spatial consistency. --- ### Demystifying Video Reasoning Authors: Ruisi Wang, Zhongang Cai, Fanyi Pu, Junxiang Xu, Wanqi Yin, Maijunxian Wang, Ran Ji, Chenyang Gu, Bo Li, Ziqi Huang, Hokin Deng, Dahua Lin et al. Published: 2026-03-17 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.16870v3 Recent advances in video generation have revealed an unexpected phenomenon: diffusion-based video models exhibit non-trivial reasoning capabilities. Prior work attributes this to a Chain-of-Frames (CoF) mechanism, where reasoning is assumed to unfold sequentially across video frames. In this work, we challenge this assumption and uncover a fundamentally different mechanism. We show that reasoning in video models instead primarily emerges along the diffusion denoising steps. Through qualitative analysis and targeted probing experiments, we find that models explore multiple candidate solutions in early denoising steps and progressively converge to a final answer, a process we term Chain-of-Steps (CoS). Beyond this core mechanism, we identify several emergent reasoning behaviors critical to model performance: (1) working memory that supports tasks requiring consistent reference, such as object permanence; (2) self-correction and enhancement, allowing recovery from incorrect intermediate solutions; and (3) perception before action, where early steps establish semantic grounding and later steps perform structured manipulation. Moreover, analysis of Diffusion Transformer layers shows that middle layers conduct key reasoning procedures. Motivated by these insights, we present a simple Training-Free Ensemble (TFE) as a proof-of-concept, demonstrating how reasoning can be improved by ensembling latent trajectories from identical models with different random seeds. Overall, our work provides the first systematic dissection of the mechanisms underlying video reasoning, offering a foundation to guide future research in better exploiting the inherent reasoning dynamics of video models as a new substrate for intelligence. --- ### SegviGen: Repurposing 3D Generative Model for Part Segmentation Authors: Lin Li, Haoran Feng, Zehuan Huang, Haohua Chen, Wenbo Nie, Shaohua Hou, Keqing Fan, Pan Hu, Sheng Wang, Buyu Li, Lu Sheng Published: 2026-03-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.16869v3 We introduce SegviGen, a framework that repurposes native 3D generative models for 3D part segmentation. Existing pipelines either lift strong 2D priors into 3D via distillation or multi-view mask aggregation, often suffering from cross-view inconsistency and blurred boundaries, or explore native 3D discriminative segmentation, which typically requires large-scale annotated 3D data and substantial training resources. In contrast, SegviGen leverages the structured priors encoded in pretrained 3D generative model to induce segmentation through distinctive part colorization, establishing a novel and efficient framework for part segmentation. Specifically, SegviGen encodes a 3D asset and predicts part-indicative colors on active voxels of a geometry-aligned reconstruction. It supports interactive part segmentation, full segmentation, and full segmentation with 2D guidance in a unified framework. Extensive experiments show that SegviGen improves over the prior state of the art by 40% on interactive part segmentation and by 15% on full segmentation, while using only 0.32% of the labeled training data. It demonstrates that pretrained 3D generative priors transfer effectively to 3D part segmentation, enabling strong performance with limited supervision. See our project page at https://fenghora.github.io/SegviGen-Page/. --- ### MessyKitchens: Contact-rich object-level 3D scene reconstruction Authors: Junaid Ahmed Ansari, Ran Ding, Fabio Pizzati, Ivan Laptev Published: 2026-03-17 Categories: cs.CV, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2603.16868v2 Monocular 3D scene reconstruction has recently seen significant progress. Powered by the modern neural architectures and large-scale data, recent methods achieve high performance in depth estimation from a single image. Meanwhile, reconstructing and decomposing common scenes into individual 3D objects remains a hard challenge due to the large variety of objects, frequent occlusions and complex object relations. Notably, beyond shape and pose estimation of individual objects, applications in robotics and animation require physically-plausible scene reconstruction where objects obey physical principles of non-penetration and realistic contacts. In this work we advance object-level scene reconstruction along two directions. First, we introduceMessyKitchens, a new dataset with real-world scenes featuring cluttered environments and providing high-fidelity object-level ground truth in terms of 3D object shapes, poses and accurate object contacts. Second, we build on the recent SAM 3D approach for single-object reconstruction and extend it with Multi-Object Decoder (MOD) for joint object-level scene reconstruction. To validate our contributions, we demonstrate MessyKitchens to significantly improve previous datasets in registration accuracy and inter-object penetration. We also compare our multi-object reconstruction approach on three datasets and demonstrate consistent and significant improvements of MOD over the state of the art. Our new benchmark, code and pre-trained models will become publicly available on our project website: https://messykitchens.github.io/. --- ### MessyKitchens: Contact-rich object-level 3D scene reconstruction Authors: Junaid Ahmed Ansari, Ran Ding, Fabio Pizzati, Ivan Laptev Published: 2026-03-17 Categories: cs.CV, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2603.16868v1 Monocular 3D scene reconstruction has recently seen significant progress. Powered by the modern neural architectures and large-scale data, recent methods achieve high performance in depth estimation from a single image. Meanwhile, reconstructing and decomposing common scenes into individual 3D objects remains a hard challenge due to the large variety of objects, frequent occlusions and complex object relations. Notably, beyond shape and pose estimation of individual objects, applications in robotics and animation require physically-plausible scene reconstruction where objects obey physical principles of non-penetration and realistic contacts. In this work we advance object-level scene reconstruction along two directions. First, we introduceMessyKitchens, a new dataset with real-world scenes featuring cluttered environments and providing high-fidelity object-level ground truth in terms of 3D object shapes, poses and accurate object contacts. Second, we build on the recent SAM 3D approach for single-object reconstruction and extend it with Multi-Object Decoder (MOD) for joint object-level scene reconstruction. To validate our contributions, we demonstrate MessyKitchens to significantly improve previous datasets in registration accuracy and inter-object penetration. We also compare our multi-object reconstruction approach on three datasets and demonstrate consistent and significant improvements of MOD over the state of the art. Our new benchmark, code and pre-trained models will become publicly available on our project website: https://messykitchens.github.io/. --- ### Efficient Reasoning on the Edge Authors: Yelysei Bondarenko, Thomas Hehn, Rob Hesselink, Romain Lepert, Fabio Valerio Massoli, Evgeny Mironov, Leyla Mirvakhabova, Tribhuvanesh Orekondy, Spyridon Stasis, Andrey Kuzmin, Anna Kuzina, Markus Nagel et al. Published: 2026-03-17 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2603.16867v2 Large language models (LLMs) with chain-of-thought reasoning achieve state-of-the-art performance across complex problem-solving tasks, but their verbose reasoning traces and large context requirements make them impractical for edge deployment. These challenges include high token generation costs, large KV-cache footprints, and inefficiencies when distilling reasoning capabilities into smaller models for mobile devices. Existing approaches often rely on distilling reasoning traces from larger models into smaller models, which are verbose and stylistically redundant, undesirable for on-device inference. In this work, we propose a lightweight approach to enable reasoning in small LLMs using LoRA adapters combined with supervised fine-tuning. We further introduce budget forcing via reinforcement learning on these adapters, significantly reducing response length with minimal accuracy loss. To address memory-bound decoding, we exploit parallel test-time scaling, improving accuracy at minor latency increase. Finally, we present a dynamic adapter-switching mechanism that activates reasoning only when needed and a KV-cache sharing strategy during prompt encoding, reducing time-to-first-token for on-device inference. Experiments on Qwen2.5-7B demonstrate that our method achieves efficient, accurate reasoning under strict resource constraints, making LLM reasoning practical for mobile scenarios. Videos demonstrating our solution running on mobile devices are available on our project page. --- ### ManiTwin: Scaling Data-Generation-Ready Digital Object Dataset to 100K Authors: Kaixuan Wang, Tianxing Chen, Jiawei Liu, Honghao Su, Shaolong Zhu, Minxuan Wang, Zixuan Li, Yue Chen, Huan-ang Gao, Yusen Qin, Jiawei Wang, Qixuan Zhang et al. Published: 2026-03-17 Categories: cs.RO, cs.AI, cs.GR, cs.LG, cs.SE arXiv: https://arxiv.org/abs/2603.16866v1 Learning in simulation provides a useful foundation for scaling robotic manipulation capabilities. However, this paradigm often suffers from a lack of data-generation-ready digital assets, in both scale and diversity. In this work, we present ManiTwin, an automated and efficient pipeline for generating data-generation-ready digital object twins. Our pipeline transforms a single image into simulation-ready and semantically annotated 3D asset, enabling large-scale robotic manipulation data generation. Using this pipeline, we construct ManiTwin-100K, a dataset containing 100K high-quality annotated 3D assets. Each asset is equipped with physical properties, language descriptions, functional annotations, and verified manipulation proposals. Experiments demonstrate that ManiTwin provides an efficient asset synthesis and annotation workflow, and that ManiTwin-100K offers high-quality and diverse assets for manipulation data generation, random scene synthesis, and VQA data generation, establishing a strong foundation for scalable simulation data synthesis and policy learning. Our webpage is available at https://manitwin.github.io/. --- ### SparkVSR: Interactive Video Super-Resolution via Sparse Keyframe Propagation Authors: Jiongze Yu, Xiangbo Gao, Pooja Verlani, Akshay Gadde, Yilin Wang, Balu Adsumilli, Zhengzhong Tu Published: 2026-03-17 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.16864v1 Video Super-Resolution (VSR) aims to restore high-quality video frames from low-resolution (LR) estimates, yet most existing VSR approaches behave like black boxes at inference time: users cannot reliably correct unexpected artifacts, but instead can only accept whatever the model produces. In this paper, we propose a novel interactive VSR framework dubbed SparkVSR that makes sparse keyframes a simple and expressive control signal. Specifically, users can first super-resolve or optionally a small set of keyframes using any off-the-shelf image super-resolution (ISR) model, then SparkVSR propagates the keyframe priors to the entire video sequence while remaining grounded by the original LR video motion. Concretely, we introduce a keyframe-conditioned latent-pixel two-stage training pipeline that fuses LR video latents with sparsely encoded HR keyframe latents to learn robust cross-space propagation and refine perceptual details. At inference time, SparkVSR supports flexible keyframe selection (manual specification, codec I-frame extraction, or random sampling) and a reference-free guidance mechanism that continuously balances keyframe adherence and blind restoration, ensuring robust performance even when reference keyframes are absent or imperfect. Experiments on multiple VSR benchmarks demonstrate improved temporal consistency and strong restoration quality, surpassing baselines by up to 24.6%, 21.8%, and 5.6% on CLIP-IQA, DOVER, and MUSIQ, respectively, enabling controllable, keyframe-driven video super-resolution. Moreover, we demonstrate that SparkVSR is a generic interactive, keyframe-conditioned video processing framework as it can be applied out of the box to unseen tasks such as old-film restoration and video style transfer. Our project page is available at: https://sparkvsr.github.io/ --- ### Chronos: Temporal-Aware Conversational Agents with Structured Event Retrieval for Long-Term Memory Authors: Sahil Sen, Elias Lumer, Anmol Gulati, Vamse Kumar Subbiah Published: 2026-03-17 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.16862v1 Recent advances in Large Language Models (LLMs) have enabled conversational AI agents to engage in extended multi-turn interactions spanning weeks or months. However, existing memory systems struggle to reason over temporally grounded facts and preferences that evolve across months of interaction and lack effective retrieval strategies for multi-hop, time-sensitive queries over long dialogue histories. We introduce Chronos, a novel temporal-aware memory framework that decomposes raw dialogue into subject-verb-object event tuples with resolved datetime ranges and entity aliases, indexing them in a structured event calendar alongside a turn calendar that preserves full conversational context. At query time, Chronos applies dynamic prompting to generate tailored retrieval guidance for each question, directing the agent on what to retrieve, how to filter across time ranges, and how to approach multi-hop reasoning through an iterative tool-calling loop over both calendars. We evaluate Chronos with 8 LLMs, both open-source and closed-source, on the LongMemEvalS benchmark comprising 500 questions spanning six categories of dialogue history tasks. Chronos Low achieves 92.60% and Chronos High scores 95.60% accuracy, setting a new state of the art with an improvement of 7.67% over the best prior system. Ablation results reveal the events calendar accounts for a 58.9% gain on the baseline while all other components yield improvements between 15.5% and 22.3%. Notably, Chronos Low alone surpasses prior approaches evaluated under their strongest model configurations. --- ### SocialOmni: Benchmarking Audio-Visual Social Interactivity in Omni Models Authors: Tianyu Xie, Jinfa Huang, Yuexiao Ma, Rongfang Luo, Yan Yang, Qingchuan Ma, Wang Chen, Yuhui Zeng, Yixuan Zou, Zhiqiang Lu, Ruize Fang, Jiebo Luo et al. Published: 2026-03-17 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.16859v3 Evaluating omni-modal large language models (OLMs) in multi-party dialogue requires more than answer correctness on pre-segmented inputs. We introduce SocialOmni, an offline diagnostic benchmark that separates three turn-level decisions: identifying who is speaking, deciding when a designated participant should enter at an annotated query time, and determining how that participant should continue the dialogue. SocialOmni contains 2,000 perception items and a quality-controlled core split of 200 interaction-generation items, including naturally occurring speaker-visibility mismatches. Each item is independently checked by three human annotators. Evaluated systems receive only query-time-bounded multimodal evidence, while manually verified reference continuations are reserved for response judging. A complete three-judge ensemble scores every eligible response, with leave-one-judge-out and family-sensitivity audits. Across 11 OLMs, rankings vary substantially by axis, and coverage-adjusted scores reveal when high conditional response quality depends on selective turn entry. The protocol does not measure persistent streaming state or wall-clock latency. --- ### SocialOmni: Benchmarking Audio-Visual Social Interactivity in Omni Models Authors: Tianyu Xie, Jinfa Huang, Yuexiao Ma, Rongfang Luo, Yan Yang, Wang Chen, Yuhui Zeng, Yixuan Zou, Qingchuan Ma, Zhiqiang Lu, Ruize Fang, Xiawu Zheng et al. Published: 2026-03-17 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.16859v2 Omni-modal large language models (OLMs) redefine human-machine interaction by natively integrating audio, vision, and text. However, existing OLM benchmarks remain anchored to static, accuracy-centric tasks, leaving a critical gap in assessing social interactivity, the fundamental capacity to navigate dynamic cues in natural dialogues. To this end, we propose SocialOmni, a comprehensive benchmark that operationalizes the evaluation of this conversational interactivity across three core dimensions: (i) speaker separation and identification (who is speaking), (ii) interruption timing control (when to interject), and (iii) natural interruption generation (how to phrase the interruption). SocialOmni features 2,000 perception samples and a quality-controlled diagnostic set of 209 interaction-generation instances with strict temporal and contextual constraints, complemented by controlled audio-visual inconsistency scenarios to test model robustness. We benchmarked 12 leading OLMs, which uncovers significant variance in their social-interaction capabilities across models. Furthermore, our analysis reveals a pronounced decoupling between a model's perceptual accuracy and its ability to generate contextually appropriate interruptions, indicating that understanding-centric metrics alone are insufficient to characterize conversational social competence. More encouragingly, these diagnostics from SocialOmni yield actionable signals for bridging the perception-interaction divide in future OLMs. --- ### SOMA: Unifying Parametric Human Body Models Authors: Jun Saito, Jiefeng Li, Michael de Ruyter, Miguel Guerrero, Edy Lim, Ehsan Hassani, Roger Blanco Ribera, Hyejin Moon, Magdalena Dadela, Marco Di Lucca, Qiao Wang, Xueting Li et al. Published: 2026-03-17 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.16858v1 Parametric human body models are foundational to human reconstruction, animation, and simulation, yet they remain mutually incompatible: SMPL, SMPL-X, MHR, Anny, and related models each diverge in mesh topology, skeletal structure, shape parameterization, and unit convention, making it impractical to exploit their complementary strengths within a single pipeline. We present SOMA, a unified body layer that bridges these heterogeneous representations through three abstraction layers. Mesh topology abstraction maps any source model's identity to a shared canonical mesh in constant time per vertex. Skeletal abstraction recovers a full set of identity-adapted joint transforms from any body shape, whether in rest pose or an arbitrary posed configuration, in a single closed-form pass, with no iterative optimization or per-model training. Pose abstraction inverts the skinning pipeline to recover unified skeleton rotations directly from posed vertices of any supported model, enabling heterogeneous motion datasets to be consumed without custom retargeting. Together, these layers reduce the $O(M^2)$ per-pair adapter problem to $O(M)$ single-backend connectors, letting practitioners freely mix identity sources and pose data at inference time. The entire pipeline is fully differentiable end-to-end and GPU-accelerated via NVIDIA-Warp. --- ### Long-Horizon Traffic Forecasting via Incident-Aware Conformal Spatio-Temporal Transformers Authors: Mayur Patil, Qadeer Ahmed, Shawn Midlam-Mohler, Stephanie Marik, Allen Sheldon, Rajeev Chhajer, Nithin Santhanam Published: 2026-03-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.16857v1 Reliable multi-horizon traffic forecasting is challenging because network conditions are stochastic, incident disruptions are intermittent, and effective spatial dependencies vary across time-of-day patterns. This study is conducted on the Ohio Department of Transportation (ODOT) traffic count data and corresponding ODOT crash records. This work utilizes a Spatio-Temporal Transformer (STT) model with Adaptive Conformal Prediction (ACP) to produce multi-horizon forecasts with calibrated uncertainty. We propose a piecewise Coefficient of Variation (CV) strategy that models hour-to-hour traveltime variability using a log-normal distribution, enabling the construction of a per-hour dynamic adjacency matrix. We further perturb edge weights using incident-related severity signals derived from the ODOT crash dataset that comprises incident clearance time, weather conditions, speed violations, work zones, and roadway functional class, to capture localized disruptions and peak/off-peak transitions. This dynamic graph construction replaces a fixed-CV assumption and better represents changing traffic conditions within the forecast window. For validation, we generate extended trips via multi-hour loop runs on the Columbus, Ohio, network in SUMO simulations and apply a Monte Carlo simulation to obtain travel-time distributions for a Vehicle Under Test (VUT). Experiments demonstrate improved long-horizon accuracy and well-calibrated prediction intervals compared to other baseline methods. --- ### Online Experiential Learning for Language Models Authors: Tianzhu Ye, Li Dong, Qingxiu Dong, Xun Wu, Shaohan Huang, Furu Wei Published: 2026-03-17 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.16856v2 The prevailing paradigm for improving large language models relies on offline training with human annotations or simulated environments, leaving the rich experience accumulated during real-world deployment entirely unexploited. We propose Online Experiential Learning (OEL), a framework that enables language models to continuously improve from their own deployment experience. OEL operates in two stages: first, transferable experiential knowledge is extracted and accumulated from interaction trajectories collected on the user side; second, this knowledge is consolidated into model parameters via on-policy context distillation, requiring no access to the user-side environment. The two stages are iterated to form an online learning loop, where the improved model collects higher-quality trajectories that yield richer experiential knowledge for subsequent rounds. We evaluate OEL on text-based game environments across multiple model scales and both thinking and non-thinking variants. OEL achieves consistent improvements over successive iterations, enhancing both task accuracy and token efficiency while preserving out-of-distribution performance. Our analysis further shows that extracted experiential knowledge is significantly more effective than raw trajectories, and that on-policy consistency between the knowledge source and the policy model is critical for effective learning. --- ### Unifying Optimization and Dynamics to Parallelize Sequential Computation: A Guide to Parallel Newton Methods for Breaking Sequential Bottlenecks Authors: Xavier Gonzalez Published: 2026-03-17 Categories: math.NA, cs.AI, cs.DC, math.DS, math.OC arXiv: https://arxiv.org/abs/2603.16850v1 Massively parallel hardware (GPUs) and long sequence data have made parallel algorithms essential for machine learning at scale. Yet dynamical systems, like recurrent neural networks and Markov chain Monte Carlo, were thought to suffer from sequential bottlenecks. Recent work showed that dynamical systems can in fact be parallelized across the sequence length by reframing their evaluation as a system of nonlinear equations, which can be solved with Newton's method using a parallel associative scan. However, these parallel Newton methods struggled with limitations, primarily inefficiency, instability, and lack of convergence guarantees. This thesis addresses these limitations with methodological and theoretical contributions, drawing particularly from optimization. Methodologically, we develop scalable and stable parallel Newton methods, based on quasi-Newton and trust-region approaches. The quasi-Newton methods are faster and more memory efficient, while the trust-region approaches are significantly more stable. Theoretically, we unify many fixed-point methods into our parallel Newton framework, including Picard and Jacobi iterations. We establish a linear convergence rate for these techniques that depends on the method's approximation accuracy and stability. Moreover, we give a precise condition, rooted in dynamical stability, that characterizes when parallelization provably accelerates a dynamical system and when it cannot. Specifically, the sign of the Largest Lyapunov Exponent of a dynamical system determines whether or not parallel Newton methods converge quickly. In sum, this thesis unlocks scalable and stable methods for parallelizing sequential computation, and provides a firm theoretical basis for when such techniques will and will not work. This thesis also serves as a guide to parallel Newton methods for researchers who want to write the next chapter in this ongoing story. --- ### GIST: Gauge-Invariant Spectral Transformers for Scalable Graph Neural Operators Authors: Mattia Rigotti, Nicholas Thumiger, Thomas Frick Published: 2026-03-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.16849v3 Neural operators on irregular meshes face a fundamental tension. Spectral positional encodings, the natural choice for capturing geometry, require cubic-complexity eigendecomposition and inadvertently break gauge invariance through numerical solver artifacts; existing efficient approximations sacrifice gauge symmetry by design. Both failure modes break discretization invariance: models fail to transfer across mesh resolutions of the same domain, and similarly across different graphs of related structure in inductive settings. We propose GIST (Gauge-Invariant Spectral Transformer), a scalable neural operator that resolves this tension by restricting attention to pairwise inner products of efficient approximate spectral embeddings. We prove these inner products estimate an exactly gauge-invariant graph kernel at end-to-end $\mathcal{O}(N)$ complexity, and establish a formal connection between gauge invariance and discretization-invariant learning with bounded mismatch error. To our knowledge, GIST is the first scalable graph neural operator with a provable discretization-mismatch bound. Empirically, GIST sets state-of-the-art on the AirfRANS, ShapeNet-Car, DrivAerNet, and DrivAerNet++ mesh benchmarks (up to 750K nodes), and additionally matches strong baselines on standard graph benchmarks (e.g., 99.50% micro-F1 on PPI). --- ### Mediocrity is the key for LLM as a Judge Anchor Selection Authors: Shachar Don-Yehiya, Asaf Yehudai, Leshem Choshen, Omri Abend Published: 2026-03-17 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.16848v2 The ``LLM-as-a-judge'' paradigm has become a standard method for evaluating open-ended generation. To address the quadratic scalability costs of pairwise comparisons, popular benchmarks like Arena-Hard and AlpacaEval compare all models against a single anchor. However, despite its widespread use, the impact of anchor selection on the reliability of the results remains largely unexplored. In this work, we systematically investigate the effect of anchor selection by evaluating 22 different anchors on the Arena-Hard-v2.0 dataset. We find that the choice of anchor is critical: a poor anchor can dramatically reduce correlation with human rankings. We identify that common anchor choices (best-performing and worst-performing models) make poor anchors. Because these extreme anchors are consistently better or worse than all other models, they are seldom indicative of the relative ranking of the models. We further quantify the effect size of anchor selection, showing it is comparable to the selection of a judge model. We conclude with actionable recommendations. First, we conduct a power analysis, and compute sufficient benchmark sizes for anchor-based evaluation, finding that standard benchmark sizes are insufficient for pairwise evaluation and fail to distinguish between competitive models reliably. Second, we provide guidelines for selecting informative anchors to ensure reliable and efficient evaluation practices. --- ### Mediocrity is the key for LLM as a Judge Anchor Selection Authors: Shachar Don-Yehiya, Asaf Yehudai, Leshem Choshen, Omri Abend Published: 2026-03-17 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.16848v1 The ``LLM-as-a-judge'' paradigm has become a standard method for evaluating open-ended generation. To address the quadratic scalability costs of pairwise comparisons, popular benchmarks like Arena-Hard and AlpacaEval compare all models against a single anchor. However, despite its widespread use, the impact of anchor selection on the reliability of the results remains largely unexplored. In this work, we systematically investigate the effect of anchor selection by evaluating 22 different anchors on the Arena-Hard-v2.0 dataset. We find that the choice of anchor is critical: a poor anchor can dramatically reduce correlation with human rankings. We identify that common anchor choices (best-performing and worst-performing models) make poor anchors. Because these extreme anchors are consistently better or worse than all other models, they are seldom indicative of the relative ranking of the models. We further quantify the effect size of anchor selection, showing it is comparable to the selection of a judge model. We conclude with actionable recommendations. First, we conduct a power analysis, and compute sufficient benchmark sizes for anchor-based evaluation, finding that standard benchmark sizes are insufficient for pairwise evaluation and fail to distinguish between competitive models reliably. Second, we provide guidelines for selecting informative anchors to ensure reliable and efficient evaluation practices. --- ### Dynamic Meta-Layer Aggregation for Byzantine-Robust Federated Learning Authors: Reek Das, Biplab Kanti Sen Published: 2026-03-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.16846v1 Federated Learning (FL) is increasingly applied in sectors like healthcare, finance, and IoT, enabling collaborative model training while safeguarding user privacy. However, FL systems are susceptible to Byzantine adversaries that inject malicious updates, which can severely compromise global model performance. Existing defenses tend to focus on specific attack types and fail against untargeted strategies, such as multi-label flipping or combinations of noise and backdoor patterns. To overcome these limitations, we propose FedAOT-a novel defense mechanism that counters multi-label flipping and untargeted poisoning attacks using a metalearning-inspired adaptive aggregation framework. FedAOT dynamically weights client updates based on their reliability, suppressing adversarial influence without relying on predefined thresholds or restrictive attack assumptions. Notably, FedAOT generalizes effectively across diverse datasets and a wide range of attack types, maintaining robust performance even in previously unseen scenarios. Experimental results demonstrate that FedAOT substantially improves model accuracy and resilience while maintaining computational efficiency, offering a scalable and practical solution for secure federated learning. --- ### M^3: Dense Matching Meets Multi-View Foundation Models for Monocular Gaussian Splatting SLAM Authors: Kerui Ren, Guanghao Li, Changjian Jiang, Yingxiang Xu, Tao Lu, Linning Xu, Junting Dong, Jiangmiao Pang, Mulin Yu, Bo Dai Published: 2026-03-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.16844v1 Streaming reconstruction from uncalibrated monocular video remains challenging, as it requires both high-precision pose estimation and computationally efficient online refinement in dynamic environments. While coupling 3D foundation models with SLAM frameworks is a promising paradigm, a critical bottleneck persists: most multi-view foundation models estimate poses in a feed-forward manner, yielding pixel-level correspondences that lack the requisite precision for rigorous geometric optimization. To address this, we present M^3, which augments the Multi-view foundation model with a dedicated Matching head to facilitate fine-grained dense correspondences and integrates it into a robust Monocular Gaussian Splatting SLAM. M^3 further enhances tracking stability by incorporating dynamic area suppression and cross-inference intrinsic alignment. Extensive experiments on diverse indoor and outdoor benchmarks demonstrate state-of-the-art accuracy in both pose estimation and scene reconstruction. Notably, M^3 reduces ATE RMSE by 64.3% compared to VGGT-SLAM 2.0 and outperforms ARTDECO by 2.11 dB in PSNR on the ScanNet++ dataset. --- ### Internalizing Agency from Reflective Experience Authors: Rui Ge, Yichao Fu, Yuyang Qian, Junda Su, Yiming Zhao, Peng Zhao, Hao Zhang Published: 2026-03-17 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.16843v1 Large language models are increasingly deployed as autonomous agents that must plan, act, and recover from mistakes through long-horizon interaction with environments that provide rich feedback. However, prevailing outcome-driven post-training methods (e.g., RL with verifiable rewards) primarily optimize final success signals, leaving rich environment feedback underutilized. Consequently, they often lead to distribution sharpening: the policy becomes better at reproducing a narrow set of already-successful behaviors, while failing to improve the feedback-grounded agency needed to expand problem-solving capacity (e.g., Pass@k) in long-horizon settings. To address this, we propose LEAFE (Learning Feedback-Grounded Agency from Reflective Experience), a framework that internalizes recovery agency from reflective experience. Specifically, during exploration, the agent summarizes environment feedback into actionable experience, backtracks to earlier decision points, and explores alternative branches with revised actions. We then distill these experience-guided corrections into the model through supervised fine-tuning, enabling the policy to recover more effectively in future interactions. Across a diverse set of interactive coding and agentic tasks under fixed interaction budgets, LEAFE consistently improves Pass@1 over the base model and achieves higher Pass@k than outcome-driven baselines (GRPO) and experience-based methods such as Early Experience, with gains of up to 14% on Pass@128. --- ### Stochastic Resetting Accelerates Reinforcement Learning Beyond Random Search Authors: Jello Zhou, David J. Schwab, Vudtiwat Ngampruetikorn Published: 2026-03-17 Categories: cs.LG, cond-mat.dis-nn, cond-mat.stat-mech, eess.SY, physics.bio-ph arXiv: https://arxiv.org/abs/2603.16842v2 Stochastic resetting -- intermittently returning a process to a fixed reference state -- has emerged as an effective mechanism for optimizing first-passage properties. Existing theory largely treats processes that search but do not learn: the searcher follows fixed dynamics, accumulating no knowledge between resets. Here we ask how stochastic resetting interacts with reinforcement learning, where the underlying dynamics adapt through experience. In tabular grid environments, we find that resetting can accelerate learning even when it does not reduce the search time of a diffusive agent. Our results reveal a distinct additional mechanism through which resetting speeds the propagation of reward information. We show that deterministic, sharp resetting accelerates learning more than the stochastic protocol but over a narrower range of reset rates. In a continuous-state task with neural-network-based value approximation, we demonstrate that resetting speeds up learning when exploration is hard and rewards are sparse. We argue further that, in the tabular tasks, resetting accelerates learning without altering the solution the agent ultimately reaches, unlike other techniques such as temporal discounting, which biases the optimal behavior. Our results establish stochastic resetting as a simple, tunable mechanism for accelerating learning by shaping how experience accumulates, extending a canonical phenomenon of statistical mechanics to adaptive systems. --- ### What DINO saw: ALiBi positional encoding reduces positional bias in Vision Transformers Authors: Moritz Pawlowsky, Antonis Vamvakeros, Alexander Weiss, Anja Bielefeld, Samuel J. Cooper, Ronan Docherty Published: 2026-03-17 Categories: cs.CV, cond-mat.mtrl-sci arXiv: https://arxiv.org/abs/2603.16840v2 Vision transformers (ViTs) - especially feature foundation models like DINOv2 - learn rich representations useful for many downstream tasks. However, architectural choices (such as positional encoding) can lead to these models displaying positional biases and artefacts independent of semantic content. This makes zero-shot adaption difficult in fields like material science, where images are often cross-sections of homogeneous microstructure (i.e. having no preferred direction). In this work, we investigate the positional bias in ViTs via linear probing, finding it present across a range of objectives and positional encodings, and subsequently reduce it by finetuning models to use ALiBi relative positional encoding. We demonstrate that these models retain desirable general semantics and their unbiased features can be used successfully in trainable segmentation of complex microscopy images. --- ### What DINO saw: ALiBi positional encoding reduces positional bias in Vision Transformers Authors: Moritz Pawlowsky, Antonis Vamvakeros, Alexander Weiss, Anja Bielefeld, Samuel J. Cooper, Ronan Docherty Published: 2026-03-17 Categories: cs.CV, cond-mat.mtrl-sci arXiv: https://arxiv.org/abs/2603.16840v1 Vision transformers (ViTs) - especially feature foundation models like DINOv2 - learn rich representations useful for many downstream tasks. However, architectural choices (such as positional encoding) can lead to these models displaying positional biases and artefacts independent of semantic content. This makes zero-shot adaption difficult in fields like material science, where images are often cross-sections of homogeneous microstructure (i.e. having no preferred direction). In this work, we investigate the positional bias in ViTs via linear probing, finding it present across a range of objectives and positional encodings, and subsequently reduce it by finetuning models to use ALiBi relative positional encoding. We demonstrate that these models retain desirable general semantics and their unbiased features can be used successfully in trainable segmentation of complex microscopy images. --- ### Learning to Present: Inverse Specification Rewards for Agentic Slide Generation Authors: Karthik Ragunath Ananda Kumar, Subrahmanyam Arunachalam Published: 2026-03-17 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.16839v1 Automated presentation generation remains a challenging task requiring coherent content creation, visual design, and audience-aware communication. This work proposes an OpenEnv-compatible reinforcement learning environment where LLM agents learn to research topics, plan content, and generate professional HTML slide presentations through tool use. We introduce a multi-component reward system combining structural validation, render quality assessment, LLM-based aesthetic scoring, content quality metrics, and an inverse specification reward that measures how faithfully generated slides convey their intended purpose. The inverse specification reward, an "inverse task" where an LLM attempts to recover the original specification from generated slides, provides a holistic quality signal. Our approach fine-tunes Qwen2.5-Coder-7B via GRPO, training only 0.5% of parameters on prompts derived from expert demonstrations collected using Claude Opus 4.6. Experiments on 48 diverse business briefs across six models demonstrate that our fine-tuned 7B model achieves 91.2% of Claude Opus 4.6's quality while improving 33.1% over the base model. The six-model comparison reveals that instruction adherence and tool-use compliance, rather than raw parameter count, determine agentic task performance. We contribute SlideRL, an open-source dataset of 288 multi-turn rollout trajectories across all six models: https://huggingface.co/datasets/KarthikRagunathAnandaKumar/sliderl-multi-turn-rollouts Code: https://github.com/pushing-the-frontier/slide-forge-llm --- ### An assessment of data-centric methods for label noise identification in remote sensing data sets Authors: Felix Kröber, Genc Hoxha, Ribana Roscher Published: 2026-03-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.16835v1 Label noise in the sense of incorrect labels is present in many real-world data sets and is known to severely limit the generalizability of deep learning models. In the field of remote sensing, however, automated treatment of label noise in data sets has received little attention to date. In particular, there is a lack of systematic analysis of the performance of data-centric methods that not only cope with label noise but also explicitly identify and isolate noisy labels. In this paper, we examine three such methods and evaluate their behavior under different label noise assumptions. To do this, we inject different types of label noise with noise levels ranging from 10 to 70% into two benchmark data sets, followed by an analysis of how well the selected methods filter the label noise and how this affects task performances. With our analyses, we clearly prove the value of data-centric methods for both parts - label noise identification and task performance improvements. Our analyses provide insights into which method is the best choice depending on the setting and objective. Finally, we show in which areas there is still a need for research in the transfer of data-centric label noise methods to remote sensing data. As such, our work is a step forward in bridging the methodological establishment of data-centric label noise methods and their usage in practical settings in the remote sensing domain. --- ### Conditional Distributional Treatment Effects: Doubly Robust Estimation and Testing Authors: Saksham Jain, Alex Luedtke Published: 2026-03-17 Categories: stat.ML, cs.LG, math.ST, stat.ME arXiv: https://arxiv.org/abs/2603.16829v2 Beyond conditional average treatment effects, treatments may impact the entire outcome distribution in covariate-dependent ways, for example, by altering the variance or tail risks for specific subpopulations. We propose a novel estimand to capture such conditional distributional treatment effects, and develop a doubly robust estimator that is minimax optimal in the local asymptotic sense. Using this, we develop a test for the global homogeneity of conditional potential outcome distributions that accommodates discrepancies beyond the maximum mean discrepancy (MMD), has provably valid type 1 error, and is consistent against fixed alternatives---the first test, to our knowledge, with such guarantees in this setting. We then provide a test that aggregates evidence across a grid of kernel-bandwidth choices. Furthermore, we derive exact closed-form expressions for two natural discrepancies (including the MMD), and provide a computationally efficient, permutation-free algorithm for our test. --- ### Conditional Distributional Treatment Effects: Doubly Robust Estimation and Testing Authors: Saksham Jain, Alex Luedtke Published: 2026-03-17 Categories: stat.ML, cs.LG, math.ST, stat.ME arXiv: https://arxiv.org/abs/2603.16829v1 Beyond conditional average treatment effects, treatments may impact the entire outcome distribution in covariate-dependent ways, for example, by altering the variance or tail risks for specific subpopulations. We propose a novel estimand to capture such conditional distributional treatment effects, and develop a doubly robust estimator that is minimax optimal in the local asymptotic sense. Using this, we develop a test for the global homogeneity of conditional potential outcome distributions that accommodates discrepancies beyond the maximum mean discrepancy (MMD), has provably valid type 1 error, and is consistent against fixed alternatives -- the first test, to our knowledge, with such guarantees in this setting. Furthermore, we derive exact closed-form expressions for two natural discrepancies (including the MMD), and provide a computationally efficient, permutation-free algorithm for our test. ---