# Research Papers — 2026-06 · bundle page 13 of 260 > Full-text markdown of papers #601–650 of 12993 published in 2026-06, newest first. AI-readable mirrors of the full 12993-paper 2026-06 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-06/page/13 [← Previous bundle](https://aipod.dev/papers/archive/2026-06/page/12.md) [Next bundle →](https://aipod.dev/papers/archive/2026-06/page/14.md) ### Bridging Scientific Heritage: An Arabic--Russian Parallel Corpus and LLM Benchmark for Sustainable Knowledge Transfer Authors: Mullosharaf K. Arabov Published: 2026-06-29 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.30943v2 Russian and Arabic are among the major languages of scientific communication. Language barriers impede the exchange of research results between these communities, which affects international collaboration and the progress of sustainability-related research. We present a benchmark for Arabic--Russian scientific translation. The benchmark includes a hybrid parallel corpus of about 27,000 sentence pairs, compiled from scientific abstracts and general-domain texts (religion, news, conversations). We fine-tune three multilingual language models -- mT5-base (580M parameters), NLLB-200-distilled-1.3B (1.3B), and Qwen2.5-7B-Instruct (7B) -- using LoRA with ranks 8, 16, 32, and 64. The Qwen2.5-7B model with QLoRA (rank 8) yields BLEU 23.15, chrF 43.89, BERTScore 0.906, and COMET 0.758. These are +4.36 BLEU and +0.051 COMET above the zero-shot baseline. Few-shot prompting with three examples does not improve performance, indicating that domain-specific fine-tuning is required. We release the models, the corpus, and the evaluation code. By lowering the language barrier for scientific texts, the work enables knowledge exchange between Arabic-speaking and Russian-speaking researchers. It contributes to sustainable partnerships (UN SDG 17) and innovation infrastructure (SDG 9), aligning with the conference's focus on technology-driven sustainable development. --- ### Bridging Scientific Heritage: An Arabic--Russian Parallel Corpus and LLM Benchmark for Sustainable Knowledge Transfer Authors: M. K. Arabov Published: 2026-06-29 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.30943v1 Russian and Arabic are among the major languages of scientific communication. Language barriers impede the exchange of research results between these communities, which affects international collaboration and the progress of sustainability-related research. We present a benchmark for Arabic--Russian scientific translation. The benchmark includes a hybrid parallel corpus of about 27,000 sentence pairs, compiled from scientific abstracts and general-domain texts (religion, news, conversations). We fine-tune three multilingual language models -- mT5-base (580M parameters), NLLB-200-distilled-1.3B (1.3B), and Qwen2.5-7B-Instruct (7B) -- using LoRA with ranks 8, 16, 32, and 64. The Qwen2.5-7B model with QLoRA (rank 8) yields BLEU 23.15, chrF 43.89, BERTScore 0.906, and COMET 0.758. These are +4.36 BLEU and +0.051 COMET above the zero-shot baseline. Few-shot prompting with three examples does not improve performance, indicating that domain-specific fine-tuning is required. We release the models, the corpus, and the evaluation code. By lowering the language barrier for scientific texts, the work enables knowledge exchange between Arabic-speaking and Russian-speaking researchers. It contributes to sustainable partnerships (UN SDG 17) and innovation infrastructure (SDG 9), aligning with the conference's focus on technology-driven sustainable development. --- ### Motion Planning in Compressed Representation Spaces Authors: Lukas Lao Beyer, Sertac Karaman Published: 2026-06-29 Categories: cs.RO, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.30940v1 Deep learning methods have vastly expanded the capabilities of motion planning in robotics applications, as learning priors from large-scale data has been shown to be essential in capturing the highly complex behavior required for solving tasks such as manipulation or navigation for autonomous vehicles. At the same time, model-based planning algorithms based on search or optimization remain an essential tool due to their flexibility, efficiency, and the ability to incorporate domain knowledge via expert-designed algorithms and objective functions. We propose a new generative framework to unify these two paradigms. First, we learn an autoencoder with a high compression ratio and a latent space of hierarchically ordered, discrete-valued tokens. Leveraging both the dimensionality reduction and the hierarchical coarse-to-fine structure learned by this autoencoder, we then perform motion planning by directly searching in the latent space of tokens. This search can optimize arbitrary objective functions specified at test time, providing a large degree of flexibility while maintaining efficiency and producing realistic solutions by relying on the generative capabilities of the highly compressed autoencoder. We evaluate our method on nuPlan and the Waymo Open Motion Dataset, showing how latent space search can be used for a variety of guided behavior generation tasks, achieving strong performance for closed-loop motion planning and multi-agent guided scenario synthesis without requiring any task-specific training. --- ### No Adaptation Without Observation: Observability-Constrained Test-Time Prompt Tuning for LiDAR Semantic Segmentation Authors: Linlian Jiang, Wentao Ju, Sadman Rakib Pinon, Jianwei Xian, Zhixiang Chi, Xinxin Zuo, Yang Wang Published: 2026-06-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.30937v1 LiDAR semantic segmentation often degrades under real-world deployment due to evolving sensing conditions, while collecting new annotations for retraining is impractical. Test-time adaptation (TTA) updates model parameters online using pseudo-label supervision, but directly applying standard TTA strategies to LiDAR data is challenging. Because pseudo-label reliability is spatially heteroscedastic under range-dependent sparsity and occlusion, uniform updates on globally shared parameters can inject unstable gradients and destabilize adaptation. We propose a geometry-constrained test-time prompt tuning framework for LiDAR semantic segmentation. Our method estimates per-location sensing reliability from depth-consistent beam terminations and neighborhood support, and uses it to reweight spatial supervision. Adaptation is confined to lightweight prompt adapters inserted into a frozen backbone, with spatial gating to prevent unreliable regions from perturbing globally shared representations. A temporally smoothed prototype alignment strategy further stabilizes online updates by accumulating reliable semantic evidence over time. Experiments on standard LiDAR benchmarks demonstrate improved adaptation stability and segmentation performance under deployment variations without additional annotations. --- ### Physics-informed Conditional Normalizing Flows for Angles-only Cislunar Orbit Determination Authors: Walther Litteri, Massimiliano Vasile Published: 2026-06-29 Categories: cs.LG, astro-ph.EP, astro-ph.IM, cs.AI arXiv: https://arxiv.org/abs/2606.30936v1 Generative Astrodynamics is advanced in this work by extending generative modelling to an orbit determination problem in the cislunar environment. The task is formulated as conditional density estimation, aiming to infer the probability distribution of the initial state from angles-only measurements over short observation arcs. A normalising flow is trained on perturbed topocentric observations from Near Rectilinear Halo Orbits, enabling a flexible and potentially multimodal posterior representation. Given new measurements, the learned density is sampled to generate statistically consistent and physics-informed state hypotheses. These estimates are refined via nonlinear least-squares minimisation, providing a competitive warm start for classical algorithms. --- ### ShardNet: Training Neural Controllers with Hard, Non-Convex Constraints Authors: Long Kiu Chung, Shreyas Kousik Published: 2026-06-29 Categories: eess.SY, cs.LG arXiv: https://arxiv.org/abs/2606.30935v1 While neural network control policies are powerful, their deployment on safety critical systems depends on ensuring that they obey strict constraints. Existing work often treats safety as a metric to optimize for, which competes with other performance objectives, if training converges at all. Instead, we introduce ShardNet, a neural network architecture that strictly enforces unions of polyhedral constraints by construction, using a differentiable projection layer parameterized by a classification network. The key insight is to embed safety into the neural network's structure, allowing performance to be optimized independently because formal safety guarantees are always given. In contrast with existing neural architectures that can only enforce simple convex constraints, ShardNet enables the first safe-by-construction synthesis of forward-invariant neural network controllers on closed-loop systems where safety constraints are expressed as nonconvex unions of polyhedras or learned value function level sets. To support this, we also introduce a technique to verify and train such value functions correctly as rectified linear unit (ReLU) networks, which has not previously been possible. On double integrator benchmarks drawn from the literature, ShardNet policies maintain 100% safety on verified sets and achieves significantly lower objective loss compared to existing formal methods. Furthermore, our value function training technique also produces safe sets more than 3 times larger than existing verification approaches. --- ### Quality-Aware Modulation for Diffusion Transformers Authors: Luke Budny, Yuhong Guo, Kevin Cheung Published: 2026-06-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.30934v1 Modern text-to-image diffusion models, such as diffusion transformers (DiT), rely on timestep or prompt embeddings to modulate the strength of the denoising process in each timestep. While this modulation communicates the current noise level, it does not provide any quality-aware information, which can lead to generated images that are unaligned, visually inconsistent, and lacking in fidelity. In this paper, we propose the Quality Representation Module (QRM), a lightweight transformer module that learns a quality-aware representation based on existing model inputs, and produces a set of vectors $M_{qrm}$. These vectors adjust the adaptive LayerNorm modulation within the DiT transformer blocks, thereby injecting a quality-sensitive signal into the denoising parameters. The QRM introduces no significant changes to the sampling schedule or diffusion backbone. Experiments include ablations on QRM training losses and architectures, as well as empirical results demonstrating consistent image quality improvements over baseline DiT-based models. --- ### Personalizing Marketplace Policies with Competing Objectives and Constrained Experiments: Evidence from a Job Marketplace Authors: Yufei Wu, Zhen Yan Published: 2026-06-29 Categories: cs.LG, stat.AP, stat.ME arXiv: https://arxiv.org/abs/2606.30932v1 Two-sided marketplaces connect distinct user groups whose interests often conflict -- improving outcomes on one side could degrade the other side's experience. To address this challenge, we deploy an integrated framework for personalizing free-value thresholds -- a policy governing the scope of complimentary services for job listings -- across a two-sided job marketplace connecting millions of employers and job seekers. Our personalized policy delivers statistically significant and economically sizable lift in the target metric while respecting engagement guardrail constraints. Direct application of standard uplift methods proves insufficient here for two reasons. First, cross-side externalities demand multi-objective optimization: maximizing employer-side metrics risks harming job seeker engagement, with effects varying substantially across job segments. Second, marketplace interference necessitates cluster-level randomization, limiting us to few discrete treatment levels -- effectively a form of positivity violation that rules out methods designed for continuous treatments. We contribute an integrated framework with three components. Our ensemble-based hybrid ranking models target and guardrail metrics separately, cutting guardrail risk by over 10% for equivalent target gains compared to single-objective approaches. A treatment effect extrapolation method extends our estimates from limited experimental variation to untested policy levels, relying on monotonicity assumptions that we validate empirically. Finally, we present production deployment, where post-launch data confirms both extrapolation accuracy and guardrail compliance. Our deployed system demonstrates that principled methodology can enable meaningful personalization even when experiments are severely constrained and different objectives compete -- common conditions that characterize many real-world marketplaces. --- ### RoPoLL: Robust Panel of LLM Judges Authors: Anish Acharya, Kris W Pan, Brian Verkhovsky Published: 2026-06-29 Categories: cs.AI, cs.LG, cs.MA, math.OC, math.PR arXiv: https://arxiv.org/abs/2606.30931v1 The LLM Jury, a Panel of LLM Evaluators (PoLL) reporting consensus scores, has become a practical alternative to single-judge LLM evaluation, yet its statistical behavior remains poorly understood. We formalize the LLM Jury under the Huber contamination model and show that PoLL incurs unbounded bias under any positive contamination, regardless of jury size, whenever a single judge fails in a biased, LLM-typical way (mode collapse, sycophancy, safety refusal). Framing jury consensus as classical robust mean estimation, we propose RoPoLL (Robust Panel of LLM-as-Judge), which preserves the PoLL panel but replaces the aggregation function with a robust mean estimator, instantiated with the geometric median (GM): tuning-free, with the optimal finite-sample breakdown point 1/2. A finite-sample error bound and a matching information-theoretic minimax lower bound agree on the parametric rate sigma*sqrt(d/N) and differ on the breakdown floor by a factor of sqrt(d), a statistical-computational gap that polynomial-time RoPoLL pays relative to the intractable Tukey halfspace median. Across 13 open-weight judges (4B-675B), three reward-model benchmarks, and four corruption regimes at rates up to 50%, RoPoLL dominates PoLL on every biased corruption type: by about 19% on cross-dimensional attacks at matched compute, and by orders of magnitude on heavy-tailed Byzantine adversaries. A 3-judge RoPoLL committee at 38B beats Mistral-Large-3 (675B) by 1.31x on HelpSteer-2 under 30% bimodal-random corruption, an 18x parameter advantage at better accuracy; a Noisy-GT control confirms the premium is paid against biased contamination, not benign imprecision. --- ### SGD at the Edge of Stability: Stochastic Stabilization with Large Learning Rates Authors: Konstantinos Emmanouilidis, Lachlan MacDonald, Salma Tarmoun, Rene Vidal Published: 2026-06-29 Categories: stat.ML, cs.LG, math.OC arXiv: https://arxiv.org/abs/2606.30930v1 Modern deep learning has been shown to operate at the edge of stability, routinely using learning rates far larger than those justified by classical optimization theory. Most prior analyses of the edge of stability phenomenon focus on deterministic gradient descent, leaving the stochastic setting largely unexplored. In this work, we provide sharp convergence guarantees for Stochastic Gradient Descent (SGD) applied to the multiclass cross-entropy loss, for both linear classifiers and two-layer neural networks. We show that the stochasticity of SGD may cause the dynamics to alternate between an edge-of-stability regime that is dominated by curvature-driven oscillations, and a stable regime in which the expected loss decreases at a controlled rate. Despite that, we prove that SGD self-stabilizes the dynamics, ensuring that the iterates return to stability in a fixed number of iterations and allowing convergence in the best-iterate sense even with large learning rates. Experiments validate our theoretical findings and illustrate the benefits of SGD in the large-stepsize regime. --- ### Behavior Cloning is Not All You Need: The Optimality of On-Policy Distillation for Noisy Expert Feedback Authors: Ved Sriraman, Peihan Liu, Daniel Hsu, Adam Block Published: 2026-06-29 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2606.30923v1 Imitation Learning is a natural framework for learning in sequential decision-making systems and has emerged as the dominant paradigm through which we understand language model training. A central puzzle is that, while in theory offline IL can be horizon-free and optimal, in practice online methods such as on-policy distillation often outperform offline methods such as supervised fine-tuning. We propose a noisy expert model to explain this gap, in which the learner only has access to a noisy version of the expert's policy, but wishes to compete against the reward achieved by a clean expert, motivated by the fact that in many applications, e.g. training language models to perform long chains of thought, the expert is often imperfect. In this setting, we show a sharp separation between offline and online IL. Offline learning from noisy trajectories is fundamentally hard: to compete with the clean expert, the sample complexity must grow exponentially, in contradistinction to the clean expert setting where no explicit horizon dependence exists. In contrast, we prove that online interaction with the noisy expert via a novel variant of OPD enables polynomial dependence on the horizon in general. We further show that, under a natural condition on the expert noise distribution, which we show to be necessary for any horizon-free sample complexity, one can obtain such a guarantee, although our proposed algorithm sacrifices statistical efficiency in its dependence on the size of the policy class. Our analysis leads to an alternative loss function that is commonly considered empirically for LM training. We further provide algorithms and lower bounds, and extend our results to the more realistic setting of unknown corruption when the clean expert is deterministic, thereby providing a theoretical foundation for why OPD can outperform SFT when training language models from imperfect teachers. --- ### Conditional Tropical Cyclogenesis Rates via Rare-Event Sampling in a Neural Weather Emulator Authors: John S. Schreck, William Chapman, Charlie Becker, David John Gagne Published: 2026-06-29 Categories: physics.ao-ph, cs.LG arXiv: https://arxiv.org/abs/2606.30920v1 We couple Forward Flux Sampling (FFS), a non-equilibrium rare-event technique from statistical mechanics, to a neural weather emulator (SDL-WXFormer, 1° grid spacing) to estimate conditional tropical cyclogenesis rates, or how often a tropical cyclone achieves a hurricane-level central pressure, without modifying model dynamics. Tropical cyclogenesis rates vary by orders of magnitude across regimes, yet direct ensemble sampling cannot resolve this variability at operationally feasible ensemble sizes. FFS decomposes the rare disturbance to mature cyclone intensification path into a flux through an initial interface pressure and a product of conditional crossing probabilities across four intermediate interface pressures. We use the 1° emulator because FFS requires O(10^4) model trajectories per initial condition, and because the model's calibrated stochastic layers provide the necessary exploratory spread. Applied to 98 Atlantic basin initial conditions spanning 21 August - 8 October 2022, FFS resolves genesis rates spanning nearly three orders of magnitude, capturing a seasonal cycle qualitatively consistent with observations. A self-consistency check comparing FFS rates to independent direct-sampling rates yields a mean ratio of 1.03 +/- 0.15 across all initial conditions. Computational enhancement factors range from 3X (most active environment) to 140X (most suppressed), with a geometric mean of 14X. Three case studies illustrate the physical diagnostics the method provides: the rate-limiting step is initial tropical organization for the Earl environment, uniformly high crossing probabilities for the Fiona precursor environment, and a compound barrier at the final intensification stages for the Ian environment. More efficient emulators would enable application of FFS to finer resolutions. --- ### Budget-Adaptive Routing: Skipping the Weak When the Strong Answers Anyway Authors: Wei Geng, Nitinder Mohan, Jörg Ott Published: 2026-06-29 Categories: cs.NI, cs.AI, cs.DC arXiv: https://arxiv.org/abs/2606.30919v1 Edge-cloud inference collaborations are often designed with a routing estimator that decides whether to offload each frame from weak models at the edge to stronger models in the cloud. Existing systems place the routing estimator after the weak detector, so the weak forward pass still runs even on frames that are later offloaded. In this paper, we argue that this weak-conditioned design can be suboptimal when the offload budget varies. First, we present a competitive weak-skipping estimator (0.153 GFLOPs, about 29x lighter than the weak detector at 4.49 GFLOPs) that extracts routing signal from raw pixels, outperforming the common after-weak placement weak-conditioned baselines. Second, we show that neither weak-skipping nor weak-conditioned placement dominates across the full operating curve, and we propose budget-adaptive routing, which selects between them by offload budget via two offline-tuned thresholds. On PASCAL VOC, our budget-adaptive router traces the upper accuracy envelope of both fixed placements across the operating range. Our method reduces per-frame latency by up to 19.1 ms (about 30% lower at rho = 0.9). Besides outperforming SOTA methods, it is surprisingly stronger than the strong model (+1.7 pp over the strong model's peak mAP) at some operating points with far less compute. Artifacts are available at https://github.com/ViGeng/bgt-ada --- ### Beyond Clean Text: Evaluating Encoder and Decoder Robustness for Bangla Event Detection in Noisy Text Authors: Tanvir Ahmed Sijan, S. M Golam Rifat, Nayeemul Islam, Md. Musfique Anwar Published: 2026-06-29 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.30914v1 Event detection (ED) systems are typically evaluated on clean, curated text, leaving their robustness to real-world noise largely unexplored, particularly for low-resource languages such as Bangla. We introduce a generalized Bangla news event ontology and a benchmark comprising 9,979 annotated sentences across 40 event subtypes, spanning clean news text, real-world Automatic Speech Recognition (ASR) transcripts, and orthographically corrupted text. We systematically evaluate fine-tuned encoder-only models (BanglaBERT and XLM-R) alongside instruction-tuned decoder-only large language models (Llama 3 and Gemma 3). Our results reveal a clear architectural trade-off: encoder models achieve higher performance on clean text but degrade substantially under noise, whereas decoder-only LLMs are markedly more robust, particularly when event triggers are corrupted. We further show that embedding annotation guidelines during instruction tuning establishes a higher performance baseline on noisy text but yields inconsistent reductions in performance degradation across noisy conditions. Finally, model scaling consistently improves the robustness of decoder-only LLMs, while combined training on clean and noisy data serves as an effective regularization strategy that disproportionately benefits encoder architectures, significantly narrowing the robustness gap. --- ### Why Solve It Twice? Hierarchical Accumulation of Skills for Transfer-Efficient ML Engineering Authors: Yongbin Kim, Yashar Talebirad, Osmar R. Zaiane Published: 2026-06-29 Categories: cs.AI, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2606.30911v2 ML engineering agents waste compute rediscovering known techniques because every competition is a cold start. We present HASTE, a hierarchical multi-agent system that organizes cross-competition knowledge into three scope tiers (global, domain, and competition-specific), each coupled to a matching agent level. An orchestrator coordinates domain specialists and promotes learning between tiers via LLM-driven abstraction. A controlled ablation provides evidence for scoped loading: holding a 159-skill inventory constant across 8 competitions, tiered loading achieves a 100% medal rate while flat loading reaches only 62.5%, the same medal rate as loading no skills, and consumes 2x the output tokens. On the full MLE-Bench Lite benchmark (22 Kaggle competitions), HASTE reaches a medal rate of 77.3% using Claude Sonnet 4.6 at 12h per competition; this is a single-seed campaign result, and multi-seed replication is the priority follow-up. In a cold-start run, the system begins with no accumulated skills. In warm-start runs, it reloads skills learned from earlier competitions, using only global and domain-level skills for transfer across competitions. Warm starts use 52% fewer refinement iterations, and the fraction of proposed changes kept by the agent rises from 42% at low inventory to 85% once 50+ skills are available. These results suggest that better knowledge organization can partly substitute for model strength and compute budget in ML-engineering agents. --- ### Investigating Multi-Agent Deliberation in Law Authors: Cor Steging, Ludi van Leeuwen, Tadeusz Zbiegień Published: 2026-06-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.30906v1 Artificial Intelligence is increasingly applied to the field of law, and has the potential to increase access to justice. One particular movement that is gaining traction is that of agentic AI, wherein AI agents, based on Large Language Models (LLMs) can take autonomous actions. In particular, multi-agent approaches in the legal domain remain largely unexplored. In this paper, we investigate multi-agent deliberation methods for legal reasoning tasks using LLMs. We explore multi-agent deliberation (MAD) and introduce two novel multi-agent frameworks inspired by courtroom procedures and legal argumentation. Our experiments on both legal and non-legal benchmarks reveal that multi-agent frameworks achieve comparable overall performance to baseline large language models, but produce significantly distinct answers. Notably, these approaches can successfully solve cases that the baseline fails to address, and vice versa. We conduct a qualitative evaluation and highlight scenarios where multi-agent frameworks outperform monolithic approaches. For example, multi-agent approaches appear better suited for answering questions that require critical thinking from multiple perspectives. Our work positions multi-agent systems as a promising direction for AI in the legal domain, while demonstrating the potential of law-inspired multi-agent approaches for deliberation. --- ### How Human Feedback Shapes AI-generated Community Notes Authors: Soham De, Isaac Slaughter, Jiawei Guo, Qiao-Yun Cheng, Jiayuan Yan, Sruti Banerjee, Martin Saveski Published: 2026-06-29 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2606.30905v1 Community Notes, a bridging-based crowd-sourced fact-checking system, has emerged as a new mechanism for moderating misleading information on social media and has been adopted by major platforms including X, Facebook, Instagram, Threads, and TikTok. Since its introduction, there has been an open question about what role AI could play in scaling and optimizing the system. Recently, X extended its Community Notes system by introducing Collaborative Notes: notes initially drafted by an LLM and iteratively refined based on feedback from human contributors. In this work, we systematically analyze the complete corpus of 19,146 collaborative notes and 211,850 instances of human feedback. First, we develop a taxonomy of human suggestions for improving AI-generated note drafts and find that suggestions involving factual corrections and additional context are most likely to be incorporated, while subjective policy judgments rarely are. Second, we examine changes in helpfulness across versions of collaborative notes and find that human feedback leads to more helpful notes, with the greatest impact coming from suggestions that challenge the main claim in the previous draft, particularly when submitted by more active contributors. Finally, we find that although collaborative notes improve through human feedback, they reach helpful status and are shown on the platform at lower rates than human-only or AI-only notes, with limited human participation emerging as a key bottleneck. Nevertheless, rather than serving as a weaker substitute, collaborative notes tend to play a complementary role, predominantly targeting posts that do not attract human-only or AI-only notes. Our analysis provides an initial description of efforts to use AI to improve crowdsourced content moderation in a real-world moderation system and outlines pathways for future improvements to such features. --- ### Structure-Regularized Interpretable TCR-Epitope Prediction Authors: Jiarui Li, Zixiang Yin, Yunbei Zhang, Janet Wang, Samuel J. Landry, Zhengming Ding, Ramgopal R. Mettu Published: 2026-06-29 Categories: q-bio.BM, cs.CE, cs.LG arXiv: https://arxiv.org/abs/2606.30902v1 T cell receptor (TCR)-epitope binding prediction is essential for understanding adaptive immunity and developing immunotherapies. Existing sequence- and structure-based models often generalize poorly to unseen epitopes and provide limited interpretability. Furthermore, the impact of generated structures on model learning remains unclear. We present TCR-SRIM, a structure-regularized interpretable-by-design model that combines protein language model embeddings with interpretable contact prototypes to capture residue-level TCR-epitope interactions. TCR-SRIM achieves state-of-the-art predictive performance and improved interpretation quality on the TCR-XAI benchmark. Using its inherent interpretability, we further evaluate the effect of generated structures on model learning. While structures predicted by AlphaFold3, TCRModel2, and tFold-TCR yield competitive performance, they lead to less accurate interaction patterns and reduced binding-site diversity than experimentally-resolved structures. Our results highlight limitations of current structure prediction models for TCR-epitope learning and demonstrate the value of interpretable-by-design models for studying generated biological structures. --- ### GRAPE: Graph-Augmented Prototype Explanations for Interactive Medical Image Diagnosis Authors: Rasul Khanbayov, Erchin Serpedin, Hasan Kurban Published: 2026-06-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.30901v2 Prototype-based medical image classifiers present three clinical limitations: they treat findings as independent, silently amplify unsafe physician feedback, and require full retraining whenever a new finding is needed. We present GRAPE (Graph-Augmented Prototype Explanations), a unified architecture that addresses all three challenges. First, a Graph Attention Task Head models anatomical concept co-occurrence, boosting macro-F1 by +13.8,pp over the prototype baseline on TBX11K. Second, a Concept-Mismatch Safety Check - the first such mechanism in prototype-based medical classifiers - warns when the model's dominant finding inside a doctor-drawn region conflicts with the claimed label, catching 85% of erroneous annotations versus 51% for MC-Dropout with no extra inference cost. Third, Open-Vocabulary Prototype Anchoring aligns visual prototypes to clinical text, allowing a new finding to be added from a single labeled image without modifying any other component. On NIH ChestX-ray14, one Effusion example recovers full-supervision localization accuracy; on TBX11K, prototype maps achieve 2.6x better lesion localization than end-to-end baselines. All three capabilities add only +1~ms latency at interactive batch size. The project page is https://github.com/KurbanIntelligenceLab/GRAPE. --- ### Curvature-Guided Module Localization for Low-Rank Detoxification of Backdoored Large Language Models Authors: Arash Raftari, Mehrdad Mahdavi, Nathan Blackthorn, Andrew Arash Mahyari Published: 2026-06-29 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2606.30899v1 Backdoor attacks pose a serious threat to large language models (LLMs) by causing otherwise benign systems to produce attacker-specified malicious behavior when a hidden trigger is present. In this work, we study post hoc detoxification of backdoored LLMs in a practical setting where the defender has access to the poisoned model but does not wish to retrain the full network from scratch. We propose a mechanistically guided weight-space repair framework that first localizes modules involved in propagating trigger-induced behavior using activation patching and Fisher/K-FAC curvature analysis, and then applies targeted low-rank repair to only the most influential modules. We evaluate the method on poisoned variants of \texttt{Llama-3.2-1B-Instruct} with triggers inserted at the beginning, middle, and end of otherwise benign prompts. Results show that the proposed approach substantially suppresses trigger-conditioned malicious responses while preserving benign model behavior. These findings suggest that backdoor removal in LLMs can be formulated as a localized structural repair problem rather than only a broad behavioral alignment problem. --- ### Knowledge-Driven Dimension Estimation from a Single Image -3D Asset Generation Technology for Digital Twin Construction Authors: Hidenori Sakaniwa, Akihito Akai, Akihiko Hyodo Published: 2026-06-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.30896v1 In the verification of in-vehicle cameras, simulation technology using virtual spaces has advanced, enabling pre-evaluation of false detections and missed detections in various scenarios. However, discrepancies in the scale of the object being verified between the virtual and real environments can lead to a decrease in camera recognition performance. For traffic signs installed at high altitudes, distance measurement using LiDAR or stereo cameras is difficult, requiring size estimation from monocular images. This paper proposes a method for estimating the scale of an object by decomposing it into multiple structural elements and integrating external knowledge regarding design rules, geometric relationships, and conventional dimensions. Specifically, this method detects each component from a monocular image and estimates the size of each component by considering its structural relationships and dimensional consistency with surrounding elements. Furthermore, it generates a 3D asset of the object by reconstructing the estimated components. This method makes it possible to place 3D assets with a scale approximating the real environment within a digital twin space and is expected to contribute to improving the verification accuracy of in-vehicle cameras for autonomous driving in virtual environments. --- ### Dynamic Prediction of Alternating Recurrent Events via Neural Network Authors: Abigail Loe, Susan Murry, Zhenke Wu Published: 2026-06-29 Categories: stat.ML, cs.LG, stat.AP arXiv: https://arxiv.org/abs/2606.30889v1 Alternating recurrent events -- event-times of a specific nature that trigger a secondary refractory period -- occur in a wide-range of fields, including behavioral science, criminal justice, and biostatistics. Analysis of these events requires careful attention to the statistical nuance, including correlated observations and repeated outcomes subject to potential censoring. We develop an online dynamic prediction framework appropriate for predicting subsequent alternating recurrent events, by developing neural network theory for a statistical audiences and applying inverse probability weighted pseudo-observations. The proposed model is applied to dynamically predict alternating recurrent event-free time, showing good performance in simulation, and outstanding capability in application to predicting periods of low mood for first-year medical residents. We close with a discussion. --- ### Training Therapeutic Judges and Multi-Agent Systems for Human-Aligned Mental Health Support Authors: Mizanur Rahman, Abeer Badawi, Elahe Rahimi, Laleh Seyyed-Kalantari, Frank Rudzicz, Enamul Hoque, Elham Dolatabadi Published: 2026-06-29 Categories: cs.CL, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2606.30887v1 Large language models show promise for mental health support, yet therapeutic quality improves only when evaluation functions as an actionable control signal rather than a passive metric. We introduce a framework that formulates therapeutic response generation as a decision-refinement problem driven by multi-dimensional, human-aligned evaluation. In Stage I, we introduce TheraJudge, an open-source therapeutic evaluator trained via preference-based optimization on human-annotated data to produce reliable judgments across 7 psychological dimensions. In Stage II, we introduce TheraAgent, which operationalizes TheraJudge's evaluations through a coordinated refinement process with specialized Critic, Coach, and Therapist roles that translate evaluative signals into targeted response revisions. Empirically, TheraJudge achieves strong agreement with clinician ratings, with intraclass correlation coefficients (ICC = 0.87-0.95), surpassing supervised baselines and strong closed-source judges, particularly on critical dimensions such as Safety, Relevance, and Empathy. Acting on these evaluations, TheraAgent yields a +0.43 improvement in human-rated therapeutic quality (on a 5-point scale) under blind evaluation, with 96\% clinician inter-rater reliability. Low-quality responses ($\leq 3$) improve by +2.45 points with a 94\% recovery rate, demonstrating targeted correction of unsafe outputs. Overall, our results indicate that effective alignment of mental-health LLMs stems from acting on human-aligned evaluation, rather than relying solely on stronger generation. We release code at https://github.com/vis-nlp/TheraAlign. --- ### A Systematic Approach to Multi-Agent AI from Advanced Regulatory Control Theory: Safe and Auditable LLM Operator Agents for Process Control Authors: Idelfonso B. R. Nogueira, Sigurd Skogestad Published: 2026-06-29 Categories: eess.SY, cs.LG arXiv: https://arxiv.org/abs/2606.30877v1 Recent literature shows that large language models (LLMs) are useful for general-purpose tasks yet perform poorly on specific domain ones. One reason is the difficulty of supplying narrow context to a general-purpose model and of bounding the task it is asked to perform. It is possible to hypothesise that a multi-agent reformulation under process-control principles offers a route to address those points, since control theory provides a discipline of decomposing a system into elements of contained scope, each defending one controlled variable, with conflicts resolved by structural priority: MIN/MAX selector networks for CV-CV switching and split-range (split-parallel) logic for MV-MV switching. The present work proposes such a reformulation, derived from Advanced Regulatory Control (ARC) theory. Each feedback loop in the ARC chain is mapped to one specialised LLM operator agent carrying the loop's control-theoretic context (controlled variable, setpoint, chain priority, selector kind). The chain's interaction logic (MIN/MAX selectors, override paths) is encapsulated as a single orchestrator agent. Two orchestrator variants are tested: a deterministic rule chain, and a Claude-based LLM orchestrator at a slower tier. The control principles limit each agent's task and inform how its limitations are handled. The multi-agent system inherits the safety property of the ARC chain: every constraint conflict is resolved deterministically by the orchestrator, regardless of the LLM output. Evaluated on a dairy-barn ventilation case over a 4-day mixed-season scenario, Qwen 2.5 7B Instruct operator agents running offline on a 24 GB consumer GPU at a 5-minute cadence produce auditable trajectories, each paired with an operator-voice rationale that supports a control campaign logbook. --- ### The Label Imitation Game: Turing Test Network for Zero-Shot Pseudo-Label Pruning Authors: Brent A. Griffin, Jason J. Corso Published: 2026-06-29 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.30875v1 Foundation model pseudo-labeling - labeling data strictly via zero-shot inference - enables massive scale, but performance is undermined by hallucinations that evade standard thresholds. To eliminate these errors, we introduce the Turing-inspired Label Imitation Game (LIG), a framework that formalizes pseudo-label pruning as an adversarial interrogation. Rather than filtering labels via isolated thresholds, we use the LIG to train a Turing Test Network (TTN), a task-agnostic "judge" that evaluates candidate pseudo-labels within a dataset-wide context. Experiments across four diverse datasets demonstrate the TTN's robustness, consistently enhancing label accuracy for three state-of-the-art vision-language models without costly supervision or retraining. Crucially, we demonstrate that learned semantic-contextual logic is a robust alternative to spatial-geometric verification, enabling a unique zero-shot task transfer capability - a TTN trained strictly on image classification datasets can effectively prune complex object detection pseudo-labels. This pruning yields F1-score gains of 28% for the worst-performing baseline categories and 44% with task-specific fine-tuning. Significantly, we also observe Category Revival, where the TTN pruning "detoxifies" the training signal for downstream models and enables them to recover from zero recall on transfer-vulnerable classes. The pre-trained TTN models and code are available at https://github.com/voxel51/ttn. --- ### Beyond expert users: agents should help users construct preferences, not just elicit them Authors: Irena Saracay, Ludwig Schmidt, Carlos Guestrin Published: 2026-06-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.30863v2 Agents typically assume an expert user -- one with well-formed preferences about what they want -- and default to clarifying questions whenever the task is underspecified. We argue this assumption is unrealistic. Users often lack the domain knowledge to have completely specified preferences; if asked about their preference on some feature, the user may be unable to answer without the agent helping the user to learn some domain knowledge needed to form a preference for that feature, e.g., via examples or explanations. To formalize these principles, we draw on the Search-Experience-Credence framework from Information Economics to introduce CoPref, a model of how users construct preferences based on agent dialog actions. We then study these ideas concretely in agentic recommender systems, proposing CoShop, an interactive benchmark. In CoShop, an agent converses with and makes recommendations for a CoPref user. The agent's performance depends on whether it can help the user gain the knowledge needed to specify the task well. Evaluating five frontier models, we find that no agent exceeds 56% accuracy on CoShop despite five turns of interaction. Failures stem not from agents' ability to find items, but from how little the interaction expands what users know about what they want. --- ### Multilingual Polarization Detection Using Transformer-Based Models with Class Weighting and Threshold Tuning Authors: Aaron Bundi Anampiu Published: 2026-06-29 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.30857v1 This paper describes our submission to SemEval-2026 Task 9 on detecting multilingual, multicultural, and multievent online polarization. We address all three subtasks: binary polarization detection, polarization type classification, and manifestation identification for English and Swahili. Our approach leverages transformer-based models (RoBERTa-base for English, AfroXLMR-base for Swahili) with class-weighted loss functions to address severe label imbalance and per-label threshold tuning to optimize multi-label classification. On the test set, we achieve F1 macro scores of 0.7901 (English) and 0.7910 (Swahili) for Subtask 1, 0.4615 (English) and 0.4808 (Swahili) for Subtask 2 and 0.4791 (English) and 0.5830 (Swahili) for Subtask 3, which give competitive performance on the leaderboard, demonstrating the effectiveness of our methods for handling imbalanced multi-label polarization detection. Our error analysis reveals that models struggle with dehumanization detection and lack of empathy. --- ### When Does Learning to Stop Help? A Cost-Aware Study of Early Exits in Reasoning Models Authors: Zhe Dong, Fang Qin, Manish Shah Published: 2026-06-29 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2606.30852v2 Reasoning models spend test-time compute unevenly across instances, and a growing family of early-exit rules -- confidence thresholds, entropy monitors, answer-stability checks, and learned stoppers -- promises to reclaim the waste. These rules, however, are evaluated under heterogeneous protocols that leave the deployment question unanswered: at a fixed tolerance for losing correct answers, which policy saves more compute, and does the saving survive probe overhead? We answer this question with a controlled study across 18 task-model settings spanning GSM8K, MATH-500, MMLU-Pro, AIME-90, and GPQA on Qwen3 and DeepSeek-R1-distilled models, using LearnStop, a hidden-state-free logistic stopper over prefix-observable features, as the learned policy instrument. Under matched lost-correct risk at $α$ = 0.15, with the scalar competitor selected on calibration data from confidence, entropy, confidence-leap, and run-stability exits, the answer forms three regimes. Learned stopping wins on all four primary Qwen3 free-form math settings (+3.2 to +21.2 pp additional total-token saving); calibrated scalar exits win on multiple-choice MMLU-Pro; and small hard benchmarks (AIME-90, GPQA) admit no certifiable aggressive policy at all. A trajectory decomposition predicts the regime: learning pays where answers oscillate and correctness evidence is spread across complementary signals, while a single confidence threshold suffices where most instances are already solved at the first checkpoint. Cost accounting sharpens the picture further -- the same policy that saves 32% of tokens under KV-cache forking costs 121% extra under black-box repeated prefilling. Together, these results replace the single-method race with a decision procedure for choosing a stopping rule from the trajectory structure and serving regime of the target workload. --- ### Test-Time Verification for Text-to-SQL via Outcome Reward Models Authors: Mattia Tritto, Giuseppe Farano, Dario Di Palma, Gaetano Rossiello, Fedelucio Narducci, Dharmashankar Subramanian, Tommaso Di Noia Published: 2026-06-29 Categories: cs.CL, cs.AI, cs.DB arXiv: https://arxiv.org/abs/2606.30851v1 Improving the reliability of large language models (LLMs) at inference time is a central challenge in structured reasoning tasks such as Text-to-SQL. Common test-time inference strategies, including Best-of-N sampling and Majority Voting, rely on heuristic signals such as execution success or output frequency, which provide limited semantic discrimination across candidate outputs. In this work, we study Outcome Reward Models (ORMs) as learned semantic scoring functions for test-time verification in Text-to-SQL. While ORMs have been previously explored for test-time scaling and alignment, their application to structured query generation remains underexplored. We introduce GradeSQL, a scalable framework for training task-specific ORMs via automated candidate generation and execution-based labeling, enabling verifier training without manual annotation. We integrate ORMs into a verification-driven Best-of-N pipeline and evaluate our approach on the BIRD and Spider benchmarks across multiple open-source LLM families. ORM-based selection consistently outperforms execution-based Best-of-N and Majority Voting, with gains of up to +4.33% on BIRD and +2.10% on Spider. We further show that ORMs scale effectively with larger candidate sets and yield stronger improvements on complex queries. Overall, our results demonstrate that ORM-based verification provides a simple, effective, and scalable alternative to heuristic test-time selection strategies for Text-to-SQL. Code datasets and models are publicly available. --- ### BayesBench: Evaluating LLM Belief Trajectories Under Multi-Turn Evidence Accumulation Authors: Ankur Samanta, Akshayaa Magesh, Tal Lancewicki, Ayush Jain, Youliang Yu, Paul Sajda, Kaveh Hassani, Aditya Modi, Daniel R. Jiang, Yonathan Efroni Published: 2026-06-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.30850v1 Large language models (LLMs) are typically deployed in multi-turn conversations, where each turn provides new evidence that should reduce epistemic uncertainty about their environment. Acting rationally then requires inferring the unobserved quantities that govern it and updating beliefs about them as evidence accumulates. Yet most evaluations only score the model's final-turn answer in a single-turn format, leaving this process unexamined. We ask how closely LLMs' belief updates match those of a rational Bayesian reasoner in multi-turn settings, and introduce BayesBench, a suite of simulation environments that probe this across three progressively complex tasks: (i) Bayesian estimation, where the model infers an unknown parameter from sequential evidence; (ii) Bayesian prediction, where the model turns inferred beliefs about a latent variable into outcome forecasts; and (iii) latent-framed Bayesian prediction, where observations are filtered through a user-persona framing, requiring joint inference over the latent state and the persona. Across seven LLMs (3B--70B), scaling improves latent inference and evidence accumulation, with updates occasionally matching the Bayesian posterior. However, these gains do not reliably carry over to downstream prediction, exposing a gap between inferring latent structure and using it to rationally update beliefs about the target outcome. --- ### SyncCache: Exploiting Asymmetric Dynamics for Fast Audio-Driven Portrait Animation Authors: Juncheng Ma, Yuxuan Du, Yanan Sun, Zhening Xing, Changlin Li, Zhenyu Tang, Bo Li, Peng-Tao Jiang, Li Yuan, Daquan Zhou, Yonghong Tian Published: 2026-06-29 Categories: cs.CV, cs.SD, eess.AS arXiv: https://arxiv.org/abs/2606.30849v1 Diffusion Transformers (DiTs) have significantly advanced audio-driven portrait animation, but their high computational cost leads to substantial inference latency. Although training-free diffusion caching accelerates inference significant, existing methods are primarily developed for text-conditioned generation and overlook the spatial and modality imbalances inherent in audio-driven portrait animation. In this paper, we propose SyncCache, a training-free caching acceleration method tailored for DiT-based portrait animation that explicitly exploits asymmetric dynamics. Specifically, high-frequency dynamics driven by audio conditions and concentrated in human regions are more challenging and critical to cache and reuse than the low-frequency visual background in portrait animation. First, we introduce Spatially-Asymmetric Probing to prioritize error sensitivity in dynamic human region. Second, through Modality-Decoupled Caching, we bypass heavy DiT block by reusing stable inter-block residuals, while continuously recomputing lightweight audio blocks to preserve precise lip synchronization. Furthermore, we introduce a cache ratio to control cache capacity and formulate memory-adaptive cache selection as an offline dynamic programming problem without online overhead. Extensive experiments demonstrate that SyncCache achieves superior speed-quality trade-offs, delivering up to 4.12x acceleration on HunyuanVideo-Avatar and 3.75x on Wan-S2V with near-lossless visual fidelity and precise audio alignment. --- ### How Can AI Find My Model? A Model-Finding Experimental Study Considering Data Formats, Embeddings, and Retrieval Strategies Authors: Jhon G. Botello, Jose J. Padilla, Erika Frydenlund, Krzysztof Rechowicz, Eric Weisel Published: 2026-06-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.30846v1 Discovering simulation models for reuse remains a fundamental challenge in Modeling and Simulation (M&S). When many models coexist, identifying those that align with a given modeling intent remains difficult. Recent advances in Artificial Intelligence (AI), particularly retrieval-based approaches, offer a promising pathway to operate at this semantic layer. In this paper, we present an experimental study investigating the impact of data representation, transformer-based embedding models, and retrieval strategies on the discovery of simulation models using natural language queries. We evaluated performance across multiple query types using standard information retrieval metrics, including recall@5 and nDCG@5. Results show that data representation matters, open-source embedding models can achieve high performance, and reranking methods are important, especially as query complexity increases. This work provides a baseline for AI-driven model discovery and discusses its role in advancing toward AI-driven composability and interoperability. --- ### A Transferable Learned Temporal Prior for Transmission Reconstruction and Decision-Relevant Uncertainty in Real Outbreak Labels Authors: Md Ahsan Karim Published: 2026-06-29 Categories: cs.LG, q-bio.QM arXiv: https://arxiv.org/abs/2606.30842v2 Reconstructing who infected whom often relies on case timing and published transmission links. However, two important questions remain: can a temporal pattern learned from other diseases transfer to a new outbreak, and how reliable are the transmission links used as ground truth? We learned a temporal prior from eleven disease groups using logistic regression. The model was locked before any target-outbreak data were accessed and was then tested without refitting on 29 Andes virus (ANDV) parent-ranking tasks. The locked prior achieved a mean reciprocal rank (MRR) of 0.571, compared with 0.274 for the strongest fair source-trained temporal baseline (permutation p<0.001). Its Top-1 accuracy was 37.9%, compared with 13.8%. The MRR advantage remained significant unless 7-8 favorable task outcomes were reversed. We separately examined the reliability of published transmission links. Among 75 epidemiologically linked inter-host pairs from the 2022 New York City mpox outbreak, 54.67% were genomically unresolved or unsupported as direct transmission links (exact 95% CI: 42.75-66.21%). We also tested whether retaining uncertain transmission edges changed source prioritization. In ANDV and Guangdong Delta outbreak graphs, the top-5 priority sets changed, with Jaccard similarity ranging from 0.429 to 0.667. These results show that temporal information learned across diseases can provide a useful ranking signal without target-specific refitting. They also show that uncertainty in published transmission links can affect which source cases are prioritized for investigation. --- ### A Transferable Learned Temporal Prior for Transmission Reconstruction and Decision-Relevant Uncertainty in Real Outbreak Labels Authors: Md Ahsan Karim Published: 2026-06-29 Categories: cs.LG, q-bio.QM arXiv: https://arxiv.org/abs/2606.30842v1 Outbreak transmission reconstruction treats epidemiological timing and transmission labels as deterministic ground truth; neither has been systematically evaluated. We trained a logistic regression temporal prior on eleven disease families, locked all parameters before accessing any target outbreak data, and applied it without refitting to a strict Andes virus (ANDV) parent-ranking benchmark of 29 tasks. The locked prior achieved mean reciprocal rank (MRR) 0.571 versus 0.274 and Top-1 accuracy 37.9% versus 13.8% against the best source-trained parametric baseline (permutation p <= 0.0002; 7-8 reversals to lose MRR significance). A phylogenetic concordance audit of 75 NYC mpox inter-host pairs - independent label-reliability evidence rather than a prior validation - found that 54.67% (exact 95% CI: 42.75-66.21%) were genomically unresolved or unsupported. Retaining uncertain edges in ANDV and Guangdong Delta graphs shifted top-5 source-priority sets (Jaccard 0.429-0.667). Transmission-label uncertainty was measurable in the outbreak evidence modules examined, and retaining uncertain links changed which source cases were prioritized for intervention. --- ### Contrastive Reflection for Iterative Prompt Optimization Authors: Derek Koh, Jinghui Mo, Benjamin H. Le, Jiening Zhan, Baofen Zheng, Kevin Bevis, Nathaniel C. Owen, Lauren Elizabeth Charney, Wenqiong Liu, Jingwei Wu Published: 2026-06-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.30840v1 LLM agents are becoming central to information retrieval: they issue retrieval queries, synthesize answers, and increasingly serve as judges for IR evaluation. Improving the prompts that control these agents is an optimization problem, but in applied IR settings it often looks less like blind search and more like debugging. Engineers need to know which behavior failed, which nearby behavior still worked, what distinguishes the two, and whether a prompt edit improves held-out quality without introducing regressions. We present Contrastive Reflection, an iterative prompt-optimization framework for agentic IR workflows. The framework starts from a task-centric quality definition: QA agents expose retrieval or reasoning traces, and grading agents expose dimension-level scores and rationales. These structured traces are used to identify error-anchored behavioral slices, add nearby successful examples from the same region, and ask a Teacher LLM to propose a targeted prompt edit. Candidate edits are accepted only when validation performance improves, optionally subject to regression checks. We instantiate the framework with a tree-based slice selector, but the contribution is the contrastive reflection loop rather than the tree itself. On a public HotpotQA retrieval-augmented QA setup, one tree-selected contrastive repair improves held-out exact-match accuracy from 51.4% to 60.4%. Failure-only and random-evidence variants improve less and break more previously correct examples. A light instruction-only comparison places the method near modern prompt optimizers: MIPROv2 reaches 59.4% and GEPA 57.0%. The result is an interpretable optimization loop for IR agents, aimed at making prompt repair more inspectable and validation-driven. --- ### A Stationary-Distribution Theory for Triplet-Based Plateau Search in Random Forest Ensemble-Size Selection Authors: Andrey A. Dukhovny, Andrey M. Lange Published: 2026-06-29 Categories: cs.LG, cs.AI, math.PR, stat.ML arXiv: https://arxiv.org/abs/2606.30837v1 The number of trees is a central computational parameter in Random Forests: increasing it reduces finite-ensemble variability but increases training and prediction cost. Plateau-based tuning adapts this parameter through local comparisons of out-of-bag scores at a geometric triplet of tree counts. After the remaining hyperparameters have stabilized, however, the central triplet point need not converge to a deterministic value; instead, it fluctuates around a stationary regime. This paper develops a stationary-distribution theory for this process. The central ensemble size $B_t$ is modeled as a birth-death Markov chain on a geometric grid, and its stationary distribution is derived through local balance. Under a leading centered folded-normal approximation, equilibrium equations are obtained for the original update rule and a symmetric modified variant, implying that the stationary center $B_*=O(\varepsilon^{-2})$ as $\varepsilon\downarrow 0$. The stationary spread is also characterized. A local Gaussian approximation and a Fokker-Planck interpretation give grid-level variance constants. After conversion to the ensemble-size scale, $σ_{B,*}=O(\varepsilon^{-2})$, while the variance is $O(\varepsilon^{-4})$. The leading relative spread is independent of $\varepsilon$ and controlled by the scale factor and update rule. These results interpret plateau-based Random Forest tuning as a stochastic process rather than a deterministic stopping rule. --- ### Partition-Guided Distance Saliency: Bridging Decision and Objective Spaces in Many-Objective Optimization Authors: Cláudio Lúcio do Val Lopes, Flávio Vinícius Cruzeiro Martins, Elizabeth Fialho Wanner Published: 2026-06-29 Categories: cs.LG, cs.NE arXiv: https://arxiv.org/abs/2606.30836v1 Explainability in Many-Objective Optimization (MaO) is currently hindered by the escalating complexity of the Pareto front, which renders the relationship between high-dimensional decision variables and objective outcomes increasingly opaque. As the number of objectives exceeds the limits of traditional visualization, decision-makers encounter a ``cognitive drought'' in identifying relevant trade-offs or specifying target regions without a priori knowledge. To bridge this interpretability gap, we introduce the {Partition-Guided Distance Saliency (PGDS)} framework, a novel XAI approach designed for continuous optimization landscapes. Our framework automates the explanation process through a three-stage pipeline that prioritizes geometric intuition over abstract rules. First, we employ a surrogate model that learns how geometric distances in the decision space map to proximity in the objective space. Second, to address the difficulty of manual target selection in high dimensions, the framework automatically partitions the objective landscape into distinct regions and identifies local ``Dominating Points'' to serve as automated targets for improvement. Third, we quantify how sensitive a solution's position is to each decision variable by measuring the distance shifts induced by perturbations to each variable. This allows PGDS to categorize features as either ``Drivers'' which facilitate convergence toward preferred regions, or ``Blockers'' which represent geometric constraints hindering further progress. Validation on 10-objective benchmarks and a physics-informed engineering problem (Welded Beam) demonstrates that PGDS provides differentiated, actionable insights that traditional visualization and rule-based XAI methods fail to provide. --- ### Geometric Dyson Brownian Motions and the Free Log-Normal Limit for a Non-Square Gaussian Matrix Product Authors: Mufan Li, Jaume de Dios Pont, Mihai Nica, Daniel M. Roy Published: 2026-06-29 Categories: math.PR, stat.ML arXiv: https://arxiv.org/abs/2606.30831v2 We study the squared singular value spectrum of a non-square product of independent real Gaussian matrices, equivalently the feature covariance spectrum of a deep linear neural network at initialization. Starting from the fixed-$m$ covariance diffusion previously obtained in the proportional depth-width limit, we record an equivalent matrix realization, describe its affine invariance, and derive the interacting diffusion satisfied by its eigenvalues. We then take a second limit, sending $m\to\infty$ on the accelerated spectral clock $τ=mt$, which corresponds in this sequential construction to the relation $dm/n\to\barτ$. We establish convergence of the empirical spectral measure path to a deterministic mean-field limit and derive a closed Burgers equation for its $T$-transform. Together with the proportional depth-width limit, these results give a rigorous sequential route from the deep non-square Gaussian product to the free log-normal limit of its feature covariance spectrum; for more general initial laws, the transform yields a free multiplicative convolution form. We further analyze the support of the free log-normal law, give a fixed point iteration for numerical evaluation and a formal Marchenko--Pastur approximation at small time, and use the limiting spectrum to predict the risk in a toy random feature model. --- ### Information Terra: A Narrative-Anchored Semantic-First Projection of Document Embeddings Authors: Brian Keith-Norambuena, Fausto German, Chris North Published: 2026-06-29 Categories: cs.HC, cs.CL, cs.IR arXiv: https://arxiv.org/abs/2606.30824v1 We introduce Information Terra, a narrative-anchored semantic-first projection that places a document corpus on an Earth-like globe whose poles are two user-chosen endpoint documents and whose prime meridian is the great-circle geodesic between them on the embedding hypersphere -- so latitude encodes narrative progress and longitude thematic deviation. Land features are recovered from document density via kernel density estimation and labeled by theme. A narrative trail built from the underlying narrative coherence graph, and constrained to be monotone in geodesic progress, provides a readable storyline. The projection's axes are semantically grounded in the user's chosen narrative endpoints, and the globe metaphor affords rotation and antipodal reading. We demonstrate the method on a 540-article Cuban Protests corpus, showing a storyline from Obama's 2016 visit to the 2021 International Aid during the protests. --- ### Separation Capacity of Scattering Networks Authors: Konstantin Häberle, Helmut Bölcskei Published: 2026-06-29 Categories: stat.ML, cs.IT, cs.LG, math.CV arXiv: https://arxiv.org/abs/2606.30822v1 In this paper, we attempt to enhance the theoretical understanding of convolutional neural networks (CNNs) as feature extractors in classification tasks by analyzing them through the lens of Cover's function-counting theory. Specifically, our focus lies on the notion of separation capacity, a combinatorial quantity derived from counting the number of realizable dichotomies (i.e., binary label assignments). Our contributions are threefold. First, we extend Cover's framework by establishing a conceptually insightful and practically useful formulation for the separation capacity. Second, leveraging this formulation, we identify the factors governing the separation capacity of feature extractors that employ a specific CNN architecture, so-called scattering networks, in terms of their network building blocks. Third, we provide practical insights for scattering network design. --- ### Mind the Residual Gap: Probabilistic Downscaling under Real-World Bias Authors: Yujin Kim, Nidhi Soma, Sarah Dean Published: 2026-06-29 Categories: cs.LG, cs.CE arXiv: https://arxiv.org/abs/2606.30821v2 Probabilistic downscaling models the conditional distribution of high-resolution fields given coarse inputs and is a core challenge in atmospheric science, climate modeling, and other multiscale physical systems. A widely used paradigm decomposes the problem into a deterministic mean predictor followed by a stochastic residual generator. While effective in idealized settings, this mean-residual approach frequently produces biased and underdispersive ensembles in real-world applications. We identify a fundamental source of this failure: residual target misspecification, where the residual distribution induced during training systematically differs from the correction distribution required at test time, a mismatch amplified by downscaling bias. We theoretically connect this misspecification to underdispersion through the spread-skill ratio and show that conditional residual distribution matching controls both residual-energy and conditional-mean mismatch. Motivated by this analysis, we introduce ReMatch (Residual Distribution Matching), which aligns training residual targets toward a held-out calibration regime via optimal transport. On a controlled synthetic benchmark with varying bias levels and a real-world HRRR-ERA5 wind-field downscaling task, ReMatch substantially reduces underdispersion, improves calibration, and outperforms strong mean-residual and super-resolution baselines. Our code is available at https://github.com/sdean-group/ReMatch.git. --- ### Mind the Residual Gap: Probabilistic Downscaling under Real-World Bias Authors: Yujin Kim, Nidhi Soma, Sarah Dean Published: 2026-06-29 Categories: cs.LG, cs.CE arXiv: https://arxiv.org/abs/2606.30821v1 Probabilistic downscaling is the task of modeling the conditional distribution of high-resolution fields given coarse inputs, and is a central challenge to atmospheric science, climate modeling, and other multiscale physical systems. A widely used paradigm decomposes the problem into a deterministic mean predictor followed by a stochastic residual generator. While effective in idealized settings, this mean--residual approach frequently produces biased and under-dispersive ensembles in real-world applications. Is this merely generic predictive uncertainty miscalibration? We show that the root cause is more fundamental: residual target misspecification, the residual distribution induced during training differs systematically from the one required at test time due to downscaling bias. To close this gap, we introduce ReMatch (Residual Distribution Matching). ReMatch aligns the training residual distribution toward the test-time regime via optimal transport in a low-dimensional PCA space. This preserves the statistical benefits of the mean--residual framework while reducing the train--test mismatch in the residual targets seen by the stochastic generator. On a controlled synthetic benchmark with varying bias levels and a real-world HRRR--ERA5 wind field downscaling task, ReMatch substantially reduces under-dispersion, improves calibration (SSR and CRPS), and outperforms strong baselines, including the standard mean--residual model and its variants, as well as state-of-the-art super-resolution models. Our code is available at https://github.com/sdean-group/ReMatch.git. --- ### AI-Generated PowerShell Malware: An Experimental Framework and Dataset Authors: Luciano Pianese, Vittorio Orbinato, Pietro Liguori, Roberto Natella Published: 2026-06-29 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2606.30819v1 Generative AI has emerged as a significant cybersecurity threat, with several recent attack campaigns leveraging LLMs to generate code for malicious purposes via scripting languages such as PowerShell. Consequently, for cybersecurity analysts, it is imperative to investigate the offensive capabilities of AI code generators. In this paper, we propose an experimental framework to assess LLM-generated PowerShell malware, which comprises a novel sandbox approach for dynamic analysis of AI-generated malware. Furthermore, we present a novel, manually curated dataset of real-world PowerShell malware, annotated in natural language to assist the training and evaluation of LLMs. Finally, this study evaluates permissive, open-weight LLMs adapted to PowerShell malware generation. Our results reveal a high degree of similarity between real malware and LLM-generated ones in terms of triggered OS malicious events, with a median Jaccard index of 84.5% and 48.4% of instances achieving complete overlap. --- ### When transformers learn "impossible" languages, what do they learn? Authors: Ram Janarthan, Coleman Haley, Sharon Goldwater Published: 2026-06-29 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2606.30815v1 Recent work suggests that transformer language models show a bias towards human languages over unnatural ("impossible") languages argued to be unacquirable by humans. However, this literature has largely based these claims on differences in sample efficiency and test-set perplexity, rather than on direct evaluations of the linguistic capacities that could plausibly explain non-attestation in human languages. We evaluate two theoretically motivated linking hypotheses: impossibility arising from deficiencies in grammatical sensitivity or generative production. Using GPT-2 style models trained on perturbed "impossible" variants of English, we measure sensitivity to grammaticality using BLiMP minimal pairs, finding that model performance exhibits only gradual degradation, mediated by the language's information locality. In contrast, these models exhibited pronounced failures in generation, producing substantially fewer high-quality sentences at longer lengths. Together, these results suggest generative deficiency and transmission failures as a plausible linking hypothesis between language model behaviour and non-attestation of impossible languages. --- ### When Calibration Rankings Reverse: Accuracy-Controlled Evaluation for Fair Comparison of LLMs Authors: Zhichao Yang, Caiqi Zhang, Ruihan Yang, Chengzu Li, Nigel Collier, Deqing Yang Published: 2026-06-29 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.30814v2 Calibration evaluates whether a model confidence aligns with its empirical accuracy. Existing studies often compare the calibration of different large language models using global calibration metrics such as Expected Calibration Error and Brier Score. We begin by showing, both theoretically and empirically, that such comparisons are confounded by differences in model accuracy. For fairer cross-model comparison, we then propose ACE, an accuracy-controlled evaluation framework with three complementary views: Instance-Aligned, Distribution-Aligned, and Candidate-Aligned calibration. Across multiple benchmarks, model families, and confidence elicitation methods, we use ACE to study two practically important comparison axes, small versus large models and thinking versus non-thinking models. We find that many previously reported calibration advantages under raw global metrics weaken substantially after accuracy control. We also find that ranking reversal is frequent: models favored by raw metrics often cease to be favored once accuracy is controlled. Our results show that raw global calibration metrics are not robust for cross-model comparison, and that fair calibration comparison requires accuracy-aware evaluation. --- ### When Calibration Rankings Reverse: Accuracy-Controlled Evaluation for Fair Comparison of LLMs Authors: Zhichao Yang, Caiqi Zhang, Ruihan Yang, Chengzu Li, Nigel Collier, Deqing Yang Published: 2026-06-29 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.30814v1 Calibration evaluates whether a model confidence aligns with its empirical accuracy. Existing studies often compare the calibration of different large language models using global calibration metrics such as Expected Calibration Error and Brier Score. We begin by showing, both theoretically and empirically, that such comparisons are confounded by differences in model accuracy. For fairer cross-model comparison, we then propose ACE, an accuracy-controlled evaluation framework with three complementary views: Instance-Aligned, Distribution-Aligned, and Candidate-Aligned calibration. Across multiple benchmarks, model families, and confidence elicitation methods, we use ACE to study two practically important comparison axes, small versus large models and thinking versus non-thinking models. We find that many previously reported calibration advantages under raw global metrics weaken substantially after accuracy control. We also find that ranking reversal is frequent: models favored by raw metrics often cease to be favored once accuracy is controlled. Our results show that raw global calibration metrics are not robust for cross-model comparison, and that fair calibration comparison requires accuracy-aware evaluation. --- ### Gradient Smoothing: Coupling Layer-wise Updates for Improved Optimization Authors: Haoming Meng, Anton Sugolov, Vardan Papyan Published: 2026-06-29 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.30813v1 Deep neural networks with repeated architectural blocks, such as transformers, often exhibit structured relationships across layers that emerge during training. Motivated by this observation, we introduce \emph{Depth-wise Gradient Augmentation}, a general optimization paradigm in which the update applied to each layer is obtained by transforming the collection of block-wise optimizer updates along the depth dimension. Within this framework, we study \emph{Gradient Smoothing}, a family of depth-wise smoothing methods, and instantiate it with a simple local \emph{Window Smoothing} operator. The resulting method operates directly on block-wise updates produced by arbitrary base optimizers (e.g., SGD, Adam, Muon), incurs minimal computational overhead, and is compatible with existing optimization pipelines. We evaluate Gradient Smoothing across a diverse set of architectures and training regimes, including language model pretraining, RL post-training of LLMs for reasoning, diffusion modeling, and image classification with Vision Transformers. Across these settings, Gradient Smoothing consistently improves optimization and generalization performance without modifying model architectures or training objectives. We further show that it promotes more structured representation evolution across depth, consistent with its interpretation as a structured depth-wise preconditioning method. Together, these results establish Depth-wise Gradient Augmentation as a promising framework for exploiting cross-depth structure in optimization and demonstrate Gradient Smoothing as a simple and broadly applicable instantiation. --- ### AVTok: 1D Unified Tokenization for Holistic Audio-Video Generation Authors: Kien T. Pham, I Chieh Chen, Qifeng Chen, Long Chen Published: 2026-06-29 Categories: cs.CV, cs.MM, cs.SD, eess.AS arXiv: https://arxiv.org/abs/2606.30811v1 Audio-video generation has recently gained unprecedented research attention, aiming to synthesize high-quality sounding video content with fine-grained synchronization and semantic alignment between the auditory and visual components. The preceding methods predominantly adopt a dual-branch design with separate tokenization and generation modules per modality, neglecting the representation gap while necessitating intensive computational resources for proper training. Inspired by recent advancements in one-dimensional visual tokenization, we present \textbf{AVTok}, a novel unified tokenizer designated for holistic audio-video generation. AVTok features a dual-stream transformer-based architecture with shared encoder-decoder and modal-specific learnable queries to efficiently and effectively encode an audio-video pair into a compact one-dimensional latent representation with a unified codebook. To cope with the heterogeneous information imbalance that hinders AVTok from exploiting aligned audio-visual information, we devise a hierarchical training strategy to progressively realize reconstruction capabilities for each modality. Extensive experiments demonstrate that AVTok excels both in audio-video reconstruction and when integrated into downstream pipelines for audio-to-video, video-to-audio, and class-conditional joint audio-video generation. AVTok paves the way for the challenge of joint audio-video tokenization and provides a potential direction to build unified large multimodal models for audio-video generation. --- ### GaussLite: Online Task-Conditioned 3D Gaussian Splatting for Real-Time Robotic Mapping Authors: Annika Thomas, Mason Peterson, Jonathan P. How Published: 2026-06-29 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2606.30809v1 Existing 3D Gaussian Splatting (3DGS) systems distribute representation capacity uniformly across a scene, ignoring the fact that many downstream robotic tasks engage only a fraction of the reconstructed geometry. This causes valuable onboard compute to be allocated towards optimizing irrelevant parts of the scene, either limiting online capacity or under-optimizing the most relevant parts of the scene. We introduce GaussLite, a task-driven 3DGS mapping system that conditions its representation density on a natural-language task specification. Given a posed RGB-D stream and a task such as "prepare to pick up the object on the desk," GaussLite uses a one-shot LLM parser to extract target and anchor objects, which are grounded per-frame by an open-vocabulary detector and segmented to produce per-pixel relevance masks in real time. The mapper allocates seeding density, gradient flow and scaling by task relevance. At matched Gaussian budget and real-time mapping at 4 Hz on resource-constrained hardware, GaussLite outperforms baselines on ROI PSNR on the Replica Dataset by an average +2.72 dB and on a real-hardware demonstration in indoor and outdoor settings by +2.23 dB. We further show that two task-specialized agents' maps can be fused into a single shared map via per-voxel voting on active-optimization counts in real time, outperforming concatenation by +3.42 dB while only sharing an average 7.08% of the map. --- ### Off the Rails: Hijacking the Scoring Head in Generative End-to-End Driving Planners with Safety-Violating Adversarial Perturbations Authors: Halima Bouzidi, Mboutidem Ekemini Mkpong, Haoyu Liu, Mohammad Abdullah Al Faruque Published: 2026-06-29 Categories: cs.RO, cs.CR, cs.CV arXiv: https://arxiv.org/abs/2606.30807v1 Generative models have recently seen rapid adoption in End-to-End (E2E) autonomous driving (AD), with diffusion-based denoising and vocabulary-based retrieval becoming the dominant trajectory-decoding paradigms. Despite their architectural diversity, current generative AD planners share a common inference pattern: a fixed set of candidate trajectories (anchors, vocabulary entries, or proposal queries) is scored by one or more learned heads conditioned on the Bird's-Eye-View (BEV) features, and the highest-scored candidate is returned as the final trajectory. Under this design, the scoring head is the only barrier between perception and the motion command, and its decision margins between competing candidates are often small. We introduce \textsc{Derail}, an adversarial framework that exploits this scoring-head attack surface. Evaluated on various generative planners, \textsc{Derail} flips the trajectory selection from a safe to an unsafe candidate, with score drops of $39$--$80\%$ and collision rates of up to $50\%$, consistently outperforming generic loss-maximization and feature-divergence attacks. Our analysis suggests that safety-violating objectives govern attack effectiveness against generative AD planners, and that the scoring-head inference pattern itself is a recurring attack surface worth explicit defensive consideration. ---