# Research Papers — 2026-06 · bundle page 48 of 260 > Full-text markdown of papers #2351–2400 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/48 [← Previous bundle](https://aipod.dev/papers/archive/2026-06/page/47.md) [Next bundle →](https://aipod.dev/papers/archive/2026-06/page/49.md) ### DiCoBench: Benchmarking Multi-Image Fine-Grained Perception via Differential and Commonality Visual Cues Authors: Geng Li, Yuxin Peng Published: 2026-06-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.26602v1 Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated impressive fine-grained perception capabilities. However, existing benchmarks predominantly rely on explicit textual cues or low-resolution inputs, failing to evaluate a model's ability to autonomously perceive implicit visual cues in high-resolution. To bridge this gap, we introduce DiCoBench, a comprehensive, multi-image high-resolution benchmark designed for cross-image fine-grained perception. DiCoBench consists of 765 meticulously curated samples categorized into two progressive tracks: Differential Visual Cues and Commonality Visual Cues, covering 8 distinct perception tasks. By formulating the benchmark as a multiple-choice question task and utilizing high-resolution imagery (approaching 2K), we eliminate evaluation metric bias and pose a substantial challenge to current state-of-the-art MLLMs. Our extensive evaluation of 18 diverse MLLMs reveals a striking performance gap compared to human accuracy (98.3\%), with top-performing models struggling significantly with micro-scale detail capture. We believe DiCoBench will serve as a challenging testbed to drive future research in autonomous, high-resolution multi-image perception. --- ### LLM-based Models for Detecting Emerging Topics in Service Feedback Authors: Mahsa Tavakoli, Ruth Bankey, Cristián Bravo Published: 2026-06-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.26595v1 Enhancing the analysis of service feedback is essential for public sector organizations, particularly tax administrations, where trust and compliance depend on fair and effective service delivery. As feedback volumes grow, identifying emerging service quality issues and potential disparities across diverse populations becomes increasingly challenging. Traditional approaches often rely on manual review or static expert-defined indicators, limiting scalability and the ability to capture complex patterns in textual feedback. This paper presents a novel methodology that integrates large language models (LLMs), statistical techniques, and human-AI collaboration to improve multilingual customer feedback analysis. The primary objective is to detect emerging service quality topics that may also reveal potential inequities in service delivery. Our framework combines fine-tuned, quantized LLMs with expert oversight to produce accurate, computationally efficient, and context-aware analyses. The proposed approach was evaluated using similarity analysis and assessments from experienced tax officers, demonstrating stronger alignment with expert judgments than baseline models. By incorporating a human-in-the-loop framework, the methodology reduces LLM fabrication while improving the reliability and relevance of generated insights. The results demonstrate the practicality of combining LLMs with human expertise to support scalable, evidence-based decision-making in public sector organizations. This work contributes to the development of responsible AI systems that enhance service quality, responsiveness, fairness, and public trust through more effective analysis of multilingual customer feedback. --- ### Content-Based Smart E-Mail Dispatcher Using Large Language Models Authors: K. Paramesha, K R Sriram, Sujan Shetty, Shamanth Kishore, R. Tejaswini Published: 2026-06-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.26593v1 Email communication has become an integral part of personal and professional life, but handling its vast volume is still a significant issue for large organisations. Manual perusal of emails and forwarding their contents and attachments to intended recipients using other instant messaging platforms has proved to be error-prone and time-consuming leading to losses in terms of productivity and creating undue stress. The main objective of this paper is to explore an alternative mechanism that is to automate the task of dispatching emails based on their contents to the respective WhatsApp groups of students of various semesters of programs in an engineering college, facilitating a smooth flow of information from one end to another end in an organisation. The dispatcher system is built using agents querying large language models (LLMs) to enable it to analyze the contents of emails and route them to the relevant groups of students for their information and consumption. The system harnesses the capabilities of LLMs in analysing the textual contents for decision-making. With a well-structured agent framework prompt that includes email content as input with instructions and context, the system figures out the relevant groups to which the email message is dispatched, thus providing the required information on time. The proposed system does not rely on labelled datasets and provides several benefits, including enhanced productivity and a reduction in the cognitive load associated with reading emails. --- ### Latent Diffusion Posterior Sampling with Surrogate Likelihood Guidance for PDE Inverse Problems Authors: Yuanzhe Wang, Alexandre M. Tartakovsky Published: 2026-06-25 Categories: cs.CE, cs.LG arXiv: https://arxiv.org/abs/2606.26592v1 We propose latent-space diffusion posterior sampling (L-DPS), an approximate Bayesian framework for high-dimensional inverse problems governed by partial differential equations (PDEs). The method addresses three challenges in PDE-constrained inversion: implicit sample-based priors without tractable densities, high-dimensional spatially distributed parameters, and the high cost of repeated forward-model evaluations during posterior sampling. L-DPS combines a variational autoencoder, an unconditional latent diffusion model, diffusion posterior sampling, and a differentiable neural surrogate. The VAE maps the parameter field to a lower-dimensional latent space, the diffusion model learns an implicit prior score in this latent space, and DPS combines this learned prior with likelihood-based guidance. The likelihood gradient is evaluated through the decoder-surrogate composition, avoiding repeated calls to the full numerical PDE solver. We evaluate the method on an inverse Darcy flow problem with an unknown spatially distributed permeability field inferred from sparse and noisy pressure observations. L-DPS produces accurate and robust inverse solutions, reduces inference cost relative to full-space DPS, and outperforms amortized inverse baselines such as conditional latent diffusion and inverse FNO in sparse and noisy regimes. We further compare L-DPS with a KLE-MAP baseline and study mixed-prior generalization and the sensitivity of inversion accuracy to surrogate forward-model error. --- ### Three-Objective Integral R2 Subset Selection: NP-Hardness and Submodular Approximation Authors: Michael T. M. Emmerich Published: 2026-06-25 Categories: math.OC, cs.CG, cs.NE arXiv: https://arxiv.org/abs/2606.26591v1 Selecting a fixed number of representative points from a finite Pareto-front approximation is a fundamental post-processing task in multiobjective optimization. This paper studies this problem for the integral R2 indicator in three objectives, where the indicator is defined as the integral of the lower envelope of weighted Tchebycheff scalarizations over the two-dimensional weight simplex. We provide two complementary algorithmic results. On the positive side, we show that the integral R2 improvement with respect to any fixed baseline is a monotone submodular set function. For the usual ideal-point based R2 indicator, with the ideal point fixed, this yields a direct gap-reduction guarantee: greedy selection closes at least a $(1-1/e)$-fraction of the maximum possible R2 gap between a fixed dominated anchor value and the best cardinality-$k$ value. We also give a tested greedy implementation that evaluates exact integral R2 values by subdivision, with worst-case running time $O(n^6)$. On the negative side, we prove that exact fixed-cardinality subset selection is NP-hard already in three objectives. The hardness proof uses a perspective transformation that maps Tchebycheff-shadow improvements to a weighted anchored-box union problem with density $(x_1+x_2+x_3)^{-4}$, and then adapts the three-dimensional anchored-box construction of Bringmann, Cabello, and Emmerich. Together, these results separate the tractable two-objective case from the three-objective case while identifying a principled approximation route based on submodular optimization. --- ### Empirical Software Engineering TerraProbe: A Layered-Oracle Framework for Detecting Deceptive Fixes in LLM-Assisted Terraform Authors: Manar Alsaid, Chimdumebi Nebolisa, Faris Abbas Published: 2026-06-25 Categories: cs.LG, cs.CR arXiv: https://arxiv.org/abs/2606.26590v1 Security misconfigurations in Terraform Infrastructure-as-Code are a growing risk in cloud deployments, and large language models are increasingly used as automated repair agents. Existing evaluations often treat a repair as successful when the targeted static-analysis finding disappears, without checking planning validity, behavioral change, or security intent. This paper presents TerraProbe, a five-layer oracle framework for evaluating LLM-assisted Terraform security repair. We apply TerraProbe to 288 first-pass repairs generated by gemini-2.5-flash-lite, GPT-4o, and Claude 3.5 Sonnet across 68 real-world TerraDS modules and 28 controlled injected-defect modules. The results show that targeted Checkov removal overstates repair success. Although targeted removal reaches 83.3 percent for the primary model, full-scanner cleanliness drops to 10.4 percent, Terraform planning succeeds for 39.6 percent, and plan comparison is reachable for 38.5 percent. Human adjudication further shows that 71.4 percent of plan-compared real-world repairs are deceptive fixes that pass automated checks while leaving the underlying vulnerability in place. This pattern is statistically indistinguishable across the three models, with deceptive-fix rates from 57.1 percent to 71.4 percent and pairwise Fisher exact p-values above 0.10. The paper introduces a four-dimensional taxonomy of deceptive fixes, validated with Cohen kappa of 0.78 and Krippendorff alpha of 0.76. IAM permission analysis confirms that wildcard Resource grants persist in all nine CKV2 AWS 11 deceptive-fix cases. TerraProbe contributes an evaluation methodology, a replication package, and the Multi-Layer Oracle Evaluation framework for distinguishing intent-aligned security repairs from scanner-passing false successes. --- ### SharQ: Bridging Activation Sparsity and FP4 Quantization for LLM Inference Authors: Haoqian Meng, Yilun Luo, Yafei Zhao, Wenyuan Liu, Huaqing Zheng, Xindian Ma, Peng Zhang Published: 2026-06-25 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.26587v1 Low-bit floating-point formats and semi-structured sparsity are increasingly supported by modern accelerators, yet combining them for LLM activation compression remains challenging: activations contain input-dependent outliers that dominate block scales in FP4 quantization, and directly applying N:M sparsity masks discards moderate values, coupling sparsification loss with quantization error. We introduce SharQ, a training-free inference method that bridges activation sparsity and FP4 quantization through an online sparse--dense decomposition. For each activation tensor, SharQ generates an input-adaptive N:M mask to extract an outlier-dominated sparse backbone, quantizes it to FP4, and defines a dense residual relative to the quantized sparse backbone rather than the unquantized sparse values. A sparse FP4 GEMM processes the backbone while a dense FP4 GEMM compensates for both mask-induced activation loss and sparse-path quantization error. The two paths share a single FP4 weight payload with path-specific scale views, and a fused preparation kernel absorbs mask generation, residual construction, and layer normalization into one operator. SharQ requires no calibration data, retraining, or model-specific tuning. Evaluated on Llama-3.1-8B, Qwen2.5-7B, Qwen3-30B-A3B, and Qwen3-VL-8B, SharQ recovers 43--63% of the NVFP4-to-FP16 accuracy gap across language and vision-language tasks, and generalizes across NVFP4, HiF4, and MXFP4 formats. On an RTX 5090, SharQ delivers 2.2--2.4$\times$ latency reduction over FP16 and 1.2--1.4$\times$ throughput improvement over FP8 in language model serving, and up to 1.58$\times$ speedup on Wan2.2-T2V-A14B video generation when combined with SageAttention. Our code is available at https://github.com/actypedef/SharQ. --- ### A Multi-Level Validation and Traceability Framework for AI-Generated Telescope Scheduling Decisions Authors: Hengchu Xiao, Chuanjun Wang Published: 2026-06-25 Categories: cs.AI, astro-ph.IM arXiv: https://arxiv.org/abs/2606.26585v1 With the gradual introduction of AI into telescope scheduling, AI-based decision-making has shown advantages in handling complex multi-constraint problems. However, its outputs often suffer from inconsistent data references, reasoning errors, and non-executable decisions, limiting applicability in high-reliability observational tasks. In this work, we propose a multi-level validation and traceable reasoning framework that performs systematic reliability verification of AI-generated decisions prior to execution, and enables explicit representation of the reasoning process to support traceable decision-making. The framework integrates data reference validation, logical consistency checks, and observational and instrumental constraint verification to filter and correct invalid decisions. It also introduces atomic reasoning units and their dependency relationships, representing scheduling decisions as a sequence of interconnected reasoning steps that support error localization and post hoc analysis. Experiments show that the framework improves executability and reliability of AI scheduling and reduces loss of transient opportunities. In particular, feedback correction and structured validation of reasoning steps enhance the ability to repair and block erroneous decisions, especially in complex scenarios. Compared with pure AI methods, the framework-enhanced approach maintains flexibility while substantially improving reliability and executability. These results demonstrate a feasible and verifiable pathway for applying AI to high-reliability astronomical observation scheduling. --- ### EvoOptiGraph: Weakness-Driven Coevolution via Graph-Based Structural Generation for Optimization Modeling Authors: Qingcan Kang, Mingyang Liu, Xiaojin Fu, Shixiong Kai, Tao Zhong, Mingxuan Yuan Published: 2026-06-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.26578v1 Automating optimization modeling from natural language with large language models (LLMs) faces two key challenges. First, training corpora lack structural diversity. Second, data generation pipelines remain static and decoupled from model learning. To address these challenges, we propose EvoOptiGraph, a novel framework where data and model co-evolve, driven by model weaknesses. EvoOptiGraph represents each mixed-integer linear program (MILP) as an attributed bipartite graph and applies validity-preserving evolutionary operators to generate structurally diverse instances. The evolved graphs are converted into solver code and natural language via deterministic compilation and verified back-translation. Training proceeds in two stages: supervised fine-tuning (SFT) on an initial dataset, followed by reinforcement learning with verifiable rewards (RLVR), where graph-derived weakness signals guide the generation of new instances targeting the model's failures. This forms a closed loop that continuously updates the training distribution. Empirical results on six public datasets show that EvoOptiGraph significantly outperforms larger generalist models, agentic methods, and specialized baselines in accuracy, executability, and generalization. These results demonstrate that targeted data-model coevolution is an effective strategy for improving LLMs on optimization modeling tasks. --- ### IDEA: Insensitive to Dynamics Mismatch via Effect Alignment for Sim-to-Real Transfer in Multi-Agent Control Authors: Chenlong Liu, Zhuohui Zhang, Xinyan Chen, Zhipeng Wang, Bin Cheng, Bin He Published: 2026-06-25 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2606.26575v1 Complex multi-agent control tasks remain challenging for traditional rule-based and model-based approaches, motivating the adoption of learning-based methods. However, learning-based methods often struggle with sim-to-real transfer because they rely on accurate dynamics modeling or system identification and learn policies in low-level control spaces that are highly sensitive to dynamics mismatch, making them costly and fragile in complex environments. To address this issue, we propose a sim-to-real method for multi-agent control, which is insensitive to dynamics mismatch via effect alignment. Our method combines random environmental structure with discrete semantic actions through closed-loop control, elevating policy learning to a semantic abstraction level. Additionally, we develop an action synchronization mechanism that mitigates inter-agent action timing mismatches, thereby enhancing the temporal consistency of the system. Experiments on four multi-agent navigation tasks demonstrate that our method substantially improves training efficiency over mainstream transfer methods and achieves higher success rates in real-world scenarios, thereby improving the robustness and deployment stability of multi-agent systems under dynamics mismatch. --- ### Revisiting Action Factorization for Complex Action Spaces Authors: Timothy Flavin, Sandip Sen Published: 2026-06-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.26574v1 Many real-world control problems involve hybrid discrete-continuous action spaces. For example, steering and signaling in autonomous driving, and aiming and firing in robotics or video-games. Despite real-world hybrid factorization and reinforcement learning framework support for complex action spaces (e.g., Gymnasium, PettingZoo, TorchRL, SeedRL, Mujoco, etc), the default environments within those frameworks often implement uniform action space configurations (LunarLander, Walker2D, Cheetah, SMAC, SUMO, Ant, Atari). Landmark hybrid-action benchmarks (RoboCup 2D HFO, SC2LE, Platform, CARLA, etc) are mostly heavyweight or archival implementations originating from papers which test one or a small number of competing factorization methods on one kind of control. This article provides a cross-sectional study of factorization methods (independent networks, shared encoder, VDN, QPLEX, Joint, Auto-Regressive) on each of three families of algorithms (PPO, SAC, DQN) across three action spaces (discretized, hybrid, continuous) over four lightweight environments (Platform, hybrid-LunarLander, Hybrid-Shoot, CoopPush). Accounting for some invalid pairings such as joint-continuous, we are left with 220 configurations to analyze each method. We provide two new C++ parallel gymnasium and petting-zoo compliant environments (CoopPush, Hybrid-Shoot) to isolate particular challenges such as state-dependent inter-action dependence. Finally, we introduce VDN-PPO and PPO-MIX which use a branching critic to assign credit to multi-headed PPO. These variants out-perform all other tested PPO factorizations. Our results suggest that branching dueling architectures balance compute and performance most effectively, with Auto-Regressive actions reaching the highest performance overall and native continuous SAC outperforming discrete and hybrid algorithms, albiet both at increased computational cost. --- ### Zero-shot Tweet-Level Stance Detection Enhanced by External Knowledge and Reflective Chain-of-Thought Reasoning Authors: Yiju Huang, Wenxian Wang, Lijun Zhou, Rui Tang, Xiao Lan, Tao Zhang, Haizhou Wang Published: 2026-06-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.26571v1 Zero-shot tweet-level stance detection confronts two primary challenges: (1) mitigating the context sparsity inherent in short texts, and (2) establishing the relevance between implicit targets and textual content. While existing methods primarily focus on incorporating external knowledge, they neglect the intrinsic semantic cues embedded within key intra-textual entities. Furthermore, current models exhibit limited capability in determining the relevance of unseen targets to the given text, thereby struggling to differentiate between "neutral" and "irrelevant" stance labels. To address these issues, we first construct a four-class, multi-topic Japanese tweet dataset. To our knowledge, this is the first Japanese tweet-level dataset for stance detection. We then propose KIRP, a zero-shot stance detection framework. It integrates external knowledge with entity reorganization for data augmentation and employs prompt chaining for reasoning. Specifically, the framework incorporates knowledge graphs to supplement and reorganize key textual entities, while reflective Chain-of-Thought (CoT) reasoning extracts and validates implicit targets. To better distinguish "neutral" from "irrelevant" labels, we adopt stance-aware contrastive learning to capture discriminative features and design a three-layer iterative prototype network for fine-grained classification. Experimental results on SemEval-2016, WT-WT, and KIRP-D show that KIRP achieves state-of-the-art performance. KIRP obtains F1 scores of 84.05% (three-class) on SemEval-2016, and 84.99% and 79.18% (four-class) on WT-WT and KIRP-D, respectively. --- ### Adversarial Diffusion Across Modalities: A Fusion Survey of Attacks, Defenses, and Evaluation for Text, Vision, and Vision-Language Models Authors: Abrar Alotaibi, Moataz Ahmed Published: 2026-06-25 Categories: cs.CR, cs.CL arXiv: https://arxiv.org/abs/2606.26566v1 Adversarial evaluation of AI systems has matured along four largely disconnected tracks: diffusion-based attacks on text and large language models (LLMs), diffusion-based attacks on image classifiers, jailbreak pipelines against vision-language models, and diffusion-based input purification defenses. Each has developed its own vocabulary, threat models, and benchmarks, with denoising diffusion models emerging as a shared generative mechanism whose recipes are now actively ported between communities. This survey performs an information-fusion exercise at the meta-research level: we integrate these four tracks into a single conceptual framework with a unified taxonomy, evaluation criteria, and research agenda, focusing on the LLM-side slice. We catalog fifty published papers across four scope areas (text/LLM, image classifier, vision-language model, defense), plus four diffusion-LLM-as-victim entries and ten non-diffusion baselines against which any new attack must be compared. We propose a six-class taxonomy of diffusion roles in adversarial pipelines, augmented by a threat-model axis recording attacker knowledge, query budget, and target accessibility, and apply a five-dimension framework (attack success rate, transferability, query budget, perplexity, defense-evasion) uniformly across modalities. The review adopts a dual attacker-defender perspective: alongside the attack catalog we cover four diffusion-based defenses that form the natural evaluation backdrop for new attacks. Our critical analysis identifies five recurring weaknesses of the current LLM-side literature, and we close with a research agenda of open questions and concrete experimental designs. The companion catalog and spreadsheet are released with the paper. We are explicit that this is a narrative review with quality assessment, not a PRISMA-compliant systematic review, and discuss the implications for replication. --- ### scBench-Long: Verifiable Benchmarking of Long-Horizon Single-Cell Biology Authors: Ian Diks, Zhen Yang, Arjun Banerjee, Tim Proctor, Kenny Workman Published: 2026-06-25 Categories: q-bio.GN, cs.AI arXiv: https://arxiv.org/abs/2606.26563v1 Single-cell studies require analysts to convert raw measurements into specific biological claims through multi-step workflows and integration of metadata, assay context, and auxiliary evidence. Existing AI-biology benchmarks largely measure broad knowledge, executable workflows, or local analysis steps. We introduce scBench-Long, a benchmark for long-horizon single-cell biology in which agents must recover scientific conclusions from raw or near-raw data without prescribed methods. The benchmark contains 21 evaluations spanning melanoma CD8 T-cell reactivity, CD8 RNA+ATAC regulatory inference, human--monkey chimera development, KRAS-driven lung tumor aging, and lethal COVID-19 lung pathology. Tasks cover paired scRNA/TCR sequencing, RNA and chromatin profiling, cross-species transcriptomics, combinatorial scRNA-seq, single-nucleus RNA-seq, immune repertoires, ortholog maps, ligand--receptor resources, and validation evidence. Candidate claims are reproduced, reviewed, and converted into controlled answer vocabularies with deterministic grading and trajectory rubrics. Across 1,068 completed trajectories, the strongest model--harness pair passes 16/63 runs (25.4\%). scBench-Long evaluates whether agents can move beyond local analysis steps and make complex scientific claims that are supported by single-cell data. --- ### Explainable Ensemble-Based Machine Learning Models for Detecting the Presence of Cirrhosis in Hepatitis C Patients Authors: Abrar Alotaibi, Lujain Alnajrani, Nawal Alsheikh, Alhatoon Alanazy, Salam Alshammasi, Meshael Almusairii, Shoog Alrassan, Aisha Alansari Published: 2026-06-25 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.26561v1 Hepatitis C is a liver infection caused by a virus, which results in mild to severe inflammation of the liver. Over many years, hepatitis C gradually damages the liver, often leading to permanent scarring, known as cirrhosis. Patients sometimes have moderate or no symptoms of liver illness for decades before developing cirrhosis. Cirrhosis typically worsens to the point of liver failure. Patients with cirrhosis may also experience brain and nerve system damage, as well as gastrointestinal hemorrhage. Treatment for cirrhosis focuses on preventing further progression of the disease. Detecting cirrhosis earlier is therefore crucial for avoiding complications. Machine learning (ML) has been shown to be effective at providing precise and accurate information for use in diagnosing several diseases. Despite this, no studies have so far used ML to detect cirrhosis in patients with hepatitis C. This study obtained a dataset consisting of 28 attributes of 2038 Egyptian patients from the ML Repository of the University of California at Irvine. Four ML algorithms were trained on the dataset to diagnose cirrhosis in hepatitis C patients: a Random Forest, a Gradient Boosting Machine, an Extreme Gradient Boosting, and an Extra Trees model. The Extra Trees model outperformed the other models achieving an accuracy of 96.92%, a recall of 94.00%, a precision of 99.81%, and an area under the receiver operating characteristic curve of 96% using only 16 of the 28 features. --- ### Erase-then-Delta Attention: Decoupling Erase and Write Addresses in Delta-Rule Linear Attention Authors: Xiao Li, Chengruidong Zhang, Hao Luo, Xi Lin, Zekun Wang, Zihan Qiu, Yunfei Mao, Langshi Chen, Man Yuan, Minmin Sun, Huiqiang Jiang, Siqi Zhang et al. Published: 2026-06-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.26560v1 Delta-rule linear attention improves recurrent memory updates by correcting what is already stored at the current write address before writing new content. However, the active correction is still anchored to that same write address. As a result, stale information stored at a different address cannot be actively removed before new content is written elsewhere. We propose Erase-then-Delta Attention (EDA), a memory update rule that decouples where to erase from where to write. The key insight is that recurrent memory models should not only correct the current write, but also selectively suppress outdated memory at an independently chosen address. Concretely, our method first applies a targeted erase step along a learned erase direction, and then performs the standard delta-style corrective write along the current write direction. This preserves the corrective behavior of delta-rule updates while expanding their memory-management capacity. Language-model pretraining experiments across dense 2.5B and MoE 25B-A2.8B model families show that EDA performs best in both settings. The gain persists after 80B-token long-context midtraining of the MoE models, where EDA also performs best in long-context evaluations from 4k to 128k contexts. A compact update analysis and memory-state probes suggest why: EDA keeps the delta-rule corrective write intact while allocating an additional cleanup path most strongly when passive decay is weak. These results suggest that recurrent memory models should decide not only what to write, but also what stale information to erase and where. --- ### SpaceRipple: Lightweight Semantic Delivery for Mission-Oriented LEO Earth Observation Satellite Networks Authors: Ziyi Yang, Hao Yuan, Yunxiang Yi, Wenbo Wang, Xing Zhang Published: 2026-06-25 Categories: cs.CV, cs.AI, cs.GR arXiv: https://arxiv.org/abs/2606.26559v1 Earth observation satellite networks generate massive volumes of high-resolution imagery, whereas inter-satellite and downlink resources remain limited. In many time-sensitive missions, ground users require mission-relevant semantic information rather than a full raw-image downlink. This paper proposes SpaceRipple, a lightweight framework for mission-oriented semantic delivery and on-board processing in Earth observation satellite networks. A sensing satellite performs adaptive compression and metadata generation to reduce inter-satellite traffic, while an edge computing satellite restores the received representation and extracts task-relevant semantic information. Unlike fidelity-driven image transmission, SpaceRipple coordinates compression, forwarding, restoration, and semantic inference within a collaborative pipeline, enabling semantic-oriented delivery instead of pixel-level image delivery. A compression-aware MoE enhancement module is further introduced to improve robustness under degraded visual inputs. Experimental results show that SpaceRipple achieves favorable reconstruction quality, improved semantic detection performance, and substantial bandwidth savings, demonstrating its potential for efficient and reliable Earth observation under constrained satellite-network resources. --- ### Coarse-to-Fine: A Hybrid Self-Supervised Method for Non-rigid 3D Shape Matching Authors: Feifan Luo, Ting Li, Zhao Li, Hongyang Chen Published: 2026-06-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.26557v2 Non-rigid 3D shape matching is a fundamental task in computer vision and graphics. In this paper, we propose a hybrid self-supervised method based on a coarse-to-fine strategy, which ensures consistency between the coarse mapping and the refined correspondence produced by our refinement module. The architecture features a dual-branch design, consisting of two symmetric functional map learning streams: one based on the Laplacian basis and the other utilizing the elastic basis. Extensive experiments show that our approach not only maintains computational efficiency, but also achieves state-of-the-art performance across a variety of challenging scenarios, including non-isometric deformations and topological noise. Finally, we rigorously demonstrate that contrastive energies promote feature discrimination. Furthermore, integrating these energies with existing methods yields consistent improvements, validating the overall efficacy of our approach. Our code is available at https://github.com/LuoFeifan77/Coarse-to-Fine-Hybrid-Self-Supervised-Matching. --- ### Perception, Verdict, and Evolution: Hindsight-Driven Self-Refining Forensics Agent for AI-Generated Image Detection Authors: Yangjun Wu, Keyu Yan, Yu Liu, Jingren Zhou, Fei Huang, Rong Zhang, Zhou Zhao, Fei Wu Published: 2026-06-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.26552v1 The rapid advancement of generative models presents a significant challenge to existing deepfake detection methods, particularly given the widespread dissemination of highly realistic AI-generated images. Although Multimodal Large Language Models (MLLMs) show strong potential for this task, existing approaches suffer from two key limitations: insufficient sensitivity to fine-grained forensic artifacts and reliance on static synthetic supervision from frontier models, leading to limited flexibility and high-cost. To address these issues, we propose ForeAgent, an agentic forensics framework for AI-generated image detection with iterative self-evolution. First, ForeAgent adopts a Perception-Verdict architecture that aggregates multi-view cues spanning semantic, spatial, and frequency-domain features, and leverages an MLLM as a verdict module to fuse these signals for a logical-grounded verdict. Second, to enable continual self-improvement, we introduce a Hindsight-Driven Self-Refining strategy following a Sampling-Reflection-Evolution paradigm. The agent performs inference rollouts on training instances. Guided by ground-truth labels as hindsight, it reflects on failure cases and low-quality reasoning trajectories to regenerate higher-quality reasoning traces. These synthesized samples are then strictly filtered through a dual-expert quality gating module. ForeAgent continuously evolves via fine-tuning on self-curated high-quality samples. Extensive experiments demonstrate that ForeAgent achieves state-of-the-art performance on the Chameleon benchmark, reaching 82.18% accuracy (+16.41% over AIDE), and achieves 93.3% mean accuracy on AIGCDetect-Benchmark across 16 generators. In addition, external evaluation shows that ForeAgent produces more consistent and causally grounded reasoning compared to GPT-5 and GPT-5-mini. --- ### PhyEditBench: A Real-World Multi-Stage Benchmark for Physics-Aware Image Editing Authors: Shengbin Guo, Shaokang He, Chaoyue Meng, Shengpeng Xiao, Xunzhi Xiang, Shaofeng Zhang, Qi Fan Published: 2026-06-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.26551v2 While instruction-based image editing, enabled by multi-modal generative models, has advanced significantly, existing benchmarks lack a comprehensive evaluation of physics-based reasoning, a critical capability for handling real-world scenarios. To address this, we introduce PhyEditBench, a benchmark designed to assess the physical understanding of editing models. Guided by a hierarchical taxonomy, we establish 4 primary classes and 12 subclasses. It comprises 238 high-quality, high-resolution, real-world instances meticulously extracted from videos to capture authentic physical dynamics, alongside 35 synthetic Anti-Physics instances. Our empirical analysis of current SOTA editing methods exposes substantial limitations in their physics-based reasoning. We further propose a training-free baseline named PhyWorld that uses test-time scaling and a latent reduction strategy. PhyWorld outperforms comparable models and suggests that the video generation process can effectively serve as a reasoning mechanism for image editing. The project page is available at https://github.com/Previsior/PhyEditBench. --- ### PMDformer: Patch-Mean Decoupling Information Transformer for Long-term Forecasting Authors: Ao Hu, Liangjian Wen, Jiang Duan, Yong Dai, He Yan, Dongkai Wang, Jun Wang, Yukun Zhang, Ruoxi Jiang, Zenglin Xu Published: 2026-06-25 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.26549v1 Long-term time series forecasting (LTSF) plays a crucial role in fields such as energy management, finance, and traffic prediction. Transformer-based models have adopted patch-based strategies to capture long-range dependencies, but accurately modeling shape similarities across patches and variables remains challenging due to scale differences. To address this, we introduce patch-mean decoupling (PMD), which separates the trend and residual shape information by subtracting the mean of each patch, preserving the original structure and ensuring that the attention mechanism captures true shape similarities. Futhermore, to more effectively model long-range dependencies and capture cross-variable relationships, we propose Trend Restoration Attention (TRA) and Proximal Variable Attention (PVA). The former module reintegrates the decoupled trend from PMD while calculating attention output. And the latter focuses cross-variable attention on the most relevant, recent time segments to avoid overfitting on outdated correlations. Combining these components, we propose PMDformer, a model designed to effectively capture shape similarity in long-term forecasting scenarios. Extensive experiments indicate that PMDformer outperforms existing state-of-the-art methods in stability and accuracy across multiple LTSF benchmarks. The code is available at https://github.com/aohu1105/PMDformer. --- ### Compiler-Driven Approximation Tuning for Hyperdimensional Computing Authors: Xavier Routh, Abdul Rafae Noor, Akash Kothari, Zheyu Li, Mahbod Afarin, Tajana Rosing, Vikram Adve Published: 2026-06-25 Categories: cs.PL, cs.CL, cs.PF arXiv: https://arxiv.org/abs/2606.26547v1 As Moore's law reaches its physical and economic limits, domain-specific approaches are increasingly employed to accelerate machine learning workloads. Hyperdimensional Computing (HDC) represents one such emerging paradigm, offering an alternative to conventional deep learning techniques. Rooted in cognitive models of computation, HDC is designed bottom-up with hardware efficiency as a first-class objective. HDC workloads map naturally to heterogeneous hardware platforms, including CPUs, GPUs, and FPGAs, as well as emerging in-memory computing technologies such as Resistive RAM (ReRAM) and Phase-Change Memory (PCM). HDC algorithms are intrinsically tolerant to noise and approximation, enabling substantial performance gains with minimal accuracy loss. In this work, we introduce ApproxHDC, a framework for automated identification and application of domain-specific approximations in HDC workloads. ApproxHDC extends the HPVM-HDC compiler infrastructure to enable retargetable compilation across diverse hardware backends, including CPUs, GPUs, and simulated ReRAM and PCM-based accelerators. The space of possible approximations is exponentially large; ApproxHDC employs efficient search and analysis to navigate it and identify high-impact configurations spanning both software and hardware levels. --- ### Can Large Language Models Reliably Code Qualitative Humanitarian Data? A Benchmark Study Against Human Expert Adjudication Authors: Jerome Marston, Tino Kreutzer, Salomé Garnier, Ella Boone, Phuong N Pham, Patrick Vinck Published: 2026-06-25 Categories: cs.LG, cs.CY arXiv: https://arxiv.org/abs/2606.26541v1 Data from affected populations are crucial for informing humanitarian response, but their value depends on timely and consistent interpretation of nuanced accounts of need. Humanitarian organizations often lack the staff, time, and specialist expertise required to analyze this information at scale. Large language models (LLMs) may expand this capacity, but their reliability for coding qualitative humanitarian data has not been directly established. This benchmark study compares 46 LLMs to a human Gold Standard using 150 high-fidelity synthetic humanitarian transcripts. Evaluation combined inter-rater reliability testing with Krippendorff's alpha, discrepancy analysis distinguishing correct, near-correct, and incorrect codes, and qualitative assessment across humanitarian-specific criteria including discrimination, complex needs hierarchies, and non-standard communication styles. The authors find that multiple LLMs can perform deductive coding at reliability levels comparable to experienced human coders, especially when structured prompts and reasoning-enabled configurations are used. At the same time, aggregate reliability metrics alone are insufficient for deployment decisions. Models varied in recognizing needs expressed indirectly, needs outside predefined categories, and protection-relevant concerns such as physical safety and discrimination. These findings suggest that LLMs can materially expand humanitarian analytical capacity, but not as substitutes for human judgment. Appropriate use requires structured codebooks, reasoning-enabled models, attention to theme-specific performance, and tiered oversight focused on categories where miscoding would have the greatest programmatic consequences. For sensitive humanitarian data, open-weights models deployed on self-hosted infrastructure may offer a viable path for combining analytical scalability with stronger data governance. --- ### CascadeFormer: Depth-Tapered Transformers Motivated by Gradient Fan-in Asymmetry Authors: Huzama Ahmad, Cao Viet Hai Nam, Se-Young Yun Published: 2026-06-25 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.26538v1 Deep Transformers are composed of uniformly stacked residual blocks, yet their deepest layers often add little value. We present two efficiency methods that exploit this asymmetry. CascadeFormer tapers width with depth to match the uneven information flow across layers, achieving comparable perplexity to a uniform baseline at the same training budget while reducing latency by 8.6% and increasing throughput by 9.4%. CascadeFlow Pruning removes layers using accumulated training gradients, with no post hoc analysis. It outperforms standard heuristics on perplexity and rank-stability and stays competitive on downstream accuracy. To motivate these methods, we propose Gradient Fan-in Asymmetry (GFA) as a structural account of why deeper layers contribute less. In Pre-LayerNorm residual stacks, the gradient at a layer is the sum of an identity path and all downstream functional paths, producing a gradient fan-in that decays linearly with depth (and quadratically under deep supervision), yielding richer gradients for early layers and sparser ones for later layers. We provide correlational and interventional evidence for GFA on models trained from scratch up to 1.2B parameters. Across Transformers and ResNets, accumulated training gradients follow the theoretical fan-in and are associated with post hoc layer importance. Two interventions point to structure rather than magnitude as the bottleneck: equalizing per-layer gradient norms does not restore late-layer value, while increasing downstream path counts via parameter-shared repetition restores and elevates it. Whether gradient magnitude proxies fan-in beyond high-rank regimes, and how these dynamics behave at the 100B+ scale, remain open questions. --- ### From Hallucination to Grounding: Diagnosing Visual Spatial Intelligence via CRISP Authors: Zhixing Li, Yinan Yu Published: 2026-06-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.26535v1 Current VLM evaluations often conflate language priors with genuine spatial reasoning. To address this, we introduce CRISP, a novel structural-diagnostic evaluation paradigm that assesses visual spatial intelligence through consistency, the alignment between implicit perception and explicit reasoning. Unlike traditional black-box QA, CRISP utilizes metric 3D Scene Graphs and an oracle intervention protocol to decouple latent reasoning capabilities from perceptual bottlenecks. This granular diagnosis uncovers a systematic perception-reasoning disconnect. Crucially, we reveal that while proprietary models possess robust latent reasoning engines, they suffer from inaccurate metric estimation and a critical failure to leverage their implicit structural representations. Conversely, open-source models remain fundamentally bottlenecked by their lack of multi-hop compositional reasoning. By shifting the focus from merely ``guessing correctly'' via language priors to genuinely ``perceiving, verifying, and reasoning,'' CRISP offers a rigorous roadmap for multimodal alignment beyond end-to-end post-training. The code and dataset are available at https://github.com/iiyamayuki/CRISP-Bench. --- ### VoiceTTA: Enhancing Zero-Shot Text-to-Speech via Reinforcement Learning-Based Test-Time Adaptation Authors: Tianxin Xie, Chenxing Li, Dong Yu, Li Liu Published: 2026-06-25 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2606.26534v1 Recently, zero-shot text-to-speech (TTS) has enabled high-fidelity and expressive speech synthesis, but it often fails to imitate unseen speaking styles from uncommon scenarios (e.g., crosstalk, dialects). Moreover, fine-tuning pretrained models requires large, high-quality datasets, limiting rapid personalization. We propose VoiceTTA, a reinforcement learning-based test-time adaptation (TTA) method that improves voice imitation of pretrained zero-shot TTS models. VoiceTTA introduces two style rewards based on coefficient-of-variation differences of F0 and energy, combined with speaker similarity and intelligibility (WER from a pretrained Whisper model), and optimizes learnable prefixes via group relative preference optimization (GRPO) in a flow matching-based model at inference time. Extensive experiments demonstrate substantial improvements on uncommon speech prompts, outperforming state-of-the-art baselines. Audio samples are available at https://voicetta.pages.dev/ --- ### DiARC: Distinguishing Positive and Negative Samples Helps Improving ARC-like Reasoning Ability of Large Language Models Authors: Yuxuan Yang, Feiyang Li, Yile Wang Published: 2026-06-25 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2606.26530v2 The Abstraction and Reasoning Corpus (ARC) contains tasks that require summarizing patterns from limited grid samples and predicting output grids. Recently, many large language model based approaches have attempted to transform it into a text-based reasoning task. However, methods based on open-source models have generally yielded unsatisfactory results, while those relying on closed-source models are too costly. Current efforts mainly focus on data augmentation, constructing ARC-like data for more comprehensive supervised fine-tuning. In this work, we argue that solving ARC-like problems requires not only positive sample supervision but also the ability to improve model reasoning by distinguishing negative samples. To this end, we draw on the idea of preference alignment and propose DiARC, a method that constructs preference pairs to enable the model to distinguish between them. Specifically, we propose three ways to construct negative samples, including output-level visual transformations, DSL-level rule inversion, and task-specific rule editing. The resulting negative samples provide informative near-miss alternatives while keeping the observed demonstrations unchanged. Experimental results across multiple ARC-like benchmarks show that DiARC consistently improves performance over baseline models. The code is released at https://github.com/szu-tera/DiARC. --- ### The inattentional gap in task conditioned AI models that omit otherwise reportable safety critical signals Authors: Kwan Soo Shin Published: 2026-06-25 Categories: cs.CL, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2606.26529v3 AI in radiology and other safety-critical workflows is evaluated on the hazards it is told to find, yet harm arises disproportionately from hazards no one specified. We show that conditioning a language or vision model on a narrow task suppresses its reporting of co-present, safety-critical signals it can otherwise report, a behavioral analogue of human inattentional blindness. Across radiology text scenarios and thoracic-image vision tasks, ordinary focused instructions suppressed reporting by up to 0.92; the gap ranged from minimal to complete across seven models, did not vary monotonically with scale, and persisted in a reasoning model, while one flagship model showed a robust safety-reporting override. We term this dissociation the Inattentional Gap: a system can score near-perfectly on specified hazards while omitting co-present safety-critical hazards. In a 24-scenario probe, an independent open-ended critic restored every omitted finding. We propose reporting-complete evaluation as an admission criterion for safety-critical deployment. --- ### Safety-Regulated Transfer Reinforcement Learning with Adaptive Teacher Guidance Authors: Wenjie Huang, Yang Li, Jingjia Teng, Mingwei Jin, Kai Song, Zeyu Yang, Qisong Yang, Yougang Bian Published: 2026-06-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.26527v2 We propose Safety-Regulated Adaptive Transfer Reinforcement Learning (SRATRL), a teacher--student framework that combines safety-triggered intervention, safety-adaptive value shaping, and policy-compatibility-based optimization for efficient target-domain adaptation. First, a safety-triggered closed-loop intervention strategy is developed that activates teacher guidance according to the instantaneous safety cost and adaptively adjusts the intervention threshold based on the student policy's recent safety performance, thereby providing timely safety supervision while progressively restoring student autonomy as its safety improves. Next, a safety-adaptive teacher-guided value-shaping scheme is introduced, in which a teacher-consistency signal is incorporated into the critic target, and its contribution is dynamically regulated by the safety-constraint multiplier, enabling stronger teacher guidance under elevated safety risks and gradually weakening such guidance as the safety constraint is better satisfied. In addition, a teacher-student policy-compatibility weighting approach is proposed to alleviate the adverse optimization effects caused by policy mismatch. It reweights teacher-intervened transitions according to the relative likelihood of the executed action under the teacher and student policies, thereby improving policy-update stability. Experimental results demonstrate that compared with a Proximal Policy Optimization with Lagrangian constraint baseline, the proposed method improves the average velocity by 6.90%, and reduces the crash ratio by 75.00%. These results demonstrate that the proposed method can reduce safety costs while maintaining competitive task efficiency. --- ### Theory-Scale Auto-Formalization of Logics for Computer Science Authors: Yuming Feng, Frederick Pu, One An, Osbert Bastani, Li Zhang, Jiani Huang, Xujie Si, Ziyang Li Published: 2026-06-25 Categories: cs.LG, cs.LO, cs.PL arXiv: https://arxiv.org/abs/2606.26525v1 Auto-formalization is critical for scalable formal verification, but existing progress largely focuses on isolated statements, while theory-scale auto-formalization, which coherently translates hundreds of interdependent definitions, lemmas, and theorems, remains open due to challenges in consistency, faithfulness, scalability, and correctness. In this paper, we introduce LCS-Bench, a stand-alone, theory-scale benchmark based on Logics for Computer Science. LCS-Bench is built through a novel semi-automated agentic pipeline that leverages concept graphs, formal signature planning, issue tracking, sorry-filling with counter-example search, complemented by faithfulness review from human experts. The resulting artifact covers 327 textbook items, over 4,076 Lean declarations, and more than 85K lines of Lean code. The dataset supports broad evaluation through a data engine that automatically derives five tracks of evaluation benchmarks, measuring different aspects of auto-formalization and theorem-proving capabilities. We also introduce a novel evaluation protocol featuring definitional equivalence checkers, enabling more fine-grained and faithful assessment. Through extensive evaluation on 14 models, we demonstrate that (1) LCS-Bench is of high quality, consistent, and faithful; (2) the benchmark is challenging, with state-of-the-art models achieving only 20.1% on auto-formalization tasks; and (3) our analysis reveals key findings regarding theory-scale auto-formalization and suggests promising directions for future work. --- ### Radical AI Interpretability Authors: Daniel A. Herrmann, Benjamin A. Levinstein Published: 2026-06-25 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.26523v1 We develop a framework for interpreting AI systems as agents, drawing on the philosophical tradition of radical interpretation and the tools of mechanistic interpretability. The core question is: given the computational facts about a system, how do we solve for its beliefs, desires, and meanings? This matters increasingly for safety. We want to be able to trust the systems we deploy, whether by understanding their goals or, more modestly, by reliably detecting deception. Interpretability researchers are building tools to read beliefs and desires off a model's internals, but there is no settled account of when such a tool has succeeded. This book supplies one. We propose criteria on both representationalist and interpretationist approaches, and tie each to tests current interpretability methods can carry out. A central lesson is that these attributions cannot be made piecemeal. Beliefs, desires, and the propositional structure they presuppose are jointly constrained, and a method that fixes one while measuring the others inherits whatever distortions that introduces. This holism becomes pressing for AI systems, which may not share the interpreter's concepts. However, it also provides leverage: a system's attitudes constrain its propositional structure, that structure constrains which attitudes can be attributed, and mechanistic interpretability can help us measure both. --- ### Assessing Post-Reform Changes in Risk Disclosure Quality with a Multidimensional Text Analysis Approach Authors: Nobuhiro Aikawa, Mitsuo Yoshida Published: 2026-06-25 Categories: cs.CL, cs.DL arXiv: https://arxiv.org/abs/2606.26522v1 While corporate narrative disclosures provide crucial information to capital markets, comprehensively evaluating their qualitative changes over time remains challenging. Narrative text is inherently multidimensional, meaning that an improvement in one textual dimension often occurs alongside changes in others. To capture these underlying dynamics, we propose a longitudinal text analysis approach combining Japanese-language NLP metric extraction with paired testing, shift function analysis, and inter-metric correlation. Our framework extends prior indicator sets by incorporating a cross-section relevance indicator to measure topical alignment between risk disclosures and management strategies. Applying this approach to evaluate Japan's 2019 disclosure reforms, we analyze 19,770 firm-year observations over a 10-year period (FY2015-FY2024). The joint analysis reveals complex shifts in disclosure patterns that are frequently masked by conventional single-indicator methods. Specifically, we find that while disclosure volume increased substantially, it was accompanied by a decline in readability. Furthermore, although the overall information structure improved, specific descriptive quality stagnated, and the degree of adaptation varied across market segments. --- ### Multipath Adaptive Gated Bottleneck Latent ODE with Raman Data Fusion for Cell Culture Process Forecasting Authors: Johnny Peng, Thanh Tung Khuat, Ellen Otte, Katarzyna Musial, Bogdan Gabrys Published: 2026-06-25 Categories: cs.LG, cs.AI, cs.CE arXiv: https://arxiv.org/abs/2606.26520v2 Mammalian cell-culture processes underpin the manufacture of many biopharmaceuticals, yet keeping a run on track is hard: critical process parameters drift over days, and an off-specification trend is often confirmed too late to intervene. Early-stage, multi-day forecasts could enable timely adjustment of feeding, sampling, and control, but bioprocess forecasting is challenging because measurements are sparse and irregularly sampled, operating conditions are heterogeneous across cell lines and media, and runs with near-identical early behaviour can diverge into different futures. We propose an adaptive framework combining a Gated Bottleneck Latent Ordinary Differential Equation (GB-Latent ODE) with Multi-Path Just-In-Time Fine Tuning (MP-JIT-FT). The GB-Latent ODE augments the stan dard Latent ODE with learnable variable-wise gating and a mask-aware bottleneck that compress high-dimensional sparse inputs, improving learning under limited data. Given a partially observed run, MP-JIT-FT retrieves similar historical trajectories, clusters the local neighbourhood into candidate regimes, and fine-tunes a separate model per regime to produce multiple plausible paths, each with a reconstruction-based confidence score, not a single averaged forecast. We further fuse Raman spectroscopy data: a machine-learning soft sensor turns dense Raman spectra into pseudo-observations that enrich the sparse offline measurements for more robust training. On 38 fed-batch 5L bioreactor runs spanning 14 conditions, MP-JIT-FT with Raman fusion achieves the best average rank and outperforms a global Latent ODE baseline on 8 of 9 target variables. Using local-divergence metrics, we show the multi-path gains are largest when locally similar prefixes diverge, whereas Raman fusion helps most when early dynamics are representative of later behaviour. --- ### What the LLM Should Not Say: Boundary-Aware Context Grounding for A Seven-Channel EEG Agent Authors: Zhiyuan Xu, Yueqing Dai, Junling Li, Junwen Luo Published: 2026-06-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.26519v2 Large language models (LLMs) can make scientific software easier to use. However, a general model does not automatically know which measurements a particular sensor can support, which algorithms are implemented in the current software, or which conclusions are justified by a computed result. These distinctions are especially important for low-channel electroencephalography (EEG), where sparse spatial coverage and variable signal quality make plausible but unsupported interpretations easy to produce. We present NeuraDock Agent, an open-source architecture that separates a deterministic local EEG engine from a hardware-aware language layer. The numerical engine parses recordings, performs quality control, executes reviewed spectral workflows, and writes machine-readable artifacts. The LLM receives only a compact, allowlisted summary and a versioned context pack. The context describes the seven-channel hardware, reviewed workflows, result fields, implementation boundaries, scientific limits, and reference cases. Raw EEG and dense per-sample arrays remain local We evaluate the system at three levels. First, 12 recordings produced identical structured results over ten numerical repetitions, and a complete Rest/Task run produced identical result, report, and figure hashes over three repetitions. Second, request-capture and failure-injection experiments confirmed the tested data boundary and preservation of local artifacts under HTTP, malformed-output, and connection failures. Third, a boundary-awareness benchmark tested 36 ordinary and adversarial questions under four context ablations and two LLMs, yielding 288 outputs.These results support hardware- and implementation-aware grounding as a practical mechanism for calibrating what an EEG agent accepts, qualifies, or refuses; they do not establish clinical validity or a validated absolute cognitive-load index. --- ### NeuraDock Visual Cognitive Load Agent Tutorial: A Quality-Gated Open-Source EEG Workflow for Alpha Dynamics and Real-Time Applications Authors: Zhiyuan Xu, Yueqing Dai, Junling Li, Junwen Luo Published: 2026-06-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.26518v1 This tutorial paper provides a step-by-step, reproducible walkthrough of NeuraDock Agent, an open-source EEG agent focused on Alpha dynamics and visual cognitive-load analysis. The goal is practical: a reader should be able to install the agent, run EEG preprocessing and quality control, generate Alpha dynamics figures, perform within-subject Rest/Task visual cognitive-load comparison, run the public mini-dataset analyses and compare them with the reference validation summary, start an online dashboard, call the real-time API from an external application, and use the LLM interpretation layer to explain quality risks. Existing EEG toolkits provide excellent offline analysis, but assembling a real-time, quality-gated cognitive-load pipeline often requires manually bridging acquisition, custom QC, Alpha feature extraction, and a web API; this tutorial closes that offline-to-online gap. The tutorial uses a quality-gated workflow: downstream Alpha and workload metrics are computed only after preprocessing and QC gating rather than directly from raw EEG. In the included mini-dataset validation, the agent processed 18 recordings, generated 10 within-subject comparisons, observed task-related posterior Alpha suppression in 7 of 10 contrasts, estimated initial evidence of within-subject repeatability, and benchmarked local online API latency. The tutorial is intended for researchers, developers, and applied teams who want a transparent path from EEG files to real-time visual cognitive-load prototypes. --- ### Forget, Anticipate and Adapt: Test Time Training for Long Videos Authors: Rajat Modi, Sebastian Noel, Xin Liang, Yogesh Singh Rawat Published: 2026-06-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.26515v3 Test Time Training (TTT) is a mechanism in which a model adapts to an incoming test-sample by performing some self-supervised (SSL) task and updating its weights even during inference. This procedure does not require labels at test-time. This paper focuses on TTT for long-videos. A major concern with existing approaches is: 1) they perform TTT updates using a sliding window containing frames in the past, whose compute increases linearly with the size of window. This becomes computationally intractable when the videos are hours long. 2) TTT is performed even when temporally close frames look similar, thereby consuming a lot of compute. We present the Frame Forgetting Network (FFN) that: 1) operates on only three frames within the sliding window, namely the frame that exits, the current frame and the frame after that. The model still manages to retain temporal context and work for hours long-videos; 2) mathematically define a surprise metric: how much new information the incoming frame contains with respect to the past seen frame. This facilitates determining how to modify the effective window size during TTT and constitutes the core mechanism of an adaptive windowing algorithm. Additionally, we curate a dataset EpicTours containing up to 3 hour long videos of walking city-tours, whereas earlier datasets on this problem were only 5 min long. We demonstrate FFNs empirical effectiveness on dense-segmentation, video classification tasks, generalization to depth-estimation, and multi-hour long videos. --- ### Temporal Validity in Retrieval Memory: Eliminating Stale-Fact Errors for AI Agents over Evolving Knowledge Authors: Neeraj Yadav Published: 2026-06-25 Categories: cs.CL, cs.AI, cs.ET, cs.LG arXiv: https://arxiv.org/abs/2606.26511v1 Retrieval-augmented generation (RAG) gives agents access to accumulated knowledge, but has no model of time. When a fact changes (e.g., a function is renamed or API restructured), RAG retrieves both the stale and current value with near-identical embedding similarity. The agent then either abstains or serves the superseded fact. We show this is a structural problem: on a calibrated dataset, cosine similarity distinguishes a contradicted fact from a duplicated one with AUROC 0.59 (near chance), as contradictions are often more embedding-similar to the original than rephrased duplicates. We present MemStrata, a retrieval memory maintaining temporal validity. It stores facts like RAG, preserving static recall, but when a fact's value is contradicted, a deterministic (subject, relation, object) supersession rule retires the stale value in a bi-temporal ledger - with no similarity threshold and no LLM call. Across six benchmarks run locally with a 7B model, MemStrata ties RAG on static knowledge and reaches 0.95-1.00 accuracy on evolving knowledge (where RAG reaches 0.20-0.47). The central result is the stale-fact-error rate: when required to answer, RAG serves superseded values 15-40% of the time; MemStrata drives this to ~0%, a failure class RAG cannot avoid. MemStrata achieves this at retrieval latency (~2.1s) versus ~16-18s for LLM-reranking baselines. We release the harness, datasets, and a marker-free evaluation protocol for memory under knowledge evolution. --- ### Budget-Aware Keyboardless Interaction Authors: Quang-Thang Nguyen, Gia-Phuc Song-Dong, Minh-Triet Tran, Trung-Nghia Le Published: 2026-06-25 Categories: cs.HC, cs.CV arXiv: https://arxiv.org/abs/2606.26508v1 Interacting with computers typically relies on traditional input devices such as keyboards, mice, and monitors, which can be cumbersome for users seeking greater mobility. Virtual keyboards have been explored to address these limitations, but they often involve complex setups or expensive equipment. This paper proposes a novel virtual keyboard system that leverages only a standard camera and a paper with a printed keyboard layout. Unlike previous methods requiring complex calibration or special lighting conditions, our approach can work on standard environment using modern computer vision technologies. Combining modern segmentation and detection models with traditional image processing algorithms, we efficiently identify the keyboard region. Touch detection is performed using an algorithm analyzing the color of the user's fingernail. Experiments demonstrated a promising results our proposed solution of keyboard and keystroke detection for practical applications. Participants attended our user study also found the proposed system interesting. --- ### DanceDuo: Bridging Human Movement and AI Choreography Authors: Gia-Cat Bui-Le, Tuong-Vy Truong-Thuy, Hai-Dang Nguyen, Trung-Nghia Le Published: 2026-06-25 Categories: cs.HC, cs.CV arXiv: https://arxiv.org/abs/2606.26507v1 In recent years, advancements in deep learning and generative models have revolutionized music-driven dance generation. This paper introduces a novel platform, namely DanceDuo, leveraging diffusion models to generate AI-choreographed dance sequences synchronized with a variety of music genres, to encourage dancing practice. The system allows users to interact with AI by selecting music tracks, humanoid models, and importing personal dance videos for comparison, fostering a rich and engaging user experience. DanceDuo not only offers dance generation but also integrates human pose estimation models to provide users with insightful comparisons of their own performances with AI-generated sequences. We conducted a comprehensive user study, revealing that users found the interface intuitive, with particular praise for the dance comparison feature. Our DanceDuo contributes significantly to the integration of AI in dance choreography, offering novel avenues for both recreational and professional applications. --- ### Humans Disengage, Reasoning Models Persist: Separating Difficulty Registration from Deliberation Allocation Authors: Han-yu Wang Published: 2026-06-25 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2606.26502v5 Large reasoning models (LRMs) tend to produce longer reasoning traces on problems that also take humans longer. This correspondence leaves open how the systems distribute further work on those problems. We distinguish *difficulty registration*, sensitivity to differences in problem difficulty, from *deliberation allocation*, the distribution of further work once difficulty is encountered. We examine both in item-matched data from three reasoning tasks. In visual abstraction (H-ARC), model trace length follows the human ordering of problems by duration. After item identity is controlled, successful human attempts last longer than failed attempts, while failed LRM attempts have longer traces than successful ones in the pooled model analysis. The estimated slopes follow the same pattern in intuitive reasoning (INTUIT). In relational reasoning (Cortes), successful attempts are longer in separate human and model analyses, while a joint fit on shared items finds a human-LRM difference. Longer human attempts include more grid actions. At comparable lengths, failed LRM traces contain more hedging on H-ARC and more repetition on Cortes. A resource-rational account relates these patterns to what further work is expected to achieve and how that progress is valued. The results identify a difference in the allocation of continued work that cross-problem duration alignment alone leaves undetected. --- ### Humans Disengage, Reasoning Models Persist: Separating Difficulty Registration from Deliberation Allocation Authors: Han-yu Wang Published: 2026-06-25 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2606.26502v2 Large reasoning models (LRMs) take longer on harder problems, just as humans do, but that surface similarity hides an opposite pattern within items. When an LRM gets a problem wrong it spends more tokens than when it gets that same problem right; humans do the reverse. We separate two levels of deliberation: how response time tracks difficulty across items (registration), and, with item identity fixed, whether an agent spends more on its own failures or successes (allocation). On a public matched human-LRM corpus, thinking LRMs reproduce the known cross-item alignment with human reaction time but diverge from humans within items: on H-ARC every model lands on the opposite side of zero, the four well-powered ones at Cohen's d = 1.47 to 3.13 against -0.10 for humans. Each agent is scored on its own scale; seconds and tokens never share an axis. The dissociation survives item fixed effects and replicates across datasets; a non-thinking baseline shows a wrong-trial expansion of its own but no cross-item alignment, so part of the effect is not specific to reasoning training. We read the human pattern as engagement versus abandonment: people stay on items they expect to solve and give up on the rest. We read the LRM pattern as length driven by uncertainty: chains grow when the model is unsure, exactly when it tends to fail. Under resource-rational metareasoning these are stopping policies that share a difficulty signal but implement opposite control; trace length captures the signal and misses the control. --- ### Mean-Field PhiBE: Continuous-Time Mean-Field Reinforcement Learning from Discrete-Time Data Authors: Erhan Bayraktar, Martin Hernandez, Qinxin Yan, Yuhua Zhu Published: 2026-06-25 Categories: math.OC, cs.LG arXiv: https://arxiv.org/abs/2606.26498v2 This paper develops a model-free framework for continuous-time mean-field control when the population evolves according to unknown controlled McKean--Vlasov dynamics and only discrete-time transition data are available. Model-based mean-field control requires the continuous-time drift and diffusion coefficients, which are not directly observed from fixed-step transitions, while a direct reduction to a discrete-time Bellman equation loses the continuous-time generator structure. To bridge these two viewpoints, we introduce a Mean-Field-PhiBE (MF-PhiBE), which incorporates discrete-time transition information into a continuous-time PDE on the Wasserstein space. The MF-PhiBE replaces the unknown infinitesimal drift and covariance in the policy-evaluation equation by one-step estimators computed from data, while preserving the generator structure of the McKean-Vlasov HJB equation. We also derive a policy-gradient theorem for entropy-regularized randomized feedback policies, expressing the actor direction through an action-wise infinitesimal advantage and the score of the policy. Combining these two ingredients yields a model-free actor-critic method. We prove a first-order consistency estimate showing that the value induced by an optimal MF-PhiBE policy approximates the optimal continuous-time value as the observation time step vanishes. For entropy-regularized LQR, we establish first-order policy convergence and second-order value convergence; under suitable conditions, the population-averaged feedback means coincide exactly. Numerical experiments on an LQR benchmark and a crowd-aversion problem illustrate the proposed framework. --- ### Mean-Field PhiBE: Continuous-Time Mean-Field Reinforcement Learning from Discrete-Time Data Authors: Erhan Bayraktar, Martin Hernandez, Qinxin Yan, Yuhua Zhu Published: 2026-06-25 Categories: math.OC, cs.LG arXiv: https://arxiv.org/abs/2606.26498v1 This paper addresses model-free continuous-time mean-field control in a setting where the population dynamics evolve continuously according to an unknown McKean-Vlasov stochastic differential equation, while only discrete-time transition data are available. In the model-based formulation, policy evaluation is naturally described by a stationary Hamilton-Jacobi-Bellman equation on $\mathcal P_2(\mathbb R^d)$, but this equation involves the drift and diffusion coefficients of the controlled McKean-Vlasov dynamics, which are not identifiable when only discrete-time data are available. On the other hand, a direct reduction to a time-discrete Bellman equation avoids the non-identifiability issue but loses the differential equation structure. To bridge these two viewpoints, we introduce a Mean-Field-PhiBE (MF-PhiBE), which incorporates discrete-time transition information into a continuous-time PDE on the Wasserstein space. The MF-PhiBE replaces the unknown infinitesimal drift and covariance in the policy-evaluation equation by one-step estimators computed from data, while preserving the generator structure of the McKean-Vlasov HJB equation. We also derive a policy-gradient theorem for entropy-regularized randomized feedback policies, expressing the actor direction through an action-wise infinitesimal advantage and the score of the policy. Combining these two ingredients yields a model-free actor-critic method. We prove a first-order consistency estimate showing that the value induced by an optimal MF-PhiBE policy approximates the optimal continuous-time value with an error of order $Δt$. In the linear-quadratic case, we show our approximation achieves second-order accuracy with only one-step data. Numerical experiments on an LQR benchmark and a crowd-aversion problem illustrate the proposed framework. --- ### Learning Probabilistic Filters with Strictly Proper Scoring Rules Authors: Eviatar Bach, Ricardo Baptista, Jochen Bröcker, Bohan Chen, Andrew Stuart Published: 2026-06-25 Categories: cs.LG, math.DS, stat.ML arXiv: https://arxiv.org/abs/2606.26497v1 Bayesian filtering of partially and noisily observed dynamical systems seeks to infer the evolving conditional distribution of the state of a dynamical system, given observations, in an online fashion. This Bayesian filtering distribution is the natural object for uncertainty quantification, but it is rarely available as a supervised learning target. However, one can often use the forecast model to generate synthetic system trajectories, along with synthetic observations. We introduce the proper scoring ensemble filter (PSEF), an ensemble data assimilation method based on training an analysis map to approximate the filtering distribution using only synthetic state--observation trajectories. The analysis step is represented as a permutation-invariant, transformer-based map that takes as input a forecast ensemble and observations, producing an analysis ensemble. Training is based on strictly proper scoring rules -- with the energy score used in our implementation -- so that probabilistic accuracy is rewarded over the whole probability distribution. We prove that, under a realizability assumption, the population objective is minimized by the true Bayesian filtering distribution. We also derive the finite-ensemble empirical objective used in training and relate its single state--observation trajectory form to the population objective, using a mean-field consistency argument. Numerical experiments show that the learned filter accurately approximates challenging filtering distributions, including nonlinear, non-Gaussian, and multi-modal posteriors, and achieves stronger performance in data assimilation tasks than classical methods or learning-based methods with mean-squared-error objectives. For close-to-Gaussian problems, learning a correction to the EnKF is the best approach, while for highly non-Gaussian problems an end-to-end approach that discards this inductive bias is superior. --- ### Clinical Harness for Governable Medical AI Skill Ecosystems Authors: Tianhan Xu, Lei Bao, Zhe Hu, Tian Shen, Yongxiang Wang Published: 2026-06-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.26494v2 Medical AI remains organized around isolated models, whereas care requires accountable capabilities that persist across time. We define clinical AI skills and propose the Clinical Harness, a runtime governance architecture that registers, orchestrates, constrains and monitors them. Using osteoporosis as an exemplar, we show how knowledge-driven, data-driven and physics-enhanced skills can support lifecycle care and provide a governed substrate for future medical agents. --- ### Nemotron-Labs-TwoTower: Diffusion Language Modeling with Pretrained Autoregressive Context Authors: Fitsum Reda, John Kamalu, Roger Waleffe, Mostofa Patwary, Mohammad Shoeybi, Bryan Catanzaro Published: 2026-06-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.26493v2 Diffusion language models offer a promising alternative to autoregressive models due to their potential for parallel and iterative generation. However, existing approaches use a single network for both context representation and iterative denoising, forcing one model to serve both roles and limiting its capacity for either role. We propose TwoTower, a block-wise autoregressive diffusion model that decouples these roles into two towers: a frozen AR context tower that causally processes clean tokens, and a trainable diffusion denoiser tower with bidirectional block attention that refines noisy blocks via cross-attention to the context. Built on Nemotron-3-Nano-30B-A3B, an open-weight 30B hybrid Mamba-Transformer MoE model, and trained on approximately 2.1T tokens, Nemotron-Labs-TwoTower retains 98.7% of the autoregressive baseline's quality while offering 2.42X higher wall-clock generation throughput. We release the code and model weights at https://huggingface.co/collections/nvidia/nemotron-labs-twotower. --- ### Evaluation-Strategy Gap in Fault Diagnosis of Deep Learning Programs Authors: Sigma Jahan Published: 2026-06-25 Categories: cs.SE, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.26492v1 Deep Learning (DL) programs can fail during training for many reasons, and diagnosing the cause is a costly and time-consuming maintenance task. Techniques for diagnosing such failures are commonly assessed using within-program cross-validation, which may be inadequate for deployment settings involving previously unseen programs. It is therefore necessary to assess how performance differs across these settings and to identify the causes of any performance gap in established fault diagnosis techniques for DL. We investigate this gap using DynFault, a corpus of 5,542 fault-injected training traces from 38 real-world DL programs. We found a gap of 0.190 in balanced accuracy for existing fault diagnosis techniques between within-program evaluation and holding out whole programs. We also found the gap comes from program-level structure in the features, which led us to examine two runtime feature sets, curvature features and optimizer features, and their behavior on unseen programs. We found that curvature features are useful for instability detection on unseen programs, while optimizer and activation features help only on programs seen during training. --- ### An Empirical Study of LLM-Generated Specifications for VeriFast Authors: Wen Fan, Minh Tran, Sanya Dod, Xin Hu, Marilyn Rego, Danning Xie, Jenna DiVincenzo, Lin Tan Published: 2026-06-25 Categories: cs.SE, cs.AI, cs.LO, cs.PL arXiv: https://arxiv.org/abs/2606.26490v1 Static verification tools can assure industrial scale software, but require significant human labor to write specifications. This is particularly true of static verifiers based on separation logic (SL verifiers), which excel at verifying heapmanipulating programs, but require many complex auxiliary specifications to reason about heap structure. Recent work applies large language models (LLMs) to generate code, tests, and proofs, including specifications for verifiers, but mostly targeting non-SL verifiers. To address this gap, this paper thoroughly evaluates how well LLMs perform when prompted to generate specifications for verifying 303 C functions with the SL verifier VeriFast. We explored eight prompting approaches, ten LLMs, and three input types in two stages. Quantitative and qualitative analyses are used to assess the LLM-generated code and specifications for functional behavior, verifiability and errors. The results show that LLMs preserve functional behavior in source code and specifications (both over 91%), but achieve modest verification success (31.4%). Using Gemini 2.5 Pro and providing formal contracts lead to higher success rates in our setting. Moreover, most errors (94%) come from LLMs' mistakes in the domainspecific knowledge of SL verifiers such as VeriFast. These findings provide guidance for optimizing LLM-generated specifications for SL verifiers. --- ### Comparing BERT Sentence-Pair Classification and Few-Shot LLM Prompting for Detecting Threat and Solution Framing in German Climate News Authors: Raven Adam, David Maier, Marie Kogler Published: 2026-06-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.26489v1 News media play a central role in shaping public perceptions of climate change, and whether coverage emphasizes threats or solutions has measurable effects on audience engagement and policy support. Automated detection of these framing patterns at the sentence level would allow researchers to analyze large corpora that are infeasible to code manually. We present a systematic comparison of two approaches for classifying sentences from German-language climate news articles as threat-oriented, solution-oriented, both, or neither. The first approach uses few-shot prompting with an open-weights large language model (Llama 4 Maverick), employing chain-of-thought reasoning and structured output with confidence scoring. The second approach fine-tunes a German BERT model (deepset/gbert-large) for sentence-pair classification, where the preceding sentence provides contextual information for the target sentence. Both approaches implement two independent binary classifiers, one for threat framing and one for solution framing. We evaluate both methods on a corpus of 440 Austrian newspaper articles that were manually coded following a detailed coding scheme developed with domain experts. The fine-tuned BERT classifiers achieve an F1 score of 0.83 for both the threat and solution tasks, while the LLM-based classifiers reach an F1 of 0.78. An ablation study confirms that providing the preceding sentence as context improves BERT classification performance substantially compared to single-sentence input. These results contribute to the growing body of work comparing fine-tuned encoder models with prompted generative models for text classification in computational social science. --- ### What Survives When You Compress a Recursive Reasoner for the Edge? Authors: Pearse Jim, Steven Kolawole, Opegbemi Matthias Busoye, Glory Bagai, Virginia Smith Published: 2026-06-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.26488v1 Recursive reasoning models can solve complex structured tasks with only a few million parameters by repeatedly updating a latent state. Deploying these models on edge hardware requires significant compression, but unlike conventional sequence models, quantization errors compound across recursive reasoning cycles rather than across output tokens. As a result, standard intuitions about compression fail to apply. In this work, we ask what survives when recursive reasoners are compressed. Across a full precision sweep, three tasks, and two recursive architectures, we find that aggressive compression preserves local prediction but destroys global reasoning: cell accuracy holds while puzzle-exact accuracy collapses to zero under naive INT4 pruning, distillation, and linear attention alike. Token-level objectives, including quantization-aware training, cannot repair it. The collapse is architectural -- it strikes MLP-mixing recursion but not attention on the same task -- and we reverse it with per-channel calibrated INT4 without retraining. We also introduce carry-trajectory fidelity, the cosine similarity to the full-precision reasoning path, as a label-free signal that predicts this damage and its recovery before a task evaluation. The combined result is a deployment recipe: flash-streamed embeddings remove a 99.4MB bottleneck, INT8 at one cycle matches full-depth accuracy at 6x fewer FLOPs (8MB SoC), and calibrated INT4 fits a 4MB microcontroller. ---