# Research Papers — 2026-06 · bundle page 205 of 260

> Full-text markdown of papers #10201–10250 of 12993 published in 2026-06, newest first. AI-readable mirrors of the full 12993-paper 2026-06 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-06/page/205
[← Previous bundle](https://aipod.dev/papers/archive/2026-06/page/204.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-06/page/206.md)

### RealDocBench: A Benchmark for Field-Level QA and Layout Understanding on Real-World Regulated Documents

Authors: Ameya Joshi, Joon Kim, Gus Eggert, Joseph Bajor, Cindy Hao, Jing Reyhan, Kushal Byatnal, Eli Badgio
Published: 2026-06-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2606.07401v1

Document parsing systems are increasingly deployed in high-stakes, regulated workflows such as mortgage underwriting, financial reporting, supply-chain logistics, and clinical records. Yet most public benchmarks evaluate parsers on clean academic layouts or synthetic prose, and report a single OCR or markdown-level similarity score. Such documents and metrics correlate poorly with what downstream agents actually need: the correct value for a specific field on a messy real-world page. We introduce RealDocBench, a two-track benchmark built from real regulated documents. The QA track contains 1,356 field-level questions over 581 documents spanning four domains, where each question is paired with a typed gold_dict of key-to-value answers and parsers are scored on both per-field and strict per-question accuracy. The layout track contains 1,500 human-verified page images annotated with COCO-style bounding boxes under a nine-class public taxonomy, scored with a Hungarian matcher that includes adjacency-aware split/merge recovery. We evaluate eighteen systems, spanning commercial parsing APIs, general-purpose VLMs, and open-source OCR models, under a uniform extraction-and-scoring protocol, and report accuracy alongside per-page cost and cache-busted latency. RealDocBench exposes a wide performance spread that single-number benchmarks hide, a persistently hard medical sub-domain, and sharp cost/latency trade-offs across operating points. We release the datasets, parser adapters, and evaluation harness to support reproducible, field-level comparison of document parsing systems.

---

### Generative Modeling of Discrete Latent Structures via Dynamic Policy Gradients

Authors: Stefan Ivanovic, Ge Liu, Mohammed El-Kebir
Published: 2026-06-05
Categories: cs.LG
arXiv: https://arxiv.org/abs/2606.07400v1

Many scientific problems require inferring unobserved mechanistic latent states from indirect observations. While classical approaches, including expectation maximization, do not scale to combinatorially large spaces, deep learning approaches such as variational autoencoders typically form artificial latent states rather than reconstructing the mechanistic ground-truth states. Here, we introduce GReinSS, a policy learning framework that uses dynamically rescaled rewards to learn latent state distributions that maximize the observed data likelihood. We show that GReinSS accurately reconstructs simulated latent sets and latent graphs, outperforming alternative policy learning and generative modeling baselines. Additionally, GReinSS reconstructs isoforms from real short-read RNA sequencing data that better match isoforms detected by orthogonal long-read sequencing than the standard RSEM algorithm. Overall, GReinSS is a principled and practically effective approach for generative modeling and inference of combinatorial latent states from indirect observations.

---

### Automatic, Debiased, and Invariant Counterfactual Generation under General Interventions

Authors: Raphael C Kim, Jingsen Zhu, Ramin Zabih, Michele Santacatterina
Published: 2026-06-05
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2606.07399v2

Generative models for counterfactual outcomes have great potential to support decision-making under complex interventions, but existing approaches are limited by unstable estimation, poor generalization across environments, and bias from nuisance model misspecification. We introduce ADIGen, a framework for automatic, debiased, and invariant counterfactual generation under general interventions, including high-dimensional interventions and outcomes. ADIGen combines Riesz regression to avoid unstable density-ratio estimation, causal invariance to improve generalization under distribution shift, and orthogonal statistical learning to obtain doubly robust guarantees against nuisance model misspecification. We provide excess-risk bounds showing that ADIGen controls counterfactual risk under general interventions, with a product-bias nuisance remainder and an invariant risk bound across environments. We then extend this framework to multiple, interacting objects with a joint intervention, and apply ADIGen to counterfactual world modeling. In contrast to standard statistical settings, the joint outcome is modeled natively without the need for exposure mappings or direct/indirect effect decompositions.

---

### Automatic, Debiased, and Invariant Counterfactual Generation under General Interventions

Authors: Raphael C Kim, Jingsen Zhu, Ramin Zabih, Michele Santacatterina
Published: 2026-06-05
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2606.07399v1

Generative models for counterfactual outcomes have great potential to support decision-making under complex interventions, but existing approaches are limited by unstable estimation, poor generalization across environments, and bias from nuisance model misspecification. We introduce ADIGen, a framework for automatic, debiased, and invariant counterfactual generation under general interventions, including high-dimensional interventions and outcomes. ADIGen combines Riesz regression to avoid unstable density-ratio estimation, causal invariance to improve generalization under distribution shift, and orthogonal statistical learning to obtain doubly robust guarantees against nuisance model misspecification. We provide excess-risk bounds showing that ADIGen controls counterfactual risk under general interventions, with a product-bias nuisance remainder and an invariant risk bound across environments.

---

### Mind the Gap: Disentangling Performance Bottlenecks in Video Instance Segmentation

Authors: Danial Hamdi, Fardin Ayar, Mahdi Javanmardi
Published: 2026-06-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2606.07394v1

In Video Instance Segmentation (VIS), classification, segmentation, and tracking objectives are jointly evaluated, but their individual contributions to performance loss remain opaque. We introduce a diagnostic framework that formulates identity and class assignment as an Integer Linear Program (ILP), yielding a model-agnostic oracle that hierarchically isolates each error source. Applied to seven VIS methods spanning online and offline paradigms across YouTube-VIS 2019/2021 and a diagnostic subset of OVIS, our analysis reveals a consistent picture. Tracking instability is a critical bottleneck for online methods, with gaps exceeding 20 AP under heavy occlusion, and grows sharply with video length and instance density. While semantic classification contributes meaningfully on standard benchmarks, its impact becomes negligible where tracking fails most. Although stronger backbones substantially lift default scores, they leave AP tracking gaps largely intact, confirming that temporal fragility is algorithmic rather than purely representational. To complement the oracle, we introduce TrackLens, a visual tool that translates gap magnitude into observable, query-level failure modes. Together, these tools provide a systematic foundation for targeting VIS's core challenge: robust long-term temporal association.

---

### Online Pandora's Box for Contextual LLM Cascading

Authors: Alexandre Belloni, Yan Chen, Yehua Wei
Published: 2026-06-05
Categories: cs.AI, cs.LG, econ.EM, stat.ML
arXiv: https://arxiv.org/abs/2606.07392v2

Motivated by Large Language Model (LLM) cascading, we propose an online contextual Pandora's Box model for adaptively querying and selecting LLM APIs. In each period, a decision-maker observes a request context and faces a two-phase decision problem. In the query phase, the decision-maker sequentially queries APIs, where each query reveals a generated output and the decision-maker incurs an (output-dependent) cost. In the selection phase, the decision-maker selects one of the generated outputs to deploy and observes only the downstream reward of the deployed output. This output-mediated feedback structure differs from classical online contextual Pandora's Box models, in which opening a box directly reveals its reward. Rather than estimating the full conditional output and cost distributions of each API, we directly model the reservation index and develop a learning approach for the query phase. Specifically, we impose a parametric structure on the contextual reservation index functions induced by the classical Weitzman's policy. Our policy combines generalized method of moments (GMM) type estimation of these reservation indices with UCB-style confidence bounds for both these indices and the shared output-level reward evaluator. Under regularity conditions, we prove that the resulting policy achieves dimension-dependent $\widetilde O(\sqrt T)$ cumulative regret over a horizon of $T$ periods.

---

### Online Pandora's Box for Contextual LLM Cascading

Authors: Alexandre Belloni, Yan Chen, Yehua Wei
Published: 2026-06-05
Categories: cs.AI, cs.LG, econ.EM, stat.ML
arXiv: https://arxiv.org/abs/2606.07392v1

Motivated by Large Language Model (LLM) cascading, we propose an online contextual Pandora's Box model for adaptively querying and selecting LLM APIs. In each period, a decision-maker observes a request context and faces a two-phase decision problem. In the query phase, the decision-maker sequentially queries APIs, where each query reveals a generated output and the decision-maker incurs an (output-dependent) cost. In the selection phase, the decision-maker selects one of the generated outputs to deploy and observes only the downstream reward of the deployed output. This output-mediated feedback structure differs from classical online contextual Pandora's Box models, in which opening a box directly reveals its reward. Rather than estimating the full conditional output and cost distributions of each API, we directly model the reservation index and develop a learning approach for the query phase. Specifically, we impose a parametric structure on the contextual reservation index functions induced by the classical Weitzman's policy. Our policy combines generalized method of moments (GMM) type estimation of these reservation indices with UCB-style confidence bounds for both these indices and the shared output-level reward evaluator. Under regularity conditions, we prove that the resulting policy achieves dimension-dependent $\widetilde O(\sqrt T)$ cumulative regret over a horizon of $T$ periods.

---

### Making the Most of Limited Data: Score-Aware Training for Text-to-Music Generation

Authors: Yun-Chen Cheng, Tzu-Hung Huang, Chih-Pin Tan
Published: 2026-06-05
Categories: cs.LG
arXiv: https://arxiv.org/abs/2606.07387v1

State-of-the-art text-to-music generation systems rely on massive proprietary datasets and industrial-scale compute, making it impossible to disentangle architectural contributions from resource advantages. We propose \textit{score-aware training}, which treats audio-caption alignment score as a direct supervision signal throughout the pipeline. Rather than discarding low-scoring segments, we repurpose them via a CLAP-conditioned Beta noise timestep schedule that routes them to high-noise training regimes, acting as an effective implicit regularizer. Complementarily, segment-level filtering removes the most misaligned examples, and a two-stage caption procedure bridges the distribution gap between verbose training captions and concise inference prompts. A REPA auxiliary loss further transfers structured semantic knowledge from pretrained CLAP and MuQ encoders without additional data. Our 450M-parameter FluxAudio-based system, submitted to the ICME 2026 ATTM Grand Challenge Efficiency Track, ranked 2nd across both tracks in the objective evaluation and 3rd in the Efficiency Track in the final MOS evaluation.

---

### Unified Geometry-Guided ML-FTLE for Tracking Transient Chaos from Scalar Time Series

Authors: S. V. Manivelan, Andrei Velichko, I. Manimehan
Published: 2026-06-05
Categories: nlin.CD, cs.LG, physics.data-an
arXiv: https://arxiv.org/abs/2606.07385v1

Detecting transient chaos from scalar observations without governing equations represents a fundamental challenge in nonlinear dynamics. We propose a geometry-guided machine learning framework that unifies predictive trajectory divergence with macroscopic attractor morphology to track abrupt regime shifts. The methodology extracts a local instability scale via out-of-sample k-nearest neighbor forecast errors to establish the ML-FTLE estimator, subsequently mapping this temporal divergence onto a structural closeness matrix derived from a minimal dictionary of Poincare occupancy grids. By employing partial least squares regression, we extract a latent geometric component calibrated directly to the empirical finite-time Lyapunov spectrum, yielding the Poincare-based geometric-guided FTLE. Validation against analytical QR-FTLE baselines confirms that fusing topological state spaces with predictive divergence systematically improves continuous transition tracking. The Structural Similarity Index optimally resolves gradual damping, while Hausdorff Distance exhibits extreme resilience during abrupt phase-space collapses. Furthermore, macroscopic spatial discretization acts as a robust topological regularizer against additive Gaussian noise, preserving deterministic signatures even at moderate signal thresholds. This equation-free framework provides a highly accurate, noise-resilient diagnostic for monitoring structural transitions in complex non-stationary systems.

---

### RhinoVLA Technical Report

Authors: Huixi Technology, :, Chen Zhang, Chenyang Zhou, Guanglei Ding, Guanghui He, Haibin Gao, Jiajia Chen, Jianyong Zhang, Lianyi Yu, Ningyi Xu, Ping Xu et al.
Published: 2026-06-05
Categories: cs.RO, cs.LG
arXiv: https://arxiv.org/abs/2606.07383v4

Vision-Language-Action (VLA) models have shown strong potential for robotic manipulation, but real-time deployment on edge hardware remains challenging. In this work, we identify VLM visual and context tokens as a major source of deployment latency: for GEMM-dominated projection operators, computation grows linearly with the number of input tokens when model dimensions are fixed. Motivated by this observation, we propose RhinoVLA, a deployment-oriented VLA model co-designed with the Huixi R1 edge SoC. RhinoVLA adopts a token-efficient Qwen3-VL backbone and a continuous Action Expert, reducing the VLM-side token and computation burden while preserving pretrained multimodal capability. To support cross-robot learning, RhinoVLA further introduces a unified interface that combines View Registry, 72D physical state-action slot space, and robotinstance LoRA, allowing heterogeneous robot observations and action schemas to be aligned under a shared policy. On the deployment side, RhinoVLA is optimized through hardware-aware compilation, mixed-precision execution, and parallel visual encoding. Experiments show that RhinoVLA achieves downstream performance comparable to π0.5 at a similar parameter scale, while reaching 11.69 Hz end-to-end inference on Huixi R1, meeting the 10 Hz real-time closedloop control target. The project will be open-sourced at https://github.com/HuixiAI/RhinoVLA.

---

### Covariance Shrinkage via Stochastic Interpolation

Authors: Mathieu Chalvidal, Florentin Coeurdoux, Eric Vanden-Eijnden
Published: 2026-06-05
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2606.07382v1

We recast classical shrinkage of high-dimensional covariance estimators as empirical risk minimization over a parametric stochastic interpolant between a source and a target distribution. This formalism recovers known shrinkage estimators as special cases and reveals three distinct mechanisms for reducing statistical risk: (i) Scheduling: the interpolant schedule determines the class of admissible covariances, and hence the achievable risk. (ii) Flow maps and couplings: whereas naive constructions amount to assuming independence between the distributions, specific coupling structures (e.g., solutions of optimal transport problems) can lower the empirical risk. Moreover, non-linear flow maps realizing such couplings free the interpolant covariance from the eigenbasis of the empirical estimate, enabling eigenvector regularization. (iii) Early stopping: estimators defined by integrating a regressed vector field afford an additional bias-variance trade-off through approximation of the true interpolant distribution. We then propose a neural estimator of the interpolant, together with an upper bound on its quadratic risk in terms of the interpolant approximation error, and validate both on synthetic experiments. Finally, we apply the estimator to real neuroimaging data, demonstrating the additional regularization power this approach offers in practice.

---

### Impact of Synthetic Lesional MR Images in Automated Focal Cortical Dysplasia Detection in Low-Data Scenarios

Authors: Prabhjot Kaur, Hakim Ouaalam, Sedat Kandemirli, Sanjay P. Prabhu, Simon K. Warfield
Published: 2026-06-05
Categories: eess.IV, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2606.07381v1

Background and Purpose: Automated detection of focal cortical dysplasia (FCD) requires large volumes of voxelwise lesion-delineated MRI data, which are difficult to acquire. This study aims to generate synthetic MRI data exhibiting FCD, assess their realism, and evaluate their impact on automated FCD detection, particularly in reducing the need for manual annotations. Methods: T1-weighted (T1w) and T2-weighted Fluid-Attenuated Inversion Recovery (FLAIR) MRI scans from 131 FCD patients and 90 healthy controls from multiple (3) sites were retrospectively studied. Synthetic MRIs were generated by conditioning a generative network on binary FCD masks. Two neuroradiologists identified real images from a random set of 14 real and 14 synthetic scans. Three nnU-Net models were trained to detect FCD using: (i) real-only (35 FCD / 35 controls), (ii) real (35 FCD / 35 controls) plus synthetic augmentation, and (iii) expanded real data (70 FCD / 70 controls). Results: Experts showed limited ability to distinguish real from synthetic images, with classification accuracy of 60% for T1w and 70% for FLAIR (inter-rater agreement kappa = 0.86). Augmenting automated FCD detection with synthetic data increased sensitivity by 8.14% (p = 0.12) and improved model confidence at true lesion sites (0.83 +/- 0.11 to 0.89 +/- 0.12; p = 0.02). The expanded real-data model further improved sensitivity to 73.8% (p < 0.001) and confidence to 0.90 +/- 0.14 (p = 0.01). Conclusion: Conditional generative networks can generate realistic synthetic FCD-MRIs, reducing labeled data needs by approximately 20% while maintaining equivalent sensitivity. Equivalent amounts of real data, when available, remain more effective than synthetic augmentation.

---

### Do Coding Agents Deceive Us? Detecting and Preventing Cheating via Capped Evaluation with Randomized Tests

Authors: Thanawat Lodkaew, Johannes Ackermann, Soichiro Nishimori, Nontawat Charoenphakdee, Masashi Sugiyama, Takashi Ishida
Published: 2026-06-05
Categories: cs.LG, cs.AI, cs.CL, stat.ME
arXiv: https://arxiv.org/abs/2606.07379v2

A growing failure mode in agent evaluation and training is that models can achieve high evaluation scores by exploiting shortcuts instead of solving the intended task, producing deceptive performance. This makes evaluation scores unreliable as measures of true task-solving ability. We propose CapCode, a framework for constructing coding datasets with randomized tests whose best achievable non-cheating performance is deliberately capped below one. This capped-performance design gives evaluation scores a clearer interpretation: scores substantially above the cap are implausible and therefore provide evidence of cheating. To prevent cheating, we propose CapReward, a reward design based on the CapCode principle to discourage optimization beyond the cap. Experiments across multiple datasets show that CapCode detects cheating while preserving performance ranking of models, and CapReward reduces cheating behavior, yielding models that better follow the intended task specification.

---

### Beyond Backscatter: InSAR coherence from detected SAR images

Authors: Francescopaolo Sica, Andrea Pulella, Michael Schmitt
Published: 2026-06-05
Categories: eess.SP, cs.CV
arXiv: https://arxiv.org/abs/2606.07374v1

In this work, we propose a deep learning framework for coherence regression directly from detected SAR images, without the need for accurate coregistration. A Residual U-Net is trained using coherence maps derived from precisely coregistered Sentinel-1 SLC data to learn the relationship between backscatter magnitudes and coherence. The model is trained on 12-day SLC pairs and evaluated across different datasets, including coregistered SLC products and open access analysis-ready data, covering diverse radiometric properties, geometries, and locations. Experimental results demonstrate that the proposed method achieves high-resolution coherence regression with improved accuracy compared to existing intensity-based approaches. The network generalizes well across diverse geographical locations and even across different temporal baselines that were never seen at training time. Additionally, the ability to operate on globally available analysis-ready data, such as ground range detected data, e.g., distributed through Google Earth Engine, enables its large-scale application in mission design, change monitoring, and diverse mapping tasks.

---

### Mitosis Detection in the Wild: Multi-Tumor and Context-Aware Generalization in the MIDOG 2025 Challenge

Authors: Marc Aubreville, Jonas Ammeling, Sweta Banerjee, Viktoria Weiss, Taryn A. Donovan, Robert Klopfleisch, Jiaqi Lv, Shan E Ahmed Raza, Raphaël Bourgade, Thomas Walter, Yasemin Topuz, Songül Varlı et al.
Published: 2026-06-05
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2606.07368v1

Automated mitosis detection is a well-established task in computational pathology. While previous benchmarks focused on scanner-induced domain shift, clinical "real-world" application requires models to be robust across the vast variance to be expected in the histological landscape. The MItosis DOmain Generalization (MIDOG) 2025 challenge was designed to evaluate algorithmic performance across unprecedented biological and contextual diversity. We curated a test dataset of 365 cases, encompassing 12 distinct human, canine and feline tumor types, digitized across multiple scanning platforms. Moving beyond hand-selected hotspots, the challenge required detection also in random tissue areas (representative of the whole slide detection situation) and challenging areas (areas rich in hard negatives). In the second track, we introduced the classification of atypical mitotic figures (AMFs). There were 18 teams submitting to the detection track, with F1 scores ranging up to 0.740. In the AMF detection track, we had 21 submissions with balanced accuracy values up to 0.908. Our analysis reveals that while most models perform reliably in traditional hotspots, significant performance degradation occurs in challenging ROIs, where false positive rates tripled. Furthermore, performance varied significantly across the 12 tumor types, highlighting "blind spots" in current state-of-the-art architectures when encountering rare or highly pleomorphic malignancies. Moreover, we evaluated the effectiveness of ensembling and found a mean increases of 1.5 and 1.3 percentage points in F1 score and balanced accuracy, respectively. In contrast, TTA showed no relevant improvement. MIDOG 2025 demonstrates that "in the wild" mitosis detection remains a significant hurdle. The transition from hotspot-only evaluation to a multi-contextual framework provides a more realistic proxy for clinical reliability.

---

### Self-evolving LLM agents with in-distribution Optimization

Authors: Yudi Zhang, Meng Fang, Zhenfang Chen, Mykola Pechenizkiy
Published: 2026-06-05
Categories: cs.LG
arXiv: https://arxiv.org/abs/2606.07367v1

Large Language Models (LLMs) have recently emerged as powerful controllers for interactive agents in complex environments, yet training them to perform reliable long-horizon decision making remains a fundamental challenge. A key difficulty lies in credit assignment: agents often receive delayed rewards only at the end of episodes. In this paper, we propose Q-Evolve, a self-evolving framework for LLM agents that unifies automatic process-reward labeling and policy learning within a principled in-distribution reinforcement learning paradigm. In each evolving iteration, our method learns an in-distribution critic from a hybrid off-policy dataset that combines expert demonstrations with agent-generated trajectories, stabilizing Bellman backups in sparse-reward settings via a weighted Implicit Q-Learning objective. The learned value function is then used to derive step-wise process rewards through advantage estimation, enabling dense and reliable supervision without environment backtracking or human annotation. Leveraging these signals, we perform behavior-proximal policy optimization that evolves the agent over the data used for process reward labeling, allowing iterative self-improvement without exacerbating distribution shift. We evaluate our method on AlfWorld, WebShop, and ScienceWorld, showing Q-Evolve outperforms strong baselines in sample efficiency, robustness, and overall task performance. Our results demonstrate that stable agent self-evolution is achievable through the co-evolution of process-level supervision and policy, both grounded within a shared in-distribution learning loop.

---

### Dash2Sim: Closed-Loop Driving Simulation from in-the-wild Dashcam Videos

Authors: Anurag Ghosh, Francesco Pittaluga, Khiem Vuong, Angela Chen, Juan Alvarez-Padilla, Manmohan Chandraker, Srinivasa Narasimhan
Published: 2026-06-05
Categories: cs.CV, cs.LG, cs.RO
arXiv: https://arxiv.org/abs/2606.07366v1

Self-driving simulations typically rely on data collected in a small number of cities or on hand-authored synthetic scenarios. Dashcam videos cover a far broader range of locations and situations, including rare or long-tailed scenarios. They are considered less usable for simulation because it is difficult to recover accurate 4D scenes from monocular in-the-wild videos. Work zones are one such class of long-tailed situations that dashcams capture. We present Dash2Sim, a framework that turns in-the-wild monocular dashcam videos into metric, geo-referenced 4D driving logs compatible with existing simulators, and verifies eachone against an independently maintained map without annotations. We apply Dash2Sim to a large video corpus to create the ROADWork4D benchmark dataset, which spans 4,244 scenes with 2.7M 3D objects across 17 cities. On a verified subset ROADWork4D-CL (2,201 scenes), we study privileged closed-loop planners and find that work zone scenarios are difficult: while rule-based and hybrid planners generalize better than learning-based ones, all fall short, failing to make the lane changes that temporary work zone channels require. Beyond planning, dense depth recovered by Dash2Sim improves novel-view synthesis quality by up to 19% on perceptual metrics, suggesting its potential to provide rich conditioning for closed-loop sensor simulation from monocular videos.

---

### A robust PPG foundation model using multimodal physiological supervision

Authors: Eloy Geenjaar, Vince Calhoun, Scott Daly, Gouthaman KV, Lie Lu, Trisha Mittal, Daniel P. Darcy
Published: 2026-06-05
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2606.07365v1

Photoplethysmography (PPG), a non-invasive measure of changes in blood volume, is widely used in both wearable devices and clinical settings. Recent PPG foundation models either use open-source ICU datasets with pretraining paradigms that require curated data and thus complicate generalization to field-like data, or use closed-source field-like PPG data. In contrast, we propose a PPG foundation model that does not require high-quality or field-like pretraining data, and instead leverages accompanying electrocardiogram and respiratory signals in ICU datasets to select contrastive samples during pretraining. Our approach allows the model to retain and learn from noisy PPG segments, improving robustness at inference. Our model, pretrained on 3x fewer subjects than existing state-of-the-art approaches, achieves performance improvements on 14 out of 15 diverse downstream tasks, including field-like daily activity and heart rate prediction. Our results demonstrate that multimodal supervision can integrate complementary physiological information to improve the robustness of PPG foundation models and enhance their generalization to consumer-grade data.

---

### Breaking the Ice: Analyzing Cold Start Latency in vLLM

Authors: Huzaifa Shaaban Kabakibo, Animesh Trivedi, Lin Wang
Published: 2026-06-05
Categories: cs.LG
arXiv: https://arxiv.org/abs/2606.07362v3

As scalable inference services become popular, the cold start latency of an inference engine becomes important. Today, vLLM has evolved into the de-facto inference engine of choice for many inference workloads. Although popular, due to its complexity and rapid evolution, there has not been a systematic study on the startup latency of its engine. With major architectural innovations under it (e.g., the V1 API, introduction of torch.compile), in this paper, we present the first detailed performance characterization of vLLM startup latency. We break down the startup process into six foundational steps and demonstrate that this process is predominantly CPU-bound. Each step exhibits consistent and interpretable scaling trends with respect to model- and system-level parameters, enabling fine-grained attribution of latency sources. Building on these insights, we develop a lightweight analytical model that accurately predicts vLLM's startup latency for a given hardware configuration, providing actionable guidance for resource planning in large-scale inference environments. All our benchmarking datasets, analysis tools, and prediction scripts are open-sourced at https://github.com/upb-cn/vllm-startup-profiler

---

### Combinatorial Landscape Analysis for Dominating Set and Vertex Coloring

Authors: Johanna Gasse, Antonia Heinen, Felix Knöfel, Timo Kötzing, Maxim Stanko
Published: 2026-06-05
Categories: cs.NE, cs.DM
arXiv: https://arxiv.org/abs/2606.07361v2

We analyze the two combinatorial problems of Dominating Set and Vertex Coloring regarding what kind of local optima are present for various instances. For a variety of graph classes each, we determine whether the induced landscapes are unimodal, plateau-unimodal (all optima are just one plateau), equimodal (all local optima are global) or truly multimodal. We do this for two different neighborhood operators, one based on making only a single change and one also allowing swaps (interchanging two parts of the solution).

---

### DirectAudioEdit: Inversion-Free Text-Guided Audio Editing via Diffusion Prediction Contrast

Authors: Zhengkun Ge, Xiaoqian Liu, Haoran Zhang, Yuan Ge, Junxiang Zhang, Zhengtao Yu, Jingbo Zhu, Tong Xiao
Published: 2026-06-05
Categories: cs.SD, cs.CL
arXiv: https://arxiv.org/abs/2606.07356v1

Text-guided audio editing aims to modify the language-specified acoustic content while preserving edit-irrelevant source components. Existing training-free methods typically rely on inversion-based editing. While inversion-free editing is appealing as it decreases computational overhead and reconstruction errors, it remains largely unexplored for audio editing. The key challenge is to construct a source-to-target editing path through diffusion denoising dynamics. In this paper, we introduce DirectAudioEdit, the first attempt to develop a training-free and inversion-free method for audio editing. Experiments on music and event-level benchmarks across two backbones show that DirectAudioEdit reduces macro-averaged FAD and KL by 15.9% and 15.8% compared with DDPM inversion, while achieving up to 64.5% editing speedup.

---

### Spatial-Temporal Decoupled Adapter for Micro-gesture Online Recognition

Authors: Xucheng Shen, Kun Li, Fei Wang, Wei Qian, Jin Jiang, Dan Guo
Published: 2026-06-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2606.07355v2

Micro-gesture online recognition aims to temporally localize and classify subtle gestures in untrimmed videos. Owing to their extremely short duration, low motion amplitude, and ambiguous visual cues, capturing discriminative spatiotemporal representations remains highly challenging. Existing parameter-efficient adapters typically employ a single branch to model spatial and temporal cues jointly, which may fail to capture the fine-grained patterns of micro-gestures. To address this limitation, we propose a Spatial-Temporal Decoupled Adapter that decomposes video adaptation into independent temporal and spatial branches via lightweight depthwise convolutions. In addition, to alleviate the long-tailed class distribution inherent in the benchmark dataset, we introduce an Adaptive Soft Balanced Augmentation method, which dynamically allocates augmentation intensity based on class rarity and learning difficulty, without manual thresholds. Our method achieves an F1 score of 0.43808, ranking 1st in Track 2 of the 4th EI-MiGA-IJCAI Challenge.

---

### Spatial-Temporal Decoupled Adapter for Micro-gesture Online Recognition

Authors: Xucheng Shen, Kun Li, Fei Wang, Wei Qian, Jin Jiang, Dan Guo
Published: 2026-06-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2606.07355v1

Micro-gesture online recognition aims to temporally localize and classify subtle gestures in untrimmed videos. Owing to their extremely short duration, low motion amplitude, and ambiguous visual cues, capturing discriminative spatiotemporal representations remains highly challenging. Existing parameter-efficient adapters typically employ a single branch to model spatial and temporal cues jointly, which may fail to capture the fine-grained patterns of micro-gestures. To address this limitation, we propose a Spatial-Temporal Decoupled Adapter that decomposes video adaptation into independent temporal and spatial branches via lightweight depthwise convolutions. In addition, to address the long-tail distribution problem in the benchmark dataset, we introduce Adaptive Soft Balanced Augmentation, which dynamically allocates augmentation intensity based on class rarity and learning difficulty, without manual thresholds. Our method achieves an F1 score of 0.43808, ranking 1st in Track 2 of the 4th EI-MiGA-IJCAI Challenge.

---

### SleepExplain: Explainable Non-Rapid Eye Movement and Rapid Eye Movement Sleep Stage Classification from EEG Signal

Authors: Rafsan Jany, Md. Hamjajul Ashmafee, Iqram Hussain, Md Azam Hossain
Published: 2026-06-05
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2606.07351v1

Classification of sleep stages is one of the most important diagnostic approaches for a variety of sleep-related disorders. Electroencephalography (EEG) is regarded as a powerful tool for examining the association between neurological effects and sleep phases since it correctly identifies sleep-related neurological alterations. During Non-Rapid Eye Movement (NREM) and Rapid Eye Movement (REM) sleep phases, a number of nerve and bodily functions are affected and therefore hold an important role both in their functionalities. This work aims to classify NREM and REM sleep stages from sleep EEG data and present a noble SleepExplain model, an explainable NREM and REM sleep stage classification to explain its predictions. In this work, sleep stages were classified using Random Forest, XGBoost, and Gradient Boosting ensemble classification models. Overall, we obtained an accuracy of 92.54% (Random Forest), 94.25% (Gradient Boosting), and 94.30% (XGBoost). For explainable classification model, we utilized a game theoretic approach, SHAP (SHapley Addictive exPlanations) to offer a convincing explanation for the prediction.

---

### TabSwift: An Efficient Tabular Foundation Model with Row-Wise Attention

Authors: Si-Yang Liu, Han-Jia Ye
Published: 2026-06-05
Categories: cs.LG
arXiv: https://arxiv.org/abs/2606.07345v1

Tabular foundation models, exemplified by TabPFN, perform prediction via in-context learning, inferring test labels directly from labeled training examples. They have demonstrated competitive performance, particularly on small-to-medium datasets. However, recent tabular foundation models often improve accuracy with increasingly complex architectures, incurring higher inference cost and limiting practical deployment. In this work, we revisit the original TabPFN design and show that a lightweight row-wise attention-only backbone can remain highly competitive with two simple enhancements: a gated attention stabilization mechanism and a small set of learnable register tokens that provide global context and improve pretraining quality. The resulting model, TabSwift, supports both classification and regression, and is competitive with stronger tabular foundation models (e.g., TabPFN v2 and TabICL) while being more efficient at inference. For latency-sensitive serving, we further introduce an adaptive layer-wise early-exit mechanism that dynamically adjusts inference depth per sample. Overall, TabSwift enables efficient and anytime tabular in-context learning for practical deployments.

---

### LLM-Guided Evolution for Medical Decision Pipelines

Authors: Ivan Sviridov, Artem Oskin, Ivan Panin, Iaroslav Bespalov, Dmitry Dylov, Ivan Oseledets, Aleksandr Nesterov
Published: 2026-06-05
Categories: cs.CL, cs.NE
arXiv: https://arxiv.org/abs/2606.07342v1

Adapting large language models (LLMs) to clinical workflows often requires costly fine-tuning or manual prompt and pipeline engineering. We study LLM-guided MAP-Elites evolution as an inference-time alternative for discovering medical decision strategies and provide an implementation repository at https://github.com/univanxx/llm_guided_evo_medical. We formulate urgency triage, interactive consultation, and medical image classification as evolutionary searches over executable artifacts optimized by task-specific fitness functions. Across all three settings, evolution improves over manually designed baselines under practical constraints. In triage, evolved programs increase Semigran accuracy from $77.3\%$ to $87.1\%$ and emergency recall from $0.60$ to $0.97$, while improving safety-weighted held-out MIMIC-ESI performance. In interactive consultation, evolved policies improve the accuracy--cost frontier across Llama-3, Qwen-3.5, and Gemma-4 and transfer to held-out iCRAFTMD. In PneumoniaMNIST, prompt-only evolution improves frozen MedGemma VLMs while preserving strict JSON outputs. Qualitative analysis shows that the gains come from interpretable program-level mechanisms, calibrated triage boundaries, targeted evidence acquisition, selective commitment, and finding-oriented visual decision rules, rather than superficial prompt rewording alone.

---

### VeriDrive: Verifiable Counterfactual Supervision for Cost-Efficient Vision-Language Planning

Authors: Zikai Zhang, Hubert P. H. Shum, Toby P. Breckon
Published: 2026-06-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2606.07338v2

Vision-language driving models increasingly use reasoning supervision to bridge perception, prediction, and planning, but existing driving rationales are often free-form and expensive to generate with frontier models. We present VeriDrive, a framework for constructing planning-oriented, verifiable counterfactual supervision. VeriDrive converts driving reasoning into a structured Perception-Evaluation-Revision chain that grounds key objects in future motion, evaluates alternative ego trajectories with rule-checkable evidence, revises risky intent toward expert behavior, and produces final planning targets. To scale data construction, VeriDrive combines local generation with validator-guided selective correction, escalating only invalid or difficult samples. We build the VeriDrive dataset on nuScenes and train under the Omni-Q protocol. Controlled open-loop experiments show that VeriDrive improves L2, Collision, and Intersection over OmniDrive while reducing logged token usage, generation time, and actual paid LLM/VLM cost. These results show that auditable intermediate fields and structured revision targets can improve vision-language planning supervision under realistic annotation budgets. Code, prompts, and validator scripts are coming soon and will be released after the review process.

---

### VeriDrive: Verifiable Counterfactual Supervision for Cost-Efficient Vision-Language Planning

Authors: Zikai Zhang, Hubert P. H. Shum, Toby P. Breckon
Published: 2026-06-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2606.07338v1

Vision-language driving models increasingly use reasoning supervision to bridge perception, prediction, and planning, but existing driving rationales are often free-form and expensive to generate with frontier models. We present VeriDrive, a framework for constructing planning-oriented, verifiable counterfactual supervision. VeriDrive converts driving reasoning into a structured Perception-Evaluation-Revision chain that grounds key objects in future motion, evaluates alternative ego trajectories with rule-checkable evidence, revises risky intent toward expert behavior, and produces final planning targets. To scale data construction, VeriDrive combines local generation with validator-guided selective correction, escalating only invalid or difficult samples. We build the VeriDrive dataset on nuScenes and train under the Omni-Q protocol. Controlled open-loop experiments show that VeriDrive improves L2, Collision, and Intersection over OmniDrive while reducing logged token usage, generation time, and actual paid LLM/VLM cost. These results show that auditable intermediate fields and structured revision targets can improve vision-language planning supervision under realistic annotation budgets. Code, prompts, and validator scripts are coming soon and will be released after the review process.

---

### How Far Can Chord-Symbol Time-Series Adaptation Carry Genre Identity? Capabilities and Boundaries in Multi-Genre Chord-Symbol Modeling

Authors: Jinju Lee
Published: 2026-06-05
Categories: cs.SD, cs.LG
arXiv: https://arxiv.org/abs/2606.07334v4

This revision updates an 11-genre chord-symbol adaptation report. The main 165-cell result is unchanged: all methods improve over the frozen pure-pop base, with no decisive method winner. v3 adds the ft-pop80-v2 multi-seed base-restoration note and corrects a few summary statistics for exact CSV faithfulness without changing conclusions.

---

### Varifold Moment Invariants for Sustainable and Explainable Contour Feature Extraction

Authors: G. Longari, J. -C. Alvarez Paiva, A. B. Tumpach
Published: 2026-06-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2606.07333v1

We introduce Varifold Moments Invariants (VMI) as a unifying framework for many previously introduced Moment Invariants. These invariants are deeply related to other contour features that are invariant under translations and rotations, like Extended Gaussian Image, Elliptic Fourier Descriptors or Shape Distributions. The advantage of the varifold approach to moments consists in being able to combine the geometry of the region, its boundary, and the family of lines tangent to it, in order to create a substantial number of invariant features with high discriminating power and clear geometric meaning. By coupling our VMI feature extraction with the light feature classifiers Random Forest or Multi-Layer-Perceptron, we outperform state-of-the-art approaches based on contours, while decreasing drastically the computational cost to the point of allowing our algorithm to run on light devices. We tested our approach on classification tasks on a large number of widely-used datasets of various types (leaves, objects, cells) and achieved high accuracy with a low number of geometrically interpretable features.

---

### AnchorWorld: Embodied Egocentric World Simulation with View-based Evolution Customization

Authors: Yu Li, Menghan Xia, Gongye Liu, Xintao Wang, Conglang Zhang, Lei Ke, Yuxuan Lin, Ruihang Chu, Pengfei Wan, Kun Gai, Yujiu Yang
Published: 2026-06-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2606.07326v1

Despite being a pivotal frontier, interactive world modeling remains underexplored in terms of the versatile controllability required by practical scenarios. To bridge this gap, we present AnchorWorld, a framework that advances egocentric simulation through enhanced interaction integrity and a flexible mechanism for world customization. First, we utilize 3D human motion as the primary interaction modality. To complement the out-of-view or truncated body parts in egocentric views, we introduce an auxiliary training supervision that incorporates exogenous viewpoints decoupled from the agent's first-person sensorium. It allows the model to observe the agent's full-body positioning relative to the environment, facilitating a more robust spatial grounding of human-world interactions. Furthermore, we propose a simple yet effective mechanism for customizing self-evolving worlds. This is achieved by defining anchor views within a unified world coordinate system, coupled with textual descriptions dictating the dynamic evolution of local scenes. Experimental results show that AnchorWorld significantly outperforms state-of-the-art baselines, while ablation studies validate the effectiveness of our key designs. Notably, our customization scheme exhibits promising spatio-temporal geometric consistency and adheres strictly to the prescribed evolutionary dynamics.

---

### A Temporal Spatial Minimax Rate for Smoothly-Varying Distributions in Wasserstein Space

Authors: Munsik Kim
Published: 2026-06-05
Categories: math.ST, cs.AI, cs.IT
arXiv: https://arxiv.org/abs/2606.07325v1

We study the minimax rate of estimating a future value $μ_{t_n+h}$ of a curve $t\mapstoμ_t$ in the $2$-Wasserstein space $\mathcal{P}_2(\mathbb{R}^d)$ from finitely many noisy snapshots of its past, under an adiabatic bound $\|\nabla_t^k v\|\le\varepsilon$ on the $k$-th covariant derivative of the velocity field. Our central result is a unified temporal-spatial minimax lower bound: over regular, locally transport-rich subclasses, every estimator incurs $W_2$-risk with $M$-exponent $γ_d(k+1)/(k+1+γ_d)$, $γ_d=\min(1/d,1/2)$ ($M$ the total sample size). It follows from a temporal-to-spatial reduction: the smoothness budget defines a reachable $W_2$-ball into which a transport packing is embedded along the time axis, and the information of the entire snapshot experiment is controlled by a Fano argument -- the spatial packing is classical, but its smoothness-admissible temporal embedding and the full-window analysis are new. The bound interpolates a dimension-free extrapolation floor of order $\varepsilon h^{k+1}$ -- the irreducible cost of an unobserved future, present even with the exact past -- and the spatial estimation curse $M^{-γ_d}$, recovering the static distribution-estimation rate as $k\to\infty$. We state the lower bound in a design-dependent form -- with a design-weighted effective sample size -- valid for arbitrary observation times, and obtain the closed-form exponent in the dense (equispaced) regime. The matching upper bound is established at $k=0$ (rate $M^{-1/(d+1)}$, $d\ge3$) and, in a translation submodel, for all $k$; for $k\ge1$ a covariant estimator attains the rate conditionally on two estimates (a comparison-geometry bias bound and an optimal-transport map-estimation rate), leaving the unconditional general-$k$ upper bound as an open problem. Numerical experiments on synthetic curved and flat families corroborate the predicted exponents.

---

### Certifiable Semantic Agreement Among LLM Agents: What the Admissibility Instrument Decides

Authors: Haoran Xu, Lei Zhang, Iadh Ounis, Xianbin Wang
Published: 2026-06-05
Categories: cs.MA, cs.AI, cs.DC
arXiv: https://arxiv.org/abs/2606.07316v2

Can a committee of LLM agents reach agreement that is certifiable at the level of meaning, not only at the level of a label? We build a protocol to find out. H-CSC emits one of three typed outcomes per round -- semantic commit, verdict commit, or typed abort -- under a common 2f+1 distinct-signer certificate, and we use it to measure what such agreement costs and buys. The answer is conditional, and the condition is not the protocol. We prove a containment lemma: whenever the semantic core is large enough to make the committed verdict deterministically valid, the verdict margin already exceeds f, so at matched deterministic guarantees no coverage separation from certificate-wrapped majority is possible. Measurement agrees: the two rules commit the identical task set. What matters instead is the admissibility instrument. Against adversaries that preserve the verdict and corrupt only the reasoning, a 442 MB fine-tuned encoder reaches AUROC 0.621-0.744 at 0-8% TPR (5% honest FPR), while a training-free lexical predicate reaches 0.865-0.982 at 38-80% (50 tasks, 200 attacks, 400 honest) and is exactly deterministic, discharging an assumption the digest proofs rely on. Honest agents disperse further than attacks displace (90th-percentile honest angular distance 0.992 rad against a 0.65 radius), so on free-text rationales no embedding filter is viable -- a property of the output schema, which when tightened collapses dispersion twenty-fold. The committed digest is not inert: under non-disclosure a similarity-preserving sketch separates faithful from substituted derived statements at AUROC 0.741 (n=350), where a cryptographic hash and a verdict-only digest score exactly 0.500. We also report a tie-break capture vulnerability found in our own protocol, and its four-line fix. We claim no safety or coverage advantage over verdict-only certification; the lemma explains why there is none to claim.

---

### Hierarchical Certified Semantic Commitment for Byzantine-Resilient LLM-Agent Collaboration

Authors: Haoran Xu, Lei Zhang, Iadh Ounis, Xianbin Wang
Published: 2026-06-05
Categories: cs.MA, cs.AI, cs.DC
arXiv: https://arxiv.org/abs/2606.07316v1

Byzantine collaboration among large-language-model agents requires a finality-control primitive: given delivered stochastic, structured natural-language proposals, the protocol must decide whether the round supports a commit, what kind of commit, or a typed safe abort. Naive aggregation hides this choice behind a single verdict; classical Byzantine fault tolerance hides it behind byte-identity that LLM proposals do not satisfy. We introduce Hierarchical Certified Semantic Commitment (H-CSC), a BFT-inspired protocol that converts embedding-derived finality signals over verdict-conditioned proposal groups into one of three typed outcomes: a semantic_commit (a 2f+1 within-verdict semantic core backs the verdict, emitting a parameter-bound digest over the quantised aggregate), a verdict_commit (strong verdict margin but dispersed semantic rationale, emitting a verdict-level certificate without claiming a semantic aggregate), or an explicit abort with a typed reason. The contribution is typed finality, not raw commit accuracy. On a controlled semantic-poisoning diagnostic (BCS_v1, 120 episodes), H-CSC commits with low angular deviation on BFT-feasible buckets (0.31 to 2.04 degrees) and aborts 100% of beyond-BFT rounds (n<3f+1) as intended. On a real LLM-agent claim-verification benchmark (MVR-50, 50 tasks) under paired static and rushing Byzantine attacks, H-CSC commits 0.90/0.92 with honest-reference-invalid rates of 0.02/0.00, statistically matching a strong certificate-emitting verdict-only baseline. Unlike that baseline, H-CSC also emits an embedding-backed semantic_commit digest on 74%/72% of rounds, supplying typed provenance. A strict-semantic ablation commits only 0.54/0.48, showing the verdict-level fallback is necessary for coverage (+0.36/+0.44) at the same <=0.04 safety floor; a 100-task cross-model check across four LLMs preserves invalid_hmaj within 0.00 to 0.03.

---

### SV-Detect: AI-generated Text Detection with Steering Vectors

Authors: Mikhail Vishnyakov, Tatiana Gaintseva
Published: 2026-06-05
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2606.07313v2

Detecting AI-generated text is especially difficult under distribution shift, such as transfer across domains, source models, and editing attacks. We propose an AI-generated text detector based on steering vectors extracted from the hidden representations of a frozen language model. At each layer, we construct a direction that separates human-written from AI-generated text, and represent each input by its layer-wise alignment with these directions. A lightweight classifier trained on these projection features yields the final detection score. Our method achieves strong performance both in-distribution and under distribution shift, including across domains, source models, and machine-editing transformations such as polishing and rewriting. Interpretation analyses show that the learned directions align with recognizable stylistic cues while capturing substantial additional signal beyond surface features. These results position AI-generated text detection as a representation-space probing problem and show that steering vectors provide a simple and effective solution.

---

### SV-Detect: AI-generated Text Detection with Steering Vectors

Authors: Mikhail Vishnyakov, Tatiana Gaintseva
Published: 2026-06-05
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2606.07313v1

Detecting machine-generated text is especially difficult under distribution shift, such as transfer across domains, source models, and editing attacks. We propose a fake-text detector based on steering vectors extracted from the hidden representations of a frozen language model. At each layer, we construct a direction that separates human-written from machine-generated text, and represent each input by its layer-wise alignment with these directions. A lightweight classifier trained on these projection features yields the final detection score. Our method achieves strong performance both in-distribution and under distribution shift, including across domains, source models, and machine-editing transformations such as polishing and rewriting. Interpretation analyses show that the learned directions align with recognizable stylistic cues while capturing substantial additional signal beyond surface features. These results position fake-text detection as a representation-space probing problem and show that steering vectors provide a simple and effective solution.

---

### CultureScore: Evaluating Cultural Faithfulness in Video Generation Models

Authors: Anku Rani, Wei Dai, Shravan Nayak, Pattie Maes, Mahdi M. Kalayeh, Paul Pu Liang
Published: 2026-06-05
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2606.07311v2

As video generation models like Veo 3.1 and LTX-2 advance, their ability to accurately represent diverse global cultures remains a critical yet understudied frontier. Current metrics, such as VideoScore, only measure visual quality but offer no mechanism for assessing cultural faithfulness. Consequently, a model that replaces a Namaste with a handshake receives the same score as one that generates the gesture correctly. We propose CultureScore, a compositional evaluation framework that decomposes cultural faithfulness into three granular dimensions: Identity (who is represented), Context (culturally localized background), and Behavior (normative gestures and interactions). We operationalize this framework through an evaluation suite spanning 10 countries, yielding 6,174 generated videos across three state-of-the-art models. Our evaluation reveals that no current model achieves culturally faithful video generation: the best-performing model reaches only 56.8\% overall CultureScore, with Behavior the most challenging dimension, which remains below 52.1\% across all models. Furthermore, human preference rankings align directionally with CultureScore but are inverted relative to VideoScore; the highest-scoring model on visual quality was ranked last by annotators, underscoring that cultural faithfulness is an essential criterion for equitable video generation. Data and code are available at https://huggingface.co/datasets/ankurani/CultureScore.

---

### Acoustic Cue Alignment in Audio Language Models for Speech Emotion Recognition

Authors: Iosif Tsangko, Andreas Triantafyllopoulos, Björn W. Schuller
Published: 2026-06-05
Categories: cs.SD, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2606.07309v1

Instruction-following audio language models (ALMs) can be augmented with explicit acoustic cues, yet it remains unclear whether such cues are used in a grounded way when the raw audio is already available. We study this question in speech emotion recognition (SER) by deriving six interpretable acoustic concept tokens from the standardised eGeMAPS paralinguistic feature set. These tokens summarise energy, pitch, dynamics, brightness, formants, and voice quality, and are appended to the textual prompt while the audio input is kept unchanged. Across the widely used FAU-Aibo and IEMOCAP benchmarks, aligned tokens improve unweighted average recall (UAR), whereas shuffled, conflicting, or corrupted tokens reduce performance relative to aligned tokens and shift confusions toward neutral. Importantly, predictions do not collapse under strong token perturbations, suggesting that the models are sensitive to the symbolic cue channel but remain partly anchored to the audio signal. We argue that token-only interventions provide a practical way to probe audio-grounded cue use, robustness, and interpretability in ALM-based affective computing.

---

### Off-Policy Evaluation with Strategic Agents via Local Disclosure

Authors: Kiet Q. H. Vo, Abbavaram Gowtham Reddy, Julian Rodemann, Siu Lun Chau, Krikamol Muandet
Published: 2026-06-05
Categories: cs.AI
arXiv: https://arxiv.org/abs/2606.07308v1

We study off-policy evaluation (OPE) under strategic behavior where decision subjects (or agents) respond to a decision maker's policy by strategically modifying their covariates. Such behavior induces a policy-dependent covariate shift, breaking the standard assumption in existing methods that covariates are exogenous to the policy. Related work addresses this challenge by imposing strong assumptions such as repeated interactions or full knowledge of agents' response behavior, substantially limiting its applicability to OPE. In contrast, we consider a one-shot OPE setting where the decision maker has only partial knowledge of the agents' response behavior. Our key insight is that disclosing local information through post-hoc explanations reveals agents' pre-strategic covariates prior to adaptation, mitigating the information loss induced by strategic behavior. Leveraging this structure, we estimate a statistical model for the agents' responses and construct a doubly robust estimator for policy value. By assuming that the agents' cost sensitivity follows a conditional log-normal distribution, we establish consistency of the proposed estimator and validate our approach empirically. More broadly, our results highlight how interaction design can mitigate information asymmetry by revealing otherwise hidden structure in agents' strategic responses.

---

### Bootstrap Theory of Representational Emergence (TBER): Explanatory Insufficiency, Transition Regimes, and the Emergence of New Representational Levels

Authors: Jacques Raynal, Pierre Slangen, Elsa Raynal, Jacques Margerit
Published: 2026-06-05
Categories: cs.LG
arXiv: https://arxiv.org/abs/2606.07303v4

Representation learning is central to modern machine learning, yet most research focuses on optimizing representations after a framework has been selected. The Bootstrap Theory of Representational Emergence (TBER) addresses a prior question: when does a new representational level become necessary? Version 4 identifies explanatory insufficiency as a positive epistemic signal for representational transition. A representation may remain useful while becoming unable to make relevant relations, transformations, distinctions, or organizational properties intelligible. TBER distinguishes two dimensions. Explanatory insufficiency may be descriptive, transformational, or related to generalization. The resulting response may belong to a local-corrective, representationally resolutive, or structurally recurrent regime. The bootstrap process is recursive: stabilized representations enable observation; anomalies expose persistent insufficiencies; candidate re-representations are generated; discriminating tests constrain them; surviving representations undergo provisional stabilization and closure assessment. Formal cases such as Kaprekar's routine and Gödelian incompleteness are used only as boundary examples of distinct transition regimes, not as proofs of TBER or models of physical or biological dynamics. The framework concerns transitions between scientific, mathematical, or computational representations. It has implications for representation learning, latent spaces, foundation models, world models, adaptive biological systems, scientific discovery, and autonomous AI. TBER suggests that future intelligent systems should not only learn representations, but also diagnose their limits, determine when re-representation is warranted, test alternatives, and recognize whether a limitation is locally resolved or structurally recurrent.

---

### Bootstrap Theory of Representational Emergence: Explanatory Insufficiency as a Driver of Representation Learning and World Models

Authors: Jacques Raynal, Pierre Slangen, Elsa Raynal, Jacques Margerit
Published: 2026-06-05
Categories: cs.LG
arXiv: https://arxiv.org/abs/2606.07303v2

Representation learning is central to modern machine learning, but most research examines how representations are optimized after a framework has been selected. Less attention is given to when a new representational level becomes necessary. This article introduces the Bootstrap Theory of Representational Emergence (TBER), an initial conceptual theory and research program describing how new representations arise when existing ones become explanatorily insufficient. A representation may remain descriptively useful while failing to make certain observations, relations, transformations, or organizational properties intelligible. TBER treats this explanatory insufficiency as a positive signal for representational transition rather than as simple falsification or prediction error. The proposed recursive process follows five stages: stabilized observation, anomaly detection, recognition of explanatory insufficiency, representational emergence, and provisional stabilization. The framework concerns transitions between scientific or computational representations, not equivalent transitions within the physical systems being observed. Its scope includes representation learning, latent spaces, foundation models, world models, digital twins, adaptive biological systems, and scientific discovery. TBER does not propose a new algorithm, model architecture, benchmark, or optimization procedure. Its contribution is meta-representational: it provides a framework for interpreting when and why new representational levels become necessary. A possible implication for future artificial intelligence is the development of systems able to detect when their own internal representations have reached explanatory limits and to initiate representational refinement or transition.

---

### Phun-Bench: Evaluating LLMs on Phonological Understanding in Chinese

Authors: Xing Yue, Yongliang Shen, Weiming Lu
Published: 2026-06-05
Categories: cs.CL
arXiv: https://arxiv.org/abs/2606.07300v1

Language is a vehicle for thought, intricately tied to sounds, symbols, and meaning. However, most large language model (LLM) research focuses on meaning (semantics) and symbols (spelling) while largely overlooking sounds. Existing benchmarks on LLMs' phonological abilities are either solvable through rote memorization or intertwined with other abilities, making them inadequate to measure LLMs' genuine ability in phonological understanding. Here, we present Phun-Bench, a purpose-built Chinese benchmark with diverse tasks and settings across three dimensions (Homophony, Rhyme, and Phonetic Similarity), designed to systematically evaluate LLMs' phonological understanding. Our results show that while LLMs excel at recalling correct pronunciations, they generally struggle to leverage phonological knowledge in the flexible and intuitive way that human speakers do. Moreover, through detailed analyses, we propose a hypothesis regarding the underlying mechanism of LLMs' phonological understanding and "perception", highlighting an underexplored frontier for future research.

---

### DuMate-DeepResearch: An Auditable Multi-Agent System with Recursive Search and Rubric-Grounded Reasoning

Authors: Lingyong Yan, Can Xu, Yukun Zhao, Wenxuan Li, Qingyang Chen, Jiulong Wu, Wenli Song, Xiangnan Li, Weixian Shi, Yiqun Chen, Xuchen Ma, Yuchen Li et al.
Published: 2026-06-05
Categories: cs.AI
arXiv: https://arxiv.org/abs/2606.07299v1

Deep Research (DR) has emerged as a new agentic paradigm to tackle complex, open-ended research tasks, demanding systems that can iteratively frame problems, acquire evidence, verify sources, and synthesize long-form reports. In practice, however, current DR systems are constrained by four interrelated limitations: long-horizon planning over an underspecified scope, the bottleneck of decomposing and scheduling such tasks within a single agent, hallucination risk in long-form synthesis, and limited process auditability. This technical report presents DuMate-DeepResearch, a multi-agent DR framework built on the Qianfan Agent Foundry. The framework decouples the Agent Core, which handles task understanding, planning, and scheduling, from an extensible Tool Ecosystem for retrieval, evidence acquisition, and report rendering, making every intermediate decision and tool invocation explicitly traceable. Building on this infrastructure, DuMate-DeepResearch further introduces three mechanisms: (i) a graph-based dynamic planning strategy expands the research roadmap coarse-to-fine and continuously revises it through reflection, re-planning, backtracking, and parallel branching; (ii) a recursive two-level execution design delegates each complex search sub-task to an inner Search Agent that runs its own planning loop, isolating noisy retrieval and stabilizing long-horizon execution; (iii) a rubric-based test-time optimization mechanism dynamically generates task-specific quality criteria and uses them as live reasoning scaffolds for evidence-grounded synthesis and adaptive stopping. Across two deep research benchmarks, DuMate-DeepResearch establishes new state-of-the-art results: the best overall score (58.03%) on DeepResearch Bench, and the best overall score (61.95%) on DeepResearch Bench II while ranking first in information recall and analysis.

---

### SWE-Explore: Benchmarking How Coding Agents Explore Repositories

Authors: Shaoqiu Zhang, Yuhang Wang, Jialiang Liang, Yuling Shi, Wenhao Zeng, Maoquan Wang, Shilin He, Ningyuan Xu, Siyu Ye, Kai Cai, Xiaodong Gu
Published: 2026-06-05
Categories: cs.SE, cs.CL
arXiv: https://arxiv.org/abs/2606.07297v1

Repository-level coding benchmarks such as SWE-bench have driven a rapid surge in the capabilities of coding agents. Yet they usually treat coding tasks as a holistic, binary prediction problem (e.g., resolved or unresolved), neglecting fine-grained agent capabilities such as repository understanding, context retrieval, code localization, and bug diagnosis. In this paper, we introduce SWE-Explore, a benchmark that isolates the evaluation of repository exploration, a critical capability of coding agents. Given a repository and an issue, SWE-Explore asks an explorer to return a ranked list of relevant code regions under a fixed line budget. SWE-Explore covers 848 issues across 10 programming languages and 203 open-source repositories. For each instance, we derive line-level ground truth from independent agent trajectories that successfully solved the same issue, distilling the specific code regions their solution paths actually consulted. We evaluate exploration along coverage, ranking, and context-efficiency dimensions, showing that these metrics strongly track downstream repair behavior. Across a broad set of retrieval methods, general coding agents, and specialized localizers, we find that agentic explorers form a clear tier above classical retrieval. While file-level localization is already strong for modern methods, line-level coverage and efficient ranking remain the key axes differentiating state-of-the-art explorers.

---

### TargetSEC: Plug-and-Play In-the-Wild Speech Emotion Conversion via Arousal-Conditioned Latent Style Diffusion

Authors: Constantin Alexander Auga
Published: 2026-06-05
Categories: cs.SD, cs.LG
arXiv: https://arxiv.org/abs/2606.07293v2

Speech Emotion Conversion (SEC) aims to transform the emotion of a source utterance into a target emotion while preserving content and speaker identity. SEC on in-the-wild data is challenging due to the non-parallel nature of training data and complex real-world acoustics. Existing fixed-duration approaches either struggle to shift the emotion effectively (high quality, low conversion) or degrade speech naturalness (low quality, high conversion). We propose TargetSEC, an embedding-driven latent diffusion framework that generates emotion-focused style embeddings conditioned on speaker identity and continuous emotion. Unlike methods that diffuse over spectrograms, TargetSEC operates in a compact latent space. Experiments on the MSP-Podcast dataset show that TargetSEC outperforms current non-duration baselines and matches or exceeds the duration-prediction baseline in conversion MSE and naturalness without explicit temporal modeling.

---

### TargetSEC: Plug-and-Play In-the-Wild Speech Emotion Conversion via Arousal-Conditioned Latent Style Diffusion

Authors: Constantin Alexander Auga
Published: 2026-06-05
Categories: cs.SD, cs.LG
arXiv: https://arxiv.org/abs/2606.07293v1

Speech Emotion Conversion (SEC) aims to transform the emotion of a source utterance into a target emotion while preserving content and speaker identity. SEC on in-the-wild data is challenging due to the non-parallel nature of training data and complex real-world acoustics. Existing fixed-duration approaches either struggle to shift the emotion effectively (high quality, low conversion) or degrade speech naturalness (low quality, high conversion). We propose TargetSEC, an embedding-driven latent diffusion framework that generates emotion-focused style embeddings conditioned on speaker identity and continuous emotion. Unlike methods that diffuse over spectrograms, TargetSEC operates in a compact latent space. Experiments on the MSP-Podcast dataset show that TargetSEC outperforms current non-duration baselines in conversion accuracy while maintaining high speech quality, and achieves performance comparable to duration-prediction systems without explicit temporal modeling.

---

### Trio: Learning Time-Series Forecasting with Temporal-Spatial-Sample Attention and Structural Causal Priors

Authors: Tao Chen, Yexu Zhou, Zhi Gong, Hengwei He, Hongda Li, Zhewei Chen, Dongjing Wang, Xin Zhang, Decheng Liu, Chunlei Peng, Zheng Chen, Wenyue Ding
Published: 2026-06-05
Categories: cs.LG
arXiv: https://arxiv.org/abs/2606.07291v1

Multivariate time-series forecasting requires models to reason over temporal dynamics, cross-variable dependencies, and historical input-output correspondences. Recent Prior-Data Fitted Networks (PFNs) suggest that synthetic tasks can be useful for learning transferable inference behavior. However, directly transferring this paradigm to time-series forecasting remains difficult, since temporal order, dynamic lags, and recurring historical patterns are not naturally captured by ordinary tabular priors. Motivated by this observation, we propose Trio, a sample-aware time-series forecasting architecture based on Temporal-Spatial-Sample attention. Temporal attention captures within-window dynamics, spatial attention models inter-variable dependencies, and sample attention retrieves relevant historical lookback-future pairs to guide the current prediction. Rather than claiming a fully general PFN-style forecaster, our goal is to study how historical input-output examples can be explicitly organized and reused within a forecasting model. We further introduce a Time-Series Structural Causal Model (TS-SCM) generator to create structured synthetic forecasting tasks with dynamic lags, cross-variable interactions, noise, feedback, and distributional drift. Experiments on synthetic, industrial, and public benchmarks show that the proposed architecture improves forecasting performance. Exploratory zero-shot experiments further suggest that TS-SCM-generated tasks may provide useful structural priors, while fully general PFN-style time-series forecasting remains an open problem.

---

### Closed-Form Spectral Regularization for Multi-Task Model Merging

Authors: Yongxian Wei, Runxi Cheng, Xingxuan Zhang, Li Shen, Chun Yuan, Peng Cui, Dacheng Tao
Published: 2026-06-05
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2606.07289v1

Model merging combines several independently fine-tuned experts into a single multi-task model without any training data, reducing the storage, serving, and decentralized-development costs of large foundation models. State-of-the-art merging methods formulate merging as a layer-wise quadratic interference minimization problem. Although this problem admits an exact closed-form pseudoinverse solution, that solution underperforms hundreds of iterations of gradient descent in practice. The iterative loop dominates the cost of the pipeline, yet its effectiveness has remained unexplained. We revisit this regime and show that the iterative solver does not primarily act as an optimizer; rather, it serves as an implicit spectral regularizer for an ill-posed normal equation, where small-eigenvalue directions of the per-layer interference operator amplify proxy noise. Building on this finding, we formalize multi-task model merging as a noisy linear inverse problem and propose a spectral filtering estimator parameterized by a per-direction filter. We instantiate this estimator with SWUDI, a closed-form method that combines a soft exponential filter, which matches the gradient-flow trajectory of iterative descent, with a hard top-K truncation that suppresses noise-amplifying small-eigenvalue directions. Furthermore, we propose SWUDI-A, an adaptive variant that replaces the global rank hyperparameter with per-layer rank rules, further improving robustness across architectures. Both variants share a single symmetric eigendecomposition per linear layer and require no training data or optimizer state. Across four general benchmarks and a multimodal merging benchmark spanning VQA, Geometry, Chart, OCR, Grounding, and modality merging, our proposed spectral solvers match or outperform state-of-the-art merging methods. Crucially, they reduce wall-clock time by 28-72x and peak GPU memory by up to 50%.

---

### ExMesh: Explicit Mesh Reconstruction with Topology Adaptation

Authors: Chuanjin Fan, Lifan Wu, Wenjie Chang, Hanzhi Chang, Wenfei Yang, Tianzhu Zhang
Published: 2026-06-05
Categories: cs.CV, cs.GR
arXiv: https://arxiv.org/abs/2606.07288v2

Reconstructing surface meshes from multi-view images has remained a core challenge in recent years. Most existing methods, whether implicit or explicit, depend on intermediate representations and post-processing steps like Marching Cubes or TSDF fusion, often resulting in artifacts and fragmented geometry. Directly optimizing explicit meshes is a promising approach. However, it presents two critical challenges. The first is how to adaptively refine mesh topology to capture detail without introducing degenerate faces. The second is how to maintain consistent UV coordinates for high-fidelity texturing as the mesh structure evolves. To overcome these, we propose ExMesh, a novel framework that directly optimizes explicit meshes by integrating differentiable optimization with discrete topology updates. Specifically, we introduce an adaptive vertex splitting and merging strategy, along with real-time UV maintenance, to enable coarse-to-fine optimization while preserving geometric integrity. To our knowledge, ExMesh is the first framework to seamlessly integrate discrete topology operations into a continuous differentiable optimization pipeline. Extensive experiments demonstrate that ExMesh achieves a balance among accuracy, computational efficiency, and mesh conciseness.

---

### ExMesh: EXplicit Mesh Reconstruction with Topology Adaptation

Authors: Chuanjin Fan, Lifan Wu, Wenjie Chang, Hanzhi Chang, Wenfei Yang, Tianzhu Zhang
Published: 2026-06-05
Categories: cs.CV, cs.GR
arXiv: https://arxiv.org/abs/2606.07288v1

Reconstructing surface meshes from multi-view images has remained a core challenge in recent years. Most existing methods, whether implicit or explicit, depend on intermediate representations and post-processing steps like Marching Cubes or TSDF fusion, often resulting in artifacts and fragmented geometry. Directly optimizing explicit meshes is a promising approach. However, it presents two critical challenges. The first is how to adaptively refine mesh topology to capture detail without introducing degenerate faces. The second is how to maintain consistent UV coordinates for high-fidelity texturing as the mesh structure evolves. To overcome these, we propose ExMesh, a novel framework that directly optimizes explicit meshes by integrating differentiable optimization with discrete topology updates. Specifically, we introduce an adaptive vertex splitting and merging strategy, along with real-time UV maintenance, to enable coarse-to-fine optimization while preserving geometric integrity. To our knowledge, ExMesh is the first framework to seamlessly integrate discrete topology operations into a continuous differentiable optimization pipeline. Extensive experiments demonstrate that ExMesh achieves a balance among accuracy, computational efficiency, and mesh conciseness.

---