# Research Papers — 2026-03 · bundle page 205 of 243

> Full-text markdown of papers #10201–10250 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/205
[← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/204.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-03/page/206.md)

### Latent Wasserstein Adversarial Imitation Learning

Authors: Siqi Yang, Kai Yan, Alexander G. Schwing, Yu-Xiong Wang
Published: 2026-03-05
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.05440v1

Imitation Learning (IL) enables agents to mimic expert behavior by learning from demonstrations. However, traditional IL methods require large amounts of medium-to-high-quality demonstrations as well as actions of expert demonstrations, both of which are often unavailable. To reduce this need, we propose Latent Wasserstein Adversarial Imitation Learning (LWAIL), a novel adversarial imitation learning framework that focuses on state-only distribution matching. It benefits from the Wasserstein distance computed in a dynamics-aware latent space. This dynamics-aware latent space differs from prior work and is obtained via a pre-training stage, where we train the Intention Conditioned Value Function (ICVF) to capture a dynamics-aware structure of the state space using a small set of randomly generated state-only data. We show that this enhances the policy's understanding of state transitions, enabling the learning process to use only one or a few state-only expert episodes to achieve expert-level performance. Through experiments on multiple MuJoCo environments, we demonstrate that our method outperforms prior Wasserstein-based IL methods and prior adversarial IL methods, achieving better results across various tasks.

---

### Planning in 8 Tokens: A Compact Discrete Tokenizer for Latent World Model

Authors: Dongwon Kim, Gawon Seo, Jinsung Lee, Minsu Cho, Suha Kwak
Published: 2026-03-05
Categories: cs.CV, cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2603.05438v1

World models provide a powerful framework for simulating environment dynamics conditioned on actions or instructions, enabling downstream tasks such as action planning or policy learning. Recent approaches leverage world models as learned simulators, but its application to decision-time planning remains computationally prohibitive for real-time control. A key bottleneck lies in latent representations: conventional tokenizers encode each observation into hundreds of tokens, making planning both slow and resource-intensive. To address this, we propose CompACT, a discrete tokenizer that compresses each observation into as few as 8 tokens, drastically reducing computational cost while preserving essential information for planning. An action-conditioned world model that occupies CompACT tokenizer achieves competitive planning performance with orders-of-magnitude faster planning, offering a practical step toward real-world deployment of world models.

---

### SAIL: Similarity-Aware Guidance and Inter-Caption Augmentation-based Learning for Weakly-Supervised Dense Video Captioning

Authors: Ye-Chan Kim, SeungJu Cha, Si-Woo Kim, Minju Jeon, Hyungee Kim, Dong-Jin Kim
Published: 2026-03-05
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.05437v2

Weakly-Supervised Dense Video Captioning aims to localize and describe events in videos trained only on caption annotations, without temporal boundaries. Prior work introduced an implicit supervision paradigm based on Gaussian masking and complementary captioning. However, existing method focuses merely on generating non-overlapping masks without considering their semantic relationship to corresponding events, resulting in simplistic, uniformly distributed masks that fail to capture semantically meaningful regions. Moreover, relying solely on ground-truth captions leads to sub-optimal performance due to the inherent sparsity of existing datasets. In this work, we propose SAIL, which constructs semantically-aware masks through cross-modal alignment. Our similarity aware training objective guides masks to emphasize video regions with high similarity to their corresponding event captions. Furthermore, to guide more accurate mask generation under sparse annotation settings, we introduce an LLM-based augmentation strategy that generates synthetic captions to provide additional alignment signals. These synthetic captions are incorporated through an inter-mask mechanism, providing auxiliary guidance for precise temporal localization without degrading the main objective. Experiments on ActivityNet Captions and YouCook2 demonstrate state-of-the-art performance on both captioning and localization metrics.

---

### CRISP: Compressed Reasoning via Iterative Self-Policy Distillation

Authors: Hejian Sang, Yuanda Xu, Zhengze Zhou, Ran He, Zhipeng Wang, Jiachen Sun
Published: 2026-03-05
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.05433v7

Reasoning models often generate far more tokens than a task requires, which raises inference cost and can compound errors. We introduce CRISP (Compressed Reasoning via Iterative Self-Policy Distillation), an on-policy self-distillation method that teaches a model to reason more concisely by distilling its own concise behavior back into itself. The method uses a single idea: condition the same model on a "be concise" instruction to obtain teacher logits, then minimize the per-token reverse KL divergence between the student and this teacher on the student's own rollouts. It requires no ground-truth answers, no token budgets, and no difficulty estimators. The reverse-KL objective is naturally difficulty-adaptive: it compresses easy problems aggressively while preserving the reasoning steps that hard problems require. On Qwen3-14B, CRISP cuts reasoning length by up to 56% on MATH-500 and 38% on the harder AIME 2024, while improving MATH-500 accuracy by up to 3.3 points over the base model and holding AIME 2024 accuracy within about one point. This behavior generalizes across model sizes and families: Qwen3-8B shows the same compression with accuracy preserved, and DeepSeek-R1-Distill-Llama-8B improves accuracy on all five benchmarks while shortening its responses. General capabilities are preserved across all three models. Code is available at https://github.com/HJSang/OPSD_Reasoning_Compression.

---

### Ensembling Language Models with Sequential Monte Carlo

Authors: Robin Shing Moon Chan, Tianyu Liu, Samuel Kiegeland, Clemente Pasti, Jacob Hoover Vigly, Timothy J. O'Donnell, Ryan Cotterell, Tim Vieira
Published: 2026-03-05
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2603.05432v1

Practitioners have access to an abundance of language models and prompting strategies for solving many language modeling tasks; yet prior work shows that modeling performance is highly sensitive to both choices. Classical machine learning ensembling techniques offer a principled approach: aggregate predictions from multiple sources to achieve better performance than any single one. However, applying ensembling to language models during decoding is challenging: naively aggregating next-token probabilities yields samples from a locally normalized, biased approximation of the generally intractable ensemble distribution over strings. In this work, we introduce a unified framework for composing $K$ language models into $f$-ensemble distributions for a wide range of functions $f\colon\mathbb{R}_{\geq 0}^{K}\to\mathbb{R}_{\geq 0}$. To sample from these distributions, we propose a byte-level sequential Monte Carlo (SMC) algorithm that operates in a shared character space, enabling ensembles of models with mismatching vocabularies and consistent sampling in the limit. We evaluate a family of $f$-ensembles across prompt and model combinations for various structured text generation tasks, highlighting the benefits of alternative aggregation strategies over traditional probability averaging, and showing that better posterior approximations can yield better ensemble performance.

---

### RelaxFlow: Text-Driven Amodal 3D Generation

Authors: Jiayin Zhu, Guoji Fu, Xiaolu Liu, Qiyuan He, Yicong Li, Angela Yao
Published: 2026-03-05
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.05425v2

Image-to-3D generation faces inherent semantic ambiguity under occlusion, where partial observation alone is often insufficient to determine object category. In this work, we formalize text-driven amodal 3D generation, where text prompts steer the completion of unseen regions while strictly preserving input observation. Crucially, we identify that these objectives demand distinct control granularities: rigid control for the observation versus relaxed structural control for the prompt. To this end, we propose RelaxFlow, a training-free dual-branch framework that decouples control granularity via a Multi-Prior Consensus Module and a Relaxation Mechanism. Theoretically, we prove that our relaxation is equivalent to applying a low-pass filter on the generative vector field, which suppresses high-frequency instance details to isolate geometric structure that accommodates the observation. To facilitate evaluation, we introduce two diagnostic benchmarks, ExtremeOcc-3D and AmbiSem-3D. Extensive experiments demonstrate that RelaxFlow successfully steers the generation of unseen regions to match the prompt intent without compromising visual fidelity.

---

### An interpretable prototype parts-based neural network for medical tabular data

Authors: Jacek Karolczak, Jerzy Stefanowski
Published: 2026-03-05
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.05423v1

The ability to interpret machine learning model decisions is critical in such domains as healthcare, where trust in model predictions is as important as their accuracy. Inspired by the development of prototype parts-based deep neural networks in computer vision, we propose a new model for tabular data, specifically tailored to medical records, that requires discretization of diagnostic result norms. Unlike the original vision models that rely on the spatial structure, our method employs trainable patching over features describing a patient, to learn meaningful prototypical parts from structured data. These parts are represented as binary or discretized feature subsets. This allows the model to express prototypes in human-readable terms, enabling alignment with clinical language and case-based reasoning. Our proposed neural network is inherently interpretable and offers interpretable concept-based predictions by comparing the patient's description to learned prototypes in the latent space of the network. In experiments, we demonstrate that the model achieves classification performance competitive to widely used baseline models on medical benchmark datasets, while also offering transparency, bridging the gap between predictive performance and interpretability in clinical decision support.

---

### DARK: Diagonal-Anchored Repulsive Knowledge Distillation for Vision-Language Models under Extreme Compression

Authors: Numan Saeed, Asif Hanif, Fadillah Adamsyah Maani, Hussain Alasmawi, Mohammad Yaqub
Published: 2026-03-05
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2603.05421v3

Compressing vision-language models for on-device deployment is increasingly important in clinical settings, but knowledge distillation (KD) degrades sharply when the teacher-student capacity gap spans an order of magnitude or more. We argue that, under such gaps, strict imitation of the teacher is a poor objective: much of the teacher's pairwise similarity structure reflects its own architectural biases rather than information a compact student can efficiently represent. We propose \textbf{Diagonal-Anchored Repulsive Knowledge Distillation (DARK)}, a contrastive KD framework that decomposes the distillation loss into a diagonal term (matched image-text pairs) and an off-diagonal term (non-target similarities). The diagonal term anchors matched-pair alignment throughout training; the off-diagonal term is annealed from positive to negative weighting, transitioning the student from imitating to \emph{repelling} the teacher's non-target similarity structure. We instantiate DARK by distilling FetalCLIP, a 427M-parameter fetal ultrasound vision-language model, into \textbf{MobileFetalCLIP}, a 75M-parameter student model with a $26\times$ smaller visual encoder, running in 1.6\,ms on an iPhone~16~Pro. The student matches or exceeds its teacher on three zero-shot benchmarks, including HC18 biometry validity (88.6\% vs.\ 83.5\%) and brain sub-plane F1 (0.784 vs.\ 0.702). Embedding-geometry and logit analyses show that DARK induces \emph{structured decorrelation}: the student preserves teacher-aligned per-image confidence while diverging from inherited inter-class confusion, suggesting that controlled repulsion can be more efficient than imitation under extreme compression.

---

### The Spatial and Temporal Resolution of Motor Intention in Multi-Target Prediction

Authors: Marie Dominique Schmidt, Ioannis Iossifidis
Published: 2026-03-05
Categories: q-bio.NC, cs.AI
arXiv: https://arxiv.org/abs/2603.05418v1

Reaching for grasping, and manipulating objects are essential motor functions in everyday life. Decoding human motor intentions is a central challenge for rehabilitation and assistive technologies. This study focuses on predicting intentions by inferring movement direction and target location from multichannel electromyography (EMG) signals, and investigating how spatially and temporally accurate such information can be detected relative to movement onset. We present a computational pipeline that combines data-driven temporal segmentation with classical and deep learning classifiers in order to analyse EMG data recorded during the planning, early execution, and target contact phases of a delayed reaching task. Early intention prediction enables devices to anticipate user actions, improving responsiveness and supporting active motor recovery in adaptive rehabilitation systems. Random Forest achieves $80\%$ accuracy and Convolutional Neural Network $75\%$ accuracy across $25$ spatial targets, each separated by $14^\circ$ azimuth/altitude. Furthermore, a systematic evaluation of EMG channels, feature sets, and temporal windows demonstrates that motor intention can be efficiently decoded even with drastically reduced data. This work sheds light on the temporal and spatial evolution of motor intention, paving the way for anticipatory control in adaptive rehabilitation systems and driving advancements in computational approaches to motor neuroscience.

---

### Emergent Introspection in AI is Content-Agnostic

Authors: Harvey Lederman, Kyle Mahowald
Published: 2026-03-05
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2603.05414v2

Introspection is a foundational cognitive ability, but its mechanism is not well understood. Recent work has shown that AI models can introspect. We study the mechanism of this introspection. We first extensively replicate Lindsey (2025)'s thought injection detection paradigm in large open-source models. We show that introspection in these models is content-agnostic: models can detect that an anomaly occurred even when they cannot reliably identify its content. The models confabulate injected concepts that are high-frequency and concrete (e.g., "apple"). They also require fewer tokens to detect an injection than to guess the correct concept (with wrong guesses coming earlier). We argue that a content-agnostic introspective mechanism is consistent with leading theories in philosophy and psychology.

---

### Video-based Locomotion Analysis for Fish Health Monitoring

Authors: Timon Palm, Clemens Seibold, Anna Hilsmann, Peter Eisert
Published: 2026-03-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.05407v1

Monitoring the health conditions of fish is essential, as it enables the early detection of disease, safeguards animal welfare, and contributes to sustainable aquaculture practices. Physiological and pathological conditions of cultivated fish can be inferred by analyzing locomotion activities. In this paper, we present a system that estimates the locomotion activities from videos using multi object tracking. The core of our approach is a YOLOv11 detector embedded in a tracking-by-detection framework. We investigate various configurations of the YOLOv11-architecture as well as extensions that incorporate multiple frames to improve detection accuracy. Our system is evaluated on a manually annotated dataset of Sulawesi ricefish recorded in a home-aquarium-like setup, demonstrating its ability to reliably measure swimming direction and speed for fish health monitoring. The dataset will be made publicly available upon publication.

---

### An Exploration-Analysis-Disambiguation Reasoning Framework for Word Sense Disambiguation with Low-Parameter LLMs

Authors: Deshan Sumanathilaka, Nicholas Micallef, Julian Hough
Published: 2026-03-05
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.05400v1

Word Sense Disambiguation (WSD) remains a key challenge in Natural Language Processing (NLP), especially when dealing with rare or domain-specific senses that are often misinterpreted. While modern high-parameter Large Language Models (LLMs) such as GPT-4-Turbo have shown state-of-the-art WSD performance, their computational and energy demands limit scalability. This study investigates whether low-parameter LLMs (<4B parameters) can achieve comparable results through fine-tuning strategies that emphasize reasoning-driven sense identification. Using the FEWS dataset augmented with semi-automated, rationale-rich annotations, we fine-tune eight small-scale open-source LLMs (e.g. Gemma and Qwen). Our results reveal that Chain-of-Thought (CoT)-based reasoning combined with neighbour-word analysis achieves performance comparable to GPT-4-Turbo in zero-shot settings. Importantly, Gemma-3-4B and Qwen-3-4B models consistently outperform all medium-parameter baselines and state-of-the-art models on FEWS, with robust generalization to unseen senses. Furthermore, evaluation on the unseen "Fool Me If You Can'' dataset confirms strong cross-domain adaptability without task-specific fine-tuning. This work demonstrates that with carefully crafted reasoning-centric fine-tuning, low-parameter LLMs can deliver accurate WSD while substantially reducing computational and energy demands.

---

### Judge Reliability Harness: Stress Testing the Reliability of LLM Judges

Authors: Sunishchal Dev, Andrew Sloan, Joshua Kavner, Nicholas Kong, Morgan Sandler
Published: 2026-03-05
Categories: cs.AI
arXiv: https://arxiv.org/abs/2603.05399v1

We present the Judge Reliability Harness, an open source library for constructing validation suites that test the reliability of LLM judges. As LLM based scoring is widely deployed in AI benchmarks, more tooling is needed to efficiently assess the reliability of these methods. Given a benchmark dataset and an LLM judge configuration, the harness generates reliability tests that evaluate both binary judgment accuracy and ordinal grading performance for free-response and agentic task formats. We evaluate four state-of-the-art judges across four benchmarks spanning safety, persuasion, misuse, and agentic behavior, and find meaningful variation in performance across models and perturbation types, highlighting opportunities to improve the robustness of LLM judges. No judge that we evaluated is uniformly reliable across benchmarks using our harness. For example, our preliminary experiments on judges revealed consistency issues as measured by accuracy in judging another LLM's ability to complete a task due to simple text formatting changes, paraphrasing, changes in verbosity, and flipping the ground truth label in LLM-produced responses. The code for this tool is available at: https://github.com/RANDCorporation/judge-reliability-harness

---

### Loop Closure via Maximal Cliques in 3D LiDAR-Based SLAM

Authors: Javier Laserna, Saurabh Gupta, Oscar Martinez Mozos, Cyrill Stachniss, Pablo San Segundo
Published: 2026-03-05
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2603.05397v1

Reliable loop closure detection remains a critical challenge in 3D LiDAR-based SLAM, especially under sensor noise, environmental ambiguity, and viewpoint variation conditions. RANSAC is often used in the context of loop closures for geometric model fitting in the presence of outliers. However, this approach may fail, leading to map inconsistency. We introduce a novel deterministic algorithm, CliReg, for loop closure validation that replaces RANSAC verification with a maximal clique search over a compatibility graph of feature correspondences. This formulation avoids random sampling and increases robustness in the presence of noise and outliers. We integrated our approach into a real- time pipeline employing binary 3D descriptors and a Hamming distance embedding binary search tree-based matching. We evaluated it on multiple real-world datasets featuring diverse LiDAR sensors. The results demonstrate that our proposed technique consistently achieves a lower pose error and more reliable loop closures than RANSAC, especially in sparse or ambiguous conditions. Additional experiments on 2D projection-based maps confirm its generality across spatial domains, making our approach a robust and efficient alternative for loop closure detection.

---

### Harnessing Synthetic Data from Generative AI for Statistical Inference

Authors: Ahmad Abdel-Azim, Ruoyu Wang, Xihong Lin
Published: 2026-03-05
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2603.05396v1

The emergence of generative AI models has dramatically expanded the availability and use of synthetic data across scientific, industrial, and policy domains. While these developments open new possibilities for data analysis, they also raise fundamental statistical questions about when synthetic data can be used in a valid, reliable, and principled manner. This paper reviews the current landscape of synthetic data generation and use from a statistical perspective, with the goal of clarifying the assumptions under which synthetic data can meaningfully support downstream discovery, inference, and prediction. We survey major classes of modern generative models, their intended use cases, and the benefits they offer, while also highlighting their limitations and characteristic failure modes. We additionally examine common pitfalls that arise when synthetic data are treated as surrogates for real observations, including biases from model misspecification, attenuated uncertainty, and difficulties in generalization. Building on these insights, we discuss emerging frameworks for the principled use of synthetic data. We conclude with practical recommendations, open problems, and cautions intended to guide both method developers and applied researchers.

---

### On the Necessity of Learnable Sheaf Laplacians

Authors: Ferran Hernandez Caralt, Mar Gonzàlez i Català, Adrián Bazaga, Pietro Liò
Published: 2026-03-05
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.05395v1

Sheaf Neural Networks (SNNs) were introduced as an extension of Graph Convolutional Networks to address oversmoothing on heterophilous graphs by attaching a sheaf to the input graph and replacing the adjacency-based operator with a sheaf Laplacian defined by (learnable) restriction maps. Prior work motivates this design through theoretical properties of sheaf diffusion and the kernel of the sheaf Laplacian, suggesting that suitable non-identity restriction maps can avoid representations converging to constants across connected components. Since oversmoothing can also be mitigated through residual connections and normalization, we revisit a trivial sheaf construction to ask whether the additional complexity of learning restriction maps is necessary. We introduce an Identity Sheaf Network baseline, where all restriction maps are fixed to the identity, and use it to ablate the empirical improvements reported by sheaf-learning architectures. Across five popular heterophilic benchmarks, the identity baseline achieves comparable performance to a range of SNN variants. Finally, we introduce the Rayleigh quotient as a normalized measure for comparing oversmoothing across models and show that, in trained networks, the behavior predicted by the diffusion-based analysis of SNNs is not reflected empirically. In particular, Identity Sheaf Networks do not appear to suffer more significant oversmoothing than their SNN counterparts.

---

### Legal interpretation and AI: from expert systems to argumentation and LLMs

Authors: Václav Janeček, Giovanni Sartor
Published: 2026-03-05
Categories: cs.AI
arXiv: https://arxiv.org/abs/2603.05392v1

AI and Law research has encountered legal interpretation in different ways, in the context of its evolving approaches and methodologies. Research on expert system has focused on legal knowledge engineering, with the goal of ensuring that human-generated interpretations can be precisely transferred into knowledge-bases, to be consistently applied. Research on argumentation has aimed at representing the structure of interpretive arguments, as well as their dialectical interactions, to assess of the acceptability of interpretive claims within argumentation frameworks. Research on machine learning has focused on the automated generation of interpretive suggestions and arguments, through general and specialised language models, now being increasingly deployed in legal practice.

---

### Fusion-CAM: Integrating Gradient and Region-Based Class Activation Maps for Robust Visual Explanations

Authors: Hajar Dekdegue, Moncef Garouani, Josiane Mothe, Jordan Bernigaud
Published: 2026-03-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.05386v1

Interpreting the decision-making process of deep convolutional neural networks remains a central challenge in achieving trustworthy and transparent artificial intelligence. Explainable AI (XAI) techniques, particularly Class Activation Map (CAM) methods, are widely adopted to visualize the input regions influencing model predictions. Gradient-based approaches (e.g. Grad-CAM) provide highly discriminative, fine-grained details by computing gradients of class activations but often yield noisy and incomplete maps that emphasize only the most salient regions rather than the complete objects. Region-based approaches (e.g. Score-CAM) aggregate information over larger areas, capturing broader object coverage at the cost of over-smoothing and reduced sensitivity to subtle features. We introduce Fusion-CAM, a novel framework that bridges this explanatory gap by unifying both paradigms through a dedicated fusion mechanism to produce robust and highly discriminative visual explanations. Our method first denoises gradient-based maps, yielding cleaner and more focused activations. It then combines the refined gradient map with region-based maps using contribution weights to enhance class coverage. Finally, we propose an adaptive similarity-based pixel-level fusion that evaluates the agreement between both paradigms and dynamically adjusts the fusion strength. This adaptive mechanism reinforces consistent activations while softly blending conflicting regions, resulting in richer, context-aware, and input-adaptive visual explanations. Extensive experiments on standard benchmarks show that Fusion-CAM consistently outperforms existing CAM variants in both qualitative visualization and quantitative evaluation, providing a robust and flexible tool for interpreting deep neural networks.

---

### ORMOT: A Dataset and Framework for Omnidirectional Referring Multi-Object Tracking

Authors: Zihan Zhou, Sijia Chen, Yanqiu Yu, En Yu, Wenbing Tao
Published: 2026-03-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.05384v2

Omnidirectional cameras provide 360° spatial coverage, making them increasingly valuable in applications such as autonomous driving and video surveillance. While Multi-Object Tracking (MOT) and its language-guided extension, Referring Multi-Object Tracking (RMOT), have achieved notable progress, existing methods rely on conventional cameras with limited fields of view, causing critical contextual cues to be lost when targets move outside the frame. This fundamentally limits the model's ability to interpret long-horizon language descriptions involving sequential actions, spatial relations, and group behaviors. In this work, we propose Omnidirectional Referring Multi-Object Tracking (ORMOT), a novel task extending RMOT to omnidirectional imagery, where 360° coverage ensures complete scene context for accurate language-guided tracking. To advance this task, we construct ORSet, a dataset comprising 27 omnidirectional scenes, 848 language descriptions, and 3,401 annotated objects. Furthermore, we propose ORTrack, an LVLM-driven framework that enables zero-shot language-guided detection and robust cross-frame association in complex 360° environments. Experiments on ORSet demonstrate that ORTrack achieves state-of-the-art performance, providing a strong baseline for future research. The dataset and code will be open-sourced at https://github.com/chen-si-jia/ORMOT.

---

### ORMOT: A Dataset and Framework for Omnidirectional Referring Multi-Object Tracking

Authors: Sijia Chen, Zihan Zhou, Yanqiu Yu, En Yu, Wenbing Tao
Published: 2026-03-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.05384v1

Multi-Object Tracking (MOT) is a fundamental task in computer vision, aiming to track targets across video frames. Existing MOT methods perform well in general visual scenes, but face significant challenges and limitations when extended to visual-language settings. To bridge this gap, the task of Referring Multi-Object Tracking (RMOT) has recently been proposed, which aims to track objects that correspond to language descriptions. However, current RMOT methods are primarily developed on datasets captured by conventional cameras, which suffer from limited field of view. This constraint often causes targets to move out of the frame, leading to fragmented tracking and loss of contextual information. In this work, we propose a novel task, called Omnidirectional Referring Multi-Object Tracking (ORMOT), which extends RMOT to omnidirectional imagery, aiming to overcome the field-of-view (FoV) limitation of conventional datasets and improve the model's ability to understand long-horizon language descriptions. To advance the ORMOT task, we construct ORSet, an Omnidirectional Referring Multi-Object Tracking dataset, which contains 27 diverse omnidirectional scenes, 848 language descriptions, and 3,401 annotated objects, providing rich visual, temporal, and language information. Furthermore, we propose ORTrack, a Large Vision-Language Model (LVLM)-driven framework tailored for Omnidirectional Referring Multi-Object Tracking. Extensive experiments on the ORSet dataset demonstrate the effectiveness of our ORTrack framework. The dataset and code will be open-sourced at https://github.com/chen-si-jia/ORMOT.

---

### OpenFrontier: General Navigation with Visual-Language Grounded Frontiers

Authors: Esteban Padilla-Cerdio, Boyang Sun, Marc Pollefeys, Hermann Blum
Published: 2026-03-05
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2603.05377v3

Open-world navigation requires robots to make decisions in complex everyday environments while adapting to flexible task requirements. Conventional navigation approaches often rely on dense 3D reconstruction and hand-crafted goal metrics, which limits their generalization across tasks and environments. Recent advances in vision-language navigation (VLN) and vision-language-action (VLA) models enable end-to-end policies conditioned on natural language, but typically require interactive training, large-scale data collection, or task-specific fine-tuning with a mobile agent. We formulate navigation as a sparse subgoal identification and reaching problem and observe that providing visual anchoring targets for high-level semantic priors enables highly efficient goal-conditioned navigation. Based on this insight, we select visual frontiers as semantic anchors and propose OpenFrontier, a navigation framework that requires no task-specific training or fine-tuning and seamlessly integrates diverse vision-language prior models. OpenFrontier enables efficient navigation with a lightweight system design, without dense 3D semantic mapping, task-specific policy training, or model fine-tuning. We evaluate OpenFrontier across multiple navigation benchmarks and demonstrate strong zero-shot performance, as well as effective real-world deployment on a mobile robot.

---

### Robust Node Affinities via Jaccard-Biased Random Walks and Rank Aggregation

Authors: Bastian Pfeifer, Michael G. Schimek
Published: 2026-03-05
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.05375v1

Estimating node similarity is a fundamental task in network analysis and graph-based machine learning, with applications in clustering, community detection, classification, and recommendation. We propose TopKGraphs, a method based on start-node-anchored random walks that bias transitions toward nodes with structurally similar neighborhoods, measured via Jaccard similarity. Rather than computing stationary distributions, walks are treated as stochastic neighborhood samplers, producing partial node rankings that are aggregated using robust rank aggregation to construct interpretable node-to-node affinity matrices. TopKGraphs provides a non-parametric, interpretable, and general-purpose representation of node similarity that can be applied in both network analysis and machine learning workflows. We evaluate the method on synthetic graphs (stochastic block models, Lancichinetti-Fortunato-Radicchi benchmark graphs), k-nearest-neighbor graphs from tabular datasets, and a curated high-confidence protein-protein interaction network. Across all scenarios, TopKGraphs achieves competitive or superior performance compared to standard similarity measures (Jaccard, Dice), a diffusion-based method (personalized PageRank), and an embedding-based approach (Node2Vec), demonstrating robustness in sparse, noisy, or heterogeneous networks. These results suggest that TopKGraphs is a versatile and interpretable tool for bridging simple local similarity measures with more complex embedding-based approaches, facilitating both data mining and network analysis applications.

---

### Embedded Inter-Subject Variability in Adversarial Learning for Inertial Sensor-Based Human Activity Recognition

Authors: Francisco M. Calatrava-Nicolás, Shoko Miyauchi, Vitor Fortes Rey, Paul Lukowicz, Todor Stoyanov, Oscar Martinez Mozos
Published: 2026-03-05
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.05371v1

This paper addresses the problem of Human Activity Recognition (HAR) using data from wearable inertial sensors. An important challenge in HAR is the model's generalization capabilities to new unseen individuals due to inter-subject variability, i.e., the same activity is performed differently by different individuals. To address this problem, we propose a novel deep adversarial framework that integrates the concept of inter-subject variability in the adversarial task, thereby encouraging subject-invariant feature representations and enhancing the classification performance in the HAR problem. Our approach outperforms previous methods in three well-established HAR datasets using a leave-one-subject-out (LOSO) cross-validation. Further results indicate that our proposed adversarial task effectively reduces inter-subject variability among different users in the feature space, and it outperforms adversarial tasks from previous works when integrated into our framework. Code: https://github.com/FranciscoCalatrava/EmbeddedSubjectVariability.git

---

### Learning Causal Structure of Time Series using Best Order Score Search

Authors: Irene Gema Castillo Mansilla, Urmi Ninad
Published: 2026-03-05
Categories: cs.LG, cs.AI, stat.ME
arXiv: https://arxiv.org/abs/2603.05370v2

Causal structure learning from observational data is central to many scientific and policy domains, but the time series setting common to many disciplines poses several challenges due to temporal dependence. In this paper we focus on score-based causal discovery for multivariate time series and introduce TS-BOSS, a time series extension of the recently proposed Best Order Score Search (BOSS) (Andrews et al. 2023). TS-BOSS performs a permutation-based search over dynamic Bayesian network structures while leveraging grow-shrink trees to cache intermediate score computations, preserving the scalability and strong empirical performance of BOSS in the static setting. We provide theoretical guarantees establishing the soundness of TS-BOSS under suitable assumptions, and we present an intermediate result that extends classical subgraph minimality results for permutation-based methods to the dynamic (time series) setting. Our experiments on synthetic data show that TS-BOSS is especially effective in high auto-correlation regimes, where it consistently achieves higher adjacency recall at comparable precision than standard constraint-based methods. Overall, TS-BOSS offers a high-performing, scalable approach for time series causal discovery and our results provide a principled bridge for extending sparsity-based, permutation-driven causal learning theory to dynamic settings.

---

### Learning Causal Structure of Time Series using Best Order Score Search

Authors: Irene Gema Castillo Mansilla, Urmi Ninad
Published: 2026-03-05
Categories: cs.LG, cs.AI, stat.ME
arXiv: https://arxiv.org/abs/2603.05370v1

Causal structure learning from observational data is central to many scientific and policy domains, but the time series setting common to many disciplines poses several challenges due to temporal dependence. In this paper we focus on score-based causal discovery for multivariate time series and introduce TS-BOSS, a time series extension of the recently proposed Best Order Score Search (BOSS) (Andrews et al. 2023). TS-BOSS performs a permutation-based search over dynamic Bayesian network structures while leveraging grow-shrink trees to cache intermediate score computations, preserving the scalability and strong empirical performance of BOSS in the static setting. We provide theoretical guarantees establishing the soundness of TS-BOSS under suitable assumptions, and we present an intermediate result that extends classical subgraph minimality results for permutation-based methods to the dynamic (time series) setting. Our experiments on synthetic data show that TS-BOSS is especially effective in high auto-correlation regimes, where it consistently achieves higher adjacency recall at comparable precision than standard constraint-based methods. Overall, TS-BOSS offers a high-performing, scalable approach for time series causal discovery and our results provide a principled bridge for extending sparsity-based, permutation-driven causal learning theory to dynamic settings.

---

### Progressive Residual Warmup for Language Model Pretraining

Authors: Tianhao Chen, Xin Xu, Lu Yin, Hao Chen, Yang Wang, Shizhe Diao, Can Yang
Published: 2026-03-05
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.05369v1

Transformer architectures serve as the backbone for most modern Large Language Models, therefore their pretraining stability and convergence speed are of central concern. Motivated by the logical dependency of sequentially stacked layers, we propose Progressive Residual Warmup (ProRes) for language model pretraining. ProRes implements an "early layer learns first" philosophy by multiplying each layer's residual with a scalar that gradually warms up from 0 to 1, with deeper layers taking longer warmup steps. In this way, deeper layers wait for early layers to settle into a more stable regime before contributing to learning. We demonstrate the effectiveness of ProRes through pretraining experiments across various model scales, as well as normalization and initialization schemes. Comprehensive analysis shows that ProRes not only stabilizes pretraining but also introduces a unique optimization trajectory, leading to faster convergence, stronger generalization and better downstream performance. Our code is available at https://github.com/dandingsky/ProRes.

---

### PACE: A Personalized Adaptive Curriculum Engine for 9-1-1 Call-taker Training

Authors: Zirong Chen, Hongchao Zhang, Meiyi Ma
Published: 2026-03-05
Categories: cs.AI
arXiv: https://arxiv.org/abs/2603.05361v2

9-1-1 call-taking training requires mastery of over a thousand interdependent skills, covering diverse incident types and protocol-specific nuances. A nationwide labor shortage is already straining training capacity, but effective instruction still demands that trainers tailor objectives to each trainee's evolving competencies. This personalization burden is one that current practice cannot scale. Partnering with Metro Nashville Department of Emergency Communications (MNDEC), we propose PACE (Personalized Adaptive Curriculum Engine), a co-pilot system that augments trainer decision-making by (1) maintaining probabilistic beliefs over trainee skill states, (2) modeling individual learning and forgetting dynamics, and (3) recommending training scenarios that balance acquisition of new competencies with retention of existing ones. PACE propagates evidence over a structured skill graph to accelerate diagnostic coverage and applies contextual bandits to select scenarios that target gaps the trainee is prepared to address. Empirical results show that PACE achieves 19.50% faster time-to-competence and 10.95% higher terminal mastery compared to state-of-the-art frameworks. Co-pilot studies with practicing training officers further demonstrate a 95.45% alignment rate between PACE's and experts' pedagogical judgments on real-world cases. Under estimation, PACE cuts turnaround time to merely 34 seconds from 11.58 minutes, up to 95.08% reduction.

---

### DiSCTT: Consensus-Guided Self-Curriculum for Efficient Test-Time Adaptation in Reasoning

Authors: Mohammad Mahdi Moradi, Sudhir Mudur
Published: 2026-03-05
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.05357v1

Test-time adaptation offers a promising avenue for improving reasoning performance in large language models without additional supervision, but existing approaches often apply a uniform optimization objective across all inputs, leading to inefficient or unstable adaptation on heterogeneous reasoning problems. We propose DiSCTT, a difficulty-aware, consensus-guided self-curriculum framework that dynamically allocates test-time optimization strategies based on instance-level epistemic uncertainty estimated from agreement among sampled reasoning trajectories. Inputs with high consensus are consolidated via supervised fine-tuning using majority-agreed solutions as pseudo-labels, while low-consensus inputs are optimized via reinforcement learning with a consensus-regularized objective that encourages diversity under relevance constraints. Across a broad suite of mathematical and general reasoning benchmarks, DiSCTT consistently outperforms strong test-time adaptation baselines, achieving higher accuracy with reduced variance and substantially lower computation and wall-clock training times. These results demonstrate that explicitly accounting for instance difficulty and uncertainty enables more stable, efficient, and effective test-time adaptation for reasoning models.

---

### Exploring the potential and limitations of Model Merging for Multi-Domain Adaptation in ASR

Authors: Carlos Carvalho, Francisco Teixeira, Thomas Rolland, Alberto Abad
Published: 2026-03-05
Categories: cs.CL, eess.AS
arXiv: https://arxiv.org/abs/2603.05354v1

Model merging is a scalable alternative to multi-task training that combines the capabilities of multiple specialised models into a single model. This is particularly attractive for large speech foundation models, which are typically adapted through domain-specific fine-tuning, resulting in multiple customised checkpoints, for which repeating full fine-tuning when new data becomes available is computationally prohibitive. In this work, we study model merging for multi-domain ASR and benchmark 11 merging algorithms for 10 European Portuguese domains, evaluating in-domain accuracy, robustness under distribution shift, as well as English and multilingual performance. We further propose BoostedTSV-M, a new merging algorithm based on TSV-M that mitigates rank collapse via singular-value boosting and improves numerical stability. Overall, our approach outperforms full fine-tuning on European Portuguese while preserving out-of-distribution generalisation in a single model.

---

### InfoFlow KV: Information-Flow-Aware KV Recomputation for Long Context

Authors: Xin Teng, Canyu Zhang, Shaoyi Zheng, Danyang Zhuo, Tianyi Zhou, Shenji Wan
Published: 2026-03-05
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.05353v3

Retrieval-augmented generation (RAG) for long-context question answering is bottlenecked by inference-time prefilling over large retrieved contexts. A common strategy is to precompute key-value (KV) caches for individual documents and selectively recompute a small subset of tokens to restore global causal dependencies, but existing methods rely on heuristics or representation discrepancies without modeling whether selected tokens can effectively influence generation. We cast selective KV recomputation as an information flow problem and show that a simple attention-norm signal from the query reliably identifies tokens that are both semantically relevant and structurally positioned to propagate information, when computed under an inference-consistent RoPE geometry. We therefore reconstruct global positional assignments for retrieved chunks and introduce an information-flow-guided chunk reordering strategy. Experiments on Large Language Model and Vision-Language Model benchmarks demonstrate consistent gains over prior methods under comparable latency.

---

### Ailed: A Psyche-Driven Chess Engine with Dynamic Emotional Modulation

Authors: Diego Armando Resendez Prado
Published: 2026-03-05
Categories: cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2603.05352v1

Chess engines passed human strength years ago, but they still don't play like humans. A grandmaster under clock pressure blunders in ways a club player on a hot streak never would. Conventional engines capture none of this. This paper proposes a personality x psyche decomposition to produce behavioral variability in chess play, drawing on patterns observed in human games. Personality is static -- a preset that pins down the engine's character. Psyche is dynamic -- a bounded scalar ψ_t \in (-100, +100), recomputed from five positional factors after every move. These two components feed into an audio-inspired signal chain (noise gate, compressor/expander, five-band equalizer, saturation limiter) that reshapes move probability distributions on the fly. The chain doesn't care what engine sits behind it: any system that outputs move probabilities will do. It needs no search and carries no state beyond ψ_t. I test the framework across 12,414 games against Maia2-1100, feeding it two probability sources that differ by ~2,800x in training data. Both show the same monotonic gradient in top-move agreement (~20-25 pp spread from stress to overconfidence), which tells us the behavioral variation comes from the signal chain, not from the model underneath. When the psyche runs overconfident, the chain mostly gets out of the way (66% agreement with vanilla Maia2). Under stress, the competitive score falls from 50.8% to 30.1%. The patterns are reminiscent of tilt and overconfidence as described in human play, but I should be upfront: this study includes no human-subject validation.

---

### A Multilingual Human Annotated Corpus of Original and Easy-to-Read Texts to Support Access to Democratic Participatory Processes

Authors: Stefan Bott, Verena Riegler, Horacio Saggion, Almudena Rascón Alcaina, Nouran Khallaf
Published: 2026-03-05
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.05345v2

Being able to understand information is a key factor for a self-determined life and society. It is also very important for participating in democratic processes. The study of automatic text simplification is often limited by the availability of high quality material for the training and evaluation on automatic simplifiers. This is true for English, but more so for less resourced languages like Spanish, Catalan and Italian. In order to fill this gap, we present a corpus of original texts for these 3 languages, with high quality simplification produced by human experts in text simplification. It was developed within the iDEM project to assess the impact of Easy-to-Read (E2R) language for democratic participation. The original texts were compiled from domains related to this topic. The corpus includes different text types, selected based on relevance, copyright availability, and ethical standards. All texts were simplified to E2R level. The corpus is particularity valuable because it includes the first annotated corpus of its kind for the Catalan language. It also represents a noteworthy contribution for Spanish and Italian, offering high-quality, human-annotated language resources that are rarely available in these domains. The corpus will be made freely accessible to the public.

---

### Building Effective AI Coding Agents for the Terminal: Scaffolding, Harness, Context Engineering, and Lessons Learned

Authors: Nghi D. Q. Bui
Published: 2026-03-05
Categories: cs.AI
arXiv: https://arxiv.org/abs/2603.05344v3

The landscape of AI coding assistance is undergoing a fundamental shift from complex IDE plugins to versatile, terminal-native agents. Operating directly where developers manage source control, execute builds, and deploy environments, CLI-based agents offer unprecedented autonomy for long-horizon development tasks. In this paper, we present OPENDEV, an open-source, command-line coding agent written in Rust, engineered specifically for this new paradigm. Effective autonomous assistance requires strict safety controls and highly efficient context management to prevent context bloat and reasoning degradation. OPENDEV overcomes these challenges through a compound AI system architecture with workload-specialized model routing, a dual-agent architecture separating planning from execution, lazy tool discovery, and adaptive context compaction that progressively reduces older observations. Furthermore, it employs an automated memory system to accumulate project-specific knowledge across sessions and counteracts instruction fade-out through event-driven system reminders. By enforcing explicit reasoning phases and prioritizing context efficiency, OPENDEV provides a secure, extensible foundation for terminal-first AI assistance, offering a blueprint for robust autonomous software engineering.

---

### Preserving Continuous Symmetry in Discrete Spaces: Geometric-Aware Quantization for SO(3)-Equivariant GNNs

Authors: Haoyu Zhou, Ping Xue, Hao Zhang, Tianfan Fu
Published: 2026-03-05
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.05343v2

Equivariant Graph Neural Networks (GNNs) are essential for physically consistent molecular simulations but suffer from high computational costs and memory bottlenecks, especially with high-order representations. While low-bit quantization offers a solution, applying it naively to rotation-sensitive features destroys the SO(3)-equivariant structure, leading to significant errors and violations of conservation laws. To address this issue, in this work, we propose a Geometric-Aware Quantization (GAQ) framework that compresses and accelerates equivariant models while rigorously preserving continuous symmetry in discrete spaces. Our approach introduces three key contributions: (1) a Magnitude-Direction Decoupled Quantization (MDDQ) scheme that separates invariant lengths from equivariant orientations to maintain geometric fidelity; (2) a symmetry-aware training strategy that treats scalar and vector features with distinct quantization schedules; and (3) a robust attention normalization mechanism to stabilize gradients in low-bit regimes. Experiments on the rMD17 benchmark demonstrate that our W4A8 models match the accuracy of FP32 baselines (9.31 meV vs. 23.20 meV) while reducing Local Equivariance Error (LEE) by over 30x compared to naive quantization. On consumer hardware, GAQ achieves 2.39x inference speedup and 4x memory reduction, enabling stable, energy-conserving molecular dynamics simulations for nanosecond timescales.

---

### On the Statistical Optimality of Optimal Decision Trees

Authors: Zineng Xu, Subhro Ghosh, Yan Shuo Tan
Published: 2026-03-05
Categories: stat.ML, cs.LG, math.ST
arXiv: https://arxiv.org/abs/2603.05340v2

While globally optimal empirical risk minimization (ERM) decision trees have become computationally feasible and empirically successful, rigorous theoretical guarantees for their statistical performance remain limited. In this work, we develop a comprehensive statistical theory for ERM trees under random design in both high-dimensional regression and classification. We first establish sharp oracle inequalities that bound the excess risk of the ERM estimator relative to the best possible approximation achievable by any tree with at most $L$ leaves, thereby characterizing the interpretability-accuracy trade-off. We derive these results using a novel uniform concentration framework based on empirically localized Rademacher complexity. Furthermore, we derive minimax optimal rates over a novel function class: the piecewise sparse heterogeneous anisotropic Besov (PSHAB) space. This space explicitly captures three key structural features encountered in practice: sparsity, anisotropic smoothness, and spatial heterogeneity. While our main results are established under sub-Gaussianity, we also provide robust guarantees that hold under heavy-tailed noise settings. Together, these findings provide a principled foundation for the optimality of ERM trees and introduce empirical process tools broadly applicable to other highly adaptive, data-driven procedures.

---

### Bayes with No Shame: Admissibility Geometries of Predictive Inference

Authors: Nicholas G. Polson, Daniel Zantedeschi
Published: 2026-03-05
Categories: stat.ML, cs.LG, math.ST
arXiv: https://arxiv.org/abs/2603.05335v4

Modern predictive systems combine predictors, sequential monitors, prediction sets, and online strategies, each with a different certificate of optimality. We study four criterion-relative geometries: Blackwell risk dominance, anytime-valid admissibility, fixed-level marginal coverage with expected-length efficiency within a declared rank-indexed family, and choice-based approachability (CApp) boundary-feasibility. We embed the four procedure types in a common product space and prove witness-based pairwise non-nesting: for every ordered pair of criterion classes, an explicit predictive system is active in both relevant coordinates, belongs to one class, and fails the other. The result records non-nesting across different object spaces and partial orders; it does not assert practical incompatibility. We separate three measure-relative coherence notions. In conditionally i.i.d. models, posterior predictive means under a single prior are martingales under the prior predictive law. For a point null, anytime-valid admissibility within e-processes is equivalent to the nonnegative martingale property. Self-consistency under a predictor's own predictive law does not imply Blackwell admissibility, as shown by a Bernoulli log-loss counterexample. Coverage admissibility is certified by exchangeability ranks within the declared rank-indexed family, while CApp boundary-feasibility uses Cesaro steering. A constrained-Bayes design schema organizes the four paradigms without collapsing their distinct decision spaces, partial orders, or risk functionals. Admissibility is criterion-relative.

---

### Bayes with No Shame: Admissibility Geometries of Predictive Inference

Authors: Nicholas G. Polson, Daniel Zantedeschi
Published: 2026-03-05
Categories: stat.ML, cs.LG, math.ST
arXiv: https://arxiv.org/abs/2603.05335v2

Four distinct admissibility geometries govern sequential and distribution-free inference: Blackwell risk dominance over convex risk sets, anytime-valid admissibility within the nonnegative supermartingale cone, marginal coverage validity over exchangeable prediction sets, and Cesàro approachability (CAA) admissibility, which reaches the risk-set boundary via approachability-style arguments rather than explicit priors. We prove a criterion separation theorem: the four classes of admissible procedures are pairwise non-nested. Each geometry carries a different certificate of optimality: a supporting-hyperplane prior (Blackwell), a nonnegative supermartingale (anytime-valid), an exchangeability rank (coverage), or a Cesàro steering argument (CAA). Martingale coherence is necessary for Blackwell admissibility and necessary and sufficient for anytime-valid admissibility within e-processes, but is not sufficient for Blackwell admissibility and is not necessary for coverage validity or CAA-admissibility. All four criteria can be viewed through a common schematic template (minimize Bayesian risk subject to a feasibility constraint), but the decision spaces, partial orders, and performance metrics differ by criterion, making them geometrically incompatible. Admissibility is irreducibly criterion-relative.

---

### Dark3R: Learning Structure from Motion in the Dark

Authors: Andrew Y Guo, Anagh Malik, SaiKiran Tedla, Yutong Dai, Yiqian Qin, Zach Salehe, Benjamin Attal, Sotiris Nousias, Kiriakos N. Kutulakos, David B. Lindell
Published: 2026-03-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.05330v1

We introduce Dark3R, a framework for structure from motion in the dark that operates directly on raw images with signal-to-noise ratios (SNRs) below $-4$ dB -- a regime where conventional feature- and learning-based methods break down. Our key insight is to adapt large-scale 3D foundation models to extreme low-light conditions through a teacher--student distillation process, enabling robust feature matching and camera pose estimation in low light. Dark3R requires no 3D supervision; it is trained solely on noisy--clean raw image pairs, which can be either captured directly or synthesized using a simple Poisson--Gaussian noise model applied to well-exposed raw images. To train and evaluate our approach, we introduce a new, exposure-bracketed dataset that includes $\sim$42,000 multi-view raw images with ground-truth 3D annotations, and we demonstrate that Dark3R achieves state-of-the-art structure from motion in the low-SNR regime. Further, we demonstrate state-of-the-art novel view synthesis in the dark using Dark3R's predicted poses and a coarse-to-fine radiance field optimization procedure.

---

### FairFinGAN: Fairness-aware Synthetic Financial Data Generation

Authors: Tai Le Quy, Dung Nguyen Tuan, Trung Nguyen Thanh, Duy Tran Cong, Huyen Giang Thi Thu, Frank Hopfgartner
Published: 2026-03-05
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.05327v1

Financial datasets often suffer from bias that can lead to unfair decision-making in automated systems. In this work, we propose FairFinGAN, a WGAN-based framework designed to generate synthetic financial data while mitigating bias with respect to the protected attribute. Our approach incorporates fairness constraints directly into the training process through a classifier, ensuring that the synthetic data is both fair and preserves utility for downstream predictive tasks. We evaluate our proposed model on five real-world financial datasets and compare it with existing GAN-based data generation methods. Experimental results show that our approach achieves superior fairness metrics without significant loss in data utility, demonstrating its potential as a tool for bias-aware data generation in financial applications.

---

### GALACTIC: Global and Local Agnostic Counterfactuals for Time-series Clustering

Authors: Christos Fragkathoulas, Eleni Psaroudaki, Themis Palpanas, Evaggelia Pitoura
Published: 2026-03-05
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.05318v2

Time-series clustering is a fundamental tool for pattern discovery, yet existing explainability methods, primarily based on feature attribution or metadata, fail to identify the transitions that move an instance across cluster boundaries. While Counterfactual Explanations (CEs) identify the minimal temporal perturbations required to alter the prediction of a model, they have been mostly confined to supervised settings. This paper introduces GALACTIC, the first unified framework to bridge local and global counterfactual explainability for unsupervised time-series clustering. At instance level (local), GALACTIC generates perturbations via a cluster-aware optimization objective that respects the target and underlying cluster assignments. At cluster level (global), to mitigate cognitive load and enhance interpretability, we formulate a representative CE selection problem. We propose a Minimum Description Length (MDL) objective to extract a non-redundant summary of global explanations that characterize the transitions between clusters. We prove that our MDL objective is supermodular, which allows the corresponding MDL reduction to be framed as a monotone submodular set function. This enables an efficient greedy selection algorithm with provable $(1-1/e)$ approximation guarantees. Extensive experimental evaluation on the UCR Archive demonstrates that GALACTIC produces significantly sparser local CEs and more concise global summaries than state-of-the-art baselines adapted for our problem, offering the first unified approach for interpreting clustered time-series through counterfactuals.

---

### How important are the genes to explain the outcome - the asymmetric Shapley value as an honest importance metric for high-dimensional features

Authors: Mark A. van de Wiel, Jeroen Goedhart, Martin Jullum, Kjersti Aas
Published: 2026-03-05
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2603.05317v1

In clinical prediction settings the importance of a high-dimensional feature like genomics is often assessed by evaluating the change in predictive performance when adding it to a set of traditional clinical variables. This approach is questionable, because it does not account for collinearity nor known directionality of dependencies between variables. We suggest to use asymmetric Shapley values as a more suitable alternative to quantify feature importance in the context of a mixed-dimensional prediction model. We focus on a setting that is particularly relevant in clinical prediction: disease state as a mediating variable for genomic effects, with additional confounders for which the direction of effects may be unknown. We derive efficient algorithms to compute local and global asymmetric Shapley values for this setting. The former are shown to be very useful for inference, whereas the latter provide interpretation by decomposing any predictive performance metric into contributions of the features. Throughout, we illustrate our framework by a leading example: the prediction of progression-free survival for colorectal cancer patients.

---

### Frequency-Aware Error-Bounded Caching for Accelerating Diffusion Transformers

Authors: Guandong Li
Published: 2026-03-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.05315v1

Diffusion Transformers (DiTs) have emerged as the dominant architecture for high-quality image and video generation, yet their iterative denoising process incurs substantial computational cost during inference. Existing caching methods accelerate DiTs by reusing intermediate computations across timesteps, but they share a common limitation: treating the denoising process as uniform across time,depth, and feature dimensions. In this work, we identify three orthogonal axes of non-uniformity in DiT denoising: (1) temporal -- sensitivity to caching errors varies dramatically across the denoising trajectory; (2) depth -- consecutive caching decisions lead to cascading approximation errors; and (3) feature -- different components of the hidden state exhibit heterogeneous temporal dynamics. Based on these observations, we propose SpectralCache, a unified caching framework comprising Timestep-Aware Dynamic Scheduling (TADS), Cumulative Error Budgets (CEB), and Frequency-Decomposed Caching (FDC). On FLUX.1-schnell at 512x512 resolution, SpectralCache achieves 2.46x speedup with LPIPS 0.217 and SSIM 0.727, outperforming TeaCache (2.12x, LPIPS 0.215, SSIM 0.734) by 16% in speed while maintaining comparable quality (LPIPS difference < 1%). Our approach is training-free, plug-and-play, and compatible with existing DiT architectures.

---

### PersianPunc: A Large-Scale Dataset and BERT-Based Approach for Persian Punctuation Restoration

Authors: Mohammad Javad Ranjbar Kalahroodi, Heshaam Faili, Azadeh Shakery
Published: 2026-03-05
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2603.05314v1

Punctuation restoration is essential for improving the readability and downstream utility of automatic speech recognition (ASR) outputs, yet remains underexplored for Persian despite its importance. We introduce PersianPunc, a large-scale, high-quality dataset of 17 million samples for Persian punctuation restoration, constructed through systematic aggregation and filtering of existing textual resources. We formulate punctuation restoration as a token-level sequence labeling task and fine-tune ParsBERT to achieve strong performance. Through comparative evaluation, we demonstrate that while large language models can perform punctuation restoration, they suffer from critical limitations: over-correction tendencies that introduce undesired edits beyond punctuation insertion (particularly problematic for speech-to-text pipelines) and substantially higher computational requirements. Our lightweight BERT-based approach achieves a macro-averaged F1 score of 91.33% on our test set while maintaining efficiency suitable for real-time applications. We make our dataset (https://huggingface.co/datasets/MohammadJRanjbar/persian-punctuation-restoration) and model (https://huggingface.co/MohammadJRanjbar/parsbert-persian-punctuation) publicly available to facilitate future research in Persian NLP and provide a scalable framework applicable to other morphologically rich, low-resource languages.

---

### Latent-Mark: An Audio Watermark Robust to Neural Codec Compression

Authors: Yen-Shan Chen, Shih-Yu Lai, Ying-Jung Tsou, Yi-Cheng Lin, Bing-Yu Chen, Yun-Nung Chen, Hung-yi Lee, Shang-Tse Chen
Published: 2026-03-05
Categories: cs.SD, cs.AI
arXiv: https://arxiv.org/abs/2603.05310v3

While existing audio watermarking techniques have achieved strong robustness against traditional digital signal processing (DSP) attacks, they remain vulnerable to neural compression. This occurs because modern neural audio codecs act as noise filters and discard the imperceptible waveform variations used in prior watermarking methods. To address this limitation, we propose Latent-Mark, the first zero-bit audio watermarking framework designed to survive neural codec compression. Our key insight is that robustness to the encode-decode process requires embedding the watermark within the codec's invariant latent space. We achieve this by optimizing the audio waveform to induce a detectable directional shift in its encoded latent representation, while constraining perturbations to align with the natural audio manifold to ensure imperceptibility. To prevent overfitting to a single codec's quantization rules, we introduce Cross-Codec Optimization, jointly optimizing the waveform across multiple surrogate codecs to target shared latent invariants. Extensive evaluations demonstrate robust zero-shot transferability to unseen neural codecs, achieving competitive resilience against traditional DSP attacks while preserving perceptual imperceptibility. We hope our work will inspire future research into universal watermarking frameworks capable of maintaining integrity across increasingly complex and diverse generative distortions.

---

### Med-V1: Small Language Models for Zero-shot and Scalable Biomedical Evidence Attribution

Authors: Qiao Jin, Yin Fang, Lauren He, Yifan Yang, Guangzhi Xiong, Zhizheng Wang, Nicholas Wan, Joey Chan, Donald C. Comeau, Robert Leaman, Charalampos S. Floudas, Aidong Zhang et al.
Published: 2026-03-05
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2603.05308v4

Assessing whether an article supports an assertion is essential for hallucination detection and claim verification. While large language models (LLMs) have the potential to automate this task, achieving strong performance requires frontier models such as GPT-5 that are prohibitively expensive to deploy at scale. To efficiently perform biomedical evidence attribution, we present Med-V1, a family of small language models with only three billion parameters. Trained on high-quality synthetic data newly developed in this study, Med-V1 substantially outperforms (+27.0% to +71.3%) its base models on five biomedical benchmarks unified into a verification format. Despite its smaller size, Med-V1 performs comparably to frontier LLMs such as GPT-5, along with high-quality explanations for its predictions. We use Med-V1 to conduct a first-of-its-kind use case study that quantifies hallucinations in LLM-generated answers under different citation instructions. Results show that the format instruction strongly affects citation validity and hallucination, with GPT-5 generating more claims but exhibiting hallucination rates similar to GPT-4o. Additionally, we present a second use case showing that Med-V1 can automatically identify high-stakes evidence misattributions in clinical practice guidelines, revealing potentially negative public health impacts that are otherwise challenging to identify at scale. Overall, Med-V1 provides an efficient and accurate lightweight alternative to frontier LLMs for practical, real-world biomedical evidence attribution. Med-V1 is available at https://github.com/NLM-DIR/Med-V1.

---

### Med-V1: Small Language Models for Zero-shot and Scalable Biomedical Evidence Attribution

Authors: Qiao Jin, Yin Fang, Lauren He, Yifan Yang, Guangzhi Xiong, Zhizheng Wang, Nicholas Wan, Joey Chan, Donald C. Comeau, Robert Leaman, Charalampos S. Floudas, Aidong Zhang et al.
Published: 2026-03-05
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2603.05308v3

Assessing whether an article supports an assertion is essential for hallucination detection and claim verification. While large language models (LLMs) have the potential to automate this task, achieving strong performance requires frontier models such as GPT-5 that are prohibitively expensive to deploy at scale. To efficiently perform biomedical evidence attribution, we present Med-V1, a family of small language models with only three billion parameters. Trained on high-quality synthetic data newly developed in this study, Med-V1 substantially outperforms (+27.0% to +71.3%) its base models on five biomedical benchmarks unified into a verification format. Despite its smaller size, Med-V1 performs comparably to frontier LLMs such as GPT-5, along with high-quality explanations for its predictions. We use Med-V1 to conduct a first-of-its-kind use case study that quantifies hallucinations in LLM-generated answers under different citation instructions. Results show that the format instruction strongly affects citation validity and hallucination, with GPT-5 generating more claims but exhibiting hallucination rates similar to GPT-4o. Additionally, we present a second use case showing that Med-V1 can automatically identify high-stakes evidence misattributions in clinical practice guidelines, revealing potentially negative public health impacts that are otherwise challenging to identify at scale. Overall, Med-V1 provides an efficient and accurate lightweight alternative to frontier LLMs for practical and real-world applications in biomedical evidence attribution and verification tasks. Med-V1 is available at https://github.com/ncbi-nlp/Med-V1.

---

### Fusion4CA: Boosting 3D Object Detection via Comprehensive Image Exploitation

Authors: Kang Luo, Xin Chen, Yangyi Xiao, Hesheng Wang
Published: 2026-03-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.05305v1

Nowadays, an increasing number of works fuse LiDAR and RGB data in the bird's-eye view (BEV) space for 3D object detection in autonomous driving systems. However, existing methods suffer from over-reliance on the LiDAR branch, with insufficient exploration of RGB information. To tackle this issue, we propose Fusion4CA, which is built upon the classic BEVFusion framework and dedicated to fully exploiting visual input with plug-and-play components. Specifically, a contrastive alignment module is designed to calibrate image features with 3D geometry, and a camera auxiliary branch is introduced to mine RGB information sufficiently during training. For further performance enhancement, we leverage an off-the-shelf cognitive adapter to make the most of pretrained image weights, and integrate a standard coordinate attention module into the fusion stage as a supplementary boost. Experiments on the nuScenes dataset demonstrate that our method achieves 69.7% mAP with only 6 training epochs and a mere 3.48% increase in inference parameters, yielding a 1.2% improvement over the baseline which is fully trained for 20 epochs. Extensive experiments in a simulated lunar environment further validate the effectiveness and generalization of our method. Our code will be released through Fusion4CA.

---

### Uniform Inductive Spatio-Temporal Kriging

Authors: Lewei Xie, Haoyu Zhang, Yulong Chen, Liangjun You, Zongxian Yang, Yifan Zhang
Published: 2026-03-05
Categories: cs.AI
arXiv: https://arxiv.org/abs/2603.05301v2

Inductive spatio-temporal kriging infers signals at unobserved locations from observed sensors, but real-world observations are often incomplete and exhibit block-wise missingness caused by failures, interruptions, or maintenance. A common impute-then-krige pipeline suffers from objective mismatch: better reconstruction on observed sensors does not necessarily improve downstream kriging, and value-dependent imputation bias can be propagated to unobserved nodes. We propose UniSTOK, a plug-and-play framework for inductive spatio-temporal kriging under incomplete observations. We first introduce Reliability-guided Signal Regulation (RSR), which estimates entry-wise reliability from temporal continuity and spatial support, and uses it to regulate the input signals so that reliable observations are emphasized while long-gap or weakly supported entries are suppressed before spatial propagation. We further introduce Residual Bias Calibration (RBC), which estimates value-conditioned residual prototypes after the main predictor converges and learns context-correction amplitudes to adaptively calibrate systematic over- or under-estimation in final kriging predictions. Extensive experiments on real-world datasets show that UniSTOK consistently improves multiple kriging backbones.

---

### WavSLM: Single-Stream Speech Language Modeling via WavLM Distillation

Authors: Luca Della Libera, Cem Subakan, Mirco Ravanelli
Published: 2026-03-05
Categories: cs.LG, cs.AI, cs.CL, cs.SD
arXiv: https://arxiv.org/abs/2603.05299v2

Large language models show that simple autoregressive training can yield scalable and coherent generation, but extending this paradigm to speech remains challenging due to the entanglement of semantic and acoustic information. Most existing speech language models rely on text supervision, hierarchical token streams, or complex hybrid architectures, departing from the single-stream generative pretraining paradigm that has proven effective in text. In this work, we introduce WavSLM, a speech language model trained by quantizing and distilling self-supervised WavLM representations into a single codebook and optimizing an autoregressive next-chunk prediction objective. WavSLM jointly models semantic and acoustic information within a single token stream without text supervision or text pretraining. Despite its simplicity, it achieves competitive performance on consistency benchmarks and speech generation while using fewer parameters, less training data, and supporting streaming inference.

---

### Latent Policy Steering through One-Step Flow Policies

Authors: Hokyun Im, Andrey Kolobov, Jianlong Fu, Youngwoon Lee
Published: 2026-03-05
Categories: cs.RO, cs.LG
arXiv: https://arxiv.org/abs/2603.05296v2

Offline reinforcement learning (RL) allows robots to learn from offline datasets without risky exploration. Yet, offline RL's performance often hinges on a brittle trade-off between (1) return maximization, which can push policies outside the dataset support, and (2) behavioral constraints, which typically require sensitive hyperparameter tuning. Latent steering offers a structural way to stay within the dataset support during RL, but existing offline adaptations commonly approximate action values using latent-space critics learned via indirect distillation, which can lose information and hinder convergence. We propose Latent Policy Steering (LPS), which enables high-fidelity latent policy improvement by backpropagating original-action-space Q-gradients through a differentiable one-step MeanFlow policy to update a latent-action-space actor. By eliminating proxy latent critics, LPS allows an original-action-space critic to guide end-to-end latent-space optimization, while the one-step MeanFlow policy serves as a behavior-constrained generative prior. This decoupling yields a robust method that works out-of-the-box with minimal tuning. Across OGBench and real-world robotic tasks, LPS achieves state-of-the-art performance and consistently outperforms behavioral cloning and strong latent steering baselines.

---