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 (CS.AI) 2026-06-19

Cost-Optimal LLM Routing with Limited User Feedback under User Satisfaction Guarantees

arXiv:2606.19376v1 Announce Type: cross Abstract: Inference costs for large language model (LLM) applications are rapidly growing, driven by surging demand and rising infrastructure cost. Users expect high-quality responses, and in commercial settings this is formally codified in Service Level Agreements (SLAs), creating a fundamental tension between cost and quality. Recent progress on cost-aware LLM request routing has shown potential to resolve this tension, but existing approaches rely on complete feedback signals, offline training, extensive per-workload tuning, and most lack SLA guarantees or inference-time adaptivity. We introduce SLARouter, an online routing algorithm that learns a cost-optimal policy from the sparse, one-sided user feedback available in production systems. SLARouter provides theoretical guarantees for both cost optimality and strict SLA compliance. Experiments across a wide range of LLM benchmarks show that SLARouter satisfies SLA constraints without the need for per-benchmark tuning, reducing operating cost by up to 2.2x over existing baselines.

02.
arXiv (CS.CL) 2026-06-11

Rewrite to Translate, Translate to Reward: Reinforcement Learning for Source Rewriting in Machine Translation

Rewriting source text with large language models (LLMs) before translation has been shown to improve machine translation (MT) quality. However, we find that prompt-based rewriting can degrade translation quality rather than improve it, particularly when smaller LLMs, such as 4B-parameter models, are used. We argue that this limitation stems from the difficulty of controlling rewriting behavior through natural-language prompts alone: a rewrite is useful only if it improves downstream translation, yet existing prompt-based methods do not explicitly optimize for this signal. To address this issue, we propose RLSR (Reinforcement Learning for Source Rewriting), a reinforcement learning framework that trains the rewriting model with a reward based on the downstream translation-quality improvement produced by each rewrite. Experiments across six MT systems and 16 language pairs show that our 4B RLSR-trained rewriting models significantly outperform both the no-rewriting baseline and prompt-based rewriting baselines at the same model scale, while remaining competitive with baselines that use a 235B LLM.

04.
arXiv (CS.AI) 2026-06-16

Prediction Bottlenecks Don't Discover Causal Structure (But Here's What They Actually Do)

arXiv:2605.09169v2 Announce Type: replace-cross Abstract: A Mamba state-space model trained only for next-step prediction appears to recover Granger-causal structure through a simple readout $S = |W_{out} W_{in}|$, with early experiments suggesting the phenomenon generalized across architectures and benefited from interventional data at $p < 10^{-5}$. We package the protocol used to test that claim – standardized synthetic generators (VAR/Lorenz/CauseMe-style), three intervention semantics ($do(X=c)$, soft-noise, random-forcing), edge-provenance cards on three real datasets, and size-matched control arms – as a reusable falsification benchmark, and walk the claim through it in five stages. The method-level claim does not survive: (i) a plain linear bottleneck does as well or better; (ii) tuned Lasso beats the bottleneck on synthetic CauseMe-style benchmarks, and on Lorenz-96 (the only real benchmark with unambiguous ground truth) classical PCMCI and Granger lead a tight cluster in which the bottleneck trails; (iii) the headline intervention advantage is roughly 60% a sample-size confound, and the residual disappears under standard $do(X=c)$ interventions, surviving only under a non-standard random-forcing scheme; (iv) even that residual reproduces, with a larger effect, in classical bivariate Granger – the effect is method-agnostic. What survives is a narrow characterization result; the benchmark is the lasting artifact, and each stage above is one of its control arms.

05.
arXiv (math.PR) 2026-06-11

Continuous stochastic flows driven by white noise and their duals

作者:

arXiv:2606.12143v1 Announce Type: new Abstract: We study a class of continuous stochastic flows driven by a space-time white noise and characterize their dual flows by explicit stochastic differential equations. A key ingredient of the proof is the convergence of solutions under coefficient approximations. As an application, we derive the dual flows in two illustrative examples, the squared Bessel flow and the Jacobi flow. We also introduce a new model of polynomially self-repelling (PSR) flow and show that it enjoys a self-duality property.

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

Dolph2Vec: Self-Supervised Representations of Dolphin Vocalizations

arXiv:2606.12503v1 Announce Type: new Abstract: Self-supervised learning (SSL) has opened new opportunities in bioacoustics by enabling scalable modeling of animal vocalizations without the need for expensive manual annotation. However, current SSL models in this domain prioritize broad generalization across species and are not optimized for uncovering the fine-grained structure of individual communication systems. In this work, we collect and release a novel dataset of over five years of longitudinal recordings, from five known dolphins in a semi-naturalistic marine environment, an unprecedented resource for studying dolphin communication. We adapt the Wav2Vec2.0 Baevski et al. (2020) architecture to this domain and introduce Dolph2Vec, the first large-scale, species-specific SSL model trained exclusively on this data. We benchmark our model on two biologically relevant tasks: signature whistle classification and whistle detection. Dolph2Vec significantly outperforms general-purpose baselines in both tasks. Beyond performance, we show that learned embeddings and codebook structure capture interpretable acoustic units aligned with dolphin whistle categories and possibly sub-whistle structure, enabling fine-grained analysis of communication patterns. Our findings demonstrate how SSL can serve as both a model and a scientific tool to explore hypotheses in animal communication research.

07.
arXiv (CS.CV) 2026-06-12

Perceive, Interact, Reason: Building Tool-Augmented Visual Agents for Spatial Reasoning

While recent vision-language models (VLMs) demonstrate strong multimodal understanding, they remain limited in spatial reasoning tasks that require active evidence acquisition and multi-step visual interaction. This limitation suggests that relying solely on implicit visual representations from vision encoders is insufficient for recovering fine-grained spatial evidence. We introduce PERception-Interaction-reason Agent (PERIA), a tool-augmented visual agent for spatial reasoning tasks across map reasoning, visual probing, and vision reconstruction. PERIA uses two lightweight tool families: vision perception tools for exposing textual, symbolic, and spatial evidence, and vision interaction tools for manipulating visual context, tracing paths, and verifying spatial relations. To train PERIA, we develop a unified recipe that combines supervised tool-use trajectory synthesis, composite rewards, and Observation-Relaxed Group-in-Group Policy Optimization (OR-GIGPO) for effective multi-tool behavior. Experiments on 13 benchmarks from 8 datasets show that PERIA-8B improves over the Qwen3-8B backbone by 10.0% on in-distribution benchmarks and 4.4% on out-of-distribution benchmarks, while outperforming previous state-of-the-art baselines of similar size by 7.0%-14.8%. It also achieves performance comparable to much larger models such as Qwen3-VL-235B-A22B-Thinking and GPT-5, demonstrating the effectiveness of PERIA in enhancing spatial reasoning capabilities.

08.
arXiv (CS.CL) 2026-06-11

Goal-Autopilot: A Verifiable Anti-Fabrication Firewall for Unattended Long-Horizon Agents

作者:

Long-horizon LLM agents are not trusted to run unattended: with no human watching, they confidently report success they never verified. We treat honesty – bounding what an agent may claim at termination – as a first-class metric for unattended autonomy, distinct from capability. We present Autopilot, an execution model that makes silent fabricated success structurally impossible rather than merely rarer. Autopilot externalizes all working state into a durable, gated finite-state machine that a scheduler advances one stateless tick at a time; a hard floor forbids any terminal "done" claim whose falsifiable gate did not actually execute and pass. We prove a No-False-Success theorem – under gate soundness, floor enforcement, and plan coverage, termination implies the goal holds – whose only trust points are empirically measurable, and show the worst case degrades to an honest stall, never a fabricated success. Because each tick rehydrates only the state machine, per-step context cost is constant in the horizon. Across a 3,150-cell paired corpus (70 tasks $\times$ 3 systems $\times$ 3 models $\times$ 5 seeds, including 50 SWE-bench Lite tasks across 11 OSS repos), Autopilot fabricates on 0.95% of cells [95% CI 0.38–1.62] while Reflexion and StateFlow baselines fabricate on 8.10% [6.48–9.81] and 25.05% [22.48–27.62] respectively. The headline contrast lives in the hard regime: on SWE-bench Lite, the firewall reduces fabrication from 33.7% (StateFlow) to 0.67%, a paired difference of $-33.07$ pp [95% CI $-36.53, -29.73$]. The mechanism is the gate, not the model: all ten Autopilot fabrications come from the strongest model, while two weaker mid-tier models never fabricate across 700 paired cells. The firewall trades coverage for honesty by design – an honest stall is recoverable; a confident wrong output shipped downstream is not.

09.
arXiv (CS.CL) 2026-06-16

SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution

Long-horizon LLM agents generate traces that could become reusable experience, but raw trajectories are noisy, local, and hard to govern. Agent Skills offer a structured artifact for combining procedural guidance, executable resources, and applicability boundaries. Yet open skill ecosystems contain redundant, uneven, environment-sensitive artifacts, and indiscriminate updates can pollute future context. We present SkillsVote, a lifecycle-governance framework for Agent Skills across collection, recommendation, attribution, and evolution. SkillsVote profiles a million-scale open source corpus for environment requirements, quality, and verifiability, and synthesizes tasks for verifiable skills. Before execution, it performs agentic library search over structured skill folders to expose instructional context. After execution, it decomposes trajectories into skill-linked subtasks, attributes outcomes to skill-guided execution, agent exploration, environment, and result signals, and admits only successful reusable discoveries to evidence-gated updates. Experiments on Terminal-Bench 2.0 and SWE-Bench Pro show that SkillsVote improves agent performance on challenging agentic coding benchmarks. The gains arise from two complementary pathways: online evolution over task streams at test time and offline transfer via frozen libraries built from either historical trajectories or curated open source skills.

10.
arXiv (CS.LG) 2026-06-17

The Implicit Bias of Steepest Descent with Mini-batch Stochastic Gradient

arXiv:2602.11557v2 Announce Type: replace Abstract: A variety of widely used optimization methods like SignSGD and Muon can be interpreted as instances of steepest descent under different norm-induced geometries. In this work, we study the implicit bias of mini-batch stochastic steepest descent in multi-class classification, characterizing how batch size, momentum, and variance reduction shape the limiting max-margin behavior and convergence rates under general entry-wise and Schatten-$p$ norms. We show that, without momentum, worst-case convergence and successful classification can only be guaranteed with full-batch gradient. In contrast, momentum enables small-batch convergence to an approximate max-margin solution through a batch-momentum trade-off, though it slows convergence. This approach provides fully explicit, dimension-free rates that improve upon prior results. Moreover, we prove that variance reduction can recover the exact full-batch implicit bias for any batch size, albeit at a slower convergence rate. Finally, we further investigate the batch-size-one steepest descent without momentum, and reveal its convergence to a fundamentally different bias via a concrete data example, which reveals a key limitation of purely stochastic updates. Overall, our unified analysis clarifies when stochastic optimization aligns with full-batch behavior, and paves the way for perform deeper explorations of the training behavior of stochastic gradient steepest descent algorithms.

11.
bioRxiv (Bioinfo) 2026-06-16

scIsoAgent enables autonomous isoform-resolved characterization and sequence-informed interpretation of long-read single-cell transcriptomes

Alternative isoform usage can alter gene function independently of total gene expression, creating a need to resolve transcript isoforms at single-cell resolution. Long-read single-cell RNA sequencing meets this need by linking cellular identity to transcript isoforms and sequence-level features. Realizing its full biological value requires reproducible workflows that connect specialized long-read analysis with biological interpretation. Existing large language model (LLM)-based biomedical agents support general omics analysis, but are not designed for isoform-resolved long-read single-cell workflows. Here, we present scIsoAgent, an autonomous LLM-powered scientific agent for long-read single-cell RNA-seq analysis. scIsoAgent turns heterogeneous long-read single-cell inputs into traceable isoform-resolved workflows, using stage-aware planning and persistent computational context to support both execution and interpretation. Across complementary evaluations, this design improved the continuity from analysis planning to executable, interactive workflows compared with general-purpose LLM baselines. In real-data reanalysis, scIsoAgent recovered major findings from published long-read single-cell resources and extended a representative differential transcript usage event into a sequence-informed functional hypothesis. By linking full-length isoform sequences with model-inferred transcript properties, scIsoAgent connects observed isoform usage with potential sequence-level functional consequences. These results demonstrate that autonomous scientific agents can transform fragmented long-read single-cell analysis into coherent, reproducible workflows for isoform-resolved discovery and biological interpretation.

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

Distribution-Agnostic Robust Trajectory Optimization via Chance-Constrained Reinforcement Learning

arXiv:2606.13605v1 Announce Type: cross Abstract: This paper presents a distribution-agnostic robust trajectory-optimization framework based on chance-constrained reinforcement learning. The uncertainty is represented here through initial conditions and process noise, with the only requirement being that it can be sampled. A deterministic nominal trajectory is first computed offline, and reinforcement learning is then used only to robustify that baseline through a structured affine closed-loop correction law comprising a feedforward control adjustment and time-varying feedback gains. Probabilistic feasibility is enforced empirically through rollout-based upper-tail quantiles, while terminal dispersion is regulated through covariance-feasibility penalties. The framework is assessed on two materially different trajectory design problems. The flagship case study is a three-dimensional multi-impulse Earth-Mars transfer, where the learned policy is benchmarked against a recent robust trajectory-optimization reference under Gaussian uncertainty and then evaluated under bounded uniform uncertainty and under process disturbances not seen during training. The second case study is a stochastic atmospheric pinpoint rocket landing problem, used to assess portability to a short-horizon continuous-thrust setting with drag, mass depletion, and glide-slope constraints. The results show that the proposed framework can remain competitive in upper-tail fuel cost while preserving probabilistic feasibility, and that the same robustification scaffold can be carried across heterogeneous spacecraft trajectory planning problems without redesign of its core stochastic-control structure.

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

BRIDGE: Biological Evidence Refinement and Heterogeneous Dynamic Gating for Gene Regulatory Networks

arXiv:2606.14734v1 Announce Type: cross Abstract: Motivation: Gene regulatory network inference from single-cell RNA sequencing (scRNA-seq) data is important for uncovering cell-state-specific transcriptional programs. However, scRNA-seq measurements are sparse and noisy, and experimentally validated TF-target interactions remain limited, making reliable inference challenging. Although graph neural networks have advanced GRN prediction, existing methods often rely on biologically unconstrained graph augmentation, such as random edge perturbation, and insufficiently control information transfer between genes and cells. These limitations may distort regulatory structures and weaken robustness under noisy and weakly supervised settings. Results: To address these issues, we propose an innovative framework named Biological Evidence Refinement and Heterogeneous Dynamic Gating for Gene Regulatory Networks (BRIDGE). BRIDGE extracts gene and cell representations from the expression matrix and its matrix dual, and performs contrastive learning in the gene space and cell space between self and neighbors across the co-expression-refined regulatory view and the original graph. It then applies heterogeneous gated encoding to adaptively regulate information transfer between genes and cells, enabling robust transcription factor-to-target gene prediction. Experiments on benchmark datasets spanning three network types and seven cell types show that BRIDGE achieves state-of-the-art AUROC and AUPRC in most settings. In particular, on Specific networks, BRIDGE improves average AUPRC by 5% over the second-best baseline, GCLink. In cross-cell-type few-shot transfer, BRIDGE consistently outperforms GCLink and GENELink across all six target cell types. A case study on hESC further supports the biological relevance of the predictions, with 9 of the top 10 and 46 of the top 100 novel TF-target interactions validated by ChIPBase.

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

Understanding the Rejection of Fixes Generated by Agentic Pull Requests – Insights from the AIDev Dataset

arXiv:2606.13468v1 Announce Type: cross Abstract: AI coding agents are increasingly used to generate pull requests (PRs) that propose code fixes in software projects. From a first exploration of the AIDev dataset, we find that 46.41\% of the fixes proposed by the agents Copilot, Devin, Cursor, and Claude are rejected. This represents a significant amount of wasted resources that require human reviews, verifications, and running tests and validations for fixes that are merely discarded. Our goal in this paper is to understand the failure modes of AI-agents, an understanding that is crucial for better integrating AI-agents as efficient teammates. In this paper, we conduct a qualitative study on a representative sample of 306 non-merged pull requests created or co-authored by the agents mentioned earlier, followed by a quantitative analysis of the reasons for rejection. Our qualitative findings identify 14 reasons divided into four high-level categories for rejecting AI-agent fixes. We observe that developers can reject fixes due to fixes whose implementation is incorrect (e.g., incomplete, wrong approach), fixes that do not pass the continuous integration (CI) pipelines and fail tests, fixes for which the agent is unable to perform the implementation (e.g., no code generated, sessions lost), and fixes whose priority is low. Our results shed light on the importance of better guiding the model at these levels: (1) proposing hints about the approach to follow for fixing an issue, (2) outlining constraints or limitations regarding the approaches that should not be taken, and (3) instructing the agent on how to validate the implementation through CI pipelines and without introducing a breaking change. Our results suggest the need for good prioritization of tasks so that generated fixes do not lead to wasted human review efforts or wasted agent resources (e.g., tokens, compute, or allowed number of requests).

15.
PLOS Medicine 2026-06-01

Prenatal exposure to asthma medications and risk of neurodevelopmental disorders and educational difficulties: A systematic review and meta-analysis

by Lama A. Shakhshir, Alexia Karain, Jill P. Pell, Claire E. Hastie, Scott M. Nelson, Michael Fleming Background Since asthma exacerbations during pregnancy risk maternal and fetal health, continued medication is important. However, some studies have reported adverse neurodevelopmental outcomes following prenatal exposure to asthma medication. Therefore, this systematic review aimed to collate the existing evidence on the associations between prenatal exposure to asthma medication and neurodevelopmental and educational outcomes. Methods and findings A systematic review was conducted in accordance with PRISMA guidelines and the PECO framework. PubMed, Medline and Embase databases were searched for studies investigating prenatal exposure to one or more asthma medication and neurodevelopmental or educational outcomes published, in English, between January 2003 and September 2024, and updated in November 2025. Studies of asthma medication used for other indications were excluded. Study quality was assessed using the Newcastle-Ottawa scale. Random-effects meta-analyses were conducted where appropriate and heterogeneity was evaluated using Cochran’s Q and I2 tests.Of 16,824 studies identified by the initial search, seven were eligible for inclusion. All investigated beta-2-adrenergic agonists (B2AA), with one including B2AA as mono- and polytherapy—and one study also investigated inhaled corticosteroids (ICS) exposure. Two reported associations with autism spectrum disorder (ASD) and one with attention-deficit hyperactivity disorder (ADHD). An updated search identified one additional eligible study, which examined both ADHD and ASD, as well as other neurodevelopmental disorders. The included eight studies (n = 3,867,170 participants) comprised cohort (n = 5) and case-control (n = 3) designs and reported inconsistent results. Meta-analysis of three studies (n = 1,380,871) indicated significant associations with ASD for exposure to B2AA both preconception (aOR 1.34, 95% CI [1.19,1.52]) and during pregnancy (aOR 1.29, 95% CI [1.16,1.42]). Heterogeneity was low, with no evidence of significant publication bias. Limitations of the included studies comprised residual confounding and exposure misclassification. Additionally, studies included in the meta-analysis were few in number and did not adequately distinguish between medication effects and underlying maternal asthma. Conclusion Meta-analysis suggested an association between prenatal exposure to B2AA and ASD. An association with ADHD, reported in a single study, requires corroboration. To date, based on our search strategy, no association has been reported with communication skills, motor skills, problem-solving and personal-social skills, or cerebral palsy.

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

Analyzing Error Propagation in Korean Spoken QA with ASR-LLM Cascades

We analyze how automatic speech recognition (ASR) errors propagate through ASR-LLM cascades in Korean spoken question answering (SQA), focusing on downstream semantic failures that conventional ASR metrics cannot fully capture. Our analysis shows that the relative downstream degradation caused by ASR errors is consistent across LLMs with different absolute performance, suggesting that cascade degradation largely tracks ASR-stage information loss. We further identify single-character Korean ASR errors as a Korean-specific loss channel, where even a minimal transcription difference can change the intended question and degrade downstream QA performance. Finally, an auxiliary comparison shows that a large audio language model outperforms an ASR-LLM cascade with an approximately matched language backbone in noisy Korean SQA, indicating the potential of direct audio input to mitigate transcript-induced information loss.

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

Beyond Artifacts: Towards Generalizable Synthetic Song Detection via Music-Intrinsic Features

arXiv:2606.16612v1 Announce Type: cross Abstract: The rapid advancement of AI music generators highlights the urgent need for reliable Synthetic Song Detection (SSD). Existing SSD methods often rely on low-level artifacts or fixed feature assumptions, struggling to capture generator-agnostic cues. To address this, we propose Sofia (Synthetic-song detection framework via music features), a flexible framework that models music-intrinsic attributes via feature-specific experts and an adaptive Mixture-of-Experts (MoE) module. By configuring Sofia with representative Vocal, Audio-effect, Global structure features, and their combinations, we present their individual and complementary contributions. To comprehensively evaluate our framework, we further construct MUSIC8K, a challenging benchmark featuring lastest emerging generators and realistic audio perturbations. Experiments show that Sofia learns generator-agnostic representations from music-intrinsic features, improving the F1 score by 18.5 points over the strongest baseline on MUSIC8K-O while maintaining strong robustness.

18.
arXiv (CS.AI) 2026-06-18

WebSP-Eval: Evaluating Web Agents on Website Security and Privacy Tasks

arXiv:2604.06367v2 Announce Type: replace-cross Abstract: Web agents automate browser tasks, ranging from simple form completion to complex workflows like ordering groceries. While current benchmarks evaluate general-purpose performance~(e.g., WebArena) or safety against malicious actions~(e.g., SafeArena), no existing framework assesses an agent's ability to successfully execute user-facing website security and privacy tasks, such as managing cookie preferences, configuring privacy-sensitive account settings, or revoking inactive sessions. To address this gap, we introduce WebSP-Eval, an evaluation framework for measuring web agent performance on website security and privacy tasks. WebSP-Eval comprises 1) a manually crafted task dataset of 200 task instances across 28 websites; 2) a robust agentic system supporting account and initial state management across runs using a custom Google Chrome extension; and 3) an automated evaluator. We evaluate a total of 8 web agent instantiations using state-of-the-art multimodal large language models, conducting a fine-grained analysis across websites, task categories, and UI elements. Our evaluation reveals that current models suffer from limited autonomous exploration capabilities to reliably solve website security and privacy tasks, and struggle with specific task categories and websites. Crucially, we identify stateful UI elements are a primary reason for agent failure, with toggles causing more than 45% task failure across many models.

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

RSRCC: A Remote Sensing Regional Change Comprehension Benchmark Constructed via Retrieval-Augmented Best-of-N Ranking

Traditional change detection identifies where changes occur, but does not explain what changed in natural language. Existing remote sensing change captioning datasets typically describe overall image-level differences, leaving fine-grained localized semantic reasoning largely unexplored. To close this gap, we present RSRCC, a new benchmark for remote sensing change question-answering containing 126k questions, split into 87k training, 17.1k validation, and 22k test instances. Unlike prior datasets, RSRCC is built around localized, change-specific questions that require reasoning about a particular semantic change. To the best of our knowledge, this is the first remote sensing change question-answering benchmark designed explicitly for such fine-grained reasoning-based supervision. To construct RSRCC, we introduce a hierarchical semi-supervised curation pipeline that uses Best-of-N ranking as a critical final ambiguity-resolution stage. First, candidate change regions are extracted from semantic segmentation masks, then initially screened using an image-text embedding model, and finally validated through retrieval-augmented vision-language curation with Best-of-N ranking. This process enables scalable filtering of noisy and ambiguous candidates while preserving semantically meaningful changes. The dataset is available at https://huggingface.co/datasets/google/RSRCC.

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

GraphBEV++: Multi-Modal Feature Alignment for Autonomous Driving

Feature misalignment in BEV perception is a critical yet often overlooked challenge in autonomous driving, especially under calibration uncertainties between LiDAR and camera sensors. To address this issue, we propose a robust multi-modal fusion framework, GraphBEV++, which systematically mitigates projection-induced misalignment. The framework consists of two key modules: LocalAlign-v2 and GlobalAlign-v2. LocalAlign-v2 introduces neighborhood-aware depth features via graph matching to correct local misalignment. It supports both LSS-based and query-based BEV representations, making it compatible with BEVFusion and BEVFormer architectures for consistent cross-paradigm alignment. GlobalAlign-v2 encompasses two variants: Deformable and Diffusion. The Deformable variant addresses global misalignment in LSS-based multi-modal BEV by explicitly learning cross-modal feature offsets. In contrast, the Diffusion variant targets implicit misalignment in query-based BEV by injecting noise to simulate misalignment and employing a denoising process to recover aligned features. Experimental results show that GraphBEV++ achieves state-of-the-art performance under misalignment noise on nuScenes and Waymo subset, improves long-range detection on Argoverse2, and generalizes effectively to the 3D occupancy prediction task, consistently improving occupancy estimation accuracy and robustness under both clean and noisy settings. Furthermore, GraphBEV++ effectively alleviates misalignment issues in end-to-end autonomous driving. Compared with five baselines (UniAD, VAD, FusionAD, MomAD, and WoTE), it demonstrates superior performance in both open-loop (nuScenes) and closed-loop (Bench2Drive and NAVSIM) evaluations across perception, prediction, and planning tasks.

22.
arXiv (quant-ph) 2026-06-19

Computing noise-canceling observables via Pauli propagation

arXiv:2606.20441v1 Announce Type: new Abstract: The pursuit of quantum advantage is driving the co-evolution of quantum processors and classical simulation methods. Despite advances in scale and quality, the accuracy of quantum simulation is ultimately limited by error rates and sampling overheads. Similarly, while classical simulation methods such as Pauli propagation have made remarkable progress, their accuracy is ultimately limited by the exponential growth of operator paths and the truncations needed to control memory and runtime. Here we show that these complementary limitations can be mitigated by embedding Pauli propagation within a hybrid error-mitigation framework that reduces quantum sampling overhead while achieving lower truncation errors with fewer classical resources than traditional Pauli propagation alone. In this framework, a target observable is classically propagated through noise-canceling inverse channels, producing a modified observable that is measured directly on a quantum processor. We prototype two implementations and benchmark their performance numerically on canonical models that challenge traditional Pauli propagation. We also perform experiments on a quantum processor using 56 superconducting qubits, revealing the tradeoffs of their respective truncation strategies. These results illustrate how classical and quantum resources can be orchestrated to extend observable estimation beyond the limits of either approach alone, providing a foundation for quantum-centric supercomputing and future demonstrations of quantum advantage.

23.
arXiv (CS.CL) 2026-06-17

A Multifaceted Analysis of Social Biases in Large Language Models

Large language models (LLMs) have rapidly become indispensable tools for acquiring information and supporting human decision-making. However, ensuring that these models uphold fairness across varied contexts is critical to their safe and responsible deployment. In this study, we undertake a comprehensive examination of four widely adopted LLMs, probing their underlying biases and inclinations across the dimensions of politics, ideology, alliance, language, and gender. Through a series of carefully designed experiments, we investigate their political neutrality using news summarization, ideological biases through news stance classification, tendencies toward specific geopolitical alliances via United Nations voting patterns, language bias in the context of multilingual story completion, and gender-related affinities as revealed by responses to the World Values Survey. Results indicate that while the LLMs are aligned to be neutral and impartial, they still show biases and affinities of different types.

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

Mechanistic Analysis of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning

Sequential fine-tuning of Large Language Models (LLMs) adaptation to target tasks often triggers catastrophic forgetting, where the acquisition of novel target skills degrades ancestral capabilities. This paper presents a systematic comparative study of catastrophic forgetting across twenty premier models representing the state-of-the-art in mid-2026. We categorize our investigation into two primary research lines: (i) a behavioral and semantic output drift analysis of ten leading closed-source models (including Claude Fable 5, GPT-5.5 High, and Gemini 3.5 Flash), and (ii) a deep mechanistic interpretation of ten prominent open-weight architectures (such as DeepSeek-V4-Pro, Llama 4 Maverick, and Qwen 3.6-27B). Through weight-space trajectory tracking, Centered Kernel Alignment (CKA), and routing gate drift calculations in Mixture-of-Experts (MoE) layers, we localize the neural circuits highly susceptible to parameter overwriting. Our findings indicate that early-layer attention heads exhibit systemic entropic dispersion, while mid-to-deep feed-forward networks (or sparse expert blocks) suffer localized representation collapse. Informed by these insights, we introduce Low-Rank Circuit Projection (LRCP), a subspace-regularized training intervention. Empirical evaluations show that LRCP successfully mitigates up to 94.2% of ancestral capabilities in open-weight configurations and matches the adaptation velocity of standard PEFT baselines.

25.
arXiv (CS.CL) 2026-06-16

Code as a Weapon: A Consensus-Labeled Prompt Bank for Measuring Coding-Model Compliance with Malicious-Code Requests

A general-purpose language model that answers a harmful question returns text; a coding model that complies with a malicious request can return a working weapon: a keylogger, ransomware, an exploit that runs as written. This asymmetry in the severity of a single act of compliance implies coding-specialized models should clear a higher refusal bar than general-purpose chat models, not a lower one, yet the field cannot tell whether they do. Refusal benchmarks for malicious code are fragmented: they mix requests for executable software with requests for harmful security knowledge and report refusal rates over non-comparable corpora. This paper's central result is that the CODE-versus-KNOWLEDGE classification axis established in a prior four-corpus release remains stable under a substantially expanded corpus pool and an independently refreshed judge panel, evidence that it measures a real construct rather than an artifact of the prompts or judges. Eight corpora spanning diverse elicitation paradigms (direct, jailbreak-decorated, indirect, and agent/interpreter: ASTRA, CySecBench, AdvBench/harmful_behaviors, JailbreakBench, MalwareBench, RedCode, RMCBench, Scam2Prompt) are classified under a five-judge consensus protocol (6,675 prompts x 5 judges = 33,375 calls), reaching Fleiss' kappa = 0.767 [95% CI 0.755, 0.777] ("substantial"). Critically, the panel shares no judge with the prior release (five paid commercial APIs replaced by five open-weight models from five vendors), yet the two panels agree on 94.45% of the 3,133 shared prompts and reach Cohen's kappa = 0.952 [0.942, 0.963] on the 3,031-prompt binary overlap: the axis survives near-total panel replacement. The released bank comprises 4,748 consensus-CODE and 1,923 consensus-KNOWLEDGE prompts, a reliability-quantified benchmark whose central classification axis is shown stable across corpus expansion and judge-panel replacement.