Explore the Frontier of Global Academia

01.

Nature Medicine 2026-06-16 DOI: HASH:edbae12e3ec07aa7c5281d604edc9274

<b>Engineered heart muscle passes early clinical milestone</b>

Authors:

Karen O’Leary↗

Engineered heart muscle allografts derived from induced pluripotent stem cells show promising early outcomes in patients with treatment-refractory advanced heart failure with reduced left ventricular ejection fraction, in support of further clinical investigation. Engineered heart muscle allografts derived from induced pluripotent stem cells show promising early outcomes in patients with treatment-refractory advanced heart failure with reduced left ventricular ejection fraction, in support of further clinical investigation.

Read & Discuss → View Source →

02.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2601.22970

Stabilizing the Q-Gradient Field for Policy Smoothness in Actor-Critic Methods

Authors:

Jeong Woon Lee↗Kyoleen Kwak↗Daeho Kim↗Hyoseok Hwang↗

arXiv:2601.22970v2 Announce Type: replace-cross Abstract: Policies learned via continuous actor-critic methods often exhibit erratic, high-frequency oscillations, making them unsuitable for physical deployment. Current approaches attempt to enforce smoothness by directly regularizing the policy's output. We argue that this approach treats the symptom rather than the cause. In this work, we theoretically establish that policy non-smoothness is fundamentally governed by the differential geometry of the critic. By applying implicit differentiation to the actor-critic objective, we prove that the sensitivity of the optimal policy is bounded by the ratio of the Q-function's mixed-partial derivative (noise sensitivity) to its action-space curvature (signal distinctness). To empirically validate this theoretical insight, we introduce PAVE (Policy-Aware Value-field Equalization), a critic-centric regularization framework that treats the critic as a scalar field and stabilizes its induced action-gradient field. PAVE rectifies the learning signal by minimizing the Q-gradient volatility while preserving local curvature. Experimental results demonstrate that PAVE achieves smoothness comparable to policy-side smoothness regularization methods, while maintaining competitive task performance, without modifying the actor.

Read & Discuss → View Source →

03.

arXiv (CS.CL) 2026-06-17 DOI: arXiv:2606.08810

Continuous Language Diffusion as a Decoder-Interface Problem

Authors:

Zhicheng Du↗Lan Ma↗

Gaussian-corrupted sentence embeddings have no direct linguistic interpretation, yet continuous diffusion language models can generate fluent text from them. We study this puzzle through Embedded Language Flows (ELF) and identify a decoder-basin mechanism: our evidence suggests that denoising becomes reliable when trajectories reach regions where the native decoder can read stable tokens. We introduce a diagnostic protocol for denoisability, semantic recoverability, order sensitivity, decoder compatibility, and trajectory reliability. It exposes failures hidden by scalar metrics: low mean-squared error can discard linguistic content, low perplexity can reflect low-entropy collapse, and clean latent reconstruction can coexist with a narrow decoder basin. A decoder-margin bound explains why token recovery depends on margin and local decoder sensitivity, not latent error alone. Auditing public ELF checkpoints reveals an interface phase diagram: early predictions are weakly readable, mid-trajectory disagreement marks a competition region, and late predictions enter a high-margin decoder basin. Once inside, token realization is surprisingly simple on generated ELF states: frozen T5 (Text-to-Text Transfer Transformer) token-embedding lookup recovers $93$–$96\%$ of native decoder decisions, and a single linear readout reaches $97.9\%$ agreement at 32k samples, leaving an $\approx1.1$–$1.2$ perplexity gap in a structured residual tail. Under conservative held-out gates, a margin rule exits roughly $17$–$28\%$ earlier in denoising steps under an explicit diagnostic monitor. Boundary checks on LangFlow, BitstreamDiffusion, and the Continuous Latent Diffusion Language Model (Cola-DLM) show that the same interface questions remain meaningful when the state object and decoder change. Continuous and latent diffusion language models should therefore be evaluated as representation-decoder systems.

Read & Discuss → View Source →

04.

arXiv (quant-ph) 2026-06-16 DOI: arXiv:2606.16784

Quantum Nonlocal Games on Graph Ensembles

Authors:

Joshua Tucker↗Chris Weeks↗Peter Drmota↗Ellis M. Ainley↗Ayush Agrawal↗Adam R. Martinez↗Erin Malinowski↗Jacob A. Blackmore↗David P. Nadlinger↗Gabriel Araneda↗David M. Lucas↗Carlos A. Perez-Delgado↗…

arXiv:2606.16784v1 Announce Type: new Abstract: Quantum entanglement is one of the most striking discoveries in all of science. This effect allows, for instance, two spatially separated agents to coordinate their actions, without communication, to an extent that is both counter-intuitive, and provably impossible by any other physical means. A recently discovered example is that of mobile agents (players) performing spatial coordination tasks such as rendezvous, where the agents aim to meet on a network without communication. Until now, demonstrations of this advantage have relied on highly idealized conditions: agents are assumed to have complete knowledge of the topography, and experiments have been restricted to simulations using data generated by qubits within a single quantum processor. Here we address both limitations by developing a theory for graph ensembles that capture topographical uncertainty and by experimentally demonstrating the advantage in rendezvous scenarios between physically separated ion-trap systems with access to remote entanglement. Moreover, we simulate a broader set of problems on superconducting hardware. Surprisingly, when players are given the ability to gather more local information the quantum advantage increases – a feat impossible by classical means. Our findings establish a concrete route toward practical quantum advantages in motion coordination problems. More broadly, they point to a new way of using portable quantum devices to enhance collective decision-making in uncertain environments.

Read & Discuss → View Source →

05.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.20523

SARLO-80: Worldwide Slant SAR Language Optic Dataset 80cm

Authors:

Sol\`ene Debuys\`ere↗Nicolas Trouv\'e↗Nathan Letheule↗Elise Colin↗Georgia Channing↗

arXiv:2606.20523v1 Announce Type: cross Abstract: Multimodal foundation models have advanced rapidly thanks to large optical benchmarks, but comparable resources for synthetic aperture radar (SAR) remain limited. Existing SAR–optical datasets largely rely on low-resolution, intensity-only Ground Range Detected~(GRD) products and do not preserve complex-valued SAR measurements or native acquisition geometry, which restricts physically grounded multimodal learning. In particular, large-scale public datasets combining very-high-resolution (VHR) SAR SLC, aligned optical imagery, and natural-language descriptions are still lacking. We present a VHR SAR–optical–text dataset built from open-access Umbra spotlight acquisitions distributed as Sensor Independent Complex Data (SICD). From around 2,500 worldwide scenes (VV/HH, 20cm–2m native resolution), we standardize all SAR data to an 80cm slant-range grid via band-limited FFT resampling and tile the imagery into 1024 by 1024 patches. For each SAR patch, we retrieve a high-resolution optical tile and warp it into the SAR grid using local coordinate correspondences for local pixel-level alignment. We further generate three caption variants (SHORT/MID/LONG) per sample to support vision–language training and evaluation. Our dataset contains 119,566 triplets (complex and amplitude slant-range SAR patch, aligned optical patch, natural-language description) covering 257 locations across 72 countries and a broad range of land types and infrastructures. We release fixed train/validation/test splits and the full preprocessing and baseline code to enable reproducible benchmarks for multimodal alignment on cross-modal retrieval and conditional generation in native SAR geometry. The dataset is publicly available on the Hugging Face Hub at https://huggingface.co/datasets/ONERA/SARLO-80.

Read & Discuss → View Source →

06.

Nature Biotechnology 2026-06-19 DOI: HASH:7fdd1f7d5c36769d9da105ef2851d7df

Efficient site-specific gene addition using R2 retrotransposons in tobacco and rice

Authors:

Zahir Ali↗

Precise integration of multikilobase DNA fragments remains a major technical barrier in plants. Here we introduce non-long terminal repeat (non-LTR) R2 retrotransposons as a versatile system for targeted gene integration in plants. We reconstituted R2 activity in Nicotiana benthamiana and benchmarked insertion efficiency and fidelity using a TMV-based episomal reporter system. We demonstrate site-specific integration of GFP (2.2 kb) and recombinase-compatible landing pads (0.6 kb) into 28S rDNA arrays, with intact cassette insertion frequencies up to 75% and 53%, respectively. To temporally constrain donor availability and avoid DNA intermediates, we combined in planta effector expression with recombinant RNA virus-mediated donor delivery. We apply R2 retrotransposons for targeted insertion of resistance cassettes within the rDNA of rice callus, achieving integration efficiencies up to 17%. These results position R2 retrotransposons as a double-strand break-free system for RNA-templated insertion of multikilobase gene cassettes at rDNA loci, for safe-harbor trait stacking in plants with potential applications in crop improvement and synthetic biology. Retrotransposons are applied in plants for safe-harbor transgene integration.

Read & Discuss → View Source →

07.

bioRxiv (Bioinfo) 2026-06-11 DOI: HASH:ab0afb05678c5e206a4781779e631bd5

inquiSTR: a toolkit for accurate and efficient population-scale tandem repeat genotyping and analysis

Authors:

De Coster↗Kucukali↗Sleegers↗Rademakers↗

Tandem repeats are highly mutable genomic elements linked to human traits and diseases. Profiling large catalogs of tandem repeats from population-scale long-read sequencing data requires accurate and efficient tools. We introduce inquiSTR, a command-line toolkit for fast genome-wide tandem repeat length genotyping. inquiSTR, with efficient parallel processing and low-memory streaming algorithms, genotypes a genome-wide repeat catalog of 1.78 million loci in less than two minutes. Benchmarking shows high accuracy and significantly faster performance compared to existing tools and truth sets. inquiSTR also provides methods for downstream analyses such as population structure inference, association testing, and outlier detection.

Read & Discuss → View Source →

08.

arXiv (CS.LG) 2026-06-19 DOI: arXiv:2606.20538

Multi-Task Bayesian In-Context Learning

Authors:

Qingyang Zhu↗Eric Karl Oermann↗Kyunghyun Cho↗

arXiv:2606.20538v1 Announce Type: new Abstract: Bayesian predictive inference provides a principled framework for uncertainty quantification, data efficiency, and robust generalization. However, exact inference is often intractable, and scalable approximations may remain computationally expensive or require restrictive modeling assumptions that degrade predictive performance. Prior-Data Fitted and in-context models have recently emerged as an amortized alternative by learning to map datasets directly to predictive distributions, but existing approaches are tightly coupled to the support of the training prior and lack explicit mechanisms for adapting to new priors at test time, resulting in limited robustness under distribution shift. We introduce a multi-task in-context learning framework for amortized hierarchical Bayesian predictive inference that explicitly represents prior information as a prefix of in-context datasets. A transformer trained on sequences of prior and target tasks learns to adapt its predictions across families of priors. On a suite of evaluations with increasing difficulty, including out-of-meta-distribution priors and priors with high-dimensional latent structures, our method matches oracle Bayesian predictors while being orders of magnitude faster. We further demonstrate its practical relevance on a real-world spatiotemporal temperature prediction benchmark. Code is available at https://github.com/martianmartina/multi-task-bayesian-icl/.

Read & Discuss → View Source →

09.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.12087

FORT-Searcher: Synthesizing Shortcut-Resistant Search Tasks for Training Deep Search Agents

Authors:

Jia Deng↗Yimeng Chen↗Xiaoqing Xiang↗Ziyang Zeng↗Shuo Tang↗Wayne Xin Zhao↗Feng Chang↗Chuan Hao↗Yuan Wei↗Ran Tao↗Bryan Dai↗Ji-Rong Wen↗…

Training deep search agents requires verifiable questions whose answers remain unavailable until sufficient evidence has been acquired through search. Existing synthesis methods often increase apparent difficulty by enriching graph structures, but structural complexity alone does not guarantee realized search difficulty: the intended search process can collapse through a cheaper identifying route. We formalize this gap with a shortcut-aware difficulty framework and identify four actionable shortcut risks: evidence co-coverage, single-clue selectivity, exposed constants, and prior-knowledge binding. To diagnose their realized effects, we use trajectory signatures including solving cost, answer hit time, and prior-shortcut rate. Guided by this framework, we introduce FORT, a Framework of Shortcut-Resistant Training-Data Synthesis. FORT constructs shortcut-resistant training data by controlling shortcut risks across entity selection, evidence graph construction, question formulation, and adversarial refinement. Experiments show that FORT induces longer pre-answer search and fewer shortcut patterns than existing open-source deep search datasets. Using the resulting trajectories, we train FORT-Searcher with supervised fine-tuning (SFT) only, and it achieves the best overall performance among comparable-size open-source search agents on challenging deep search benchmarks. Relevant resources will be made available at https://github.com/RUCAIBox/FORT-Searcher.

Read & Discuss → View Source →

10.

arXiv (CS.LG) 2026-06-12 DOI: arXiv:2606.12845

A Privacy-Preserving Framework Using Remote Data Science for Inter-Institutional Student Retention Prediction

Authors:

John Fields↗K M Sajjadul Islam↗Ruchitha Thota↗Victor Chen↗Praveen Madiraju↗

arXiv:2606.12845v1 Announce Type: cross Abstract: This study explores privacy-preserving machine learning (PPML) techniques using the PySyft platform to enable collaborative prediction of student retention between institutions. We developed a remote data science (RDS) framework with a semi-air-gapped architecture consisting of high-side and low-side servers, allowing researchers from three universities to build predictive models on sensitive student data without direct data access. Using historical data from a small private university (N=720), we evaluated three synthetic data generation approaches and validated the framework through inter-institutional collaboration. The results demonstrate consistent classification performance across institutions (Macro F1: 0.690–0.695) while maintaining strict Family Educational Rights and Privacy Act (FERPA) compliance. We also propose Data-Type-Aware Templates, a novel synthetic data method that prioritizes privacy over distributional fidelity. Our findings confirm that RDS-based PPML is technically feasible for educational settings and offers a practical alternative to federated learning for small-scale inter-institutional collaborations. The code is available at https://github.com/jtfields/NAIRR240195-Privacy-Preserving-Machine-Learning.

Read & Discuss → View Source →

11.

arXiv (CS.CV) 2026-06-11 DOI: arXiv:2506.21855

Periodic-MAE: Periodic Video Masked Autoencoder for rPPG Estimation

Authors:

Jiho Choi↗Sang Jun Lee↗

In this paper, we propose Periodic-MAE, a self-supervised framework for learning generalizable spatio-temporal representations of periodic physiological signals from unlabeled facial videos. The proposed method leverages a masked autoencoder (MAE), which learns high-dimensional facial representations by reconstructing masked video tokens without relying on remote photoplethysmography (rPPG) specific supervision. To explicitly align representation learning with the characteristics of rPPG, we introduce a periodicity-aware frame masking strategy based on video resampling, enabling the encoder to learn representations that capture quasi-periodic temporal patterns relevant to pulse signal estimation. In addition, physiological bandlimit constraints are integrated into the MAE pre-training framework, exploiting the sparsity of pulse signals in the frequency domain to guide the learned representations toward physiologically meaningful patterns. After pre-training, the learned representations are transferred to downstream rPPG estimation, where the encoder serves as a generic feature extractor for recovering pulse-related signals from facial videos. We conduct extensive experiments on four benchmark datasets, including PURE, UBFC-rPPG, MMPD, and V4V. Moreover, we evaluate the proposed approach on a real-world rPPG dataset collected under unconstrained lighting conditions and subject motion. Experimental results demonstrate that Periodic-MAE consistently improves rPPG estimation performance, particularly in challenging cross-dataset and real-world evaluation settings. Our code is available at https://github.com/ziiho08/Periodic-MAE.

Read & Discuss → View Source →

12.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2606.18950

RTSGameBench: An RTS Benchmark for Strategic Reasoning by Vision-Language Models

Authors:

San Kim↗Daechul Ahn↗Reokyoung Kim↗Hyeonbeom Choi↗Seungyeon Jwa↗Jonghyun Choi↗

arXiv:2606.18950v1 Announce Type: new Abstract: Modern Vision-Language Models (VLMs) often struggle with strategic reasoning, i.e., anticipating and influencing other agents' actions, under uncertainty in competitive and cooperative settings. Real-time strategy (RTS) games can be a natural testbed for diagnosing this limitation, as they demand coordination with allies, adaptation to opponents' strategy, and long-horizon planning under partial observability. However, existing RTS benchmarks offer limited evaluation scope, lack systematic competency diagnosis, and remain fixed in the pre-designed scenario coverage. To address these limitations, we present RTSGameBench, which is built on Beyond All Reason, a large-scale RTS game with an expanded battlefield that demands broader strategy diversity than the existing testbeds. The proposed benchmark provides evaluations through diverse gameplay across various matchup structures, diagnostic assessment via mini-games, each targeting an individual strategic competency, and extensible coverage via a self-evolving generation framework that converts free-form queries into new mini-games, improving over successive cycles. Additionally, for VLMs to operate in large-scale RTS games, we provide RTSGameAgent that manages units by an FSM with agentic memory. We empirically validate that multiple state-of-the-art VLMs do not perform well when matchups demand tighter coordination, multiagent coordination and when task scale increases.

Read & Discuss → View Source →

13.

arXiv (quant-ph) 2026-06-12 DOI: arXiv:2606.12637

Roto-Reflection Geometry of Pure Two-Qubit Entanglement

Authors:

Stanislav Filatov↗Marcis Auzinsh↗

arXiv:2606.12637v1 Announce Type: new Abstract: Pure two-qubit entanglement is usually characterized by scalar quantities such as concurrence. Here we show that it also has a natural geometric form. In the Pauli correlation tensor, maximally entangled states appear as improper orthogonal maps between two local Bloch spheres. These maps are roto-reflections. For partially entangled pure states, the same roto-reflection geometry is recovered after separating the contraction associated with concurrence. We call the corresponding geometric object the Entanglement Roto-Reflection Plane (ERRP). It organizes the maximally correlated directions of the two-qubit state and provides a covariant geometric complement to the scalar magnitude of entanglement.

Read & Discuss → View Source →

14.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.16243

LiFT: Local Search via Linear Programming for Overfitting-Controlled Transformers

Authors:

Abhishek Shukla↗Anikeit Khanna↗Ankur Sinha↗Faiz Hamid↗

This paper proposes a Linear Programming (LP)-based local search framework for fine-tuning pretrained transformer models with explicit control against overfitting. The approach formulates transformer fine-tuning as a bilevel optimization-based regularization problem, in which model parameters and regularization hyperparameters are jointly updated. Information collected during initial warm-up iterations, including validation gradients and training Hessian information, is used to construct a local descent direction by solving an LP that minimizes a scaled directional derivative while preserving training optimality. This validation-aware descent direction enables focused local updates of both parameters and regularization hyperparameters, reducing overfitting without requiring repeated full retraining cycles. The resulting method, termed Linear Programming-based Fine-Tuning (LiFT) for transformers, differs from conventional fine-tuning by systematically identifying task-specific updates rather than relying on heuristic or grid-based hyperparameter selection. Experiments on GPT-2 Small fine-tuned on WikiText-2 demonstrate that LiFT enables effective adaptation through selective tuning of transformer blocks and regularization parameters, yielding consistent improvements in test perplexity across multiple layer configurations and regularization settings, with particularly pronounced gains in overfitting-prone scenarios. Beyond empirical performance, LiFT establishes a principled connection between transformer fine-tuning, bilevel optimization, local search, and regularization theory.

Read & Discuss → View Source →

15.

arXiv (CS.CV) 2026-06-11 DOI: arXiv:2606.12402

DIRECT: When and Where Should You Allocate Test-Time Compute in Embodied Planners?

Authors:

Jadelynn Dao↗Milan Ganai↗Yasmina Abukhadra↗Ajay Sridhar↗Mozhgan Nasr Azadani↗Katie Luo↗Clark Barrett↗Jiajun Wu↗Chelsea Finn↗Marco Pavone↗

Vision-Language Models (VLMs) are increasingly deployed as high-level planners for embodied agents, with an emerging strategy of scaling test-time compute to improve capability. However, we observe that doing so increases latency, token usage, and FLOPs while yielding uneven, often diminishing gains in downstream success, limiting where embodied agents can be deployed. We argue that choosing when and where to spend test-time compute is central to bringing frontier performance to the real world. We introduce DIRECT, a routing framework that uses multimodal scene context to allocate compute per prompt, improving the success–cost Pareto frontier over fixed model selection. Across three dominant scaling axes, namely chain-of-thought depth, model size, and memory history, our experiments on VLABench and RoboMME show that test-time compute is not a uniform lever: different axes yield qualitatively distinct capability gains. We validate these insights on a physical Franka arm in a DROID setup spanning zero-shot manipulation and long-horizon chaining, where our router matches or exceeds a stronger model's success rate at up to 65% lower average latency. Ultimately, our results show that naively scaling test-time compute is wasteful, and that DIRECT can provide frontier-level embodied planning in robotic systems at a fraction of the cost. Project page can be found at jadee-dao.github.io/direct/.

Read & Discuss → View Source →

16.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2606.16073

Stop the Sampler! Classifier-Based Adaptive Stopping for Sampling Kernels

Authors:

Kirill Korolev↗Nikita Morozov↗Stepan Pavlenko↗Esmeralda S. Whitammer↗Sergey Samsonov↗

arXiv:2606.16073v1 Announce Type: new Abstract: Sampling from complex, unnormalized probability densities is a fundamental challenge in Bayesian inference and probabilistic modeling. While Markov chain Monte Carlo (MCMC) methods provide asymptotic guarantees, they often suffer from slow mixing and high computational costs due to fixed or manually tuned trajectory lengths. In this work, we propose a novel framework that treats trajectory termination as a learnable component of the sampling dynamics. By framing MCMC within the theory of non-acyclic generative flow networks (GFlowNets), we train state-dependent neural classifiers to decide when a trajectory has reached a high-density region and should terminate. We theoretically establish the connection between optimal classifiers and the target density via detailed balance conditions and introduce a multilevel training scheme to facilitate exploration in complex geometries. Experimental results across various benchmark densities demonstrate that our approach significantly reduces average trajectory lengths while improving mode coverage and mixing compared to standard MCMC baselines.

Read & Discuss → View Source →

17.

bioRxiv (Bioinfo) 2026-06-15 DOI: HASH:7dfc4d6b7e129cac3c3b5baa70bf6b0d

Inferring Cell Fate Trajectories in Time-Resolved Metabolic RNA Labeling data

Authors:

Audit↗Peyre↗Cantini↗

Single-cell RNA sequencing provides high-resolution snapshots of cellular states but lacks direct information about transcriptional dynamics. Metabolic RNA labeling addresses this limitation by distinguishing newly synthesized RNA, offering insight into the direction of cell state changes, and providing valuable information when attempting to recover the underlying continuous dynamics from static snapshots of cell distributions. However, existing trajectory inference methods do not fully exploit this additional signal. Here, we propose FLOWSATATE, a framework for single-cell trajectory inference that leverages time-resolved RNA labeling within an Optimal Transport setting. We model cell dynamics as a gradient flow in an inferred potential landscape parameterized by a neural network, integrating both total and labeled RNA across time points. The learned potential enables identification of key genes and transcription factors driving cell fate decisions and supports prediction of future cellular states. We benchmark our approach on its ability to generalize unseen data and recover coherent trajectories. We also apply it to study colorectal cancer response to demethylation treatment as well as neuronal differentiation of embryonic stem cells.

Read & Discuss → View Source →

18.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2606.11195

From Consumption to Reflection: Designing Human-AI Relations for Stable Reasoning

Authors:

Rikard Rosenbacke↗Carl Rosenbacke↗Victor Rosenbacke↗Martin McKee↗

arXiv:2606.11195v1 Announce Type: cross Abstract: Large language models (LLMs) have transformed how humans access information, but not how we reason with it. Their fluency accelerates consumption while bypassing the slow, reflective processes that underpin sound judgment. This paper introduces Relational Reflective Intelligence (RRI), an inference-time governance layer that operationalizes reflection through auditable reasoning loops. RRI operates not inside the model but around it, providing a practical structure for stable, auditable reasoning between humans and LLMs. The core premise is that LLMs inherit cognitive vulnerabilities similar to those that shape human thought: reliance on intuitive shortcuts, confusion between representation and reality, and a preference for coherence over falsification. When humans and models share these tendencies, their errors compound. We refer to this as relational drift, a failure that arises from interaction rather than from the model alone. Addressing this requires a shift from modeling relations between words to structuring relations between model outputs and human reasoning. RRI provides this missing layer through three components: the Rose-Frame, which identifies likely breakdowns in reasoning; the Architect's Pen, which introduces targeted reflection steps at critical moments; and an inference-time workflow that embeds these steps without retraining the model. Together, these elements transform human-AI interaction into a joint reasoning system with explicit checkpoints, conflict surfacing, and an auditable trail of assumptions. Rather than making machines think like humans or forcing humans to reason like machines, RRI creates a structured interaction in which both compensate for each other's limitations. It reframes AI safety as a cognitive architecture problem, where reliable decisions depend on embedding reflection directly into the interaction process.

Read & Discuss → View Source →

19.

arXiv (CS.LG) 2026-06-11 DOI: arXiv:2606.11968

Efficient Multinomial Logistic Bandit via Frequent Directions

Authors:

Linzhe He↗Yu-Jie Zhang↗Sifan Yang↗Lijun Zhang↗

arXiv:2606.11968v1 Announce Type: new Abstract: This paper studies efficient online algorithms for multinomial logistic bandits (MLogB), where the feedback distribution over $K+1$ outcomes follows a multinomial logistic model of $d$-dimensional action vectors. A representative UCB-type algorithm, OFUL-MLogB, achieves a regret bound of $\tilde{\mathcal{O}}(Kd\sqrt{T})$, but still requires $\mathcal{O}(K^3d^3)$ time and $\mathcal{O}(K^2d^2)$ space per round due to parameter estimation and optimistic reward construction, which is prohibitive in high-dimensional settings. To address this limitation, we propose EOFD-MLogB, which integrates frequent directions matrix sketching into OFUL-MLogB. By maintaining a low-rank SVD sketch of the accumulated Hessian, constrained online Newton updates in parameter estimation and $Kd \times K$ spectral-norm computations in the reward bonus are reduced to one-dimensional root-finding tasks and $K \times K$ eigenvalue computations, respectively. This yields dominant per-round time complexity $\mathcal{O}(Kd(m+K)^2)$ and space complexity $\mathcal{O}(Kd(m+K))$, where $m \ll d$ is the sketch size. We further prove a regret bound of $\tilde{\mathcal{O}}(\Delta_T(Kd\ln\Delta_T+m)\sqrt{T})$, where the sketching error factor $\Delta_T$ is controlled by the $m$-truncated spectral tail of the Hessian. Thus, when the Hessian is approximately low-rank, the regret is close to that of OFUL-MLogB. Experiments validate the computational efficiency and competitive performance.

Read & Discuss → View Source →

20.

arXiv (quant-ph) 2026-06-16 DOI: arXiv:2606.01110

Accelerating physics-informed neural networks for full waveform inversion using a hybrid quantum-classical finite-basis architecture

Authors:

Hoang Anh Nguyen↗Divakar Vashisth↗Ali Tura↗

arXiv:2606.01110v2 Announce Type: replace-cross Abstract: Full waveform inversion (FWI) reconstructs heterogeneous material properties from receiver data but remains computationally demanding. Physics-informed neural networks (PINNs) and their domain-decomposed variants (FBPINNs) offer a mesh-free alternative but face convergence challenges when representing complex velocity fields. We present a hybrid quantum-classical FBPINN for acoustic FWI, bringing together quantum computing and classical machine learning, in which the decomposed wavefield network and the global velocity network are implemented as classical-to-quantum pipelines terminating in parameterized quantum circuits (PQCs). The PQCs are realized as differentiable JAX statevector simulators, enabling end-to-end automatic differentiation through the classical PINN, the quantum circuit, and the physics-informed loss. On a geophysical anomaly benchmark, the quantum hybrid reaches a lower L1 velocity error than the primary classical FBPINN baseline in approximately 8x fewer training iterations, despite using approximately 33% fewer trainable parameters, and it outperforms all 15 classical hyperparameter variants tested. A second benchmark (checkerboard) demonstrates the generality of the inversion pipeline, confirming that the quantum hybrid architecture can recover structured spatial variations beyond the localized anomaly benchmark. Our framework is broadly applicable to wave-based inverse problems beyond geophysics, including medical ultrasound tomography and non-destructive evaluation.

Read & Discuss → View Source →

21.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.19721

OnDeFog: Online Decision Transformer under Frame Dropping

Authors:

Daiki Yotsufuji↗Kenta Nishihara↗Shoma Shimizu↗Kento Uchida↗Shinichi Shirakawa↗

arXiv:2606.19721v1 Announce Type: cross Abstract: In challenging real-world reinforcement learning applications, communication delays or sensor failures often cause frame dropping, in which the agent cannot receive the dropped states and associated rewards. To address the performance degradation caused by frame dropping, the Decision Transformer under Random Frame Dropping (DeFog) was developed by incorporating additional mechanisms into the decision transformer to tackle frame dropping. Although DeFog can mitigate performance degradation in frame-dropping environments, since DeFog is an offline learning method, it struggles to effectively generalize to novel states not adequately represented in the training dataset. In this study, we propose OnDeFog, which integrates the mechanisms in DeFog with the online decision transformer (ODT), an online reinforcement learning method that learns policies through direct environmental interaction. Comprehensive experimental evaluation demonstrates that our proposed OnDeFog achieves superior performance compared to ODT in environments characterized by high dropping frame rate and outperforms DeFog on datasets containing a large amount of low-reward data.

Read & Discuss → View Source →

22.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.20376

CRAX: Fast Safe Reinforcement Learning Benchmarking

Authors:

Tristan Tomilin↗Mourad Boustani↗Mickey Beurskens↗Thiago D. Sim\~ao↗

arXiv:2606.20376v1 Announce Type: cross Abstract: Safety is a core concern for deploying reinforcement learning (RL) agents in real-world domains such as robotics and autonomous driving. While benchmarks have been central to progress in RL, existing safety benchmarks with high-fidelity 3D physics remain computationally slow, limiting large-scale experimentation and rapid prototyping. To address this gap, we propose CRAX (Constrained RL Accelerated with JAX). Built on top of the MuJoCo XLA (MJX) physics engine with realistic 3D dynamics, CRAX leverages vectorized operations and hardware acceleration, yielding up to ~100x speedups over comparable CPU-based safety benchmarks. The benchmark features six environment suites and three agent-specific tasks, each spanning three difficulty levels. Evaluating six popular safe RL methods shows that no single approach dominates across all tasks, and reveals the trade-offs between performance and safety. We find that curriculum learning across difficulty levels and safety transfer can improve performance over direct training in harder settings.

Read & Discuss → View Source →

23.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.15266

Evaluating and Preserving Lexical Stress in English-to-Chinese Speech-to-Speech Translation

Authors:

Yuchen Song↗Xi Chen↗Mingze Li↗Satoshi Nakamura↗

Speech-to-speech translation (S2ST) systems have achieved impressive progress in semantic accuracy and speech naturalness. However, the cross-lingual transfer of lexical stress, a vital cue for emphasis and speaker intent, remains heavily underexplored, compounded by a lack of reliable automatic evaluation metrics for tonal languages like Chinese. We investigate English-to-Chinese S2ST stress transfer by constructing a stress-annotated Chinese dataset and an XLS-R-based Mandarin stress detector. Integrating this with the English EmphAssess system, we propose a novel objective metric for cross-lingual stress evaluation. Furthermore, we fine-tune CosyVoice3 to build a stress-aware S2ST system. Experiments demonstrate that our proposed S2ST architecture significantly outperforms existing systems in stress translation capability while maintaining competitive translation quality. Furthermore, our evaluation metric exhibits a strong correlation with human subjective judgments.

Read & Discuss → View Source →

24.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2606.07082

On the Geometry of On-Policy Distillation

Authors:

Zhennan Shen↗Yanshu Li↗Qingyu Yin↗Chak Tou Leong↗Zhilin Wang↗Yanxu Chen↗Rongduo Han↗Sunbowen Lee↗Yi R. Fung↗

arXiv:2606.07082v2 Announce Type: replace-cross Abstract: On-policy distillation (OPD) is increasingly used to improve large language model reasoning, but its training dynamics remain poorly understood. We characterize the trajectory of OPD updates in parameter space and compare it with supervised fine-tuning (SFT) and reinforcement learning with verifiable rewards (RLVR). A suite of parameter-space diagnostics consistently places OPD in a relaxed off-principal regime: compared with SFT, its updates affect fewer weights and avoid principal directions more strongly, while compared with RLVR, they remain less tightly constrained. Beyond this static localization, OPD exhibits subspace locking: its cumulative updates rapidly enter a narrow low-dimensional channel. Constraining training to the update subspace formed early in training preserves OPD performance but substantially degrades SFT, indicating that the locked subspace is functionally sufficient for OPD. Control experiments further show that sparsifying the update tokens and shifting rollout generation off-policy preserve the rank dynamics, whereas mixing the OPD objective with RLVR changes them. Overall, these results suggest that OPD is not merely an intermediate point between SFT and RLVR, but induces its own update geometry in parameter space.

Read & Discuss → View Source →

25.

arXiv (CS.AI) 2026-06-17 DOI: arXiv:2606.17882

Structural Preservation and the Logical Expressiveness of Graph Neural Networks

Authors:

Przemys{\l}aw Andrzej Wa{\l}\k{e}ga↗Bernardo Cuenca Grau↗

arXiv:2606.17882v1 Announce Type: new Abstract: Bridges between graph neural networks (GNNs) and logical formalisms have been established by fixing architectural choices, such as the types of aggregation, combination, and activation functions. These choices define restricted classes of GNNs for which tight correspondences with logical formalisms can be obtained, by showing that logical formulae can be translated into equivalent GNNs and, conversely, that GNNs can be translated into equivalent formulae. In this paper we take a semantic perspective by establishing the logical expressiveness of classes of GNN classifiers that are preserved under structural properties: embeddings (extensions), injective homomorphisms, and homomorphisms. We show that, for each such property, there exists a fragment of graded modal logic characterising the class of GNNs. In particular, preservation under embeddings, injective homomorphisms, and homomorphisms corresponds to existential graded modal logic, its existential-positive fragment, and existential-positive modal logic, respectively. These results characterise the expressiveness of broad classes of GNNs independently of specific architectural choices, but we also show that each of these classes admits a GNN architecture of the same expressiveness. Technically, our approach uses a new well-quasi-order result for trees of bounded height, yielding finite representations of unravelling-invariant classes.

Read & Discuss → View Source →