Academic Intelligence · Curated Daily

探索全球前沿学术脉络

AcademicHub 汇聚顶级期刊与预印本平台的实时文献。定制您的专属科研雷达,利用大语言模型自动生成交叉领域文献分析简报。

01.
Nature (Science) 2026-06-17

A mosaic of whole-body representations on the human precentral gyrus

Understanding how the body is represented in the motor cortex is key to understanding how the brain controls movement. Although the motor cortex has been mapped in animal models at a fine scale1–10, characterization in humans remains primarily limited to low-resolution recording11–16 and stimulation techniques17–20. Here we created a comprehensive map of the human motor cortex at single-neuron resolution, spanning microelectrode array recordings from 20 arrays across 8 individuals with paralysis from spinal cord injury, amyotrophic lateral sclerosis or brainstem stroke, all enrolled in brain–computer interface clinical trials. These arrays broadly sample the crown of the precentral gyrus (PCG; thought to be composed largely of the premotor cortex (Brodmann area 6)). We found that body parts were highly intermixed, such that the entire body was represented in all sampled locations of the PCG, although the relative strength of body parts was roughly consistent with the motor homunculus17,18. We also found two speech-preferential areas with a broadly tuned, orofacial-dominant area in between them. Throughout the PCG, movement representations of the four limbs were interlinked, with homologous movements of different limbs (for example, toe curl and hand close) having correlated representations. These data provide evidence consistent with an intermixed, interrelated and behaviour-centred organization of the motor cortex3,21. The resulting map also provides important targeting information for brain–computer interfaces that seek to restore motor function. A comprehensive map of the human motor cortex at single-neuron resolution is described.

02.
medRxiv (Medicine) 2026-06-11

Genetic Susceptibility to Incisional Hernia: Evaluation of Hernia Polygenic Risk Scores

Objectives: Incisional hernia (IH) affects 13-30% of people after abdominal surgery, resulting in substantial morbidity and costs. While clinical risk factors have been studied extensively, genomic risk for IH is incompletely understood. We aimed to evaluate the impact of polygenic risk scores (PRS) on IH risk prediction. Methods] We created and evaluated three PRS for abdominal hernia, ventral hernia and latent hernia susceptibility for prediction of IH in an institutional biobank. The primary outcome was defined as the diagnosis or repair of an IH based on ICD-9/10-CM/PCS and CPT codes. Clinical covariates included age, sex, body mass index (BMI), smoking status, index procedure type, and perioperative surgical site infection. A phenome-wide association study (PheWAS) was performed to assess clinical associations with increased PRS. We then tested the ability of the PRS to improve prediction for IH by modeling clinical covariates with and without PRS in patients who underwent abdominal surgery. Model performance was assessed using 10 iterations of 5-fold cross-validation to estimate Brier scores and area under the receiver operating characteristic curve (AUROC), which were compared using cross-model Bayesian analysis of variance. Results: In 55,809 subjects, assessed PRS was significantly associated with incisional, umbilical, and ventral hernia on PheWAS, with 1.19 greater odds of developing IH per 1-SD increase in PRS (95% CI: 1.13-1.25, P < 0.001). Of 9,909 subjects who underwent qualifying abdominal surgery, 706 developed IH. In this cohort, the latent hernia susceptibility PRS was associated with a 16% increased hazard of developing IH per 1-SD increase (HR 1.16; 95% CI: 1.07-1.26; P < 0.001). Compared to a predictive model using clinical covariates (Brier score = 0.047, 95% CI: 0.046-0.048; AUROC = 0.660, 95% CI: 0.653-0.666), addition of the PRS showed similar Brier score and AUROC estimates (Brier score = 0.047, 95% CI: 0.046-0.048; AUROC: 0.667, 95% CI: 0.661-0.673) at five years. Cross-model Bayesian analysis demonstrated >99% probability of practical equivalence when trying to detect a difference of [&ge;] 0.02. Conclusion: All three PRS for hernia were independently associated with IH, suggesting that genomic factors contribute significantly to IH development. However, none of the three PRS meaningfully improved clinical IH risk prediction in patients who underwent abdominal surgery. This suggests that clinical comorbidities and surgical techniques may be equally as important as genomic architecture.

03.
arXiv (CS.AI) 2026-06-19

Deontic Policies for Runtime Governance of Agentic AI Systems

arXiv:2606.19464v1 Announce Type: new Abstract: Autonomous agentic AI systems driven by Large Language Models (LLMs) introduce a new class of security, privacy, and compliance challenges: an agent that can invoke tools, manipulate data, install software, and coordinate with peer agents across organizational boundaries must be constrained not just by authentication and access control, but by the full structure of enterprise governance. This includes specifying what agents are permitted and prohibited from doing, what they areobliged to do after certain actions (e.g., notify the CISO), under what conditions a standing obligation may be waived, and which rules take precedence when policies conflict. This governance problem exceeds what current policy engines provide. Systems such as XACML, Rego, and Cedar address only the permit/prohibit subset of this governance structure. They do not provide obligation lifecycle management, meta-policy conflict resolution, dispensations that waive obligations in specific circumstances, and ontological reasoning over domain class hierarchies commonly found in applications such as healthcare, cybersecurity, or data privacy. We propose AgenticRei, which realizes key governance requirements such as obligations, dispensations, policy conflict resolutions, and reasoning over policies, as well as the basic permit/prohibit constraints. We use a deontic policy language built on the Rei framework, expressed as OWL (Web Ontology Language) and evaluated at runtime by a high-performance logic engine entirely outside the LLM. The same pipeline governs both tool invocations by the agent and agent-to-agent messages. We show through examples that deontic policies capture governance constraints around security and privacy that mostly cannot be expressed in current production engines. Our approach composes naturally with industry-standard frameworks like A2AS.

04.
arXiv (quant-ph) 2026-06-11

Measurement incompatibility and quantum steering via linear programming

arXiv:2506.03045v3 Announce Type: replace Abstract: The problem of deciding whether a set of quantum measurements is jointly measurable is known to be equivalent to determining whether a quantum assemblage is unsteerable. This problem can be formulated as a semidefinite program (SDP). However, the number of variables and constraints in such a formulation grows exponentially with the number of measurements, rendering it intractable for large measurement sets. In this work, we circumvent this problem by transforming the SDP into a hierarchy of linear programs that compute upper and lower bounds on the incompatibility robustness with a complexity that grows polynomially in the number of measurements. The hierarchy is guaranteed to converge and it can be applied to arbitrary measurements – including non-projective POVMs (Positive Operator-Valued Measures) – in arbitrary dimensions. While convergence becomes impractical in high dimensions, in the case of qubits our method reliably provides accurate upper and lower bounds for the incompatibility robustness of sets with several hundred measurements in a short time using a standard laptop. We also apply our methods to qutrits, obtaining non-trivial upper and lower bounds in scenarios that are otherwise intractable using the standard SDP approach, although such bounds are significantly looser than the ones obtained in the qubit case. Finally, we show how our methods can be used to construct local hidden state models for states (i.e., to prove that a state cannot lead to steering under any possible local measurements), or conversely, to certify that a given state exhibits steering; for two-qubit quantum states, our approach is comparable to, and in some cases outperforms, the current best methods.

05.
arXiv (quant-ph) 2026-06-12

To Cool, or Not to Cool? Displacement Sensing with Hot Quantum States

arXiv:2606.13650v1 Announce Type: new Abstract: Quantum-enhanced displacement sensing with bosonic systems is typically formulated assuming that the oscillator is cooled close to its ground state before nonclassical probe preparation. We investigate whether such near-ground-state initialization is necessary, or whether sensitive probes can instead be generated directly from thermal states. We analyze hot quantum probes produced by squeezing, number-raising, and Schrödinger-cat-state generation applied to thermal inputs. We identify two distinct mechanisms by which thermal mixedness can remain compatible with enhanced displacement sensitivity. First, projecting a mixed probe onto a definite parity sector removes the usual thermal suppression of the displacement quantum Fisher information, which can then increase with initial thermal occupation. Second, coherent superpositions of opposite displacements can retain sensitivity through coherence between their displaced components, even when the underlying state is mixed. We use these two mechanisms to classify hot-state protocols according to whether their sensitivity comes from parity selection, coherence between displaced components, or both. Finally, we formulate an experimentally relevant optimization problem comparing initial cooling with direct hot-state preparation under realistic decoherence and show that complete cooling is not universally optimal. Our results establish hot-state engineering as a route to quantum-enhanced bosonic displacement sensing without mandatory ground-state initialization.

06.
arXiv (CS.CL) 2026-06-19

NEST: Narrative Event Structures in Time for Long Video Understanding

Recent progress in vision-language models has enabled the processing of increasingly long video sequences, but the ability to handle extended token streams does not translate to understanding of narrative structure in long videos. Existing long video benchmarks focus on needle-in-a-haystack retrieval rather than evaluating how low-level actions form events, how events interact across time, and how narratives progress, for example, whether a model can connect an early setback, such as a job loss to a later relationship breakup, despite long gaps, intervening scenes, or flashbacks that reframe what occurred. We introduce NEST (Narrative Event Structures in Time for Long Video Understanding), a dataset of 1005 full-length movies (avg. 98 minutes), each annotated with 102 multimodal narrative events grounded in visual content, dialogue, and audio. NEST captures multimodal narrative events with structured annotations grounded in visual content, dialogue, and audio, and links them through relations that reflect narrative structure, including temporal ordering, hierarchical composition, and long-range dependencies. We introduce baselines for event trigger detection (ETD), event localization (EL), event argument extraction (EAE), and event relation extraction (ERE). The benchmark is highly challenging for grounded event discovery, with ETD below 8%, EL under 6%, and EAE below 11%. In contrast, ERE is more tractable once events are given, reaching 35.45% F1 zero-shot and 44.42% F1 after fine-tuning.

07.
arXiv (CS.CL) 2026-06-11

Verifiable Environments Are LEGO Bricks: Recursive Composition for Reasoning Generalization

Reinforcement Learning (RL) with verifiable environments has emerged as a powerful approach for enhancing the reasoning capabilities of Large Language Models (LLMs). While prior research demonstrates that scaling environment quantity improves RL performance, existing manual or individual construction methods suffer from linear scaling limits, thereby hindering scalable reasoning generalization. This paper introduces RACES (Recursive Automated Composition for Environment Scaling), a framework that conceptualizes verifiable environments as composable building blocks that can be recursively assembled. The key insight is that when the codomain (output type) of one environment matches the domain (input type) of another, they can be automatically fused into a new verifiable environment, enabling recursive composition. RACES is implemented with 300 individual environments and defines a set of composition operators (\textsc{SEQUENTIAL}, \textsc{PARALLEL}, \textsc{SORT}, and \textsc{SELECT}) that induce diverse reasoning patterns. Extensive experiments show that RL training on these composite environments consistently enhances reasoning generalization. Specifically, RACES improves DeepSeek-R1-Distill-Qwen-14B by an average of 3.1 points (from 48.2 to 51.3) and boosts Qwen3-14B performance from 58.8 to 61.1 on six benchmarks, which are unseen during the construction of training environments. Moreover, RACES achieves performance comparable to training on 300 individual environments using only 50 base environments, demonstrating significant efficiency in environment utilization.

08.
bioRxiv (Bioinfo) 2026-06-13

Reinforcement learning-driven unified generative framework for multi-objective RNA codon design

Current RNA codon design methods are limited by inefficient long-sequence processing and poor generalizability, often relying on a decoupled "generate-or-optimize" paradigm. We introduce RNARL, a reinforcement learning-driven framework that unifies sequence generation with multi-objective optimization. RNARL directly learns to generate high-performance sequences, effectively optimizing sequences over 3,900 nucleotides and demonstrating superior performance and universality across six species and five RNA types. RNARL thus establishes an effective and generalizable framework for RNA codon design. Finally, a user-friendly web platform is freely available to facilitate its application for RNA therapeutic design.

09.
arXiv (CS.AI) 2026-06-19

Automating SKILL.md Generation for Computer-Using Agents via Interaction Trajectory Mining

arXiv:2606.20363v1 Announce Type: new Abstract: Explicit skill libraries make computer-using agents easier to inspect, but it remains unclear whether such libraries can be mined from interaction data in a way that improves downstream policies. We study this question through a three-stage pipeline that segments GUI trajectories, clusters segments into candidate skills, and trains a skill-aware policy from the resulting annotations. The mined clusters are readable on the source benchmark: five of eight clusters have at least 0.95 purity against InteraSkill Workflows labels. However, readability does not imply transfer. GRPO improves IW skill-step accuracy only from 18.5\% to 20.5\%, leaves BrowseComp+ essentially unchanged, and underperforms trivial frequency priors on key source-domain metrics. We therefore present the method as a diagnostic study: trajectory mining can expose inspectable skill structure, but the current boundary detector, orderless segment representation, and offline reward model are insufficient for reliable cross-domain policy improvement.

10.
arXiv (CS.CL) 2026-06-19

Clusters are All You Need: Pre-Training the Tsetlin Machine with Semantic Clusters from Language Models for Interpretability

Pre-trained language models such as BERT achieve strong text classification performance but lack transparency, limiting their use in high-stakes settings. The Tsetlin Machine (TM) offers fully interpretable, clause-based reasoning but captures little semantic information, and prior attempts to bridge the two rely on static word embeddings that miss contextual meaning. We propose a semantic pre-training framework that transfers knowledge from a pre-trained language model into a TM without using embeddings. Text samples are grouped into semantically coherent clusters with K-means or Top2Vec, and the resulting cluster-sample pairs pre-train a non-negated TM with enhanced Type I feedback. The TM thereby learns interpretable semantic keywords that are fine-tuned on downstream tasks. Across five datasets, our method substantially outperforms vanilla and embedding-based TMs and reaches performance competitive with BERT while remaining interpretable.

11.
arXiv (CS.LG) 2026-06-16

Contextual Bandits for Maximizing Stimulated Word-of-Mouth Rewards

arXiv:2606.15146v1 Announce Type: new Abstract: Stimulated word-of-mouth is a strategy that promotes information sharing through prompts or incentives. Optimizing stimulated word-of-mouth through social networks requires identifying and targeting connected users who are most susceptible to spillover, a phenomenon where the influence of recommendations extends beyond the immediate audience to impact their connected users. The probability of spillover varies across individuals, and their connections, leading to heterogeneity. Understanding and accurately estimating the spillover probabilities among users in social networks is crucial for improving the effectiveness of stimulated word-of-mouth. To address this, we present a novel contextual multi-armed bandit framework that learns individual spillover probabilities and ranks connected users to maximize rewards from stimulated word-of-mouth. Experiments on real-world network datasets demonstrate that accounting for spillover heterogeneity enhances the targeting precision of top-$k$ connected users, boosting rewards and outperforming baseline methods that do not learn individual spillover effects.

12.
arXiv (CS.CL) 2026-06-18

Want Better Synthetic Data? Steer It: Activation Steering for Low-Resource Language Generation

Large language models (LLMs) have become an effective tool for synthetic data generation, including for low-resource languages, where generated data can improve downstream task performance. Current best-performing approaches typically rely on few-shot prompting with target-language examples, which increases inference costs and may reduce diversity through lexical anchoring. In this work, we investigate activation steering as an alternative for low-resource synthetic data generation. We study two steering strategies: Language Steering, which targets the linguistic identity of a language, and Quality Steering, which captures well-formedness by contrasting human-written and backtranslated text representations. We evaluate these methods across four open-source LLMs, multiple layers, and 11 typologically diverse languages by generating sentiment and topic classification data and finetuning smaller classifiers. Steering is applied in both zero-shot and few-shot prompting settings and compared against non-steered counterparts. Our results show that steering on early layers consistently improves the diversity of generated data while often yielding stronger downstream model performance, particularly for low-resource languages.

13.
arXiv (CS.CV) 2026-06-11

Semantic search for 100M+ galaxy images using AI-generated captions

Finding scientifically interesting phenomena through slow manual labeling campaigns severely limits our ability to explore the billions of galaxy images produced by telescopes. In this work, we develop a pipeline to create a semantic search engine from completely unlabeled image data. Our method leverages Vision-Language Models (VLMs) to generate descriptions for galaxy images, then contrastively aligns a pre-trained astronomy foundation model with these embedded descriptions to produce searchable embeddings at scale. We find that current VLMs provide descriptions that are sufficiently informative to train a semantic search model that outperforms direct image similarity search. Our model, AION-Search, achieves state-of-the-art zero-shot performance on finding rare phenomena despite training on randomly selected images with no deliberate curation for rare cases. Furthermore, we introduce a VLM-based re-ranking method that nearly doubles the recall for our most challenging targets in the top-100 results. For the first time, AION-Search enables flexible semantic search for over 100 million galaxy images, enabling discovery from previously infeasible searches, including the identification of 36 new extragalactic stellar stream candidates. More broadly, our work provides an approach for making large, unlabeled scientific image archives semantically searchable, expanding data exploration capabilities in fields from Earth observation to microscopy. The code, data, and app are publicly available at https://github.com/NolanKoblischke/AION-Search

14.
arXiv (CS.CL) 2026-06-11

VietMed-MCQ: A Consistency-Filtered Data Synthesis Framework for Vietnamese Traditional Medicine Evaluation

Large Language Models (LLMs) have demonstrated remarkable proficiency in general medical domains. However, their performance significantly degrades in specialized, culturally specific domains such as Vietnamese Traditional Medicine (VTM), primarily due to the scarcity of high-quality, structured benchmarks. In this paper, we introduce VietMed-MCQ, a novel multiple-choice question dataset generated via a Retrieval-Augmented Generation (RAG) pipeline with an automated consistency check mechanism. Unlike previous synthetic datasets, our framework incorporates a dual-model validation approach to ensure reasoning consistency through independent answer verification, though the substring-based evidence checking has known limitations. The complete dataset of 3,190 questions spans three difficulty levels and underwent validation by one medical expert and four students, achieving 94.2 percent approval with substantial inter-rater agreement (Fleiss' kappa = 0.82). We benchmark seven open-source models on VietMed-MCQ. Results reveal that general-purpose models with strong Chinese priors outperform Vietnamese-centric models, highlighting cross-lingual conceptual transfer, while all models still struggle with complex diagnostic reasoning. Our code and dataset are publicly available to foster research in low-resource medical domains.

15.
arXiv (CS.CL) 2026-06-18

GrowthHacker: Automated Off-Policy Evaluation Optimization Using Code-Modifying LLM Agents

With data-driven development now widely adopted, online A/B testing is an established method for measuring the effects of new technologies. However, deploying online experiments demands resources for design, implementation, and deployment, and may negatively impact users (e.g., unsafe or unethical outcomes) while requiring weeks of data collection. To address this, the growing research area of off-policy evaluation (OPE), or offline A/B testing, assesses new technologies offline using previously collected logged data. OPE is also a fundamental problem in reinforcement learning and is important where online testing is expensive or risky, such as healthcare, recommender systems, education, and robotics. Despite advances in code-generation large language models (LLMs) and agentic workflows, little is known about whether and how LLMs and LLM-based agents can automatically optimize OPE implementations. We propose GrowthHacker, a benchmark that evaluates baseline LLMs and LLM-based agents on large-scale public datasets. GrowthHacker autonomously and iteratively modifies code, runs OPE, and uses the metrics to guide subsequent optimization. We evaluate methods on Open Bandit Pipeline (OBP) and Scope-RL, and develop a two_agent framework that addresses limitations of existing frameworks while reducing complexity. Across both libraries, two_agent shows the highest reliability (98.1%-100% success rate) and positive-outcome rate (78%), with a median improvement of 4.4% among positive outcomes; CrewAI achieves the highest average improvement (37.9%) and is the only framework with zero extreme-value failures. AutoGen and Default each reach 65% positive-outcome rates. These results establish the feasibility of using LLM-based agents as automated "growth hackers" to continuously improve OPE systems, with implications for scaling data-driven decision-making where manual optimization is expensive.

16.
arXiv (CS.CV) 2026-06-15

Overhead Wildlife Locator (OWL): Benchmarking Weakly Supervised Learning for Aerial Wildlife Surveys

Automated aerial wildlife surveys increasingly rely on deep learning, yet standard object detectors require bounding-box annotations, reported to be up to seven times slower and three times more expensive to produce than point-level labels. To address this bottleneck, we introduce the Overhead Wildlife Locator (OWL), a weakly supervised density-estimation framework with three variants: OWL-C, a fully convolutional model for high-throughput screening; OWL-T, a Swin-augmented hybrid for heterogeneous, cluttered scenes; and OWL-D, built on a frozen DINOv3 ViT-H+/16 encoder with a DPT-style fusion decoder. We benchmark all three against POLO, YOLOv11n, and YOLOv11l across five public aerial datasets, from sparse fixed-wing savanna surveys to dense UAV paddock imagery, and against the published HerdNet baseline on its native Delplanque split. OWL-D sets a new state of the art on Delplanque (0.934 AP vs. HerdNet's 0.840) and records the highest AP on four of the five datasets. Performance is regime-dependent: on the extreme-density SheepCounter UAV dataset the hybrid OWL-T leads (0.978 AP) and the convolutional variants attain the lowest counting error, whereas the foundation-based OWL-D degrades, indicating which variant suits which survey type. We further validate operational readiness on the Alaska Department of Fish and Game's 2022 Central Arctic Caribou census: under cross-herd and cross-temporal transfer, OWL-C fine-tuned on the 2017 Porcupine Caribou Herd split attains F1 = 0.965 on a held-out patch test set, with a signed count error of +3.1% aggregated across the released test patches. We release the OWL code, model weights, and the annotated Porcupine Caribou Herd 2017 (PCH) and Central Arctic Herd 2022 (CAH) patches, the first open patch-level datasets for large-scale caribou aerial surveys, at https://github.com/microsoft/MegaDetector-Overhead.

18.
arXiv (CS.CV) 2026-06-15

A Unified Theory of Sinusoidal Activation Families for Implicit Neural Representations

Implicit Neural Representations (INRs) model continuous signals with compact neural networks and have become a standard tool in vision, graphics, and signal processing. A central challenge is accurately capturing fine detail without heavy hand-crafted encodings or brittle training heuristics. Across the literature, periodic activations have emerged as a compelling remedy: from SIREN, which uses a single sinusoid with a fixed global frequency, to more recent architectures employing multiple sinusoids and, in some cases, trainable frequencies and phases. We study this family of sinusoidal activations and develop a principled theoretical and practical framework for trainable sinusoidal activations in INRs. Concretely, we instantiate this framework with Sinusoidal Trainable Activation Functions (STAF), a Fourier-like activation whose amplitudes, frequencies, and phases are learned. Our analysis (i) establishes a Kronecker-equivalence construction that expresses trainable sinusoidal activations with standard sine networks and quantifies expressive growth, (ii) characterizes how the Neural Tangent Kernel (NTK) spectrum changes under trainable sinusoidal parameterization, and (iii) provides an initialization that yields standard normal post-activations without asymptotic central limit theorem (CLT) arguments. Empirically, on images, audio, shapes, inverse problems (super-resolution, denoising) and NeRF, STAF is competitive and often stronger on distortion-oriented reconstruction metrics such as PSNR/SSIM across the evaluated INR tasks, with favorable parameter efficiency under layer-wise sharing. While periodic activations can alleviate practical manifestations of spectral bias, our results indicate they do not eliminate it; instead, trainable sinusoids can improve the observed capacity-optimization trade-off in the evaluated settings.

19.
arXiv (CS.LG) 2026-06-12

Self-Guidance: Enhancing Neural Codecs via Decoder Manifold Alignment

arXiv:2606.12940v1 Announce Type: cross Abstract: Neural speech codecs based on Vector-Quantized VAEs (VQ-VAEs) are core audio tokenizers for speech LLMs, yet their reconstruction fidelity is bottlenecked by quantization error. Modifying the quantizer or increasing model capacity are common fixes, but they complicate downstream language modeling. Our core idea is to align the decoder's internal feature manifolds when processing both the quantized tokens and their original continuous embeddings, using a lightweight feature-mapping loss. This requires minimal training overhead and no inference-time changes. Applied to XCodec2, self-guidance improves all reconstruction metrics, achieving state-of-the-art low-bitrate performance. Notably, it enables a 4x codebook reduction without fidelity loss, which downstream TTS experiments show significantly improves LLM-based synthesis by simplifying the token modeling space. Multiple statistical observations and visualizations corroborate the enhanced internal manifold alignment in the decoder. Extensive experiments confirm its generality across various inductive biases. Self-guidance thus establishes an efficient, broadly applicable method for high-fidelity neural audio coding.

20.
arXiv (CS.CV) 2026-06-17

Disentangling Perception and Reasoning in Multimodal LLMs via Reward Design

Reinforcement learning with verifiable rewards has driven major gains in LLM reasoning, and it is intuitive to assume this recipe will transfer well to multimodal models. However, multimodal models do two things: first, perceive what is in an image, then reason about what it implies. Because these stages are graded jointly, it is hard to tell how much room reasoning alone has to grow. We study this on algorithmic visual puzzles, where both components are necessary and show that perception, not reasoning, is the binding constraint. Replacing images with simple textual descriptions raises performance by over 20 points on average for Claude models. We then evaluate six reward designs aimed at inducing visual grounding during reasoning without chain-of-thought supervision. Training Qwen-2.5-VL-7B with GRPO, reward design induces long, structured reasoning with self-reflection and visual references, yielding a 5.56-point gain over the base model. These gains are, however, uneven; no single reward improves all categories, and rewards with verifiable accuracy signals trade out-of-domain transfer for in-domain accuracy. These results point to perception-aware reward design as a path forward, so that signals correct perception at its source rather than the reasoning that inherits its errors.

21.
arXiv (CS.AI) 2026-06-16

AIRMap: AI-Generated Radio Maps for Wireless Digital Twins

arXiv:2511.05522v4 Announce Type: replace-cross Abstract: Accurate, low-latency channel modeling is essential for real-time wireless network simulation and digital-twin applications. Traditional modeling methods like ray tracing are however computationally demanding and unsuited to model dynamic conditions. In this paper, we propose AIRMap, a deep-learning framework for ultra-fast radio-map estimation, along with an automated pipeline for creating the largest radio-map dataset to date. AIRMap uses a single-input U-Net autoencoder that processes only a 2D elevation map of terrain and building heights. Trained on 1.2M Boston-area samples and validated across four distinct urban and rural environments with varying terrain and building density, AIRMap predicts path gain with under 4 dB RMSE in 4 ms per inference on an NVIDIA L40S-over 100x faster than GPU-accelerated ray tracing based radio maps. A lightweight calibration using just 20% of field measurements reduces the median error to approximately 5%, significantly outperforming traditional simulators, which exceed 50% error. Integration into the Colosseum emulator and the Sionna SYS platform demonstrate near-zero error in spectral efficiency and block-error rate compared to measurement-based channels. These findings validate AIRMap's potential for scalable, accurate, and real-time radio map estimation in wireless digital twins.

22.
arXiv (CS.AI) 2026-06-15

Can LLMs Accurately Score Medical Diagnoses and Clinical Reasoning?

arXiv:2604.14892v3 Announce Type: replace-cross Abstract: Evaluating medical AI systems using expert clinician panels is costly and slow, motivating the use of large language models (LLMs) as alternative adjudicators. Here, we evaluate an LLM Jury, composed of three frontier AI models, for scoring 3334 diagnoses on 300 real-world low- and middle-income country (LMIC) hospital cases. Both LLM- and clinician-generated diagnoses are scored against expert panel diagnoses across four dimensions: diagnosis, differential diagnosis, clinical reasoning, and negative treatment risk. The LLM Jury scores are compared with expert and independent re-scoring panel scores to assess error metrics, inter-rater agreement, severe-risk errors, and the effect of post hoc calibration using isotonic regression. In our data, we find that: (i) the uncalibrated LLM Jury scores preserve ordinal agreement with the expert clinician panel scores, but are systematically lower; (ii) the probability of severe-risk errors is lower for the LLM Jury than the human expert re-score panels; (iii) the LLM Jury combined with LLM diagnoses can be used to identify diagnoses at high risk of error, enabling targeted expert review and improved panel efficiency; (iv) the calibrated LLM Jury scores and rankings of diagnosing agents show excellent agreement with those of the primary expert panels; (v) LLM Jury models show no self-preference bias, they did not score diagnoses generated by their own underlying model or models from the same vendor more (or less) favourably than those generated by other models. Together, these results provide evidence that a calibrated LLM Jury is a trustworthy and reliable proxy for expert clinician evaluation in medical AI benchmarking. Confirming these findings in other clinical settings is an important direction for future work.

24.
arXiv (CS.LG) 2026-06-16

If These Walls Could Talk: Critical Play with Large Language Models in Museums

arXiv:2606.15565v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly being used in museums to as role playing chatbots which let visitors talk to simulated versions of people and artefacts from the past. While such installations can be playful and engaging, they are also problematic because LLMs cannot be trusted to speak truthfully. I identify a fundamental dilemma for the use of LLMs in museum chatbots: LLMs cannot be trusted to tell the truth, and efforts to make them more reliable may ruin that which is attractive about the bots in the first place - their ability to engage in life-like conversation. In response, I propose designing for critical play with LLM-based bots: Designing for playful interactions with bots that are unreliable but still able to represent the past in an adequate and engaging manner - as fictional characters representing historical narratives, styles of discourse, diverse perspectives, humor and satire.

25.
arXiv (CS.LG) 2026-06-19

Critical Percolation as a Synthetic Data Model for Interpretability

arXiv:2606.20347v1 Announce Type: new Abstract: Neural networks learn features that reflect the hierarchical, multi-scale structure of natural data. Synthetic datasets used to evaluate interpretability methods typically lack this structure, limiting their value as realistic toy models. To close this gap, we introduce a family of synthetic datasets consisting of hierarchical functions defined on critical mean-field percolation clusters embedded in a high-dimensional data space. The percolation data consists of sparse, low-dimensional fractal clusters with a power-law size distribution. Latent variables modeling a taxonomic hierarchy generate each data point's target value. The data model is analytically tractable with known critical exponents that fix its properties without requiring hyperparameter tuning. We leverage a mapping between percolation clusters, random trees, and additive coalescence to propose an almost linear-time algorithm to jointly sample a random tree and its hierarchical latent decomposition, enabling data generation at arbitrary scale. Using probing experiments, we find that the model's ground-truth latent variables can be linearly decoded from neural network activations. Together, sparsity, self-similarity, power-law statistics, and analytical tractability make critical percolation a principled testbed for interpretability research.