中 EN
Sign In Register

Academic Intelligence · Curated Daily

Explore the Frontier of Global Academia

AcademicHub aggregates real-time literature from top journals and preprint platforms. Build your personal research radar and let large language models compile cross-disciplinary analysis briefings automatically.

Sign In Register
01.
arXiv (math.PR) 2026-06-15

Sectional Curvature for Kantorovich-Wasserstein and Hellinger-Kantorovich Geometries

Authors:
Karl-Theodor Sturm↗

arXiv:2606.14318v1 Announce Type: cross Abstract: We derive an explicit formula for the sectional curvature of the space ${\cal M}(M)$ of finite measures on a Riemannian manifold M. The space ${\cal M}(M)$ is equipped with the Hellinger-Kantorovich metric $HK$. Even in the case M=R^n, the curvature is comprised of two parts: the `lifted part' is negative, and the `twisted part' is positive. It will be analyzed in detail for the multidimensional torus. Our general approach to sectional curvature in geodesic spaces also leads to new insights into the curvature of the space $P_2(M)$ of probability measures on M equipped with the Kantorovich-Wasserstein metric $W_2$.

Read & Discuss → View Source →
02.
arXiv (CS.CL) 2026-06-17

A Recipe for Long-Context Reasoning in Large Language Models via On-Policy Optimization and Distillation

Authors:
Miguel Moura Ramos↗Duarte M. Alves↗Andr\'e F. T. Martins↗

Existing approaches to post-train models for long-context tasks face complementary limitations: (i) supervised fine-tuning (SFT) provides stable supervision but suffers from exposure bias; (ii) reinforcement learning methods such as Group Relative Policy Optimization (GRPO) train on model-generated trajectories but struggle with long-horizon credit assignment and sparse rewards; and (iii) on-policy distillation (OPD) provides dense token-level guidance but does not directly optimize task rewards. We study these complementary strategies for long-context alignment and derive a recipe that combines GRPO with OPD-style teacher guidance: the student learns from its own rollouts using outcome-level rewards, while a stronger teacher provides dense token-level regularization in place of the standard reference policy. This is especially useful when process-level supervision is difficult to obtain. To support this study, we introduce LongBlocks, a synthetic multilingual dataset spanning multi-hop reasoning, contextual grounding, and long-form generation. Through controlled ablations, we isolate the roles of cold-start initialization, teacher anchoring, and data mixing, showing that our recipe yields a more stable and effective path to long-context reasoning than GRPO or OPD while preserving short-context capabilities.

Read & Discuss → View Source →
03.
arXiv (quant-ph) 2026-06-16

Programmable Gauge-Field Textures with Ultracold Atoms in Momentum Space

Authors:
Hongru Wang↗Hang Li↗Yichen Pan↗Yuyan Luo↗Bryce Gadway↗Tao Chen↗Bo Yan↗

arXiv:2606.15124v1 Announce Type: cross Abstract: Synthetic gauge fields with ultracold atoms offer a route to quantum matter in which electromagnetic environments can be designed rather than merely imposed. While the Harper-Hofstadter model has been realized in several cold-atom systems, existing implementations are largely limited to spatially uniform magnetic fluxes. Here we experimentally realize a highly programmable two-dimensional momentum-state lattice of ultracold atoms with local control over the Peierls phase pattern, enabling direct implementation of Harper-Hofstadter Hamiltonians with tunable and spatially structured synthetic gauge fields. We observe a crossover from ballistic to strongly flux-modified bulk dynamics with suppressed transport. By introducing a synthetic electric field through site-dependent energy gradients, we further demonstrate Hall-type transverse drift arising from the interplay between electric and magnetic fields. In addition, we engineer a synthetic flux domain wall separating regions with opposite magnetic fluxes and observe anisotropic propagation guided along the interface. These results move cold-atom gauge-field engineering from uniform magnetic backgrounds toward designer gauge textures, providing an experimental setting for transport across programmable topological interfaces.

Read & Discuss → View Source →
04.
Nature Medicine 2026-06-15

Long-term independent use of an intracortical brain–computer interface for speech and cursor control

Authors:
Nicholas S. Card↗

Brain–computer interfaces (BCIs) can provide naturalistic communication and digital access to people with severe paralysis by decoding neural activity associated with attempted speech and movement. Recent work has demonstrated highly accurate intracortical BCIs for speech and cursor control, but two critical capabilities needed for practical viability were unmet: independent at-home operation without researcher assistance and reliable long-term performance supporting accurate speech and cursor decoding. Here we demonstrate the independent and near-daily use of a multimodal BCI with novel brain-to-text speech and computer cursor decoders by a man with paralysis and severe dysarthria due to amyotrophic lateral sclerosis. Over nearly 2 years, the participant used the BCI for more than 3,800 h at home with no researchers present to maintain rich interpersonal communication with his family and friends, independently control his personal computer and sustain full-time employment—despite being paralyzed. He communicated 183,060 sentences—totaling 1,960,163 words—at an average rate of 56 words per minute. He labeled 92% of sentences as being decoded at least mostly correctly. In formal quantifications of performance where he was asked to say words presented on a screen, attempted speech was consistently decoded with more than 99% word accuracy (125,000 word vocabulary). The participant also used the speech BCI as keyboard input and the cursor BCI as mouse input to control his personal computer, enabling him to send text messages and emails and to browse the internet. These results demonstrate that intracortical BCIs have the potential to support independent use in the home, marking a critical step toward practical assistive technology for people with severe motor impairment. An automated intracortical brain–computer interface, used at home with no researcher intervention, provides long-term and accurate restoration of speech-based communication and cursor-based computer usage in a person with severe dysarthria due to amyotrophic lateral sclerosis.

Read & Discuss → View Source →
05.
arXiv (CS.CL) 2026-06-16

Calibrated Triage, Not Autonomy: Confidence Estimation for Medical Vision-Language Models

Authors:
Reza Khanmohammadi↗Kundan Thind↗Mohammad M. Ghassemi↗

A vision-language model can answer a question about a medical image fluently and confidently while barely using the image, leaning instead on language priors. In medicine this is the failure that matters most, because the answer looks trustworthy and is not, and the only protection is a confidence score reliable enough to tell the system when to abstain. We ask a deployment question rather than an accuracy one: how much imaging work a model can safely handle alone, and which confidence signal makes that possible. We evaluate seven confidence estimators across five open-weight LVLMs and three medical visual-question-answering datasets spanning broad clinical imaging, radiology, and pathology, with every probe trained only on natural images and applied without adaptation. Recast as bounded selective prediction (automate a case only when confidence clears a threshold, defer the rest), the comparison is cautionary. The standard metrics are poor guides: discrimination barely separates the methods, and the weak calibration of a cheap self-report is cheaply removed by off-domain temperature scaling without changing deployable yield. What distinguishes a usable estimator is the high-confidence region a clinician acts on: the weakest baselines are confidently wrong on 41 to 45 percent of their errors against 1 to 4 percent for the best probe, and no estimator is reliably best across domains or models. Safe handoff is governed at two levels: base-model competence sets a ceiling, so a well-calibrated score recovers roughly a third of radiology cases at a 20 percent error tolerance but almost none of pathology; the confidence layer then decides how much of that ceiling is reachable. The usable role today is calibrated triage, not autonomy: automate the cases a calibrated score marks safe, route the rest to a clinician. We release all outputs, correctness judgments, and confidence scores, with code.

Read & Discuss → View Source →
06.
arXiv (quant-ph) 2026-06-17

Singular Vector Finite Element Basis Functions for Tetrahedra in Complex Electromagnetic Geometries

Authors:
Samuel T. Elkin↗Ghazi Khan↗Ebrahim Forati↗Brandon W. Langley↗Dogan Timucin↗Reza Molavi↗Thomas E. Roth↗

arXiv:2606.18140v1 Announce Type: cross Abstract: Electromagnetic finite element method (FEM) implementations using traditional basis functions struggle to accurately represent field behavior near singular features such as conducting wedges. To combat this, specialized singular basis functions have been introduced to directly model the singular fields in these regions, leading to substantially improved performance. While these efforts have been pursued extensively in 2D, few functions have been developed for 3D elements. In this work, we develop basis functions for this in tetrahedra. Unlike prior functions, these basis functions are additive, meaning they are included alongside the standard vector basis functions to achieve more robust performance. Further, these functions are designed to be adaptable to tetrahedra touching several unique singular features by using combinations of basis functions singular with respect to each node and edge in the element, making them applicable to highly complex geometries. Higher-order interpolatory versions of the basis functions for modeling singular behavior with greater accuracy are also provided. These basis functions lead to substantial improvements in accuracy relative to the standard basis functions, and allow otherwise expensive simulations to be performed at far lower costs. As an application example, we perform simulations to extract critical quantities for designing superconducting qubits that significantly depend on the behavior of singular fields. In Ansys HFSS, this took 21.27 hours and a peak memory usage of 6.23 TB with 800 processors available, while using our singular basis functions achieved comparable results in 196 seconds while using 27.24 GB of memory and only 16 processors. Due to these benefits, our singular basis functions could be applied to enable design optimization of electromagnetic geometries with dominantly singular behavior, such as superconducting qubits.

Read & Discuss → View Source →
08.
arXiv (CS.CV) 2026-06-11

Making Foresight Actionable: Repurposing Representation Alignment in World Action Models

Authors:
Lu Qiu↗Yizhuo Li↗Yi Chen↗Yuying Ge↗Yixiao Ge↗Xihui Liu↗

World Action Models (WAMs) offer a promising route for robot manipulation by using video generation models to model future scene evolution before producing control actions. However, our empirical observations reveal a phenomenon: generating plausible visual futures does not always guarantee the extraction of accurate actions. To diagnose this failure, we conduct action-head attention analysis and causal interventions. We find that the action decoder fails to focus on task-relevant interaction regions and remains sensitive to perturbations in task-irrelevant areas. This reveals a representation mismatch: hidden states optimized for visual reconstruction are not inherently organized in a form useful for low-level action control. In this paper, we propose AGRA, an Action-Grounded Representation Alignment objective that regularizes the world-action interface by aligning intermediate video diffusion features with spatially coherent semantic representations from a foundation visual encoder. We evaluate AGRA on real-world manipulation tasks. Experiments show that AGRA makes world model representations more action-grounded: by focusing the action decoder on the correct interaction regions, it improves object localization accuracy and affordance understanding, and makes the policy more robust to perturbations in task-irrelevant regions. As a result, AGRA consistently improves both in-distribution performance and out-of-distribution generalization over the baseline world action model.

Read & Discuss → View Source →
09.
arXiv (CS.LG) 2026-06-17

Variational autoencoders with latent high-dimensional steady geometric flows for dynamics

Authors:
Andrew Gracyk↗

arXiv:2410.10137v5 Announce Type: replace Abstract: We develop Riemannian approaches to variational autoencoders (VAEs) for PDE-type ambient data with regularizing geometric latent dynamics, which we refer to as VAE-DLM, or VAEs with dynamical latent manifolds. We redevelop the VAE framework such that manifold geometries, subject to our geometric flow, embedded in Euclidean space are learned in the intermediary latent space developed by encoders and decoders. By tailoring the geometric flow in which the latent space evolves, we induce latent geometric properties of our choosing, which are reflected in empirical performance. We reformulate the traditional evidence lower bound (ELBO) loss with a considerate choice of prior. We develop a linear geometric flow with a steady-state regularizing term. This flow requires only automatic differentiation of one time derivative, and can be solved in moderately high dimensions in a physics-informed approach, allowing more expressive latent representations. We discuss how this flow can be formulated as a gradient flow, and maintains entropy away from metric singularity. This, along with an eigenvalue penalization condition, helps ensure the manifold is sufficiently large in measure, nondegenerate, and a canonical geometry, which contribute to a robust representation. Our methods focus on the modified multi-layer perceptron architecture with tanh activations for the manifold encoder-decoder. We demonstrate, on our datasets of interest, our methods perform at least as well as the traditional VAE, and oftentimes better. Our methods can outperform this and a VAE endowed with our proposed architecture, frequently reducing out-of-distribution (OOD) error between 15% to 35% on select datasets. We highlight our method on ambient PDEs whose solutions maintain minimal variation in late times. We provide empirical justification towards how we can improve robust learning for external dynamics with VAEs.

Read & Discuss → View Source →
10.
arXiv (CS.AI) 2026-06-12

AgentBeats: Agentifying Agent Assessment for Openness, Standardization, and Reproducibility

Authors:
Xiaoyuan Liu↗Jianhong Tu↗Yuqi Chen↗Siyuan Xie↗Sihan Ren↗Tianneng Shi↗Gal Gantar↗Evan Sandoval↗Donghyun Lee↗Daniel Miao↗Peter J. Gilbert↗Nick Hynes↗…

arXiv:2606.13608v1 Announce Type: new Abstract: Agent systems are advancing quickly across domains, but their evaluation remains fragmented. Most benchmarks rely on fixed, LLM-centric harnesses that require heavy integration, create test-production mismatch, and limit fair comparison across diverse agent designs. The root problem is the lack of an open, agent-agnostic assessment interface. We advocate Agentified Agent Assessment (AAA), where evaluation is performed by judge agents and all participants interact through standardized protocols: A2A for task management and MCP for tool access. Conventional benchmarking defines two separate interfaces, one for the benchmark and one for the agent, while AAA only needs one; this yields a generic, unified framework that separates assessment logic from agent implementation and enables reproducible, interoperable, and multi-agent evaluation. We further introduce AgentBeats as a concrete realization of AAA: we identify five practical operation modes that make standardized assessment compatible with real-world constraints on openness, privacy, and reproducibility. To evaluate our design at scale, we conduct two studies: a five-month open competition that drew 298 judge agents across 12 categories together with 467 subject agents from independent participants, showing that AAA applies across a heterogeneous range of benchmarks; and a case study on coding agents that confirms agentified evaluation preserves fidelity with the public record while surfacing previously missing head-to-head results, yielding research insights about agent design. Combining a community-scale field study and a controlled coding case study, we verify that AAA delivers coverage, practicality, and fidelity across heterogeneous scenarios at scale. Together, AAA and AgentBeats offer a clear path toward open, standardized, and reproducible agent assessment.

Read & Discuss → View Source →
11.
arXiv (CS.CL) 2026-06-16

Building Customer Support AI Agents at 100M-User Scale: An Evaluation-Driven Framework

Authors:
Aman Gupta↗Kevin Rossell↗Edesio Alcoba\c{c}a↗Jose Chrystian Lima Pacheco↗Carolina Baptista de Lima↗Shao Tang↗Luiz Paulo Rabachini↗Luis Moneda↗Herbert Fei↗Daniel Silva↗Rohan Ramanath↗

The rapid rise in LLM capabilities has made AI agents increasingly viable across a broad range of tasks. Among the most promising applications is building production-ready customer-facing agents, a challenge that demands coordinated excellence in evaluation methodology, context engineering, training, and online measurement. Yet these critical pillars are typically developed in isolation, creating blind spots that only surface after deployment. In this paper, we present a unified framework that bridges offline development with online impact for customer support AI agents at Nubank, a company with 100M+ users. Our approach integrates several key components: (1) structured context engineering tailored to customer support agents, (2) systematic human-in-the-loop prompt iteration, (3) rigorous LLM judge evaluation with measured inter-rater agreement and GEPA optimization for consistency, and (4) ideation-to-production validation. A central insight is that evaluation-pipeline quality directly determines iteration velocity. We present results from five production deployments spanning distinct domains: card delivery, debt management, credit-limit support, card management, and product explanation. These deployments deliver consistent customer-satisfaction gains while substantially accelerating iteration. In our card-delivery deployment, large-scale A/B testing yields a 37 percentage-point improvement in AI transactional Net Promoter Score and a 29 percentage-point gain in self-service rate over prior agent variants, alongside a strong correlation between offline simulation metrics and online outcomes, demonstrating that eval-driven development reliably predicts production impact. On most use cases, AI satisfaction reaches within a few percentage points of expert human agents.

Read & Discuss → View Source →
12.
arXiv (CS.CL) 2026-06-18

Beyond Scalar Scores: Exploring LLM-based Metrics for Clinical Significance Evaluation in Radiology Reports

Authors:
Qingyu Lu↗Ruochen Li↗Liang Ding↗Yufei Xia↗Youxiang Zhu↗Dacheng Tao↗

Reliable evaluation of generated radiology reports requires strict clinical accuracy, as omitted critical findings or mischaracterized radiographic observations can directly affect patient care. Existing metrics obscure this requirement by reducing report quality to a medically ungrounded scalar. Although Large Language Models (LLMs) possess rich medical knowledge, they likewise struggle to draw a reliable boundary between clinically significant errors and harmless variation. We study this boundary using ReEvalMed benchmark as testbed and evaluate metric-level clinical significance from detecting true clinical errors ("Discrimination") and tolerating insignificant variations ("Robustness"). Across 8 LLM evaluators under one-pass and two-pass settings, we identify a widespread discrimination bias: models effectively detect errors but also over-penalize harmless rephrasings. To mitigate this, we synthesize 4k report pairs and train lightweight interpretable metrics on Qwen3-8B and MedGemma-4B. Our trained metric sharpens the clinical significance boundary, surpassing 32B-scale medical LLMs and remaining competitive with proprietary models. Crucially, the more costly two-pass setting fails to consistently improve overall performance and mainly trades discrimination for robustness. These findings suggest one-pass trained metrics as the practical choice for cost-sensitive deployment, with two-pass inference reserved for settings where D-R balance is critical. We will release the dataset and metric.

Read & Discuss → View Source →
14.
arXiv (CS.CV) 2026-06-12

AudioX-Turbo: A Unified Framework for Efficient Anything-to-Audio Generation

Authors:
Zeyue Tian↗Lei Ke↗Zhaoyang Liu↗Ruibin Yuan↗Liumeng Xue↗Yujiu Yang↗Weijia Chen↗Xu Tan↗Qifeng Chen↗Wei Xue↗Yike Guo↗

Audio and music generation based on flexible multimodal control signals is a widely applicable topic, with the following key challenges: 1) a unified multimodal modeling framework, 2) large-scale, high-quality training data, and 3) the prohibitive inference cost of multi-step diffusion sampling. As such, we propose AudioX-Turbo, a unified and efficient framework for anything-to-audio generation that integrates varied multimodal conditions (i.e., text, video, and audio signals) in this work. AudioX-Turbo follows a teacher-student paradigm. The teacher AudioX-Base is built on a Multimodal Diffusion Transformer with a Multimodal Adaptive Fusion module that aligns diverse multimodal inputs for high-fidelity synthesis, and is then distilled into the few-step student AudioX-Turbo via Distribution Matching Distillation adapted to flow matching, complemented by a diffusion-based discriminator for high-quality few-step generation. To support the training of AudioX-Turbo, we construct a large-scale, high-quality dataset, IF-caps-Pro, comprising approximately 9.2M samples curated through a two-stage data collection and annotation pipeline. We benchmark AudioX-Turbo across a wide range of tasks, finding that our model achieves superior performance, especially on text-to-audio and text-to-music generation, while operating at only 4 sampling steps and requiring approximately 25x fewer function evaluations (NFE) than multi-step baselines. These results demonstrate that our method is capable of audio generation under flexible multimodal control, showing efficient and powerful instruction-following capabilities. The code and datasets will be available at https://zeyuet.github.io/AudioX-Turbo/.

Read & Discuss → View Source →
15.
arXiv (CS.CV) 2026-06-17

ActWorld: From Explorable to Interactive World Model via Action-Aware Memory

Authors:
Zhexiao Xiong↗Yizhi Song↗Hao Kang↗Qing Yan↗Liming Jiang↗Jenson Yang↗Zhoujie Fu↗Stathi Fotiadis↗Angtian Wang↗Zichuan Liu↗Bo Liu↗Yiding Yang↗…

Interactive world models aim to simulate environment dynamics under real-time user actions. However, their action vocabulary is largely confined to navigation: most actions correspond to motion (e.g., walk, turn, look around), while interaction with objects in the scene (e.g., pick up plates, open doors, or trigger physical responses) is either absent, restricted to game domains, or relegated to prompt-to-full-video scenarios. The resulting worlds are visually explorable but not truly actionable. In this work, we present ActWorld, an interactive world model that extends prior navigation-centric generators to support mid-rollout object interaction within a chunk-autoregressive framework. We argue that the navigation-interaction gap stems from two bottlenecks. First, a data bottleneck: the lack of human-object interaction data with accurate, dense labels. Second, a memory bottleneck: recency-biased history compression in existing world models discards the event-transition frames that causally determine subsequent object states, leading to an action-forgetting pathology. On the data side, we construct a 100K interaction video dataset, each annotated with per-chunk captions via chain-of-thought reasoning. On the model side, we introduce a hierarchical action-aware memory design that routes history compression by interaction importance, complemented by a persistent memory bank that maintains event-update and object-identity tokens across long rollouts. Experiments show that ActWorld supports both flexible navigation and rich object interaction within a single model, substantially improving interaction fidelity over navigation-only baselines without sacrificing viewpoint control. Project page is available at https://interactwm.github.io/ActWorld.

Read & Discuss → View Source →
16.
arXiv (CS.AI) 2026-06-12

MLUBench: A Benchmark for Lifelong Unlearning Evaluation in MLLMs

Authors:
He Li↗Haoang Chi↗Qizhou Wang↗Yunxin Mao↗Zhiheng Zhang↗Jie Tan↗Tongliang Liu↗Wenjing Yang↗Bo Han↗

arXiv:2606.12809v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) are trained on massive multimodal data, making data unlearning increasingly important as data owners may request the removal of specific content. In practice, these requests often arrive sequentially over time, giving rise to the challenging problem of MLLM Lifelong Unlearning. However, most existing benchmarks are limited in scale and scope, failing to capture the complexities of MLLM lifelong unlearning. To fill this gap, we introduce the MLUBench, a large-scale and comprehensive benchmark featuring 127 entities across 9 classes under lifelong unlearning requests. We perform extensive experiments using MLUBench and reveal that existing unlearning methods suffer from severe, cumulative degradation. More critically, we further identify the unique challenge of this problem: unlike in unimodal models, MLLM lifelong unlearning is constrained by the need to preserve multimodal alignment. Continually unlearning from one modality could degrade the entire model. To alleviate this challenge, we propose LUMoE, an effective method. Experiments demonstrate that LUMoE significantly mitigates the degradation problem faced by baselines. The source code and the MLUBench dataset are open-sourced in https://github.com/lihe-maxsize/Lifelong_Unlearning_main.

Read & Discuss → View Source →
17.
arXiv (quant-ph) 2026-06-16

Entangled states are typically incomparable

Authors:
Vishesh Jain↗Matthew Kwan↗Marcus Michelen↗

arXiv:2406.03335v2 Announce Type: replace Abstract: Consider a bipartite quantum system, where Alice and Bob jointly possess a pure state $|\psi\rangle$. Using local quantum operations on their respective subsystems, and unlimited classical communication, Alice and Bob may be able to transform $|\psi\rangle$ into another state $|\phi\rangle$. Famously, Nielsen's theorem [Phys. Rev. Lett., 1999] provides a necessary and sufficient algebraic criterion for such a transformation to be possible (namely, the local spectrum of $|\phi\rangle$ should majorise the local spectrum of $|\psi\rangle$). In the paper where Nielsen proved this theorem, he conjectured that in the limit of large dimensionality, for almost all pairs of states $|\psi\rangle, |\phi\rangle$ (according to the natural unitary invariant measure) such a transformation is not possible. That is to say, typical pairs of quantum states $|\psi\rangle, |\phi\rangle$ are entangled in fundamentally different ways, that cannot be converted to each other via local operations and classical communication. Via Nielsen's theorem, this conjecture can be equivalently stated as a conjecture about majorisation of spectra of random matrices from the so-called trace-normalised complex Wishart-Laguerre ensemble. Concretely, let $X$ and $Y$ be independent $n \times m$ random matrices whose entries are i.i.d. standard complex Gaussians; then Nielsen's conjecture says that the probability that the spectrum of $X X^\dagger / \operatorname{tr}(X X^\dagger)$ majorises the spectrum of $Y Y^\dagger / \operatorname{tr}(Y Y^\dagger)$ tends to zero as both $n$ and $m$ grow large. We prove this conjecture, and we also confirm some related predictions of Cunden, Facchi, Florio and Gramegna [J. Phys. A., 2020; Phys. Rev. A., 2021].

Read & Discuss → View Source →
18.
arXiv (CS.AI) 2026-06-17

Trustworthy Self-Composable Big-Data-as-a-Service: An LLM-Orchestrated Multi-Agent Framework for Automated Data Engineering, AutoML, MLOps Deployment, and Drift-Aware Lifecycle Optimization

Authors:
Aueaphum Aueawatthanaphisut↗Badri Raj Lamichhane↗

arXiv:2606.17915v1 Announce Type: cross Abstract: Big-Data-as-a-Service (BDaaS) platforms require re liable automation across data ingestion, cleaning, feature engi neering, model development, deployment, and post-deployment monitoring. However, existing LLM-based data science agents and AutoML systems mainly focus on isolated workflow stages, leaving limited support for lifecycle-level orchestration, artifact governance, human oversight, and drift-aware adaptation. This paper proposes a trustworthy self-composable BDaaS frame work based on LLM-orchestrated multi-agent collaboration. The proposed architecture decomposes the BDaaS lifecycle into specialized agents for data ingestion, data cleaning, feature engineering, AutoML training, model evaluation, MLOps de ployment, monitoring, and drift detection. A central LLM or chestration layer coordinates agent execution, validates interme diate outputs, manages workflow context, and enables dynamic workflow composition. The framework also incorporates shared artifact governance, reproducibility support, human-in-the-loop checkpoints, and drift-aware feedback loops. A prototype-based evaluation is conducted using controlled tabular benchmark datasets with missing values, categorical variables, outliers, class imbalance, and simulated covariate drift. Compared with manual ML, AutoML-only, and single-agent LLM baselines, the pro posed multi-agent BDaaS pipeline achieves competitive predictive performance while improving lifecycle-level reliability, including workflow completion, artifact traceability, deployment readiness, reproducibility, and drift recovery. The results suggest that LLM-orchestrated multi-agent systems can extend conventional AutoML toward trustworthy, adaptive, and production-oriented BDaaS lifecycle automation.

Read & Discuss → View Source →
19.
arXiv (CS.CV) 2026-06-16

The Vision Encoder as a Privacy Boundary: Visual-Token Side Channels in Encoder-Free Vision-Language Models

Authors:
Chenyu Zhou↗Qiliang Jiang↗Shuning Wu↗Xu Zhou↗

A vision encoder compresses image pixels into semantic embeddings, implicitly acting as a privacy boundary by preserving semantic content while attenuating pixel-local detail required for exact text recovery. Encoder-free vision-language models (VLMs) remove this boundary by routing image patches directly into the language-model token stream, thereby exposing an architectural privacy attack surface: intermediate visual tokens become a pre-output side channel. Under a token-access adversary, decoders invert visual-token streams from two encoder-free VLMs, Gemma4 and Fuyu, recovering recognizable image structure and readable held-out access codes, whereas matched encoder-based controls localize target regions but recover no exact strings. Within-model ablations show that the operative factor is spatial sampling fidelity of the visual-token grid, especially character-direction sampling density, rather than token or value count. The leakage is not limited to exported tokens: Gemma4 layer-0 key-value cache tensors are directly invertible, placing the side channel within KV caches commonly persisted by production serving stacks for decoding efficiency. The attack survives clutter, realistic document degradation, and zero-shot transfer to public document images, and it resists value-level defenses such as additive noise and quantization. Effective mitigation must therefore reduce spatial sampling, making removal of the vision encoder a first-class privacy decision in VLM deployment.

Read & Discuss → View Source →
20.
arXiv (CS.AI) 2026-06-16

Running hardware-aware neural architecture search on embedded devices under 512MB of RAM

Authors:
Andrea Mattia Garavagno↗Edoardo Ragusa↗Paolo Gastaldo↗Antonio Frisoli↗

arXiv:2606.14824v1 Announce Type: cross Abstract: This document proposes a novel approach to hardware-aware neural architecture search (HW NAS) that considers the resources available on the computing platform running it, enabling its execution on various embedded devices. The presented HW NAS produces tiny convolutional neural networks (CNNs) targeting low-end microcontroller units (MCUs), typically involved in the Internet of Things (IoT) or wearable robotics, opening new use cases. A gateway could run it to tailor CNNs' architecture on the acquired data without using external servers, ensuring privacy. The proposed technique achieves state-of-the-art results in the human-recognition tasks on the Visual Wake Word dataset, a standard TinyML benchmark, on several embedded devices.

Read & Discuss → View Source →
21.
arXiv (CS.CL) 2026-06-17

Self-Generated Error Training for Token Editing in Diffusion Language Models

Authors:
Lin Yao↗

Token-to-token (T2T) editing lets LLaDA2.1 revise committed tokens during block-diffusion decoding. The released recipe trains this editor on random vocabulary corruptions, but at inference the editor sees the model's own fluent, high-confidence draft errors instead. We study this training-inference mismatch and propose self-generated T2T, which performs a no-gradient draft pass, fills masked positions with predicted tokens, and supervises recovery in a second pass under these self-generated corruptions. We implement the update as a short LoRA continued-pretraining pass on LLaDA2.1-mini and evaluate on several benchmarks under the official Q-Mode T2T procedure with unchanged inference parameters. The method generally improves accuracy while reducing T2T edit intensity, mitigating failure modes such as final-digit transcription errors after otherwise correct reasoning and excessive self-correction before short factual answers.

Read & Discuss → View Source →
22.
arXiv (CS.AI) 2026-06-19

Formal Verification of Learned Multi-Agent Communication Policies via Decision Tree Distillation

Authors:
Ahmad Farooq↗Kamran Iqbal↗

arXiv:2606.19632v1 Announce Type: cross Abstract: Multi-agent reinforcement learning (MARL) enables agents to develop coordination strategies through emergent communication, but neural policies lack the formal safety guarantees required for safety-critical robotic deployment in drone swarms and autonomous vehicle fleets. We present the first end-to-end framework for safety verification of learned multi-agent communication policies through policy abstraction: neural policies are distilled into interpretable decision trees, then formally verified, with empirical validation confirming that verified safety properties transfer to original networks. Our four-stage pipeline consists of domain-specific feature extraction from agent observations, decision tree distillation achieving 97.9% +/- 1.2% fidelity to neural policies, automated translation to PRISM probabilistic model checker specifications with complete feature-to-state-variable correspondence, and compositional verification of Probabilistic Computation Tree Logic (PCTL) properties via pairwise decomposition with union-bound aggregation and empirical neighbor modeling. Evaluating Vector-Quantized Variational Information Bottleneck (VQ-VIB) policies for multi-drone coordination with 5-7 agents, we verify 18 temporal logic properties across safety, liveness, and cooperation, achieving 88.9% property satisfaction with all five safety thresholds satisfied (0.3% collision probability vs. 1% threshold). Monte Carlo validation of original neural policies confirms that verified safety properties transfer with

Read & Discuss → View Source →
23.
medRxiv (Medicine) 2026-06-17

The Unreliable Judges: Assessing Reproducibility and Self-Preference Bias of LLMs as Free-Text Evaluators

Authors:
Alvarez-Arenas↗J. I↗mananes↗jimenez-carretero↗Sanchez-Cabo↗

Large Language Models (LLMs) are transforming clinical practice and research, but their adoption requires rigorous evaluation. While human assessment is ideal, its cost has driven the widespread use of LLMs as evaluators. We introduce an open-source reciprocal framework comparing 71 human experts against six LLMs. AI evaluators show a strong self-preference bias, yet neither group reliably identified whether a response was human- or AI-generated. AI scores correlated with surface features such as length and lexical diversity, whereas human scores did not. By probing the evaluator's hidden states and applying targeted steering, we show that verbosity is a major causal driver of the bias. Moreover, shuffling question-response pairings shows that long responses keep high scores even when they no longer answer the question, whereas short ones do not, demonstrating that AI judges reward verbosity largely independently of content alignment. Finally, API-based and batch inference inflate stochasticity, underscoring the need for controlled deployment.

Read & Discuss → View Source →
24.
Nature (Science) 2026-06-16

Mathematicians are developing rules for AI use — other fields should follow

Authors: Unknown Author

The mathematics community is right to call for transparency, integrity and fairness to be protected when AI tools are used. Researchers in other disciplines could learn from this approach. The mathematics community is right to call for transparency, integrity and fairness to be protected when AI tools are used. Researchers in other disciplines could learn from this approach.

Read & Discuss → View Source →
25.
arXiv (CS.CV) 2026-06-16

Vision-Language Models as Zero-Annotation Oracles in Histopathology

Authors:
Vishal Jain↗Giorgio Buzzanca↗Sarah Cechnicka↗Maarten Naesens↗Priyanka Koshy↗Tri Nguyen↗Jesper Kers↗Candice Roufosse↗Bernhard Kainz↗

Foreground segmentation is the critical first step of every computational pathology pipeline, yet existing methods rely on hand-tuned heuristics or supervised models that overfit to narrow stain and scanner distributions, failing silently on specialised stains such as Jones silver or Elastica van Gieson. We propose a coarse-to-fine approach that recasts foreground segmentation as a visual perception task and leverages general-purpose vision-language models (VLMs) as zero-annotation oracles. Our key insight is that tissue-versus-background discrimination is a natural-image recognition problem, not a histopathological one, so VLMs trained on internet-scale corpora generalise where domain-specific models cannot. We introduce Leica-75, a benchmark of 75 renal transplant whole-slide images spanning three stain families. On Leica-75, our method achieves the highest segmentation quality on out-of-distribution stains (Dice 0.858 +/- 0.027 on Jones, 0.853 +/- 0.041 on EVG) with 7x lower cross-stain variance than the best supervised baseline, while remaining competitive on in-distribution H&E. Few-shot prompting with automatically curated exemplars (Auto-context) rescues hard cases on Stress-32 (n=32), a curated stress-test subset (Dice 0.470 to 0.819 for the 2B model). VLM-based annotation review matches human expert consensus (kappa=0.989 for blur detection; mean precision/recall grading accuracy 0.708 vs. human 0.646 for segmentation mask review). The resulting pseudo-labels are used to distil lightweight student models that are as performant as the teacher model while running for a fraction of the cost. Our framework provides a principled, scalable solution to a persistent infrastructure bottleneck in digital pathology.

Read & Discuss → View Source →