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

Quantum charge pumping in helical systems: A comparative study of short- and long-range hopping

arXiv:2606.12914v1 Announce Type: cross Abstract: Using the Keldysh non-equilibrium Green's function approach, we investigate charge pumping through a single-stranded helical structure described by a tight-binding model that includes either short-range hopping (SRH) or long-range hopping (LRH). While quantum pumping has been studied in various low-dimensional systems, the detailed behavior of the spectral current and the pumped dc current in helical geometries in the presence of higher-order electron hopping (beyond nearest neighbors) has not yet been systematically explored. Here, we focus on the interplay between helicity and extended hopping ranges, analyzing how they jointly control the energy-resolved and dc pumped currents under time-periodic end potentials. For LRH, the pumped dc current exhibits pronounced plateau-like regions as a function of chemical potential when energy levels are sparsely spaced – consistent with adiabatic transport – whereas SRH yields more parameter-sensitive currents without clear plateaus. The plateau stability is controlled by the drive frequency: at higher frequencies, Floquet side-band mixing destroys the plateaus, leading to oscillatory currents. The phase dependence remains nearly sinusoidal, and the current vanishes at zero phase lag, confirming the necessity of out-of-phase potentials. Crucially, in helical systems, the decay exponent $(\ell_c)$ acts as an effective structural parameter that can tune both the magnitude and sign of the pumped current, offering a geometric knob for controlling quantum pumping. Our findings not only fill a gap in the understanding of spectral and pumped currents in helical systems with extended hopping but also provide tools that can be applied to analyze similar phenomena in other chiral or quasi-one-dimensional systems.

02.
arXiv (CS.AI) 2026-06-16

Beyond Scalars: Evaluating and Understanding LLM Reasoning via Geometric Progress and Stability

arXiv:2603.10384v3 Announce Type: replace Abstract: Evaluating LLM reliability via scalar probabilities often fails to capture the structural dynamics of reasoning. We introduce TRACED, a framework that assesses reasoning quality through theoretically grounded geometric kinematics. By decomposing reasoning traces into Progress (displacement) and Stability (curvature), we reveal a distinct topological divergence: correct reasoning manifests as high-progress, stable trajectories, whereas hallucinations are characterized by low-progress, unstable patterns (stalled displacement with high curvature fluctuations). Leveraging these signatures, our probabilistic framework achieves competitive performance and superior robustness across diverse benchmarks. Crucially, TRACED bridges geometry and cognition by mapping high curvature to ''Hesitation Loops'' and displacement to ''Certainty Accumulation'', offering a physical lens to decode the internal dynamics of machine thought.

03.
medRxiv (Medicine) 2026-06-15

Genome-wide colocalization of body fat distribution GWAS and subcutaneous adipose eQTLs identifies SNX10, DGKQ, and CBX3 as candidate causal genes for cardiometabolic disease

作者:

Background: Genome-wide association studies (GWAS) have identified hundreds of loci associated with body fat distribution, yet the causal genes and regulatory mechanisms through which these variants exert their effects remain largely unknown. Expression quantitative trait locus (eQTL) colocalization provides a powerful framework for identifying genes whose expression is genetically coregulated with complex traits. Methods: We performed a genome-wide colocalization analysis integrating waist-hip ratio adjusted for body mass index (WHRadjBMI) GWAS summary statistics from 694,649 individuals (Pulit et al., 2019) with subcutaneous adipose tissue eQTLs from the Genotype-Tissue Expression (GTEx) Project v8 (N = 581 donors). GWAS coordinates were lifted from GRCh37 to GRCh38 to enable direct alignment with GTEx data. We incorporated CAVIAR fine-mapping results to overcome the limitation of FDR-significant eQTL filtering. Colocalization was assessed using the approximate Bayes factor framework (coloc.abf) across 335 independent genome-wide significant loci. Results: Of 2,897 locus-gene pairs tested, 489 (16.9%) showed strong colocalization (PP.H4 > 0.8) and 618 (21.3%) showed moderate evidence (PP.H4 > 0.5). The strongest colocalization was observed for SNX10 (sorting nexin 10; PP.H4 = 1.000), a recently characterized regulator of adipocyte differentiation and female-specific diet-induced obesity. Other top hits included DGKQ (diacylglycerol kinase theta; PP.H4 = 0.9999999), an emerging pharmacological target for insulin resistance, and CBX3 (chromobox 3; PP.H4 = 0.9999974), an epigenetic regulator linked to cardiovascular disease. Established adiposity genes including GRB14 (PP.H4 = 0.681) and KLF14 (PP.H4 = 0.590) were recovered, validating our approach. Several loci exhibited extensive allelic heterogeneity, with 50 genes colocalizing at a single chromosome 3 locus. Conclusions: Our analysis provides a comprehensive map of adipose tissue gene regulatory mechanisms underlying genetic risk for body fat distribution. The identification of SNX10, DGKQ, and CBX3 as high-confidence candidate causal genes advances the translation of GWAS associations into mechanistic understanding and therapeutic targets for obesity-related cardiometabolic disease.

04.
medRxiv (Medicine) 2026-06-16

Investigating naming error patterns after non-invasive brain stimulation and language treatment in persons with aphasia

Abstract Background: Transcranial direct current stimulation (tDCS) paired with behavioral language therapy can improve naming in persons with aphasia (PWA), yet naming errors persist. Little is known about how naming error patterns change after non-invasive brain stimulation is combined with language treatment. Aims: To examine whether right cerebellar tDCS plus computerized aphasia therapy changes the types of naming errors in people with chronic aphasia across timepoints, and to determine whether effects differ by cerebellar tDCS polarity (anode vs. cathode). Methods and Procedures: In a randomized, double-blind, sham-controlled, within-subject crossover study, we retrospectively analyzed behavioral data from 24 individuals with post-stroke aphasia. Each participant completed two 15-session intervention periods (3-5 sessions/week) with active cerebellar tDCS + computerized aphasia therapy and sham + computerized aphasia therapy, separated by a two-month washout. General linear models (GLMs) assessed longitudinal changes in six error types (semantic, phonological real word, phonological nonword, no response, mixed, unrelated) on an untrained picture naming task (Philadelphia Naming Test; PNT) and a trained task (Naming 80; N80). Additional GLMs evaluated polarity effects with 2 (Group: anode vs. cathode) x 2 (Treatment) interactions, and treatment-order effects with 2 (Group: tDCS-first vs. sham-first) x 2 (Treatment) interactions. Outcomes and Results: Active cerebellar tDCS did not significantly change error types for trained items (N80). For untrained items (PNT), active tDCS reduced several error types relative to sham, with the clearest and most durable reduction in phonological nonword errors; more moderate reductions occurred for phonological real word and unrelated errors. Mixed errors showed a marginally opposite pattern, tending to increase after tDCS and decrease after sham. Polarity analyses indicated broadly similar effects across anodal and cathodal stimulation overall, but only the anode group showed a reliable treatment effect for phonological nonword errors on the PNT. Treatment-order analyses revealed no significant order effects. Conclusions: Our results indicate a shift in naming error types, particularly after tDCS treatment for the untrained naming task (PNT). These findings may help guide the course of treatment approaches of those with aphasia and what error naming pattern types may show changes post stroke when combining non-invasive brain stimulation and computerized aphasia therapy. Clinical Trial Registration: Cerebellar Transcranial Direct Current Stimulation and Aphasia Treatment [NCT02901574] Keywords: aphasia, naming errors, non-invasive brain stimulation, cerebellar tDCS, computerized aphasia treatment

05.
arXiv (CS.LG) 2026-06-12

Is Spurious Correlation Removal Always Learnable?

arXiv:2606.12930v1 Announce Type: new Abstract: Invariant learning can fail even when the invariant structure is statistically identifiable. We show a conditional computational barrier: under a black-box samplable supervised sparse recovery primitive motivated by average-case sparse-recovery reductions, there exist samplable multi-environment instances with a one-dimensional predictive invariant subspace ($k=1$) that are learnable with polynomial samples by exhaustive search, while any polynomial-time constant-accuracy recovery algorithm would contradict the primitive. We further quantify environment diversity by a separation parameter $\gamma$, which controls identifiability and the curvature of invariance objectives. Under sufficient diversity and local Gaussian regularity, the minimax risk is $\mathbb{E}[\dist(\hat{V},V_{\mathrm{inv}})^2]=\Theta(k(d-k)/(n|\mathcal{E}|))$, and under label-induced shifts a phase transition occurs at $n^*\propto k(d-k)/(|\mathcal{E}|\gamma^2)$ with refined estimation error scaling proportional to $1/\gamma^2$. Synthetic and real datasets illustrate the predicted gaps and transitions and motivate simple diversity diagnostics.

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

NeuroClaw Technical Report

Agentic artificial intelligence systems promise to accelerate scientific workflows, but neuroimaging poses unique challenges: heterogeneous modalities (sMRI, fMRI, dMRI, EEG), long multi-stage pipelines, and persistent reproducibility risks. To address this gap, we present NeuroClaw, a domain-specialized multi-agent research assistant for executable and reproducible neuroimaging research. NeuroClaw operates directly on raw neuroimaging data across formats and modalities, grounding decisions in dataset semantics and BIDS metadata so users need not prepare curated inputs or bespoke model code. The platform combines harness engineering with end-to-end environment management, including pinned Python environments, Docker support, automated installers for common neuroimaging tools, and GPU configuration. In practice, this layer emphasizes checkpointing, post-execution verification, structured audit traces, and controlled runtime setup, making toolchains more transparent while improving reproducibility and auditability. A three-tier skill/agent hierarchy separates user-facing interaction, high-level orchestration, and low-level tool skills to decompose complex workflows into safe, reusable units. Alongside the NeuroClaw framework, we introduce NeuroBench, a system-level benchmark for executability, artifact validity, and reproducibility readiness. Across multiple multimodal LLMs, NeuroClaw-enabled runs yield consistent and substantial score improvements compared with direct agent invocation. Project homepage: https://cuhk-aim-group.github.io/NeuroClaw/index.html

07.
arXiv (CS.CL) 2026-06-18

DreamReasoner-8B: Block-Size Curriculum Learning for Diffusion Reasoning Models

Block diffusion language models accelerate decoding through parallel block-wise denoising, yet whether they can be reliably scaled for long chain-of-thought (CoT) reasoning remains unresolved. To this end, we develop DreamReasoner-8B, an open-source block diffusion reasoning model, and conduct a systematic study of how training and inference block sizes affect long-CoT reasoning. Our analysis reveals a stark performance disparity: training with large block sizes yields remarkably poor reasoning, whereas small block sizes preserve effective reasoning. To bridge this granularity gap, we propose block-size curriculum learning, which gradually transitions training from fine-grained to coarse-grained block sizes, thereby overcoming this limitation and enabling strong reasoning performance that generalizes across diverse inference block sizes. On mathematical and code reasoning benchmarks, DreamReasoner-8B achieves results competitive with leading open autoregressive models such as Qwen3-8B. This work establishes a practical foundation for efficient, reasoning-capable diffusion language models. We release our model at https://github.com/DreamLM/DreamReasoner.

08.
arXiv (CS.AI) 2026-06-12

Humor Style Drives Laughter, Topic Shapes Acceptability: Evaluating Bilingual Personal and Political Robot-Delivered AI Jokes

arXiv:2606.13256v1 Announce Type: cross Abstract: Humor plays a central role in human social relationships, and recent advances in computational humor create new opportunities for integrating humor into human-robot interaction (HRI). While large language models (LLMs) can generate diverse forms of humor, it remains unclear how humor style, joke content, and language preference shape perceptions of robot-delivered humor in group settings. In this exploratory study, we employed a mixed factorial design in which participants evaluated AI-generated jokes delivered by a robot in a university classroom. We examined the effects of humor type (Affiliative, Self-Enhancing, Aggressive, Self-Defeating) and joke content (person-related vs. political) on perceived funniness and appropriateness, as well as preferred language. Results show that humor type significantly influences funniness, with Aggressive and Affiliative humor rated higher, while joke content primarily affects appropriateness, with person-related jokes preferred over political ones. Language preference was shaped by both joke content and participants' self-reported fluency and humor practices.

09.
arXiv (CS.CL) 2026-06-11

WorldReasoner: Evaluating Whether Language Model Agents Forecast Events with Valid Reasoning

Forecasting real-world events requires language-model agents to reason under uncertainty from incomplete, time-bounded information. Yet evaluating whether agents genuinely forecast requires more than final-answer accuracy: a model may be correct by recalling memorized training facts, citing fabricated evidence, or producing an unsupported causal story. We present WorldReasoner, an evaluation framework for temporally valid event forecasting. Each task gives an agent a resolved forecasting question, a simulated forecast date, and access only to evidence available before that date; after resolution, the framework scores the submitted probability, cited evidence, and optional causal event graph. WorldReasoner reports three complementary axes: outcome quality against resolved answers, evidence quality over cited sources, and reasoning quality against post-resolution hindsight graphs. The benchmark is built by an agentic construction pipeline that generates forecasting questions, collects time-stamped evidence, and builds hindsight reference graphs at scale, yielding 345 resolved tasks derived from 14,141 articles with graphs covering 8,087 extracted events. Across six controlled agent settings, temporally valid retrieval is the strongest driver of outcome accuracy; causal graph construction improves key-event recovery; and correct graph-enabled forecasts are more strongly grounded in key events and relevant sources, yet agents still struggle to convert grounded evidence into calibrated probabilities.

10.
arXiv (CS.LG) 2026-06-11

Learning What to Say to Your VLA: Mostly Harmless Vision Language Action Model Steering

arXiv:2606.12299v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models provide a natural language interface to robot control, but the mapping from language to behavior is often brittle and unintuitive: semantically similar instructions can induce drastically different behaviors, while some capabilities may not be elicitable through prompting alone. As a result, both human instructions and zero-shot language models can fail to reliably steer VLAs toward successful task execution. In this work, we propose a framework that interactively searches for language sequences that improve closed-loop VLA task performance, distills these sequences into a test-time language feedback policy (LFP), and learns an improvement head that predicts when language steering will improve performance. We conformalize this improvement head to prevent harmful steering interventions, where the LFP decreases task performance relative to the original instruction on out-of-distribution scenarios. Crucially, our approach operates on arbitrary frozen pre-trained VLAs, requiring neither access to the original training distribution nor fine-tuning of the underlying model. On seen environments, our conformalized LFP improves base VLA performance by 24.7% in simulation and 65.0% in hardware. On visual and semantic perturbations, our conformalized LFP has strong harmlessness guarantees, and produces recovery behaviors not observed with open-loop prompting.

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

GraphInfer-Bench: Benchmarking LLM's Inference Capability on Graphs

Graph analysis underlies many applications whose answers cannot be looked up in a single record or retrieved along a path: laundering rings, drug repurposing, user preference, and scientific theme are all inferred from a node together with its neighbourhood. We introduce GraphInfer-Bench, a benchmark for whether LLMs can perform this graph inference: producing an open-ended answer that no single node supports and no path retrieves. Existing graph-QA protocols cannot test this capability: algorithm simulation, node classification, single-node description, KG-QA, and GraphRAG all admit answers retrievable from one node or along a path. GraphInfer-Bench defines five tasks along Description (what a region is) and Comparison (how regions differ), each constructed so the ground truth lives in no single node. The release contains 42,000 samples across six real-world graphs, produced automatically and screened by a four-layer quality-control protocol. We evaluate four method families against the same tasks: graph-token alignment models, zero-shot frontier closed-source LLMs, Graph2Text supervised fine-tuning, and plain GNNs as a structural reference. No method family closes the gap. Graph-token alignment partially handles description tasks (relational, theme) but collapses on comparison tasks. Frontier LLMs lead on outlier detection and community partition among LLM-based methods but lag on masked-node prediction. Graph2Text SFT is the strongest LLM-based method on the description side yet falls behind frontier LLMs on comparison. Across every task, plain GNNs match or beat the strongest LLM-based row, with the largest margin on community detection. GraphInfer-Bench surfaces graph inference as an open capability gap rather than a property of any one architecture.

12.
arXiv (math.PR) 2026-06-19

The central heat trace on large compact classical groups

arXiv:2511.08288v2 Announce Type: replace-cross Abstract: We study the large-$N$ asymptotics of the central trace of the heat kernel on compact classical groups. For every classical family $G_N\subset \mathrm{GL}_N(\C)$, we prove a full large-$N$ asymptotic expansion, using a highest weights/partitions correspondence adapted to the large-rank regime, under which the eigenvalues of the Laplace–Beltrami operator stabilize as observables in the algebra of shifted symmetric functions. Then, we prove a random surface representation of the trace in terms of ramified coverings of the torus. We provide two independent applications: an explicit large-rank counting law for the Casimir spectrum, with exponential Hardy–Ramanujan-type growth in contrast with the polynomial behavior of Weyl's law at fixed rank, and a rigorous probabilistic formulation of the Yang–Mills/Hurwitz duality on a two-dimensional torus initiated by Gross and Taylor, completing a previous work of the authors. We also extend this duality to a Yang–Mills/Gromov–Witten duality by expressing the coefficients of the central heat trace as explicit functionals of the generating function of Gromov–Witten invariants.

13.
arXiv (CS.CL) 2026-06-16

XAI-Grounded Explanation Generation for Speech Deepfake Detection with Training-Free Multimodal Large Language Models

Speech deepfake detection (SDD) systems require trustworthy explanations for reliable decision-making. Existing explanation ways mainly fall into two categories. Traditional explainable AI (XAI), such as gradient-based attribution, produces low-level attribution signals tightly coupled with model decisions, and harder to be understood by human than natural language explanations. Meanwhile, large language model (LLM)-based explanation generation often produces generic and ungrounded descriptions due to the lack of heuristic evidence and task-specific supervision, stemming from limited grounded explanation datasets for SDD. We therefore propose a training-free explanation framework that integrates XAI evidence with multimodal LLMs to generate grounded and specific explanations. Using the PartialSpoof dataset, we construct a grounded explanation dataset and show that methods with XAI increase inside accuracy by over 45\%, verified through human evaluation and faithfulness checks.

14.
arXiv (CS.CL) 2026-06-12

Examining the Cognitive Gap Between Authors and Peer Reviewers on Academic Paper Novelty

Novelty is a crucial metric for assessing the quality of academic papers. Scholars strive to highlight the novel aspects of their work, particularly in the title, abstract, and introduction. Peer review, serving as the gatekeeper of scientific rigor, rigorously evaluates the novelty of papers, yet a cognitive gap may exist between author self-promotion and reviewer evaluation. To investigate this, we analyzed 15,328 academic papers published in Nature Communications from 2016 to 2021, along with their peer-review comments. We found that both reviewers and authors emphasize result-oriented innovation, with reviewers adopting a more comprehensive evaluation perspective. Furthermore, by examining promotional intensity against inherent paper novelty, we found that its effect depends on the paper's actual innovation level. Highly innovative papers benefit from stronger promotional language, receiving more positive evaluations. We also found that promotional language significantly correlates with reviewer disagreement on novelty specifically for papers of moderate innovativeness, whereas it has negligible impact for papers with either very high or very low novelty. This reveals how promotional language operates most prominently in the gray area of academic evaluation.

15.
arXiv (CS.AI) 2026-06-19

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

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

16.
arXiv (quant-ph) 2026-06-17

Variational Quantum Eigensolver-Based Quantum Bootstrap Embedding for Molecules

作者:

arXiv:2606.17095v1 Announce Type: cross Abstract: Simulating strongly correlated molecular systems on near-term quantum hardware remains challenging due to modern hardware's limited quantum volume and moderate-fidelity qubits. One potential way to circumvent this challenge is through bootstrap embedding (BE). Bootstrap embedding breaks molecules into smaller fragments that are then embedded into the "bath" of other fragments in an iterative way. Bootstrap embedding is appealing for quantum simulation because fragmenting the system reduces the qubit requirements for any given fragment. In this work, we develop a quantum bootstrap embedding (QBE) workflow that uses variational quantum eigensolver (VQE) fragment solvers and study the algorithmic choices that determine the overall VQE-QBE algorithm's success. To improve efficiency, we introduce FastAdaptVQE, a sparse matrix-accelerated form of the adaptive variational quantum eigensolver (ADAPT-VQE) that replaces symbolic commutator evaluation with direct statevector linear algebra, and MatrixFreeAdaptVQE, a matrix-free extension that removes the sparse-matrix memory bottleneck that appears when treating larger fragments. We also modify the ADAPT-VQE operator selection step by replacing the purely greedy choice with a look-ahead strategy. Benchmarks on $H_4$ and $F_2$ reach chemical accuracy, within 1 kcal/mol of bootstrap embedding results using a full configuration interaction (FCI) solver. These results show that combining QBE with VQE can accurately calculate energies of molecular systems. This research lays the foundation for extending energy calculations to larger molecular systems and quantum materials on near-term quantum hardware.

17.
arXiv (CS.CL) 2026-06-16

SkillWiki: A Living Knowledge Infrastructure for Agent Skills

While knowledge is managed through Wikipedia and software through GitHub, agent skills still lack an infrastructure for large-scale production, governance, and evolution. SkillWiki is a living knowledge infrastructure that supports the organization, grounding, and continuous evolution of agent skills by transforming heterogeneous knowledge into reusable skill assets linked to their originating evidence. Our demonstration presents the complete skill lifecycle, from knowledge ingestion and skill production to provenance-aware exploration, governance, and execution-driven evolution. SkillWiki highlights a future in which knowledge, skills, and execution experience co-evolve within a shared infrastructure. The live demonstration and source code are publicly available at https://github.com/Huangdingcheng/SkillWiki.

18.
arXiv (math.PR) 2026-06-11

Matrix Discrepancy for Representations of Finite Groups

arXiv:2606.12181v1 Announce Type: new Abstract: Given a finite group $G$, we prove that there exist signs $\varepsilon\in\{\pm1\}^G$ such that $$\left\| \sum_{g\in G} \varepsilon_g\rho(g) \right\|\leq C\, \sqrt{|G|},$$ where $\rho$ is the left regular representation of $G$, and $C$ is a universal constant. This special case of the Matrix Spencer conjecture was posed in [BKMZ24], where it was established for simple groups.

19.
arXiv (CS.CL) 2026-06-16

A large-scale pipeline for LLM-assisted corpus annotation: variation and change in the English consider construction

As natural language corpora expand at an unprecedented rate, manual annotation remains a significant methodological bottleneck in corpus linguistic work. We address this challenge by presenting a scalable pipeline for automating grammatical annotation in voluminous corpora using large language models (LLMs). Unlike previous supervised and iterative approaches, our method employs a four-phase workflow: prompt engineering, pre-hoc evaluation, automated batch processing, and post-hoc validation. We demonstrate the pipeline's accessibility and effectiveness through a diachronic case study of variation in the English evaluative consider construction (consider X as/to be/{\O} Y). We annotate 143,933 'consider' concordance lines from the Corpus of Historical American English (COHA) via the OpenAI API in under 60 hours, achieving 98%+ accuracy on two sophisticated annotation procedures. A Bayesian multinomial GAM fitted to 44,527 true positives of the evaluative construction reveals previously undocumented genre-specific trajectories of change, enabling us to advance new hypotheses about the relationship between register formality and competing pressures of morphosyntactic reduction and enhancement. Our results suggest that LLMs can perform a range of data preparation tasks at scale with minimal human intervention, unlocking substantive research questions previously beyond practical reach, though implementation requires attention to costs, licensing, and other ethical considerations.

20.
arXiv (CS.CL) 2026-06-16

GRACE: Step-Level Benchmark for Faithful Reasoning over Context

Many reasoning tasks require models to reason over input context, from document-grounded question answering to rule-based deduction. Chain-of-Thought (CoT) prompting produces traces that appear transparent, yet individual steps can silently deviate from the source evidence, even when the final answer is correct. Existing methods detect hallucinations at the response level but fail to identify where in the chain a failure occurs or what type it is. We introduce GRACE, the first human-annotated step-level faithfulness benchmark with a data-driven error taxonomy for context-grounded textual reasoning. GRACE covers CoT traces from 10 models across 4 source datasets, with each step annotated for faithfulness, error category, and natural language explanation. A data-driven taxonomy, discovered bottom-up via unsupervised clustering, organizes failures into two tracks: GRACE-Inference (deductive errors) and GRACE-Grounding (factual grounding errors), with four categories each. The evaluation set is human-annotated and challenging by design. Our experiments reveal substantial headroom for current models. In addition, integrating step-level faithfulness signals into reinforcement learning pipelines improves both downstream accuracy and reasoning reliability.

21.
arXiv (CS.CV) 2026-06-11

CoVEBench: Can Video Editing Models Handle Complex Instructions?

While recent text-guided video editing models excel at elementary tasks (e.g., style transfer, object insertion), real-world user requests are highly compositional. A single prompt often demands multiple coupled edits, such as modifying subjects, actions, and camera views, while strictly preserving unrelated spatiotemporal content. Existing benchmarks, heavily constrained by isolated edits and coarse global metrics, fail to diagnose how models handle such complex workflows. To address this gap, we introduce CoVEBench, a compositional video editing benchmark comprising 416 curated source videos, 626 multi-point editing instructions, and 9,990 fine-grained checklist items. Covering diverse editing dimensions, CoVEBench evaluates models via MLLM-judged instruction compliance and video fidelity, alongside automated metrics for video quality. Extensive experiments reveal that compositional editing remains a profound challenge: current models frequently omit edits, violate preservation constraints, or introduce artifacts when handling multiple operations simultaneously. CoVEBench provides a challenging, diagnostic testbed to advance video editing toward realistic user workflows.

22.
arXiv (CS.CL) 2026-06-11

Models That Know How Evaluations Are Designed Score Safer

The validity of AI safety evaluations depends on models behaving consistently across controlled and deployment settings. Prior work has identified test-time contextual cues, such as hypothetical scenarios, as a source of verbalized evaluation awareness and subsequent behavioral shift. In this paper, we investigate a potential explanation of this phenomenon: evaluation meta-knowledge, defined as parametric knowledge about the structural traits that characterize evaluations. Similar to dataset contamination, where benchmark exposure leads to higher performance through memorization, we hypothesize that models trained on texts describing evaluation practices may implicitly learn to recognize and respond to evaluation-like contexts, for instance, through exposure to scientific articles or social media posts about AI benchmarking. To test this, we fine-tune models on synthetic documents describing evaluation traits such as verifiable structures or moral dilemmas. Evaluating this fine-tuned model on six safety benchmarks, we find that it is significantly safer than the base model and control model. This behavioral shift persists even when restricting the analysis to responses lacking explicit verbalization of evaluation awareness. Our results demonstrate that evaluation meta-knowledge may inflate safety benchmark performance, introducing a novel confounder that is independent of explicit memorization or verbalized evaluation awareness, thus, challenging to detect. These findings have important implications for the design and interpretation of AI safety evaluations. Our code and models are available at https://github.com/compass-group-tue/arxiv2026_evaluation_meta_knowledge.

23.
arXiv (quant-ph) 2026-06-19

Operator Learning for efficient Quantum Computation

arXiv:2606.20184v1 Announce Type: new Abstract: An efficient implementation of quantum algorithms is often hindered by the lack of efficient primitives for operators and state preparation. This limits both the ability of near-term quantum hardware to simulate complex problems and the potential of fault-tolerant algorithms to achieve practical quantum advantage. To address this, we propose a full-stack variational framework that transforms arbitrary operators to compact quantum circuits. The resulting variational circuits can be tailored to the connectivity and long-range interaction of the target hardware. The learning process employs backpropagation together with a cost function that efficiently optimizes unitary operators and non-unitary – dense or sparse – operators using only a single ancilla qubit for block encoding. Additionally, we introduce a regularization term that reduces the approximation error. The approach is validated for both quantum mechanical and engineering applications. In the former case, we learn propagators that arise in native quantum problems – such as quantum simulation and quantum chemistry – and achieve improved resource scaling in comparison to standard Suzuki-Trotter expansions. In the latter case, we demonstrate the approach's ability to implement the second-order central finite difference approximation of the Laplace operator – relevant for solving partial differential equations – while improving upon current error metrics. The final example deals with learning a dense, non-unitary operator that arises in the analysis of inviscid potential flow around an airfoil. This universality of the framework opens the door for solving general problems beyond prototypical engineering and quantum applications.

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

Thinking with Visual Grounding

arXiv:2606.16122v1 Announce Type: new Abstract: Visual thinking should not only sound right; it should show its evidence. While recent vision-language models (VLMs) can produce natural-language reasoning traces, these traces often leave the supporting image regions implicit, making them hard to verify and difficult to supervise. We introduce visually grounded thinking, a reasoning process in which models interleave natural-language thoughts with explicit point or box groundings of the visual evidence used at each step. This lets the model express intermediate reasoning in language while grounding key objects in the image regions they refer to. To train this behavior, we construct a scalable synthesis pipeline that distills correct visual reasoning traces, extracts the visual objects required by the traces, grounds them with a SAM3-based agent, and derives aligned point and box supervision from the resulting masks. We further propose grounding-aware reinforcement learning, which combines answer correctness rewards with dense grounding rewards that score whether generated object references match the correct image evidence. Across two counting benchmarks and four spatial reasoning benchmarks, adding visually grounded thinking to Gemma3-4B-IT consistently improves performance over the original model and the non-grounded thinking baseline. On spatial reasoning, the visually grounded thinking 4B models match, and in some cases surpass, Gemma3-27B-IT from the same model family. Our analysis shows that point grounding is well suited to counting, while box grounding benefits most from explicit grounding rewards on spatial tasks. Overall, our results show that VLMs think better when their intermediate thoughts are tied to the image regions that make them true.

25.
arXiv (CS.LG) 2026-06-12

PhysMetrics.Weather: An Evaluation Framework for Physical Consistency in ML Weather Models

arXiv:2606.10642v2 Announce Type: replace Abstract: Machine learning weather prediction (MLWP) models have achieved impressive forecasting performance at a small fraction of the computational costs required for traditional physics-based methods. However, they are primarily (1) data-driven and (2) evaluated using pixel-wide error metrics (e.g., RMSE), so there are no guarantees that their forecasts are consistent with known physical laws. We introduce PhysMetrics$.$Weather, an evaluation framework that assesses the physical realism of MLWP models across three types of metrics: conservation, spectral, and dynamical. By quantifying physical realism, this tool guides the development of physics-informed architectures and helps evaluate whether MLWP models are reliable for operational use. Our framework is available on Github at https://github.com/Emmakast/PhysMetrics.Weather.