探索全球前沿学术脉络

01.

Nature (Science) 2026-06-12 DOI: HASH:b76b70f83b4df9e48ac849f1596ca545

Daily briefing: How Venus flytraps snap shut

作者:

Flora Graham↗

Softening cells enable flytraps to shut with astonishing speed. Plus, the cutting-edge science happening at the World Cup and why scientists shouldn’t ignore the Pope’s AI message. Softening cells enable flytraps to shut with astonishing speed. Plus, the cutting-edge science happening at the World Cup and why scientists shouldn’t ignore the Pope’s AI message.

阅读与讨论 → 访问原文 →

02.

arXiv (CS.LG) 2026-06-12 DOI: arXiv:2606.12507

Rubric-Guided Self-Distillation: Post-Training Without Rubric Verifiers

作者:

MohammadHossein Rezaei↗Anas Mahmoud↗Zihao Wang↗Utkarsh Tyagi↗Advait Gosai↗Razvan-Gabriel Dumitru↗Aakash Sabharwal↗Bing Liu↗Yunzhong He↗

arXiv:2606.12507v1 Announce Type: new Abstract: Rubrics have emerged as an alternative to RLVR in open-ended domains where a single ground-truth final answer is not available. Existing rubric-based training methods rely on an LLM verifier that scores each rollout against rubrics. This introduces substantial training-time overhead, exposes optimization to verifier-specific biases, and reduces rubric feedback to a sparse end-of-trajectory signal. We propose Rubric-Guided Self-Distillation (RGSD), a verifier-free training method in which the base policy, conditioned on the rubric, serves as the teacher for the unconditioned student. RGSD distills the rubric-conditioned teacher distribution into the student token-by-token, replacing sparse trajectory-level rewards with dense per-token learning signals and removing the LLM judge from the training loop entirely. Across Qwen-2.5 (3B, 7B) and Qwen3-Thinking (4B, 8B) models on medical and science domains, RGSD achieves rubric satisfaction comparable to judge-based GRPO while using one on-policy rollout per prompt and no training-time verifier calls. Ablations show that raw rubrics provide a stronger teacher enrichment signal than self-generated reference responses, while a stronger GRPO judge can outperform RGSD in some settings, positioning RGSD as a complementary verifier-free alternative when verifier cost or reliability is the bottleneck.

阅读与讨论 → 访问原文 →

03.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.16407

A Mechanistic Understanding of Pronoun Fidelity in LLMs

作者:

Katharina Trinley↗Jesujoba O. Alabi↗Dietrich Klakow↗Vagrant Gautam↗

Faithful and robust pronoun use is important for fair and coherent generations, yet large language models largely fail when multiple referents use different pronouns. To study the interplay of reasoning, repetition, and bias in this task, prior work relies exclusively on behavioural approaches, which may not reflect a model's internal workings. Therefore, we provide a mechanistic, model-internal perspective on pronoun fidelity, testing whether three mechanisms – group entity binding (G), recency bias (R), and stereotypical bias (S) – are causally implemented across several SOTA language models. Using Boundless Distributed Alignment Search, we find all three coexist as causal subspaces distributed across network depth. No single mechanism fully explains model behaviour, but a combination of the three consistently accounts for 91-99.5%. An attention head analysis further reveals two competing copying routes; group binding and stereotype share a localized concept-level route that retrieves a bound occupation-pronoun unit, while recency uses a distributed token-level route that repeats surface forms. In sum, pronoun fidelity arises from competition between simultaneously active causal subspaces.

阅读与讨论 → 访问原文 →

04.

arXiv (CS.CL) 2026-06-19 DOI: arXiv:2606.19808

Think Again or Think Longer? Selective Verification for Budget-Aware Reasoning

作者:

Sajib Acharjee Dip↗Dawei Zhou↗Liqing Zhang↗

Test-time reasoning is increasingly used as a serving-time control knob, but extra reasoning is not uniformly valuable: it can repair failed attempts, waste compute on already-correct answers, or introduce harmful answer changes. We study this as a deployment allocation problem rather than a new-verifier problem. We introduce \sevra, Selective Verification for Reasoning Allocation, a serving-layer controller that decides whether to preserve a frozen solver's initial answer or invoke active verification. Using a frozen Qwen3-4B solver, we log intervention outcomes and train recoverability-aware gates from serving-visible attempt state. On \mathfive, selective verification reaches 76.3\% accuracy, compared with 75.5\% for always verifying, while reducing post-generation tokens by 26.8\% and harmful flips from 2.2\% to 1.0\%. However, an 8,192-token initial solve reaches 76.0\% accuracy with 28\% fewer total model tokens, showing that selective recovery is useful but not the best tested cost frontier. In frozen transfer to \gsm, the selective policy verifies only 3.0\% of examples, improves accuracy from 93.4\% to 94.5\%, and reduces verification tokens by 91.2\% relative to always verifying; again, a longer initial solve matches its accuracy with fewer realized tokens. On CommonsenseQA, always-on verification hurts, while Self-Consistency@5 improves accuracy at about five times the realized token cost. The resulting deployment rule is: tune the initial budget first, then use selective recovery when explicit checks, bounded retries, auditability, or regression-risk control matter.

阅读与讨论 → 访问原文 →

05.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.12203

Adaptive Multi-Resolution Procedural Knowledge Compression for Large Language Models

作者:

Changyue Wang↗Weihang Su↗Qingyao Ai↗Yichen Tang↗Runzhong Qiao↗Xuancheng Li↗Min Zhang↗Yiqun Liu↗

Large language models (LLMs) are widely used to tackle complex tasks with autonomous workflows. Recently, reusable natural language skills have emerged as a popular paradigm to inject procedural knowledge into LLM applications. Since popular skills are often invoked repeatedly, placing their full text in every context significantly increases prefill cost and latency. While text compression techniques have the potential to solve this problem, most existing methods are designed to compress factual knowledge in documents instead of procedural knowledge, making them insufficient for skill compression. In this paper, we argue that an effective skill compression method should: 1) preserve logical dependencies among workflows and tool protocols, 2) enable lightweight, offline compression for frequently updated community skills, and 3) be adaptable to varying complexities across skills. To address this, we present SKIM (SKIll coMpression), an adaptive multi-resolution soft token compression framework for procedural skills. Depending on the complexity of each skill, SKIM creates different numbers of soft tokens that not only improve the efficiency of LLM inference, but also preserve the effectiveness of skill usage. Experiments indicate that SKIM compresses skills to 30 to 60 percent of their original token length while preserving task performance better than existing compression methods.We have released our code at https://github.com/bebr2/SKIM .

阅读与讨论 → 访问原文 →

06.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2605.12713

Controllable Quantum Memory Capacity in Quantum Reservoir Networks with Tunable partial-SWAPs

作者:

Erik L. Connerty↗Ethan N. Evans↗

arXiv:2605.12713v3 Announce Type: replace-cross Abstract: In the field of quantum reservoir computing (QRC), many different computational models and architectures have been proposed. From these models, we identify feedback-based models – which use a feedback mechanism to re-embed classical measurements from the QRC – and recurrent models – which use a multi-register approach with memory and readout qubits – as the two major competing architectures that have been discussed and validated on hardware. In this paper, we advance upon the recurrent architectures, which employ a two register approach to endow the QRC with a fading memory. While these approaches have been validated on hardware and have demonstrated great real-world performance on noisy-intermediate-scale-quantum (NISQ) quantum processing units (QPUs), the exact mechanism through which the memory capacity arises is not completely understood or fully controllable. With this, we augment the recurrent approaches and present a hardware-realizable mechanism, which we call a tunable partial-SWAP, that allows for the direct control of the rate of memory dissipation from a QRN implemented on a gate-based QPU. The theory behind this mechanism is discussed in terms of a controlled amplitude-damping channel and validation experiments using a randomized short-term memory capacity (STMC) recall benchmark and the NARMA-5 dataset are conducted using simulation and IBM QPUs, respectively.

阅读与讨论 → 访问原文 →

07.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2606.14211

Closing the Reflection Gap: A Free Calibration Bonus for Agentic RL

作者:

Yinglun Zhu↗

arXiv:2606.14211v1 Announce Type: new Abstract: LLMs are increasingly deployed as agents that interact with external environments and observe feedback such as execution results, error messages, and tool outputs. A well-functioning agent should be able to leverage this feedback to accurately assess its own performance. Yet we find a persistent reflection gap: LLM agents tend to mis-assess their own outputs after observing concrete environment feedback – even for questions they correctly answered – and standard RL barely helps due to a credit-assignment mismatch. To close this gap, we propose RefGRPO, a simple yet effective fix that augments standard RL algorithms with two key ingredients: a free calibration bonus computed by contrasting the agent's own reflection with the actual outcome (requiring no additional reward model, LLM judge, or external annotation), and a dynamic schedule on its coefficient. Compared to standard RL baselines, our method simultaneously improves reflection calibration (e.g., reduces underconfidence rate $44.4\% \to 7.7\%$) and task accuracy (e.g., $75.1\% \to 76.5\%$) on text-to-SQL across five benchmarks. The resulting calibrated reflection turns the agent into its own verifier grounded in environment feedback, which further enables (i) better self-improvement that uses reflections as pseudo-rewards without outcome supervision, and (ii) more effective test-time selective prediction by committing only to rollouts flagged as correct.

阅读与讨论 → 访问原文 →

08.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2606.13100

LEDGER: A Long-Context Benchmark of Corporate Annual Reports for Grounded Financial Retrieval and Extraction

作者:

Charles Moslonka↗Amaury de Vitry↗Arthur Garnier↗Hicham Randrianarivo↗Emmanuel Malherbe↗

Finance reporting is a natural proving ground for large language models, and the very-long-context capabilities of recent models across all sizes make rigorous evaluation in this domain an increasingly pressing need. Yet most public financial resources reduce the task to plain-text SEC 10-K filings paired with a handful of question-answer items. We release LEDGER (Long-context Evaluation of Documents for Grounded Extraction and Retrieval), a corpus of 4,999 digitized corporate annual reports - full documents with figures, tables, and narrative, not just regulatory filings. Each report is labeled with 31 consolidated financial KPIs to be extracted and linked to the market's reaction at the earnings date. From this data we derive three evaluation benchmarks spanning the difficulty spectrum: a pure page-level KPI retrieval task with TREC-style relevance judgments over 118,048 questions in natural language, a conversational "needle-in-a-haystack" single-value lookup, and a full KPI extraction task, both from long, numerically dense reports. We additionally provide human OCR-quality annotations with inter-annotator agreement and the complete extraction, validation, and scoring toolchain. We further demonstrate the dataset's research utility with a case study linking CEO-letter rhetoric to post-publication market impact.

阅读与讨论 → 访问原文 →

09.

arXiv (quant-ph) 2026-06-12 DOI: arXiv:2402.14755

Entanglement Detection by Approximate Entanglement Witnesses

作者:

Samuel Dai↗Ning Bao↗

arXiv:2402.14755v2 Announce Type: replace Abstract: The problem of determining whether a given quantum state is separable is known to be computationally difficult. We develop an approach to this problem based on approximations of convex polytopes in high dimensions. By showing that a convex polytope constructed from a finite number of hyperplanes approximates the Euclidean ball arbitrarily well in high dimensions, we find evidence that a finite set of approximate entanglement witnesses is potentially sufficient to determine the entanglement of a state with high probability.

阅读与讨论 → 访问原文 →

10.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.17028

HAMON: Passive Optical Sequence Mixing for Long-Horizon Forecasting

作者:

Alper Y{\i}ld{\i}r{\i}m↗

arXiv:2606.17028v1 Announce Type: cross Abstract: Simple linear and frequency-domain models remain surprisingly competitive in long-horizon time-series forecasting, and recent mechanistic evidence suggests that standard forecasting benchmarks may not require the dense superposed representations that make transformers powerful in other domains. This raises a substrate-level question: if the core forecasting operator is often low-complexity and approximately linear, does it need to be implemented as learned digital temporal mixing? We introduce HAMON, a passive diffractive optical forecasting core in which historical values are encoded onto an optical aperture, future positions are left dark, and cascaded trainable phase masks with free-space diffraction shape the forecast directly in the output field. At inference, prediction is performed by a single passive optical propagation pass with no trainable digital sequence-mixing layer. Across standard benchmarks, HAMON outperforms the strongest digital baselines considered on ETTm2 at all horizons and on ETTh2 at all but the longest horizon, improving MSE by up to 14\% and doing so consistently across horizons rather than at isolated points. It is competitive on Weather and trails the strongest baselines on the remaining ETT settings and on the high-channel-count Traffic and Electricity datasets. Phase encoding, intensity-compatible readout, and phase-scrambling ablations, together with a TorchOptics cross-simulator check, indicate that the forecasts arise from the data-bearing optical field rather than from a digital forecasting head. Because the passive core uses standard Fourier optics, HAMON defines a concrete target for optical hardware and for passive physical sequence mixing.

阅读与讨论 → 访问原文 →

11.

arXiv (CS.CL) 2026-06-17 DOI: arXiv:2606.18158

The Measurement Gap in the Automation of EU Law: Benchmarking Doctrinal Legal Reasoning under the EU AI Act

作者:

Mich\`ele Finck↗

Large language models now produce legal text of at least median quality, yet no existing benchmark can evaluate whether they perform doctrinal legal reasoning, which forms the interpretive core of legal work, rather than the ancillary, paralegal tasks that most current legal-AI evaluations measure. This measurement gap is not only methodological but legal: the EU AI Act makes "appropriate accuracy" a binding requirement for high-risk AI used in the judicial domain, yet that requirement cannot acquire operational content without the very doctrinal-reasoning benchmark the field lacks.

阅读与讨论 → 访问原文 →

12.

bioRxiv (Bioinfo) 2026-06-16 DOI: HASH:9d473aed50fe8d9f178c00ebae70fa0e

Evidence for recombination in dengue virus genomes

作者:

de Paula Oliveira↗Jacob Machado↗Prieto Oliveira↗Ocana↗

Recombination is a key driver of RNA virus evolution, yet its extent and evolutionary implications in dengue virus (DENV) remain incompletely understood. We conducted a comprehensive, genome-wide recombination screen across 6,905 complete DENV genomes representing all four serotypes, 82 countries, and eight decades of sampling (1944-2023) retrieved from the Bacterial and Viral Bioinformatics Resource Center. Using seven complementary recombination detection methods implemented in RDP5, we identified 66 recombination events across 53 unique recombinant sequences, of which 29 are newly described. Events included intra-genotypic (n = 18), inter-genotypic (n = 32), and inter-serotypic (n = 16) exchanges spanning 14 genotypes and four continents, with no meaningful serotype-level enrichment (Cramer's V = 0.054). Recombination was concentrated in non-structural genes, most frequently NS3 (19 events), NS5 (17), and NS2 (12), while the capsid gene contained no recombination events, consistent with strong functional constraint. Single-nucleotide polymorphism analyses confirmed low divergence between recombinants and their inferred parents in both recombinant and non-recombinant regions. Phylogenomic analysis of 6,642 sequences revealed that recombinants cluster significantly closer to their major parents (p = 8.9 x 10-6 ) and that their removal does not significantly alter tree topology (p = 0.898), suggesting that the short length of recombinant regions limits phylogenetic conflict. We also introduce RECOSIM, an unsupervised machine-learning tool for recombination detection that achieved higher precision than RDP5 on both simulated (93.4% vs. 80.0%) and empirical (98.1% vs. 39.3%) datasets. Collectively, these results establish recombination as a widespread, pan-serotypic phenomenon in DENV with implications for genomic surveillance, vaccine evaluation, and evolutionary inference.

阅读与讨论 → 访问原文 →

13.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.11211

Calibration Drift Under Reasoning: How Chain-of-Thought Budgets Induce Overconfidence in Large Language Models

作者:

Prakul Sunil Hiremath↗Harshit R. Hiremath↗

The ability of large language models (LLMs) to express calibrated uncertainty is important for safe deployment. Chain-of-thought (CoT) reasoning is widely used to improve accuracy and reliability, but its effect on calibration is not fully understood. We show that this picture is incomplete: in some settings, increasing the reasoning budget beyond a task-specific threshold can cause models to become systematically overconfident, assigning high confidence to incorrect answers. We call this phenomenon Calibration Drift Under Reasoning (CDUR) and study it both theoretically and empirically. We define reasoning budget B and analyze conditions under which Expected Calibration Error ECE(B) follows a non-monotonic pattern: it first decreases as reasoning corrects errors, then increases as longer reasoning produces internally consistent but incorrect explanations. We propose a Hypothesis Lock-In model based on autoregressive generation to explain this behavior. We evaluate Llama-3.1-8B and Llama-3.3-70B on 47 reasoning-trap questions across four reasoning budgets and three seeds (1,368 API calls; 574 valid responses). The 8B model shows non-monotonic calibration behavior, while results for the 70B model are limited to baseline evaluation and are inconclusive for budget-dependent effects. We introduce CABStop, a calibration-aware stopping rule that halts reasoning when confidence diverges from an auxiliary accuracy estimate. These results suggest that increasing reasoning depth does not always improve reliability and should be monitored carefully.

阅读与讨论 → 访问原文 →

14.

arXiv (CS.CV) 2026-06-17 DOI: arXiv:2606.17998

AIGS-Net: Compact Illumination Field Modeling via 2D Gaussian Splatting for Fast Low-Light Image Enhancement

作者:

Yuhan Chen↗Kunyang Huang↗Fuchen Li↗Zhuohan Qin↗Guofa Li↗Wenbo Chu↗Keqiang Li↗

Existing low-light image enhancement methods often face a bottleneck between the representation capacity of illumination-field modeling and computational complexity. To address this issue, this paper proposes an Adaptive Illumination Gaussian Splatting Network (AIGS-Net), an ultra-lightweight architecture for fast low-light enhancement. Unlike conventional static priors, AIGS-Net constructs an input-adaptive 2D Gaussian Splatting illumination field. The opacity of Gaussian basis functions is dynamically modulated by relative luminance statistics of the input image, and spatially varying illumination compensation is rendered through ordered alpha compositing. To guide adaptive illumination compensation efficiently, a zero-parameter nonlinear multiscale contextual encoding module is introduced to extract low-frequency structures and local contrast cues without additional convolutional weights. To suppress noise amplification and sensor-induced color bias, AIGS-Net integrates noise-mask estimation, locked single-channel Gamma mapping, cross-channel consistency regularization, and target color-alignment constraints. Experiments on LOL and LSRW benchmarks show that AIGS-Net improves detail recovery and color fidelity while requiring only approximately 40 learnable parameters, achieving an effective trade-off between enhancement quality and extreme inference efficiency.

阅读与讨论 → 访问原文 →

15.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.15923

Runtime Analysis of Cartesian Genetic Programming in Evolving Boolean Functions

作者:

Duc-Cuong Dang↗Roman Kalkreuth↗Andre Opris↗

arXiv:2606.15923v1 Announce Type: cross Abstract: Cartesian Genetic Programming (CGP) is among the practical and popular forms of Genetic Programming as it uses a graph-based representation of programs. This paper presents a first runtime analysis of CGP in evolving Boolean functions using complete training sets. We prove an asymptotic bound $O(n D^5)$ for the expected number of fitness evaluations of CGP to construct a conjunction of $n$ inputs using at most $D \geq n-1$ binary gates, a minimal function set, and even with a strict survival selection. When the non-strict selection is used, the bound is improved to $O(n D^4)$. Our analysis reveals interesting characteristics of CGP induced search, which have been only observed empirically. In particular, enabling the acceptance of equally good solutions, including those with connected gates non-contributing to fitness, can lead to a speedup, and consequently a better asymptotic time bound. In contrast to conjunctions, we also prove a negative result which shows that CGP requires exponential time to evolve an exclusive disjunction. Experiments evolving conjunctions complement our theoretical findings. The use of incomplete training sets is found to further reduce the average number of fitness evaluations while maintaining a good level of generalisation.

阅读与讨论 → 访问原文 →

16.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.19714

AURA: Adaptive Uncertainty-aware Refinement for LLM-as-a-Judge Auditing

作者:

Zilong Zhang↗Yi-Ting Hung↗Weiyi He↗Junxi Zhang↗Lei Ding↗Chi-Kuang Yeh↗

arXiv:2606.19714v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as judges for open-ended generation, as large-scale human evaluation is often expensive and difficult to scale, yet their preferences remain imperfect proxies for human judgment. Existing auditing pipelines often assume that a reliable subset of examples or clean supervision signals are available beforehand, for example from human annotation, heuristic filtering, or the outputs of strong judges. In LLM evaluation, this assumption is fragile: the initial split may inherit judge bias, while human verification is typically too scarce to define stable groups at scale. We propose AURA, an adaptive uncertainty–aware refinement framework for auditing pairwise LLM–as–a–judge decisions under selected human verification. AURA iteratively learns a human-consistency signal, propagates reliable evidence, and prioritizes uncertain comparisons for human review. The key idea is to treat trust in a judge as a latent quantity that is progressively refined as evidence accumulates. We provide a compact formulation, a stable refinement procedure, and a comprehensive evaluation on both synthetic and real pairwise LLM-answer data.

阅读与讨论 → 访问原文 →

17.

medRxiv (Medicine) 2026-06-10 DOI: HASH:b3b65f71babe7ca3801deb8ef2a09788

General-purpose large language models can achieve physician-level accuracy in complex medical data extraction

作者:

Rajeev↗Narayan↗

Background: Unstructured data represent about 80% of total electronic health records (EHR) data. Structuring this free text is essential for advancing clinical research, including cohort selection for trials, retrospective studies, and the development of disease registries. While manual chart review (MCR) remains the gold standard for extracting this clinical data, the process is inherently slow, resource-intensive, and susceptible to errors from human fatigue. We evaluated the extraction accuracy, safety, and efficiency of the HeLIX (Hepatology Logic-Integrated Extraction) framework, a Large Language Model (LLM) protocol using Google Gemini 3 Pro, compared to a gold-standard Manual Chart Review (MCR). Methods: A prospective validation study was conducted using 50 high-complexity, simulated hepatology discharge summaries designed to replicate the real-world heterogeneity of EHRs. The HeLIX framework employed a Zero-Shot, Structured Chain-of-Thought (CoT) prompting strategy enforced by a three-layer architecture: Clinical Reasoning Trace, Schema Enforcement, and Evidence Verification. The model extracted 45 distinct clinical variables. Performance was benchmarked against a consensus MCR. Results: Across 2,250 evaluated data points, the model achieved an overall Extraction Accuracy of 99.24% (95% CI: 98.8%-99.5%), with perfect concordance in 35/45 (77.8%) variables. For binary diagnostic variables, the model demonstrated an overall F1-score of 0.98, Recall of 0.99 and substantial inter-rater reliability (Cohens {kappa} = 0.97). Hallucinations were exceptionally rare (2/2250; 0.08%). Critical errors affecting clinical management occurred in only 2 instances (

阅读与讨论 → 访问原文 →

18.

arXiv (CS.AI) 2026-06-17 DOI: arXiv:2606.17199

PowerOPD: Stabilizing On-Policy Distillation with Bounded Power Transformation

作者:

Anhao Zhao↗Junlong Tong↗Yingqi Fan↗Ping Nie↗Wenjie Li↗Xiaoyu Shen↗

arXiv:2606.17199v1 Announce Type: cross Abstract: Standard on-policy distillation (OPD) for large language models estimates the reverse-KL objective using student-sampled tokens, yielding an unbiased single-sample Monte Carlo estimator that avoids vocabulary-wide computation. However, we show that this estimator suffers from severe training pathologies in practice: sample inefficiency, unstable generation dynamics, and a substantial performance gap compared to exact full-vocabulary OPD. Reward-level diagnosis traces these pathologies to the log-ratio reward, which is unbounded by construction, producing extremely high-variance gradients concentrated at early positions and persisting throughout training; standard post-hoc scaling fail as they operate only after this distortion occurs. To solve this problem, we propose PowerOPD: a family of natively bounded, sign-consistent rewards from the Box-Cox power transformation, parameterized by alpha > 0, of which the log-ratio is the degenerate alpha -> 0 limit. Across six mathematical reasoning benchmarks and four Qwen3 teacher-student pairs, PowerOPD achieves benchmark-averaged Avg@8/Pass@8 gains of up to +6.37/+5.71 over vanilla OPD, +3.01/+3.54 over post-hoc stabilization, and +2.59/+8.90 over full-vocabulary OPD, while reducing wall-clock time by 59.2% and peak GPU memory by 23.1%. Larger alpha generally improves accuracy, consistently shortens responses, and keeps gradient norms more than 3,000x smaller than vanilla OPD.

阅读与讨论 → 访问原文 →

19.

arXiv (CS.AI) 2026-06-17 DOI: arXiv:2603.28378

Membership Inference Attacks against Large Audio Language Models

作者:

Jia-Kai Dong↗Yu-Xiang Lin↗Hung-Yi Lee↗

arXiv:2603.28378v2 Announce Type: replace-cross Abstract: We present the first systematic Membership Inference Attack (MIA) evaluation of LALMs. Using Multi-modal Blind Baselines based on textual, spectral and prosodic features, we demonstrate that common audio datasets exhibit near-perfect train/test separability (AUC ~ 1.0) even without model inference, thus MIA may primarily detect distribution shift. We therefore introduce a blind-baseline protocol to control for this confound. Under this protocol, we identify that the distribution-matched datasets enable reliable MIA evaluation without distribution-shift artifacts. We benchmark multiple MIA methods and conduct modality disentanglement experiments on these datasets. The results reveal that LALM memorization is cross-modal, arising only from binding a speaker's vocal identity with its text. These findings establish a principled standard for auditing LALMs beyond spurious correlations. Our codebase is available at https://github.com/snooow1029/ALM_MIA.

阅读与讨论 → 访问原文 →

20.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2606.11976

Exploration Structure in LLM Agents for Multi-File Change Localization

作者:

Akeela Darryl Fattha↗Kia Ying Chua↗Lingxiao Jiang↗Laura Wynter↗

arXiv:2606.11976v1 Announce Type: cross Abstract: Software engineering tools increasingly rely on LLM based agents to localize files to change to resolve a software issue. Most AI agents explore repositories linearly, that is, visiting one directory or file per step. We postulate that this is a structural mismatch for changes that span several subsystems. We compare linear sequential exploration against non-linear, domain-scoped parallel agentic exploration. Using SWE Bench Pro as initial benchmark, we focus on ansible as an exemplar. We construct an approach for persistent-session evaluation of GitHub issues anchored at a single base commit. We compare our non-linear domain-agent file traversal system against a base LLM without direct repository access, a single agent Recursive Language Model (RLM) baseline with a persistent Python REPL and an external CLI baseline using Codex 5.5 High. Domain scoped parallel agent spawning with a small Haiku-class model achieves the highest micro F1 among Haiku class models by a large margin. Domain-agents is the second highest behind only the much larger Codex 5.5 High on our own expanded benchmark including over more recent PRs from 2025 and 2026. On the original, curated, 2020 SWE-bench Pro benchmark, a larger Sonnet plain LLM baseline attains higher micro F1 by predicting few files, leading to higher precision, but at significantly lower all gold recall. We also present three additional findings. First, documentation evolution is a latent dependency unresolved by any approach. Second, naive file system access can degrade localization driven by test-file over prediction. Lastly, forced multi-agent consultation does not measurably help and raises token cost substantially.

阅读与讨论 → 访问原文 →

21.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.16742

Revealing Artifacts via Noise Amplification: A Novel Perspective for AI-Generated Video Detection

作者:

Renxi Cheng↗Jie Gui↗Hongsong Wang↗

With the rapid advancement of video generation models, distinguishing between AI-generated and authentic videos has emerged as a challenging endeavor. The majority of existing research endeavors concentrate on the development of detectors for identifying samples generated by generative adversarial networks. Nevertheless, the detection of AI-generated videos, particularly those produced by text-to-video models, still remains an uncharted territory. Although state-of-the-art text-to-video models can generate realistic visual content similar to real videos, they fall short of generating the details of the images and the changes in details within the videos. Inspired by this, we address AI-generated video detection from a novel perspective of bit-planes, which can effectively describe the details or noises in images or videos. To this end, we propose a simple yet effective approach called Noise Amplification. This approach first extracts noise signals based on bit-planes, then amplifies these noise signals, and finally feeds them into the discriminator networks for video fake classification. Noise amplification is comprehensively constructed by incorporating three aspects: pixel-level intensity enhancement, region-level spatial amplification, and frame-level temporal aggregation. To evaluate methods of AI-generated video detection in challenging scenarios, we also introduce a benchmark named HardGVD. Extensive experiments on both the large-scale dataset GenVidBench and HardGVD show that our simple approach significantly outperforms state-of-the-art methods.

阅读与讨论 → 访问原文 →

22.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2606.18268

Towards Multi-Agent-Simulation-Based Community Note Evaluation

作者:

Changxi Wen↗Shuning Zhang↗Bohao Chu↗Yuwei Chuai↗Hui Wang↗Dai Shi↗Xin Yi↗Hewu Li↗

arXiv:2606.18268v1 Announce Type: cross Abstract: Community-based fact-checking that relies on cross-consensus is expanding rapidly on social media platforms. However, the delay and low-ratio of cross-consensus community fact-checks rated by human contributors remains a significant challenge. To address this, we first created ComRate, a large-scale dataset comprising 2.5 million community notes and over 209 million ratings sourced from $\mathbb{X}$. We then propose MultiCom, a persona-guided multi-agent rating framework for community note evaluation. MultiCom simulates diverse rater population by clustering contributors in a matrix-factorized rater space and prompting persona agents to generate structured assessments based on the official community notes rating schema. These agents output structured and explainable judgments, such as confidence, agreement signals and reasons. An out-of-fold calibrated aggregation algorithm combines features such as raw votes and diagnostic reason signals for reliable prediction. Extensive evaluations demonstrate that MultiCom outperforms alternative methods, achieving an average accuracy of 84.7% (balanced accuracy 68.3%, macro-F1 60.1%) on the evaluation set.

阅读与讨论 → 访问原文 →

23.

bioRxiv (Bioinfo) 2026-06-16 DOI: HASH:19f1cd33692fa5c7124fade43d2c2b56

Physics-Driven Zero-Shot Reconstruction of Isotropic 3D Fluorescence Microscopy under Undersampled Acquisition

作者:

Cao↗Jin↗Xin↗Hou↗Fu↗Li↗Gao↗Wang↗Saimi↗Ren↗Yuan↗Chen↗…

Three-dimensional (3D) imaging represents the development of next generation of fluorescence microscopy. However, routine axial down-sampling makes isotropic resolution unrealistic. Here, we propose DeepUI, a physical zero-shot framework designed to achieve isotropic 3D fluorescence images from a low axial sampling rate. DeepUI fully leverages the intrinsic characteristics of 3D images through physics-guided degradation, which incorporates spatial-frequency joint learning to generate a scaled optical transfer function, combined with noise degradation and an up-sampling branch. Typically requiring just 5 minutes for training and 0.5 minutes for high-throughput and fast prediction, we demonstrate the superior performance of DeepUI to get isotropic results, and the exclusivity to axial down-sampling conditions, even in more challenging conditions, including defocused background, noise, and resolution blur.

阅读与讨论 → 访问原文 →

24.

arXiv (CS.LG) 2026-06-18 DOI: arXiv:2606.19297

Does VLA Even Know the Basics? Measuring Commonsense and World Knowledge Retention in Vision-Language-Action Models

作者:

Nikita Kachaev↗Andrey Moskalenko↗Matvey Skripkin↗Nikita Kurlaev↗Daria Pugacheva↗Albina Burlova↗Mikhail Kolosov↗Denis Shepelev↗Andrey Kuznetsov↗Elena Tutubalina↗Aleksandr I. Panov↗Alexey K. Kovalev↗…

arXiv:2606.19297v1 Announce Type: new Abstract: Embodied Vision-Language-Action (VLA) models are typically obtained by fine-tuning powerful pretrained VLMs on robotics data, yet it is unclear how much commonsense and factual knowledge they retain after adaptation. Failures on knowledge-sensitive tasks are ambiguous, conflating missing knowledge with poor generalization of low-level control. We introduce Act2Answer, a lightweight protocol that adapts VLM knowledge benchmarks to VLA evaluation by requiring agents to answer through action. Each question becomes a short tabletop episode where the agent performs a single object-placement action to select among candidate answers, yielding an action-grounded success rate with reduced control confounds. We curate a test suite of such environments across diverse commonsense and world-knowledge categories and introduce layerwise intent probing to localize answer-relevant information across the VLM backbone and action head. In a large-scale study of 7 VLA models and 9 VLM baselines, we systematically rank models across categories, finding that VLAs show solid performance on simple concepts while exhibiting larger gaps on richer semantic categories relative to their source VLMs, that VQA co-training is associated with better knowledge retention, and that answer-relevant signals peak in middle VLA layers but attenuate in upper layers. Act2Answer is available at https://tttonyalpha.github.io/act2answer/.

阅读与讨论 → 访问原文 →

25.

arXiv (CS.LG) 2026-06-19 DOI: arXiv:2606.20183

Effective Dimension Governs Generalization in Quantum Kernel Vision Models

作者:

Jian Xu↗Delu Zeng↗John Paisley↗Qibin Zhao↗

arXiv:2606.20183v1 Announce Type: new Abstract: Recent quantum vision models-quantum vision transformers and quantum convolutional networks-report two striking but unexplained empirical phenomena: (i) ansatze with more, or more uniformly distributed, entanglement generalize better, and (ii) injecting quantum noise can improve test accuracy rather than degrade it. These observations are currently treated as curiosities, discovered by grid search and explained, if at all, by hand. We show that both are manifestations of a single, measurable quantity: the effective dimension $d_eff$ of the (noise-shaped) quantum feature kernel. Working primarily with quantum-kernel vision models-a quantum feature map read out by a kernel classifier-we give a spectral account in which entanglement structure and quantum noise are two knobs that move $d_eff$; in an overfitting regime, contracting $d_eff$ acts as ridge-like regularization. We analyze the mechanism: an exact decomposition of the depolarized kernel $K_p=(1-p)^2K+\tfrac{p(2-p)}{D}\mathbf{1}\mathbf{1}^\top$ with $d_eff(K_p)\to1$, a contraction result (and its boundary) for amplitude damping, a kernel-machine capacity bound, and a capacity/alignment risk decomposition; the monotone contraction operative in our entangled experiments is verified empirically, not proven in general. Along the one-parameter depolarizing family the collapse is instead exact by construction; we use it only to confirm the kernel decomposition to machine precision and at up to $12$ qubits, not as evidence for $d_eff$. Amplitude damping contracts $d_eff$ and lifts test accuracy by up to $+13\%$ along an inverted-U sweet spot; the effect's sign flips between the over- and under-fitting regimes; noise injection matches an explicit spectral-filtering frontier. Our results organize two reported anecdotes into a single measurable principle for designing quantum-vision models.

阅读与讨论 → 访问原文 →