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.
medRxiv (Medicine) 2026-06-19

A soluble bi-specific fusion protein for the improved expansion of human CD8+ CAR-T cells

The success of Chimeric Antigen Receptor (CAR) T cell therapy is heavily dependent on the quality of the final cellular product. Current expansion protocols often rely on reagents that require removal from cell culture media, posing logistical challenges in manufacturing, and can also lead to terminal differentiation. Here, we evaluate the use of a soluble, bead-free T cell activator, T cell expansion protein (T-CEP), as a streamlined alternative for generating potent CAR-T cells. Human T cells were activated with T-CEP or known T cell activators (Dynabeads and TransAct) and transduced with either CD19 or interleukin-13 (IL-13) mutein (tetravariant-13; TV-13)-based CAR lentiviral vectors. Our results demonstrate that T-CEP supports robust CAR-T cell expansion and achieves transduction efficiencies comparable to commercial reagents for both types of CAR-T cells. Notably, T-CEP significantly favored the expansion of CD8+ T cells, yielding an enhanced CD27+ phenotype and a lower CD4:CD8 ratio compared to TransAct. Cytotoxicity assays confirmed that T-CEP-expanded CAR-T cells possess cytolytic function equivalent to commercial reagents for both CARs, while exhibiting lower levels of inflammatory cytokine secretion. In summary, T-CEP represents a competitive alternative to existing expansion agents, as it does not require its removal during CAR-T manufacturing and generates a CD8+ dominant, less-differentiated phenotype without compromising efficacy.

02.
medRxiv (Medicine) 2026-06-11

Large-scale proteomics and timing of hypertensive disorders of pregnancy

Background: Hypertensive disorders of pregnancy (HDP) may first be diagnosed antepartum, during labor, or postpartum. We utilized untargeted large-scale proteomics to identify pathways associated with HDP based on timing of onset. Methods: We performed a nested case-control study comparing differential protein expression, from the SomaScan 7K platform, based on timing of onset of HDP versus controls (referent) using first-trimester samples from the NuMoM2b-Heart Health Study, a multi-site cohort that followed nulliparous individuals from the first trimester. Associations of proteins with timing of onset of HDP, adjusted for co-variates, were assessed using logistic regression q value-based false discovery rates and pathway enrichment and differential expression analysis were conducted. Results: Of 1628 individuals included, 678 had HDP, of which 67% manifested antepartum (AP), 29% intrapartum (IP), and 3% postpartum (PP). After adjusting for co-variates, compared to controls, 698 proteins, 39 proteins, and 144 proteins were differentially expressed in those with HDP according to AP, IP, PP onset, respectively. There was little overlap in individual protein expression based on timing of HDP. Pathway enrichment and graphical summary analyses suggested distinct processes. Specifically, there was downregulation of angiogenic proteins in AP HDP, downregulation of immune-related proteins in IP HDP, and upregulation of complement activation promoting fibrotic changes leading to cardiac dysfunction in PP HDP. Conclusion: There are differences in first-trimester protein expression based on whether HDP first manifests AP, IP or PP. This raises the possibility that there may be distinct mechanistic phenotypes that could uniquely inform diagnostic and therapeutic targets for HDP.

03.
arXiv (CS.CV) 2026-06-12

SPARC: Reliable Spatial Annotations from Robot Demonstrations at Scale

This work introduces Spatial Annotations from Robot Demonstrations with Reliability Calibration (SPARC), a risk-aware framework that automatically labels robot demonstrations with structured spatial annotations and assigns each annotation a reliability score. Structured spatial annotations, such as bounding boxes, object trajectories, and manipulation phase labels, benefit a broad range of robotics applications from training grounded robot policies and embodied foundation models to motion planning and hierarchical task composition. Existing automated pipelines generate such annotations at scale but provide no reliable quality signal: detector confidence is poorly calibrated for annotation correctness, forcing a choice between accepting noisy labels or discarding useful samples. In contrast to existing automated pipelines, SPARC leverages the spatio-temporal structure inherent to robot tasks to generate a reliability signal, reducing noisy labels and retaining more useful samples. We further introduce Interaction-Aware Bench (IA-Bench), a benchmark that measures model accuracy in grounding the locations of interacted objects in robot demonstrations. On 1.7k human-annotated demonstrations spanning diverse embodiments and scenarios, SPARC significantly outperforms detection-only baselines in localization accuracy while retaining three times more samples at high-precision operating points. Our experiments demonstrate that models finetuned on our annotations achieve state-of-the-art results on object-grounding and pointing benchmarks among similarly sized models, while remaining competitive on broader spatial-reasoning suites without manually verified or annotated training data. Furthermore, policies trained on SPARC-generated annotations outperform baselines in cluttered, visually ambiguous real-world scenes. Code, data, and models are available at intuitive-robots.github.io/sparc-labeling.

04.
arXiv (CS.CV) 2026-06-17

Learning a Maximum Entropy Model for Visual Textures using Diffusion

Visual textures – spatially homogeneous image regions containing repeated elements (e.g. a field of grass, the bark of a tree) – are ubiquitous in visual scenes and provide important cues for recognizing and analyzing materials and objects. A number of existing texture models extract essential statistics from a single texture image, and can then generate high-quality samples that are visually similar to the original by matching these statistics. However, their statistics are either hand-designed or based on a network pretrained for another purpose (e.g., object recognition). Here, we develop the first principled method for unsupervised learning of a set of statistics that are used to constrain a maximum entropy probability model. We leverage methods developed for generative diffusion models to derive training and sampling procedures, and compare these to the traditional method of sampling via matching the statistics. Despite the compactness of our trained model (512 statistics), it generates texture images whose quality is as good as or better than the current state-of-the-art model (~177k statistics). A more direct comparison of the two models, obtained by synthesizing images that are indistinguishable for one model but maximally different for the other, reveals their relative strengths and weaknesses. Finally, we show that unlike previous statistical texture models, a straight trajectory in the representation space of our model generates homogeneous texture samples that interpolate smoothly between the features of the two end points.

05.
arXiv (CS.LG) 2026-06-17

Public transit gains and spatially uneven travel demand changes after NYC congestion pricing

arXiv:2606.17530v1 Announce Type: cross Abstract: New York City implemented the nation's first cordon-based congestion pricing program in January 2025, providing an opportunity to evaluate how system-wide urban mobility responds to large-scale pricing interventions. Because such policies generate spillovers across modes and locations, credible control groups are difficult to construct. We address this challenge using time series foundation models to generate probabilistic counterfactual demand forecasts with calibrated uncertainty. Applying this framework to bus, subway, and aggregate trip volume data, we find that post-policy bus and subway ridership increased significantly relative to expected no-policy demand, while overall travel demand decreased modestly. The effects are spatially heterogeneous: while reductions in overall travel demand are concentrated within the Congestion Relief Zone, transit gains extend beyond Manhattan's core. Socio-demographic analyses further reveal uneven adaptation across neighborhoods, highlighting spatial equity implications. Our framework provides a scalable approach for the uncertainty-aware evaluation of system-wide urban interventions when clean control groups are unavailable.

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

MIRAGE: Auditing Anti-Muslim Bias in Frontier LLMs Across Reasoning, Agentic, and Time-Coupled Conditions

arXiv:2606.16562v1 Announce Type: new Abstract: Five years after the discovery of persistent anti-Muslim bias in large language models, most evaluations remain confined to single-turn prompt completion, a setting that no longer reflects how frontier LLMs are deployed. We introduce MIRAGE (Muslim-Identity Reasoning and Agentic Generation Evaluation), a benchmark of 1{,}200 prompts spanning three deployment-realistic conditions: direct completion, chain-of-thought reasoning, and simulated agentic decision-making across content moderation, lending triage, refugee claim summarization, and hiring screens. Across six frontier models, we find that (i) chain-of-thought reasoning amplifies rather than suppresses Muslim-violence associations by 12–34\% relative to direct completion, (ii) agentic decisions exhibit a 9–22 percentage-point asymmetry between Muslim and matched non-Muslim cases on identical evidence, and (iii) bias is sharply time-coupled to retrieved news context, increasing 18–27\% under recent-conflict retrieval. Existing prompt-based mitigations transfer poorly across our three conditions, suppressing direct-completion bias while leaving agentic asymmetry largely intact. We release MIRAGE and an open evaluation harness to support targeted mitigation research.

07.
arXiv (CS.AI) 2026-06-16

Reward Hacking in Language Model Agents: Revisiting AI Safety Gridworlds

arXiv:2606.15385v1 Announce Type: new Abstract: Reward hacking, where AI systems exploit misspecified objectives to achieve high reward without satisfying intended goals, remains a central challenge in AI safety. Yet most known instances have been discovered post hoc in frontier systems where controlled study is impractical. We adapt the AI Safety Gridworlds framework into a text-based evaluation suite that reformulates classic reinforcement learning safety tasks for language-based agents. Across frontier and mid-scale models, we find that specification gaming emerges zero-shot: models systematically achieve high observed reward while underperforming on hidden safety objectives, and even apparently safe behaviors can reflect misunderstanding rather than principled safety. Reinforcement learning does not correct these failures: direct reward optimization widens the gap between observed and hidden reward, as the model's initial competence causes it to lock into locally rewarding strategies before discovering safer alternatives. This pattern persists across model scales (1.5B–14B) and is not resolved by finer credit assignment, exploration prompts, or entropy regularization. Our results show that reward hacking arises naturally when optimizing proxy objectives with capable language model agents and resists standard mitigations, suggesting that proxy-reward failures in agentic settings may require approaches beyond standard exploration and credit-assignment fixes. To facilitate reproducibility, the code for this work is available at \href{https://github.com/asparius/verl-agent-safety}{our public repository}.

08.
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).

09.
arXiv (CS.LG) 2026-06-18

Estimating carbon pools in the European Shelf sea environment: replacing reanalysis by model-informed machine learning?

arXiv:2508.10178v3 Announce Type: replace-cross Abstract: Shelf seas are important for the economy and the carbon cycle, but shelf sea observations for carbon pools are often sparse, or highly uncertain. An alternative can be provided by carbon reanalyses (whether assimilating proxy variables, such as chlorophyll-$a$, or directly carbon), but these are often expensive to run. We propose to use a computationally cheap ensemble of neural networks (i.e. deep ensemble) to learn the relationship between the directly observable (atmospheric, riverine and ocean) variables and marine carbon pools from a coupled physics-biogeochemistry model. The deep ensemble was trained on a North-West European Shelf (NWES) physical-biogeochemistry model free run simulation. After training, the deep ensemble was run using inputs from the NWES reanalysis instead of the free run, demonstrating that it can efficiently predict several NWES carbon pools (e.g., detritus, zooplankton, heterotrophic bacteria) in much better agreement with the reanalysis than the free run, while also providing uncertainty information. We further show that the deep ensemble performs similarly well when it is driven directly by the observations assimilated into the reanalysis, with the limitation that carbon pools can then be predicted only at the observed locations and times. We focus on explainability of the results and demonstrate potential use of the deep ensembles for future climate what-if scenarios. We suggest that model-informed machine learning presents a viable alternative to expensive reanalyses and could complement observations, wherever they are missing and/or highly uncertain.

10.
arXiv (CS.LG) 2026-06-15

A Complexity Measure for Active Learning in Multi-group Mean Estimation

arXiv:2606.14690v1 Announce Type: new Abstract: We study a max-risk objective for active learning in a multi-group mean estimation $d$-armed bandits: a learner adaptively allocates a budget of $T$ samples across $d$ groups to minimize the worst-case uncertainty index $\max_{k\in[d]}\sigma_k^2/n_k$, where $\sigma_k$ is the standard deviation of the distribution of arm $d$, and $n_k$ is the number of times arm $d$ is sampled. We develop a local minimax framework and prove the first general lower bound for this objective, valid for any finite-variance hypothesis class. The bound separates difficulty into three orthogonal factors: a budget term, a heteroscedasticity index measuring how unevenly the uncertainty is spread across arms, and a model-dependent complexity measure, the Variance Local Curvature ($\mathrm{VLC}$), which captures how much information a local change of variance creates inside the hypothesis class. For smooth classes, the $\mathrm{VLC}$ is a reparametrization of a variance–Fisher information, with closed-form values for common families. Benchmarking against the strongest available upper bound shows near-optimality up to logarithmic factors in broad regimes, and pinpoints a systematic gap in highly heterogeneous instances. Our proof introduces two key ingredients: a loss-induced $\ell_1$ geometry on the decision space, and a representation-based instance generator that reduces hard-instance construction to an explicit random matrix calculation.

11.
arXiv (CS.CL) 2026-06-12

LLMs Can Better Capture Human Judgments–With the Right Prompts

Are large language models (LLMs) bad at capturing human judgment? Two commonly stated limitations are that LLMs fail to capture full distributions of responses, and that their judgments are unstable across wording variations. We demonstrate simple prompting strategies that mitigate these limitations. Across two datasets–a U.S.-representative set of 144 moral scenarios and 38 moral beliefs from the International Social Survey Programme's Family and Changing Gender Roles module covering 32 countries–we show how simple elicitation techniques help improve AI-human alignment. First, prompting models to report standard deviations and response proportions recovers the full range of human responses better than common strategies. Second, ensuring scenarios are clear to human participants–as reflected in human confusion ratings–boosts model alignment, and LLMs can track human confusion ratings. At the same time, we find that LLMs' estimates of their own error are poorly calibrated, though they can predict human variability relatively well. These results suggest that asking better questions to LLMs can yield better answers.

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

Confidence Calibration for Multimodal LLMs: An Empirical Study through Medical VQA

arXiv:2606.19950v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) show great potential in medical tasks, but their elicited confidence often misaligns with actual accuracy, potentially leading to misdiagnosis or overlooking correct advice. This study presents the first comprehensive analysis of the relationship between accuracy and confidence in medical MLLMs. It proposes a novel method that combines Multi-Strategy Fusion-Based Interrogation (MS-FBI) with auxiliary expert LLM assessment, aiming to improve confidence calibration in Medical Visual Question Answering (VQA). Experiments demonstrate that our method reduces the Expected Calibration Error (ECE) by an average of 40\% across three Medical VQA datasets, significantly enhancing MLLMs' reliability. The findings highlight the importance of domain-specific calibration for MLLMs in healthcare, offering a more trustworthy solution for AI-assisted diagnosis.

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

Towards Advanced Mathematical Reasoning for LLMs via First-Order Logic Theorem Proving

Large language models (LLMs) have shown promising first-order logic (FOL) reasoning capabilities with applications in various areas. However, their effectiveness in complex mathematical reasoning involving multi-step FOL deductions is still under-researched. While LLMs perform competitively on established mathematical reasoning benchmarks, they struggle with multi-step FOL tasks, as demonstrated by Deepseek-Prover-V2-7B's low accuracy (4.2%) on our proposed theorem proving dataset. This issue arises from the limited exploration of diverse proof strategies and the potential for early reasoning mistakes to undermine entire proofs. To address these issues, we propose DREAM, a self-adaptive solution that enhances the Diversity and REAsonability of LLMs' generation strategies. DREAM incorporates an Axiom-Driven Strategy Diversification mechanism to promote varied strategic outcomes and a Sub-Proposition Error Feedback to help LLMs reflect on and correct their proofs. Our contributions include pioneering advancements in LLMs' mathematical reasoning through FOL theorem proving, introducing a novel inference stage solution that improves performance by 0.6% to 6.4%, and providing a curated dataset of 447 mathematical theorems in Lean 4 format for evaluation.

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

FlexiBrain: Resolution-Agnostic Voxel-Level Encoding for Native fMRI

arXiv:2606.11500v1 Announce Type: cross Abstract: The success of large-scale deep learning models in neuroscience is fundamentally constrained by severe data heterogeneity. Native fMRI data aggregated from diverse sources exhibit substantial variation in both spatial and temporal resolutions. Consequently, most existing frameworks rely on lengthy, rigid preprocessing pipelines that enforce uniformity across datasets. This practice introduces two critical limitations: (1) potential degradation of subject-specific anatomical information; (2) significant computational overhead, often requiring hours of processing per subject. Here, we propose FlexiBrain, a resolution-agnostic voxel-level encoding framework for native fMRI based on Mamba-JEPA. FlexiBrain defines patch sizes in real-world physical units and employs a dynamic patch resizing, thereby bypassing destructive spatial standardization while enabling direct ingestion of data in native space. We instantiate the framework using an efficient Mamba-JEPA backbone to model high-dimensional 4D fMRI signals. Across five diverse downstream neuroscience tasks, FlexiBrain consistently outperforms recent state-of-the-art methods, achieving gains of up to 12 percentage points without external data augmentation. Importantly, FlexiBrain functions as a seamless plug-in module, substantially reducing preprocessing costs and accelerating the development of robust voxel-level fMRI foundation models. Code is available at https://github.com/OneMore1/FlexiBrain.

15.
arXiv (CS.LG) 2026-06-12

How Much Memory Do We Need? Adaptive Memory Gate for Neural Operators

arXiv:2606.13443v1 Announce Type: new Abstract: Neural operators have emerged as a powerful data-driven approach for solving time-dependent PDEs. Among recent advances, memory-augmented neural operators explicitly incorporate past states and have achieved remarkable performance under low-resolution observation settings. However, existing approaches apply a fixed memory weight regardless of observation conditions, such as resolution or physical parameters, limiting their adaptability. Our preliminary experiments reveal that optimal memory weight varies with resolution and viscosity, implying that a fixed memory weight cannot simultaneously optimize performance across diverse settings. We propose AMGFNO, which dynamically modulates memory weight through a learnable gate. On the Kuramoto-Sivashinsky and Burgers' equations, AMGFNO achieves 55-79% nRMSE reduction over at low resolution, with the learned gate value automatically decreasing from $\bar{g} \approx 0.7$ to near-zero as resolution increases.

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

Adapting Prithvi-EO for Fallow Detection for Food-Water Nexus: ViT-Adapter Necks and Parameter-Efficient Backbone tuning of Geospatial Foundation Model

Understanding spatial distribution of fallow land is important for optimizing the food-water (FW) nexus, given fallowing's role in crop rotation and water conservation. Fallow is a low accuracy class in USDA Cropland Data Layer (CDL). Geospatial foundation model (GFM), Prithvi-EO has shown strong transferability across computer vision tasks. However, its Vision Transformer (ViT) backbone produces features at a single spatial scale that are ill-suited for the multi-scale features required by object detection heads. Existing approaches synthesise multi-scale pyramids through scaling of single stride tokens, sacrificing spatial heterogeneity, and full backbone fine-tuning is computationally prohibitive for GFMs. We evaluate a fallow detection pipeline combining two parameter-efficient fine tuning (PEFT) schemes: Low-Rank Adaptation (LoRA) and a hybrid PEFT, with three neck designs: pseudo multi-scale, Lite ViT-Adapter, and Full ViT-Adapter. Our best configuration, Lite ViT-Adapter with a one-stage head, achieves a mAP@50 of 0.9479 with the Diou loss, suggesting the effectiveness of center-aware localization for irregular fallow field detection. ViT-Adapter free one-stage detection under LoRA improves the adapter-free anchor-based approach by 6.42%, and the best configuration improves baseline adapter-free anchor-based approach by 25.70%. These results demonstrate that lightweight spatial prior fusion and selective backbone unfreezing enable Prithvi-EO to capture local fallow patterns more effectively, outperforming approaches that rely on reshaped single-stride ViT tokens.

17.
bioRxiv (Bioinfo) 2026-06-14

Systematic AI-Driven Drug Repurposing via Clinical Trial Data Mining: A Framework and Six Cross-Therapeutic Case Studies.

作者:

Drug repurposing, the application of approved or shelved compounds to new therapeutic indications, offers a cost- and time-efficient alternative to de novo drug discovery. However, the systematic identification of repurposing candidates from the rapidly expanding body of clinical trial data remains a significant challenge. Here we present a publicly accessible AI-powered tool that mines the ClinicalTrials.gov registry to identify approved drugs with under-explored therapeutic potential in high-value disease areas. The tool integrates natural language processing, mechanism-of-action pathway analysis, and trial density scoring to surface candidates where biological plausibility is high and clinical trial coverage is sparse. We demonstrate the tool's utility across six cross-therapeutic case studies spanning oncology, cardiology, neurology, rare diseases, immunology, and infectious disease. Key findings include: the identification of Zonisamide as an under-explored combination candidate for obesity alongside GLP-1 receptor agonists; mechanistic validation of SGLT2 inhibitors in heart failure with preserved ejection fraction (HFpEF); and a novel cross-domain mapping of anti-TNF biologics to early-stage neurodegeneration via shared neuroinflammatory pathways. The tool is freely accessible and designed to lower the barrier for academic and industry researchers to systematically pursue repurposing opportunities.

18.
arXiv (CS.CL) 2026-06-16

Cloze: An Open Research Platform for Studying Human-AI Conversations in Mental Health Contexts

Cloze is an open-source web platform for conducting controlled, monitored studies of human-AI conversation in mental health research contexts. Consumer large language model (LLM) products such as ChatGPT, Claude, and Gemini are built for individual productivity, and offer researchers little experimental control, inconsistent data export, and no shared safety scaffolding that holds across providers. Cloze gives research teams a single environment in which they configure which models participants converse with, how the AI is instructed, how conversations are scheduled over time, and which safety constraints apply unconditionally, while every message is captured with full provenance (model version, prompt configuration, timing). The platform currently supports OpenAI, Anthropic, Google, and locally hosted open-weight models served through Ollama behind a unified interface, and runs in the cloud or fully on premises so that participant data need never leave an institution. Cloze is research infrastructure for building an evidence base on human-AI interaction in mental health contexts. It is not a therapeutic product.

19.
arXiv (CS.CV) 2026-06-18

The Reward Was in Your Data All Along: Correcting Flow Matching with Discriminator-Guided RL

Score- and flow-matching models often rely on preference-based reinforcement learning for two purposes: aligning with subjective preferences and, surprisingly, recovering properties such as visual realism and coherent object structure that matching-based training is intended to learn from the data itself. We argue that this reflects a structural mismatch. Matching losses measure $\ell_2$ regression error on the velocity or score field under training-time marginals, a proxy poorly aligned with the visual and semantic properties that determine sample quality at inference. Given a reward aligned with these properties, RL sidesteps the mismatch by evaluating the model on its own samples and following the reward landscape directly. The challenge is to obtain such a reward without relying on human preferences, which are expensive and conflate data realism with annotator inclinations. We propose Discriminator-Guided RL (DRL). DRL trains a discriminator to separate data from base-model samples in a pretrained representation space and uses its logit as the reward in KL-regularized RL. The pretrained space restricts the discriminator to perceptually meaningful directions, and the logit estimates the log-likelihood ratio between data and model, which is the optimal reward for targeting the data distribution. Across SiT, JiT, REPA, and RAE, DRL reduces guidance-free FID (e.g., $9.38 \to 2.62$ on SiT) and semantic-space FD (e.g., $88.2 \to 19.3$ on DINOv3 for SiT), with consistent gains across all backbones, and improves human-preference rewards without training on them. It also yields a better Pareto frontier between preference reward and image fidelity under subsequent preference-based post-training, increasing alignment while reducing low-level artifacts such as oversaturation and excessive brightness.

20.
arXiv (CS.AI) 2026-06-18

What Does the Weight Norm Control in Grokking? Logit-Scale Mediation under Cross-Entropy

arXiv:2606.18465v1 Announce Type: cross Abstract: Grokking, the delayed jump from memorization to generalization, is usually tied to the weight norm: a smaller norm generalizes sooner. We ask what the norm actually controls. Holding the weight norm fixed by clamping and varying only an output temperature, we slide the grokking delay across its entire norm-induced range under cross-entropy; matching the effective logit scale back to baseline recovers about 85% of the delay at two moduli. Across a grid of norms and temperatures the delay collapses onto the logit scale alone (R2 = 0.97), with the norm adding 1-2% beyond it. The effect is loss-dependent: under mean-squared error the logit scale is pinned and the norm acts through a different route. A memorization control, a float64 softmax-collapse audit, and a no-LayerNorm transformer point to the same channel. Forking arms from one identical state, the delay follows the held norm value and not the clamp operation, which closes a rescaling-artifact concern. The proximal variable is the logit scale and the softmax saturation it drives; the weight norm is only an upstream handle. All numbers, tables, and figures reproduce from released code and data.

21.
arXiv (CS.LG) 2026-06-15

A Stationarity-and-Coupling Criterion for Training-Free Time-Lagged Spectral Embeddings of Multivariate Time Series

arXiv:2606.13823v1 Announce Type: new Abstract: We study training-free fixed-length descriptors for multivariate time series and ask not merely whether such a descriptor performs well, but when it can be expected to work at all. Our object of study is $D(\tau)$, built from a time-lagged correlation matrix truncated at the Marchenko-Pastur edge so that only signal-bearing eigenvalues survive and classified by cosine similarity to class centroids with zero learned parameters. The central contribution is not the descriptor but a falsifiable applicability criterion for it. Working from a stationary Gaussian VAR(1) model, we argue that $D(\tau)$ separates two classes when the signals are approximately stationary and the class information lives in their cross-channel temporal coupling rather than in marginal per-channel power. We derive, semi-formally, three consequences: a distinguishability condition, why the static ($\tau=0$) covariance collapses to chance, and why a stationary but power-discriminated paradigm defeats the descriptor. The criterion is operational: a two-part pre-flight test – an augmented Dickey-Fuller stationarity check and a power-baseline saturation check – predicts applicability before any training. We validate both halves on a mixed assortment. On four paradigms that satisfy the criterion (Sleep-EDF, BCI-IV-2a, MIT-BIH, ESC-50) the descriptor is competitive with strong baselines at a fraction of their cost, reaching $88.5\pm4.5\%$ under 20-subject leave-one-subject-out on Sleep-EDF on a single CPU thread. On three that violate it – non-stationary ERPs, and financial-volatility and wearable-stress regimes that are power-discriminated – it fails exactly as the pre-flight predicts, and these negatives are the more informative half. We are explicit that $D(\tau)$ is not the most accurate representation; its value is a compact, training-free embedding whose domain of validity is known in advance.

22.
arXiv (CS.AI) 2026-06-19

Calibration Without Comprehension: Diagnosing the Limits of Fine-Tuning LLMs for Vulnerability Detection in Systems Software

arXiv:2606.20502v1 Announce Type: cross Abstract: Whether LLMs scoring well on vulnerability benchmarks genuinely reason about security or merely pattern-match on contaminated data remains unresolved. We present CWE-Trace, a framework for LLM vulnerability detection built from 834 manually curated Linux kernel samples spanning 74 CWEs. The framework enforces a strict temporal split (pre-2025 historical set / post-cutoff leakage-free set), preserves context-aware vulnerable–patched pairs, and introduces two diagnostic metrics: the Directional Failure Index (DFI) and Hierarchical Distance and Direction (HDD). We evaluate eight vanilla LLMs and 15 LoRA fine-tuned variants across non-targeted detection, targeted detection, and CWE classification. Our analysis yields two key results. First, data contamination provides no measurable advantage. Function-level analysis shows that 84% of nominally contaminated samples carry no usable memorization signal: vulnerable functions are absent or cross-mapped across datasets, and ~31% of contaminated samples carry CWE misclassification. Second, backbone directional priors dominate fine-tuning. Models exhibit stable, systematic failure modes (DFI ranging from -85.5 to +94.8 pp) that persist from historical to post-cutoff data and resist correction. Fine-tuning shifts the output threshold without changing the decision policy. This is calibration without comprehension: output distributions adapt to training data while the underlying security reasoning remains absent. The weakest backbone at binary detection (DeepSeek-R1) gains the most in coarse CWE classification, revealing that detection and understanding are decoupled capabilities. The best detection score reaches only 52.1% (+2.1 pp above chance); exact CWE ranking remains below 1.3% Top-1 accuracy, confirming that current LLMs lack reliable security reasoning for systems software, regardless of fine-tuning strategy.

23.
arXiv (quant-ph) 2026-06-15

Efficient and simple Gibbs state preparation of the 2D toric code via duality to classical Ising chains

arXiv:2508.00126v2 Announce Type: replace Abstract: We introduce the notion of polynomial-depth duality transformations, which relates two sets of operator algebras through a conjugation by a poly-depth quantum circuit, and make use of this to construct efficient Gibbs samplers for a variety of interesting quantum Hamiltonians as they are poly-depth dual to classical Hamiltonians. This is for example the case for the 2D toric code, which is demonstrated to be poly-depth dual to two decoupled classical Ising spin chains for any system size, and we give evidence that such dualities hold for a wide class of stabilizer Hamiltonians. Additionally, we extend the above notion of duality to Lindbladians in order to show that mixing times and other quantities such as the spectral gap or the modified logarithmic Sobolev inequality are preserved under duality.

24.
arXiv (CS.AI) 2026-06-11

Workflow-GYM: Towards Long-Horizon Evaluation of Computer-use Agentic tasks in Real-World Professional Fields

arXiv:2606.11042v2 Announce Type: replace Abstract: Recent years have witnessed the rapid evolution of AI agents toward handling increasingly complex, real-world tasks. However, existing benchmarks rarely evaluate whether agents can operate graphical user interfaces to complete long-horizon, high-value professional workflows across diverse domains. Current GUI benchmarks still predominantly focus on general-purpose software, relatively simple applications, and short-horizon tasks, leaving it largely unknown whether modern agents can follow user instructions to autonomously operate domain-specific professional software and accomplish economically valuable work in an end-to-end manner. To bridge this gap, we introduce Workflow-GYM, a benchmark for long-horizon GUI tasks centered on professional domains and specialized software environments. Through extensive experiments on state-of-the-art models, we find that even the strongest models achieve only slightly above 30% success rates, highlighting that professional long-horizon GUI workflows remain highly challenging for current GUI agents. Further analysis reveals that current agents struggle to maintain long-horizon workflow consistency, frequently exhibiting workflow stage omission, error propagation, objective drift, and insufficient understanding of professional software environments. Our findings provide important insights into the limitations of current agent systems and suggest key directions for the next generation of GUI-agent research.

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

In-Context Learning Is Provably Bayesian Inference: A Generalization Theory for Meta-Learning

arXiv:2510.10981v3 Announce Type: replace-cross Abstract: This paper develops a finite-sample statistical theory for in-context learning (ICL), analyzed within a meta-learning framework that accommodates mixtures of diverse task types. We introduce a principled risk decomposition that separates the total ICL risk into two orthogonal components: Bayes Gap and Posterior Variance. The Bayes Gap quantifies how well the trained model approximates the Bayes-optimal in-context predictor. For a uniform-attention Transformer, we derive a non-asymptotic upper bound on this gap, which explicitly clarifies the dependence on the number of pretraining prompts and their context length. The Posterior Variance is a model-independent risk representing the intrinsic task uncertainty. Our key finding is that this term is determined solely by the difficulty of the true underlying task, while the uncertainty arising from the task mixture vanishes exponentially fast with only a few in-context examples. Together, these results provide a unified view of ICL: the Transformer selects the optimal meta-algorithm during pretraining and rapidly converges to the optimal algorithm for the true task at test time.