中 EN
Sign In Register

Academic Intelligence · Curated Daily

Explore the Frontier of Global Academia

AcademicHub aggregates real-time literature from top journals and preprint platforms. Build your personal research radar and let large language models compile cross-disciplinary analysis briefings automatically.

Sign In Register
01.
arXiv (CS.AI) 2026-06-19

FM-Agent: Scaling Formal Methods to Large Systems via LLM-Based Hoare-Style Reasoning

Authors:
Haoran Ding↗Zhaoguo Wang↗Haibo Chen↗

arXiv:2604.11556v2 Announce Type: replace-cross Abstract: LLM-assisted software development has become increasingly prevalent, and can generate large-scale systems, such as compilers. It becomes crucial to strengthen the correctness of the generated code. However, automated reasoning for large-scale systems remains challenging due to code complexity. Hoare logic offers an approach to decomposing a large system into smaller components and reasoning about them separately (i.e., compositional reasoning). However, existing works still struggle to scale, because Hoare logic requires writing formal specifications for each function, imposing a heavy human burden. The problem is exacerbated when code is generated by LLMs, as developers lack a deep understanding of each function's expected behavior. This paper presents FM-Agent, the first framework that realizes automated compositional reasoning for large-scale systems. Leveraging LLMs, FM-Agent introduces a top-down paradigm to automatically generate function-level specifications. Specifically, FM-Agent derives the specification of a function from how its callers expect the function to behave, so the generated specifications can reflect the developer's intent of a function even if the implementation is buggy. Developers' intent is usually expressed in natural language, while existing verifiers only support formulas. Therefore, FM-Agent generalizes Hoare-style inference to reason about functions against natural-language specifications. Finally, to confirm bug existence and explain bug causes, FM-Agent automatically generates test cases to trigger potential bugs. In our evaluation, FM-Agent successfully reasons about large-scale systems within 2 days, each of which has up to 143k LoC. These systems have already been tested by their developers, but FM-Agent still finds 522 newly discovered bugs. These bugs can cause serious consequences, including system crashes and incorrect execution results.

Read & Discuss → View Source →
02.
arXiv (CS.CL) 2026-06-16

T-Mem: Memory That Anticipates, Not Archives

Authors:
Weidong Guo↗Dakai Wang↗Zixuan Wang↗Hui Liu↗Yu Xu↗

Long-term memory is essential for conversational agents to remain coherent across extended dialogues, follow through on commitments made many sessions earlier, and adapt their behaviour to each user. Current LLM-backed long-term conversational memory, however, is reachability-bounded by the similarity between a query and stored content, both lexical and dense-vector. The approach is effective when query and memory share surface features such as wording or named entities (we call this descriptive). But it misses another, equally valuable class of cases, where query and memory do not share surface features and are tied only by a latent semantic arc (associative). On this regime prevailing long-term memory systems collectively fail. Covering this other half is what allows an assistant, for the first time, to actively draw on past dialogue as a semantic asset. On the memory side, this is the engineering counterpart of what cognitive science calls episodic future thinking: rehearsing past experience for the future contexts under which it will need to be found. We call these write-time rehearsals triggers. We propose T-Mem, the first long-term conversational memory architecture that covers both descriptive and associative recall. At each of two evidence granularities, single facts and full exchanges, T-Mem instantiates one descriptive trigger family and one associative trigger family, so that every memory remains reachable from both surface-similar and relevance-bound queries. As empirical validation, T-Mem reaches state-of-the-art on both LoCoMo and LoCoMo-Plus.

Read & Discuss → View Source →
03.
arXiv (CS.LG) 2026-06-16

Simulation-Augmented Multi-Step Split Conformal Prediction for Aggregated Forecasts

Authors:
Andro Sabashvili↗

arXiv:2606.16356v1 Announce Type: new Abstract: We study uncertainty quantification for aggregated forecasting tasks such as annual totals and year-over-year growth rates. We propose SA-MSCP, a simulation-augmented multi-step split conformal method that generates future paths from cross-validated residuals using a block bootstrap and constructs prediction intervals from empirical quantiles. Experiments show that SA-MSCP improves empirical coverage over a simulated-path baseline for aggregated and growth-rate targets. Our results demonstrate that simulation-enhanced conformal calibration is an effective and general framework for uncertainty quantification in aggregated time-series forecasting.

Read & Discuss → View Source →
04.
arXiv (CS.CV) 2026-06-16

BBR-Net: Boundary-Balanced Replay for Continual Medical Image Segmentation

Authors:
Zahid Ullah↗Sieun Choi↗Jihie Kim↗

Continual learning for medical image segmentation remains challenging under domain shift because replay-based methods often preserve appearance information without explicitly modeling anatomical structure. This study investigates whether structural consistency governs knowledge retention in continual cardiac ultrasound segmentation. We propose the Boundary-Balanced Replay Network (BBR-Net), which selects replay samples using boundary-aware priority and class balance to preserve anatomically informative regions. The method is evaluated on CAMUS and CardiacNet under forward (CAMUS to CardiacNet) and reverse (CardiacNet to CAMUS) task orders. In the forward setting, BBR-Net retains source-task performance close to an offline joint-training reference, while markedly reducing catastrophic forgetting and preserving competitive target-task adaptation. Ablation results show that boundary-aware prioritization contributes to retention and improves the balance between source-task preservation and target-task adaptation when combined with class-aware sampling. In contrast, the reverse setting reveals that structure-aware replay fails when initial representations are learned from noisy and structurally inconsistent data. To isolate this effect, we conduct a controlled structural perturbation analysis by progressively corrupting source-task boundaries while keeping the dataset, architecture, and training protocol fixed. Forgetting increases consistently as structural reliability decreases, suggesting that replay effectiveness is strongly influenced by the quality of stored structural information, rather than by memory capacity alone. These findings indicate that preserving anatomical structure under domain shift is a central factor in continual medical image segmentation, and that replay mechanisms should account for structural reliability to support robust knowledge retention.

Read & Discuss → View Source →
05.
arXiv (CS.AI) 2026-06-12

A Zero-shot Generalized Graph Anomaly Detection Framework via Node Reconstruction

Authors:
Phan Nguyen↗Dat Cao↗Hien Chu↗Khue Hoang↗

arXiv:2606.12673v1 Announce Type: cross Abstract: Cross-domain graph anomaly detection (GAD) aims to identify abnormal nodes in unseen target graphs, showing strong potential in real-world applications with heterogeneous graph data. However, existing methods often depend on dataset-specific feature semantics and structural patterns, which limits their ability to generalize across different domains. To address this challenge, we propose AlignGAD, a zero-shot generalized graph anomaly detection framework. Our framework is built upon three key components: a Global Unification Module that aligns heterogeneous node features and normalizes graph signals in the spectral domain; a Clustering Module that constructs cluster-aware graph views to capture group-level abnormal patterns; and a Node Discrepancy Scoring Module that measures reconstruction discrepancy and aggregates anomaly evidence from different graph views. Experiments on multiple real-world datasets demonstrate the effectiveness of AlignGAD under the zero-shot GAD setting.

Read & Discuss → View Source →
06.
arXiv (CS.AI) 2026-06-11

OCSVM-Guided Representation Learning for Unsupervised Anomaly Detection

Authors:
Nicolas Pinon↗Robin Trombetta↗Carole Lartizien↗

arXiv:2507.21164v2 Announce Type: replace-cross Abstract: Unsupervised anomaly detection (UAD) aims to detect anomalies without labeled data, a necessity in many machine learning applications where anomalous samples are rare or not available. Most state-of-the-art methods fall into two categories: reconstruction-based approaches, which often reconstruct anomalies too well, and decoupled representation learning with density estimators, which can suffer from suboptimal feature spaces. While some recent methods attempt to couple feature learning and anomaly detection, they often rely on surrogate objectives, restrict kernel choices, or introduce approximations that limit their expressiveness and robustness. To address this challenge, we propose a novel method that couples representation learning with an analytically solvable One-Class SVM (OCSVM), through a custom loss formulation that directly aligns latent features with the OCSVM decision boundary. The model is evaluated on two tasks: a \deleted{new} benchmark based on MNIST-C, and a challenging brain MRI \deleted{subtle} lesion detection task. Unlike most methods that focus on large, hyperintense lesions at the image level, our approach succeeds to target small, non-hyperintense lesions, while we evaluate voxel-wise metrics, addressing a more clinically relevant scenario. Both experiments evaluate a form of robustness to domain shifts, including corruption types in MNIST-C and texture or population age variations in MRI. Results demonstrate performance and robustness of our proposed model, highlighting its potential for general UAD and real-world medical imaging applications. The source code is available at https://github.com/Nicolas-Pinon/uad_ocsvm_guided_repr_learning.

Read & Discuss → View Source →
07.
arXiv (CS.AI) 2026-06-18

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

Authors:
Truong Xuan Khanh↗

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.

Read & Discuss → View Source →
08.
arXiv (CS.CL) 2026-06-16

Can LLM Agents Infer World Models? Evidence from Agentic Automata Learning

Authors:
Reef Menaged↗Gili Lior↗Shauli Ravfogel↗Roee Aharoni↗Gabriel Stanovsky↗

We propose agentic automata learning to evaluate the extent to which tool-calling LLM agents can uncover hidden environments through interaction. In our setup, an agent should uncover a hidden deterministic finite automaton (DFA) by interacting with an oracle through (1) membership queries ("Does this string belong to the target language?") and (2) equivalence queries ("Is this the target DFA?"). This yields a scalable testbed with controlled task complexity, measurable interaction efficiency, and strong baselines (classic automata-learning algorithms). Evaluating state-of-the-art LLMs, we find that performance drops sharply as DFA size increases. Reasoning models are markedly stronger than non-reasoning models, yet trajectory analyses reveal recurring failures in query planning, evidence integration, and hypothesis construction. Overall, our results show that current LLM agents can sometimes perform non-trivial interactive discovery, but remain far less robust and efficient than classic algorithms for the task.

Read & Discuss → View Source →
09.
arXiv (CS.CV) 2026-06-11

3D-CBM: A Framework for Concept-Based Interpretability in Generative 3D Modeling

Authors:
Ahmad Al-Kabbany↗

This research introduces a framework for incorporating Concept Bottleneck Models (CBMs) into 3D generative architectures to address the inherent 'semantic gap' in deep geometric learning. As deep models become central to 3D content creation, explainability shifts from a peripheral feature to a fundamental requirement for trust and accountability in safety-critical domains such as healthcare and manufacturing. CBMs provide an intrinsic interpretability solution by constraining latent representations to align with human-defined concepts, yet their application to unstructured 3D data remains largely unexplored. We design, implement, and validate a formal 3D-CBM architecture that maps raw geometric inputs, including point clouds and meshes, into a multi-tiered taxonomy of interpretable primitives and functional attributes. The framework further identifies strategic datasets, such as PartNet and ShapeNet, specialized for concept-based supervision. Experimental results from a 3D part-manipulation proof-of-concept experiment demonstrate the framework's efficacy, achieving a concept prediction accuracy of 88.8\% and a Chamfer Distance of 0.0115. Critically, the model enables precise test-time intervention, allowing for the interactive correction of structural errors. This work establishes a foundation for semantically-steerable 3D generation and invites further exploration into collaborative human-in-the-loop design systems.

Read & Discuss → View Source →
10.
arXiv (CS.LG) 2026-06-16

MUNI: Multimodal Unified Latent Diffusion for Coherent Any-to-Any Generation

Authors:
Kyeongmin Yeo↗Yunhong Min↗Minhyuk Sung↗

arXiv:2606.16408v1 Announce Type: new Abstract: We introduce MUNI, an end-to-end multimodal latent diffusion framework for any-to-any generation that unifies subset-conditioned cross-modal generation and unconditional joint sampling through a shared stochastic latent. Existing multimodal generative models are largely LLM-based, which limits leveraging modality-specific generators and requires text-paired data for training. Recent diffusion- and flow-based any-to-any extensions take a different direction but still rely on text-aligned embeddings, fully-paired training, or matched-dimensionality deterministic mappings. MUNI rests on two complementary contributions, one architectural and one in the training objective. First, we extend latent diffusion to multimodal any-to-any generation end-to-end: instead of the standard two-stage recipe that precomputes a frozen latent space and then fits a prior over it, MUNI jointly trains modality-specific encoders, expressive decoders, and a single shared flow-based prior under one objective. Second, we identify that the standard aggregation rules of multimodal variational inference are insufficient once coupled with a learned prior and expressive decoders. A suitable shared latent must simultaneously satisfy coherence across generated modalities, predictive sufficiency of subset latents, and minimality of the latent content. We propose a routed training objective whose structural choices align the latent with these criteria and admit a minimal-sufficiency characterization in the realizable setting. Experiments on PolyMNIST-Quadrant-Labels and a large-scale image-text-audio benchmark show MUNI matching or exceeding the strongest baselines on conditional generation while opening its largest margins on unconditional coherence. Project page: https://muni-proj.github.io/.

Read & Discuss → View Source →
11.
arXiv (quant-ph) 2026-06-19

Computing noise-canceling observables via Pauli propagation

Authors:
Andrew Eddins↗Caleb Johnson↗Alberto Baiardi↗Francesco Tacchino↗Ewout van den Berg↗Roy Elkabetz↗Vinay Tripathi↗Swarnadeep Majumder↗Max Rossmannek↗Liran Shirizly↗Abhinav Kandala↗

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.

Read & Discuss → View Source →
12.
arXiv (math.PR) 2026-06-15

A random approach to the multibonacci sequence

Authors:
Hac\`ene Belbachir↗Hamza Zeggada↗

arXiv:2606.14294v1 Announce Type: cross Abstract: This paper presents a random approach to the multibonacci sequence. We generalise the model introduced by Benjamin, Levin, Mahlburg, and Quinn, which is based on a random tiling method using dominoes and squares that leads to the Fibonacci sequence, and which was extended to the tribonacci case in a previous work by the authors. Our approach employs tiling with linear $k$-ominoes, $k=1,\ldots,s$, combined with specific colouring, to generate a weighted multibonacci sequence. For a natural random variable~$X$ defined by this model, we establish the distribution of $X$ in terms of multibonacci numbers and compute $\mathbb{E}[X] = 2^{s+1}-3$.

Read & Discuss → View Source →
13.
medRxiv (Medicine) 2026-06-11

What level of expertise is necessary to generate ACLS training test questions: pre-med students vs. artificial intelligence?

Authors:
LoGalbo↗S. S↗Richman↗Wang↗Saji↗Traore↗Oliva↗Wu↗Drudi↗Foster↗Bhandari↗Delfillo↗…

Abstract Introduction In-hospital cardiac arrest carries high mortality despite standardized ACLS training. Educators face increasing time constraints in developing assessment tools for ACLS training. Two possible solutions to this problem are using pre-medical students or using artificial intelligence to generate test questions. This study compared the quality of pre-medical student-generated ACLS test questions vs. AI-generated ACLS test questions, testing the hypothesis that AI-generated questions are non-inferior to student-generated questions. Methods Ten pre-medical students created ACLS questions following predefined criteria, while an AI model (Northwell's Artificial Intelligence Hub) generated comparable questions. A blinded ACLS-certified physician evaluated questions on the qualities of Alignment, Clarity, Cognitive Level, and Question Design using a standardized rubric (Likert scale: 1 = poor quality, 5 = excellent). Student's T-test and Chi-square analysis were used to compare the quality of questions on different rubric domains within each arm (student vs. AI) and within one domain (eg, question Clarity) between arms. The Student's T test was used when 2 comparator groups were compared (eg, Clarity of student-generated vs. AI-generated questions) within one arm. The ANOVA test was used when comparing more than 2 comparator groups (eg, Alignment vs. Clarity vs. Cognitive Level) within one arm. Statistical significance was set as a priority at p

Read & Discuss → View Source →
14.
arXiv (CS.AI) 2026-06-16

Gender Differences in AI Literacy Workshop Outcomes and Deepfake Engagement

Authors:
Jake Renzella↗Christian Bergh↗Natasha Banks↗Alexandra Vassar↗

arXiv:2606.14718v1 Announce Type: cross Abstract: As Artificial Intelligence (AI) literacy initiatives expand in K-12 settings, understanding how gender shapes student baseline perceptions, tool-use, and responsiveness to interventions is essential for equitable curriculum design. This study examines gender differences in AI literacy, safety awareness, and STEM career aspirations among Australian secondary students (Years 7, 8, and 10; N(pre) = 199, n(post) = 136) from two co-educational government schools who participated in a one-day AI literacy workshop. Using statistical regression methods controlling for year level and school, we found that pre-workshop, male students reported significantly higher STEM career interest across all three domains (AI, computer science, and engineering), while female students were significantly more likely to use AI for schoolwork and to seek advice from AI tools. Gender-differentiated patterns also emerged in deepfake behaviours: males were significantly more likely to have created or shared deepfake content. Both genders improved in AI knowledge post-intervention, yet females showed a richer profile of gains: wider conceptual understanding, greater confidence, and meaningful increases in AI and CS career interest that partially narrowed the gender STEM gap. These findings highlight the need for gender-responsive AI curricula, particularly deepfake safety education for male students, and demonstrate that even single-day workshops can narrow gender gaps in STEM aspirations and AI confidence.

Read & Discuss → View Source →
15.
arXiv (CS.LG) 2026-06-16

ExpRL: Exploratory RL for LLM Mid-Training

Authors:
Violet Xiang↗Amrith Setlur↗Chase Blagden↗Nick Haber↗Aviral Kumar↗

arXiv:2606.17024v1 Announce Type: new Abstract: Sparse reward reinforcement learning (RL) has become a standard tool for improving LLM reasoning, but its success depends critically on the coverage present in the base model. In practice, models are often primed for RL through mid-training on curated reasoning traces that teach useful primitive skills such as decomposition, verification, or self-correction. Although effective, this strategy requires manually specifying what the model should learn, and it remains unclear whether such primitive coverage is enough for much harder problems, which require combining these skills into broader solution strategies. We study a more automated approach: RL-based mid-training using large corpora of human-written question-answer data. Rather than treating reference solutions as targets to imitate, our method, ExpRL, uses them as reward scaffolds: references are hidden from the policy and used only to construct problem-specific grading rubrics for judging on-policy reasoning traces. The policy samples from the original problem prompt, while an LLM judge compares the sampled reasoning trace against the reference solution and assigns outcome-level or process-level dense rewards. This lets ExpRL reinforce partial progress, useful intermediate reductions, and productive reasoning behaviors that sparse final-answer rewards often fail to upweight. On challenging math reasoning tasks, ExpRL yields stronger RL priming than SFT, sparse-reward GRPO, and self-distillation, and provides a better initialization for subsequent sparse-reward RL. Additional mixed-domain experiments further suggest that ExpRL can extend beyond the original math-only setting.

Read & Discuss → View Source →
16.
arXiv (CS.CL) 2026-06-11

Small Experiments, Cheaper Decisions: A Case Study in Staged Promotion for Micro-Pretraining

Authors:
Felipe Chavarro Polania↗

Short pretraining runs can reduce experimental cost, but they can also over-promote configurations that only look strong at tiny budgets. We study an auditable staged-promotion protocol for a fixed micro-pretraining runner on two heterogeneous host blocks: Windows A100 and Linux L40S. Starting from twelve prior-screened configurations, we use staged budgets of 2 minutes, 5 minutes, 10 minutes, 60 minutes, and 12 hours, with frozen promotion rules before expensive continuations. The early screens are intentionally treated as unstable: the 5- and 10-minute rankings are host-sensitive, and the eventual 12-hour top-ranked condition is not the mean-best condition at the replicated 10-minute gate. Because seed ranges differ across stages, these changes are operational promotion evidence, not within-seed curves. A replicated 60-minute gate keeps the Staged Factorial Screening bridge reference in the promoted set, where it ranks first in all four 60-minute host-seed cells. In the final 12-hour confirmation package, the bridge condition ranks first in all four host-seed cells across two seeds; the greedy comparator does not meet the frozen 0.010 val_bpb near-equivalence rule; and the cheaper d8/ar48 (depth-8, aspect-48) sentinel does not meet the frozen 0.020 mean-gap rule. The executed 12-hour branch spends 144 GPU-hours, and the full staged protocol records 169.2 training GPU-hours including screening stages. Continuing all four 60-minute candidates would spend 192 GPU-hours, while continuing all nine replicated 10-minute candidates would spend 432 GPU-hours. The latter numbers are accounting counterfactuals for unrun continuations, not evidence that skipped candidates could not have overtaken the reference. The result is a bounded cost-allocation finding, not a claim of global optimality, capacity-normalized superiority, or superiority over adaptive hyperparameter optimization methods.

Read & Discuss → View Source →
17.
medRxiv (Medicine) 2026-06-16

Wildfire pollution exposure during childhood adversely affects cognitive and neural development

Authors:
Judd↗kievit↗

Air pollution has well-documented negative cardiovascular and respiratory consequences. However, the impact of particulate matter pollution (PM2.5) on brain development is unclear. Animal studies suggest that exposure to early-life PM2.5 can cause adverse neurodevelopmental outcomes, but in vivo human work has been hampered by cross-sectional designs and heavily confounded PM2.5 exposure measures. Here we use an innovative natural experimental design to isolate the effects of wildfire pollution on neurocognitive development in a large cohort of children (N>9000, 4 waves, age 9-16). Doing so, we find that greater wildfire PM2.5 exposure is robustly associated with slower brain development and shallower cognitive improvement across early adolescence. Our study underscores the urgent public health concern that wildfire PM2.5 poses for childhood development.

Read & Discuss → View Source →
18.
arXiv (CS.CV) 2026-06-15

RT-VLA: Real-Time Vision-Language-Action Models via Knowledge Distillation

Authors:
Xiangyu Huang↗Zhenlin Hua↗Han Zhou↗Shounak Sural↗Ragunathan Rajkumar↗

Vision-Language-Action (VLA) models have shown strong potential for end-to-end autonomous driving by jointly modeling visual perception, language reasoning, explainability and action prediction. However, their large vision-language backbones and reasoning modules introduce substantial inference latency and thereby prevent their deployment in the unforgiving reality of the road networks. We propose RT-VLA, a lightweight, distilled VLA model that transfers the driving and reasoning capabilities of the state-of-the-art SimLingo model into a compact student through multi-level supervised distillation. RT-VLA preserves language-based reasoning and supports post-hoc explanation through offline language analysis of safety-critical driving moments without adding latency to real-time control. Compared to the SimLingo teacher, RT-VLA maintains competitive closed-loop driving and language reasoning performance while reducing inference time by 44.8X in vision-only mode and 7.9X in vision+language mode. These results suggest that supervised distillation is a practical approach for building real-time, explainable VLA-style autonomous driving models.

Read & Discuss → View Source →
19.
arXiv (CS.CL) 2026-06-19

The Voice Behind the Words: Quantifying Intersectional Bias in SpeechLLMs

Authors:
Shree Harsha Bokkahalli Satish↗Christoph Minixhofer↗Maria Teleki↗James Caverlee↗Ond\v{r}ej Klejch↗Peter Bell↗Gustav Eje Henter↗\'Eva Sz\'ekely↗

Speech Large Language Models (SpeechLLMs) process spoken input directly, retaining cues such as accent and perceived gender that were previously removed in cascaded pipelines. This introduces speaker identity dependent variation in responses. We present a large-scale intersectional evaluation of accent and gender bias in three SpeechLLMs using 2,880 controlled interactions across six English accents and two gender presentations, keeping linguistic content constant through voice cloning. Using pointwise LLM-judge ratings, pairwise comparisons, and Best-Worst Scaling with human validation, we detect recurring directional disparities. Eastern European-accented speech receives lower helpfulness scores, particularly for female-presenting voices. Responses remain polite but differ in helpfulness. While LLM judges capture the directional trend of these biases, human evaluators exhibit significantly higher sensitivity, showing stronger accent-level contrasts.

Read & Discuss → View Source →
20.
arXiv (CS.CV) 2026-06-16

Gaussian Spatial Priors for Anatomy-Aware Object Detection in Surgical Videos

Authors:
Yunfan Li↗Artem Shmelev↗Himanshu Gupta↗

Detecting anatomical structures in surgical video is essential for intraoperative safety frameworks such as the Critical View of Myopectineal Orifice (CVMPO) in inguinal hernia repair. While prominent structures like the Cooper's Ligament and Triangle of Doom are reliably detected by standard methods, smaller structures such as the epigastric vessels remain challenging due to their visual ambiguity and intermittent visibility. We observe that the spatial relationship between structures is anatomically constrained, and propose a Gaussian Spatial Prior (GSP) module that encodes this relationship as a compact, parametric bias injected into the self-attention of a DAB-DETR decoder. The prior is computed offline from training annotations as a small set of frozen Gaussian parameters and recomputed at each decoder layer using the iteratively refined reference points. On a dataset of inguinal hernia repair videos with 5-fold cross-validation, GSP improves dependent class detection by $+33.5\%$ ($AP_{50}$) over DAB-DETR and $+53.9\%$ over YOLOv26, while also improving anchor detection by $+6.0\%$. These gains are statistically significant across all folds ($p=0.012$, paired $t-$test).

Read & Discuss → View Source →
21.
arXiv (CS.CL) 2026-06-16

FinBalance: A Multi-Document Accounting Reconciliation Benchmark

Authors:
Sasank Tumpati↗Devansh Agarwal↗Ayush Kedia↗Arjun Neekhra↗Murari Mandal↗Krishna Garg↗Yash Sinha↗Suman Gupta↗Dhruv Kumar↗

Existing financial-NLP benchmarks mostly evaluate prepared artifacts such as filings, tables, or extracted values. Real accounting begins earlier: source documents must be reconciled into cited journal entries, aggregated into a balance sheet, and checked for contradictions. We introduce FinBalance, a multi-document accounting reconciliation benchmark built from source-document bundles across eight industries, three period types, and five difficulty levels. Human-authored business scenarios, accounting policies, tax/FX treatments, document schemas, distractors, and inconsistency templates are composed by a deterministic generator whose ledger produces journal entries,balance sheets, and 23 inconsistency-code labels. On a 710-record evaluation split, six contemporary LLMs reach at most 46% exact final-balance-sheet accuracy. Four models show a 26-41 pp gap between BS_exact, the model's reported balance sheet, and BS_recon, the balance sheet obtained by replaying its entries through our ledger. Models often recover numerically plausible entries but fail to bind them to supporting documents and aggregate them consistently. Citation-pressure prompting barely changes document-linking errors, while ledger-feedback ablations substantially improve reported balance sheets and expose inconsistency-detection trade-offs. Expert finance reviewers validate the benchmark design and labels.

Read & Discuss → View Source →
22.
arXiv (CS.LG) 2026-06-18

A Human-in-the-Loop Bayesian Optimization Framework for Constraint-Aware Bioprocess Development

Authors:
Samuel Stricker↗Claus Wirnsperger↗Alessandro Butt\'e↗Laura Helleckes↗Gonzalo Guill\'en Gos\'albez↗Antonio del Rio Chanona↗Mehmet Mercang\"oz↗

arXiv:2606.19230v1 Announce Type: new Abstract: This work presents an extension to Pareto Front Guided Sampling (PFGS), a Human-in-the-Loop (HitL) Bayesian Optimization (BO) framework in which Gaussian process (GP) surrogate-derived quantities are reformulated as objectives of a multi-objective optimization problem, and the resulting Pareto front is exposed to a domain expert for interactive candidate selection rather than returning a single automated recommendation. The framework is extended in two directions: constrained optimization is addressed by incorporating the posterior probability of satisfying output specification limits as an explicit Pareto objective, computed analytically from the GP posterior distribution; robust optimization is addressed by a Monte Carlo sampling strategy that estimates expected lower-confidence performance over a user-defined variability of input perturbations, capturing performance degradation under likely implementation deviations. The resulting multi-dimensional Pareto representation renders trade-offs between predicted performance, model uncertainty, probabilistic constraint satisfaction, and input robustness simultaneously visible through pairwise two-dimensional projections on an interactive dashboard, enabling selection criteria to be iteratively refined as the surrogate model improves and development objectives evolve. The framework is showcased on an eight-dimensional fed-batch Chinese Hamster Ovary (CHO) cell culture simulator demonstrating systematic identification of high-performing, feasibility-compliant, and perturbation-resilient operating conditions, and illustrating how expert-defined requirements provide a principled stopping criterion and support informed allocation of experimental resources.

Read & Discuss → View Source →
24.
arXiv (CS.AI) 2026-06-15

The Insurability Frontier of AI Risk: Mapping Threats to Affirmative Coverage, Silent Exposures, and Exclusions

Authors:
Alex Leung↗Rex Zhang↗Ervin Ling↗Kentaroh Toyoda↗SiewMei Loh↗

arXiv:2605.18784v2 Announce Type: replace-cross Abstract: The rapid diffusion of agentic AI has created a new coverage problem for commercial insurance: some AI-mediated losses are now affirmatively insured, some create silent-AI exposure under legacy cyber, technology errors-and-omissions (E&O), directors-and-officers (D&O), employment practices liability (EPLI), crime, and media policies, and others are being actively excluded. This paper maps that emerging boundary by coding 55 AI threat classes against 26 insurance products, endorsements, and exclusion regimes using public carrier materials and OWASP/MITRE threat catalogs. We identify a four-tier insurability frontier: affirmatively insured perils, silent-AI exposures, actively excluded perils, and perils outside conventional private insurance structures. Our coding measures publicly claimed positioning rather than executed contract wording; the headline statistics describe what carriers publicly state about coverage, not what would be paid in any specific claim. Three patterns emerge. First, affirmative AI coverage is beginning to differentiate by primary risk emphasis: public materials often position Munich Re around model performance and drift, Armilla and parts of the Lloyd's market around hallucination and broader AI liability, Tokio Marine Kiln and CFC around IP and technology E&O concerns, Apollo ibott around emerging autonomous system liability, and Coalition around deepfake and AI-enabled cyber response. Second, legacy lines retain silent-AI exposure where AI is an instrumentality rather than the legal cause of loss. Third, foundation model concentration is the clearest genuinely novel insurability frontier because upstream model failure can correlate losses across many cedents at once; the relevant market design question is which insurability constraint each candidate structure relaxes, not merely which systemic risk template exists.

Read & Discuss → View Source →
25.
arXiv (CS.LG) 2026-06-19

A Critical Look at Targeted Instruction Selection: Disentangling What Matters (and What Doesn't)

Authors:
Nihal V. Nayak↗Paula Rodriguez-Diaz↗Neha Hulkund↗Sara Beery↗David Alvarez-Melis↗

arXiv:2602.14696v2 Announce Type: replace Abstract: Instruction fine-tuning of large language models (LLMs) often involves selecting a subset of instruction training data from a large candidate pool, using a small query set from the target task. Despite growing interest, the literature on targeted instruction selection remains fragmented and opaque: methods vary widely in selection budgets, often omit zero-shot baselines, and frequently entangle the contributions of key components. As a result, practitioners lack actionable guidance on selecting instructions for their target tasks. In this work, we aim to bring clarity to this landscape by disentangling and systematically analyzing the two core ingredients: data representation and selection algorithms. Our framework enables controlled comparisons across models, tasks, and budgets. We find that only gradient-based data representations choose subsets whose similarity to the query consistently predicts performance across datasets, models, and candidate pools. While no single method dominates, gradient-based representations paired with greedy round-robin selection often perform best on average at low budgets, but these gains diminish at larger budgets. Finally, we unify several existing selection algorithms as forms of approximate distance minimization between the selected subset and the query set, and support this view with new generalization bounds. More broadly, our findings provide critical insights and a foundation for more principled data selection in LLM fine-tuning. The code is available at https://github.com/dcml-lab/targeted-instruction-selection.

Read & Discuss → View Source →