# Research Papers — 2026-06 · bundle page 140 of 260

> Full-text markdown of papers #6951–7000 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/140
[← Previous bundle](https://aipod.dev/papers/archive/2026-06/page/139.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-06/page/141.md)

### Teacher-Student Structure for Domain Adaptation in Ensemble Audio-Visual Video Deepfake Detection

Authors: Elham Abolhasani, Maryam Ramezani, Hamid R. Rabiee
Published: 2026-06-13
Categories: cs.MM, cs.AI, cs.CV, cs.LG, cs.SD
arXiv: https://arxiv.org/abs/2606.15117v1

The rapid advancement of generative AI models is leading to more realistic deepfake media, encompassing the manipulation of audio, video, or both. This raises severe privacy and societal concerns. Numerous studies in this area have yielded promising intra-domain results; however, these models frequently exhibit decreased efficacy when faced with data from dissimilar domains. Consequently, recent deepfake detection approaches focus on enhancing the generalization ability through multiple techniques that incorporate all input modalities, including audio, images, and their interactions. In this regard, we propose the EAV-DFD method, a generalized deep ensemble audio-visual model (EAV-DFD) combined with a domain adaptation mechanism utilizing a teacher-student framework to enhance the model's ability to perform and generalize effectively across unseen domains. To evaluate the model's performance, we used the FakeAVCeleb dataset as the primary domain and the DFDC, Deepfake_TIMIT, and PolyGlotFake datasets as an unseen domain. Our experimental results demonstrate that the proposed framework is efficient in domain adaptation, improving AUC performance of the model by 4.09%, 17.94%, and 0.5% on three unseen datasets, using only a small portion of them to train the student model. This leads to a novel deepfake detection model capable of adapting to new domains and interpreting which modality has been manipulated, highlighting the potential of our approach for real-world applications.

---

### Diversity-Driven Offline Multi-Objective Optimization via Nested Pareto Set Learning

Authors: Yiyi Zhu, Yaolin Wen, Xiang Xia, Xin An, Hanyi Si, Xiang Shu, Yangde Fu, Liang Dou, Hong Qian
Published: 2026-06-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2606.15115v1

Multi-objective optimization (MOO) has emerged as a powerful approach to solving complex optimization problems involving multiple objectives. In many practical scenarios, function evaluations are unavailable or prohibitively expensive, necessitating optimization solely based on a fixed offline dataset. In this setting, known as offline MOO, the goal is to find out the Pareto set without access to the true objective functions. This setting suffers from the out-of-distribution (OOD) issue, where the surrogate model is not accurate for unseen designs. Due to the OOD issue, surrogate errors may cause the optimizer to select solutions that do not lie on the true Pareto front and are biased toward its extremes. To address this, this paper proposes Diversity-driven Offline Multi-Objective Optimization (DOMOO), which aims to find out a diverse and high-quality set of solutions. First, DOMOO incorporates an accumulative risk control module that estimates the potential risk of candidate solutions and alleviates the OOD issue between the training data and the generated solutions. In addition, a nested Pareto set learning (PSL) strategy is proposed to jointly learn preference and PSL parameters, then optimize them, enabling adaptation to diverse Pareto front geometries. To further enhance solution quality, we design a diversity-driven selection strategy that extracts a representative and well-distributed set of final solutions. To achieve this diversity-driven selection strategy, we propose $\text{IGD}_\text{offline}$, a tailored indicator for the offline setting that considers both diversity and convergence, and avoids the bias of hypervolume indicator. Extensive experiments on synthetic and real-world benchmarks show that DOMOO achieves the best average rank across tasks in both convergence and diversity among the compared methods.

---

### Learn Temporal Consistency For Robust Satellite Video Detector

Authors: Weilong Guo, Shengyang Li, Yanfeng Gu
Published: 2026-06-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2606.15112v1

Satellite video object detection (SVOD) for oriented and fine-grained objects plays an important role in satellite applications. Most existing SVOD methods only focus on one or a few coarse-grained categories of moving objects and represent objects with horizontal bounding boxes. They have difficulty extracting complete, accurate, and consistent information about objects in whole satellite videos. In this paper, we propose a satellite video object detection framework based on Temporal Consistency Learning (TCL). TCL adeptly detects oriented and fine-grained objects by leveraging the rich temporal contexts within satellite videos. The framework integrates three key modules: temporal and fine-grained feature aggregation (TFA), structure encoding (SE), and temporal consistency constraint (TCC). TFA and TCC modules facilitate consistent representation learning across frames, while the SE module encodes both appearance and structural information for precise fine-grained recognition. Experimental results on the SAT-MTB benchmark dataset demonstrate TCL's superior performance, achieving a new state-of-the-art oriented and fine-grained detection accuracy of 47.7% mAP--a 4.8% improvement over the baseline. Furthermore, our TCL framework readily accommodates existing image-based detectors, leading to enhanced detection accuracies.

---

### Physics-Driven Zero-Shot MRI Reconstruction with Non-local Image Priors

Authors: Lingtong Zhang, Wenlei Li, Mu He, Li Xiao, Yang Ji
Published: 2026-06-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2606.15110v1

Zero-Shot Self-Supervised Learning (ZS-SSL) has emerged as a promising paradigm for accelerated Magnetic Resonance Imaging (MRI) reconstruction, eliminating the reliance on fully-sampled external datasets. However, learning solely from a single under-sampled scan suffers from supervision scarcity and optimization instability, often leading to overfitting or artifacts. To address these challenges, we propose a robust physics-driven ZS-SSL framework that synergizes physical consistency with image-domain non-local priors. Our method introduces three core innovations: (1) a Coil Sensitivity Map (CSM)-Guided Dynamic Repository, which stabilizes the training trajectory by filtering physically inconsistent artifacts based on coil sensitivity constraints; (2) a SPIRiT-based regularization, which enforces k-space self-consistency via a learned correlation kernel and stochastic masking; (3) a Non-Local Self-Similarity (NSS) Pixel Bank, which leverages the high-fidelity reference established by the former modules to explicitly mine non-local anatomical similarities, thereby augmenting supervision in the image domain. Extensive experiments on the FastMRI dataset demonstrate that our approach achieves state-of-the-art performance, particularly under high acceleration factors, effectively bridging the gap between zero-shot learning and supervised methods. The code is available at https://github.com/Zolento/NS-SSL.

---

### Towards Verifiable Agentic Data Science: Solving Irregular TSQA Via Tool-Grounded Reasoning

Authors: Sanhorn Chen, Xiaoyang Chen, Boyu Liu, Roy Zhao
Published: 2026-06-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2606.15107v1

Time series data in real-world deployments is overwhelmingly irregular. Observations are asynchronous, missing values are informative rather than random, and sampling frequencies vary across sensors and operational windows. However, existing Time Series Question Answering (TSQA) benchmarks mostly assume regularly sampled inputs, leaving a fundamental gap in understanding how large language models (LLMs) and AI agents perform under irregular conditions. To bridge this gap, we introduce IRTS-ToolBench, a benchmark of 1,700 questions spanning 10 task types across 13 domains. IRTS-ToolBench is designed to be used independently by any researcher working on LLM-based irregular time series analysis, providing standardized inputs and a reproducible evaluation protocol. Code can be found in https://github.com/SanhornC/IRTS-ToolBench.

---

### Text-Driven Fusion for Infrared and Visible Images: Achieving Image Scene Adaptation on Hyperbolic Space

Authors: Huan Kang, Hui Li, Tianyang Xu, Tao Zhou, Xiao-Jun Wu, Josef Kittler
Published: 2026-06-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2606.15104v1

Infrared and visible image fusion aims to integrate complementary modalities, while existing Euclidean methods impose rigid distance metrics that distort multi-modal interactions and parent-to-child semantic hierarchies. To overcome these limitations, we introduce a text-driven fusion framework empowered by hyperbolic manifold learning. During training, BLIP-extracted text prompts serve as topological anchors within the hyperbolic space, guiding vision-attribute alignment through hyperbolic embeddings that naturally accommodate varying semantic granularities. By exploiting the exponential volume growth dictated by the Poincaré ball's negative curvature, this approach seamlessly embeds hierarchical trees to encode coarse-to-fine semantics without metric saturation, while the vast peripheral space prevents texture distortion during cross-modal fusion. At inference, the fusion process autonomously adapts to input content using the learned text-attribute priors, completely eliminating the need for textual input. Experimental results show our method outperforms state-of-the-art approaches on benchmark datasets, with code available at https://github.com/Shaoyun2023/TEDFusion.

---

### Think Less, Act Early: Reinforced Latent Reasoning with Early Exit in Vision-Language-Action Models

Authors: Dianqiao Lei, Lianlei Shan
Published: 2026-06-13
Categories: cs.CV, cs.LG, cs.RO
arXiv: https://arxiv.org/abs/2606.15099v1

Existing Vision-Language-Action (VLA) models predominantly rely on explicit Chain-of-Thought (CoT) reasoning to bridge perception and action. While effective, this paradigm suffers from high computational costs and error propagation in multi-step tasks. In this paper, we propose Adaptive Variable Alignment VLA (AVA-VLA), a novel Latent Reasoning VLA framework that models reasoning as a sequence of unobservable latent variables, bypassing the need for explicit text generation. However, latent trajectories are inherently susceptible to noise interference and misalignment with downstream objectives. To address this, we introduce a Reinforcement Learning-based Denoising mechanism that treats latent state generation as a sequential decision process, optimizing reasoning trajectories via task-level rewards. Furthermore, we incorporate an Early-Exit Strategy that adaptively terminates reasoning based on state confidence, enabling a dynamic trade-off between depth and efficiency. Extensive experiments on embodied decision benchmarks demonstrate that AVA-VLA achieves a 6x inference speedup over explicit CoT methods while attaining a 98.3% average success rate on LIBERO, improving both efficiency and long-horizon stability over full-reasoning baselines.

---

### VGPT-RSI for RH-Adjacent Formal Progress: Boundary Certificates, Verified Finite Lagarias Inequalities, and Explicit Failure Localization

Authors: Zhixin Hu, Tao Xu, Xiaodian Sun, Li Jin, Momiao Xiong
Published: 2026-06-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2606.15096v1

The Riemann Hypothesis remains one of the central unsolved problems in mathematics. Rather than claiming proof, we investigate whether a verifiable AI-assisted reasoning system can produce reliable, formally checked partial progress while explicitly identifying the remaining mathematical obstructions. We apply the Verifiable Growing Physical Transformer with Recursive Self-Improvement (VGPT-RSI) to two RH-adjacent certification tasks. First, we construct and verify a finite RH-boundary certificate for inequality on a parameterized safe lower curve over a region. The numerical boundary curve is converted into a certificate-backed lower curve, audited using outward-rounded interval arithmetic and Arb/FLINT ball arithmetic, and then checked in Rocq/CoqInterval for the parameterized theorem. Second, we initiate a formal Lagarias-route certificate. Lagarias criterion states that RH is equivalent to the global inequality. We formalize the finite quantity and produce a Coq-checked finite certificate. The final system identifies the exact unresolved mathematical bottlenecks: formalizing the Lagarias equivalence, proving the global tail theorem beyond any finite cutoff, and potentially reducing counterexamples to colossally abundant or related extremal integers. These results demonstrate that VGPT-RSI can produce certified RH-adjacent formal progress, organize proof dependencies, and avoid overclaiming when the remaining obstruction is genuinely mathematical.

---

### High-Dimensional Random Projection for Activation Steering in Language Models

Authors: Minh-Hieu Pham, Bach Do, Laziz Abdullaev, Tan Minh Nguyen, Khoat Than
Published: 2026-06-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2606.15092v1

Activation steering has emerged as a key methodology for controlling the behavior of large language models (LLMs). Existing difference-in-means based methods, however, are fundamentally limited: they capture only mean differences between class activations and fail to recover discriminative signals that naturally exist in the nonlinear feature subspace under the superposition hypothesis. Motivated by that, we propose High-Dimensional Random-projection for Activation Steering (HiDRA), a training-free approach that integrates seamlessly with existing activation steering methods. By performing activation addition in the projected high-dimensional space, HiDRA can provably capture a better discriminative structure beyond the reach of linear methods. Experiments across diverse LLM families and benchmarks demonstrate that HiDRA consistently outperforms baseline counterparts, achieving stronger behavioral control without significant computational overhead.

---

### Sensory Restoration via Brain-Computer Interfaces: A Unified 2 x 2 Framework and Convergence Roadmap

Authors: Xuan-The Tran
Published: 2026-06-13
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2606.15091v2

Millions of individuals worldwide suffer from sensory and communication deficits caused by neurodegenerative diseases, stroke, or trauma. Brain-computer interfaces (BCIs) offer a promising avenue for sensory and motor restoration. However, the scientific literature remains highly fragmented between invasive neuroprosthetics and non-invasive electrophysiological decoders, with a lack of consistent terminology and comparison metrics. This chapter proposes a unified 2 x 2 framework categorizing BCIs along two axes: degree of invasiveness (invasive vs. non-invasive) and signal direction (afferent sensory-IN vs. efferent sensory-OUT). We define and distinguish the paradigms of restoration, substitution, and augmentation. Furthermore, we outline a structural roadmap for the convergence of these modalities over near-, medium-, and long-term horizons, focusing on physical limits and the integrative role of machine learning foundation models.

---

### When the Same Musical Knowledge Forgets Differently: A Clean Probe of Pathway-Dependent Forgetting

Authors: Yu Liu, Zhiwei Yang, Wenxiao Zhang, Cong Cao, Fangfang Yuan, Kun Peng, Haimei Qin, Lei Jiang, Jin B. Hong, Hao Peng, Yanbing Liu
Published: 2026-06-13
Categories: cs.SD, cs.CL, eess.AS
arXiv: https://arxiv.org/abs/2606.15088v2

A model can learn that the piano piece Für Elise is calm and reflective by listening to the audio or by reading a text description, but does it matter which route that knowledge took when it is later at risk of being forgotten? Forgetting research in multimodal models measures what knowledge is lost under adaptation, yet has not asked whether acquisition route affects how easily that knowledge is forgotten. We call this untested premise the Pathway-Invariant Assumption. Music understanding enables a clean test because a music clip and a canonical text description can be aligned to the same perceptual content, allowing the same knowledge unit to enter a model through listening or reading while the target remains fixed. Across multiple architecturally distinct audio-language models, we observe a consistent asymmetry: text-pathway knowledge is forgotten more than matched audio-pathway knowledge under identical adaptation pressure. To attribute this effect to route rather than confounds, we introduce the Paired Pathway Controlled Protocol (PPCP), a three-phase design that establishes matched pathway baselines, activates both pathways under symmetric supervision on the same knowledge pool, and applies identical forgetting pressure to both pathways. The gap is stable across models and gain-controlled analyses, persists when contradictory overwrite is replaced by correct-label cross-domain learning, remains under single-modality pressure, and is not removed by lightweight replay. Two independent routing-depth controls confirm that the effect is not explained by architectural depth, pointing to input representation as the dominant factor. Under PPCP, our results demonstrate that forgetting is highly route-dependent, establishing acquisition route as a new analytical dimension for forgetting research and multimodal system design.

---

### An Integrable Token Mixing Layer from the Generalized Yang Baxter Equation

Authors: Snigdha Chandan Khilar
Published: 2026-06-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2606.15085v1

The YB Mixer is a sequence token mixing layer derived from free fermion and generalized Yang Baxter structures. It applies a core principle from integrable systems where a local algebraic constraint guarantees global computational stability. By using the Ising exchange algebra the mixer creates a free fermionic structure that acts as an exactly norm preserving orthogonal map. This algebra also produces commuting transfer matrices which allow inference to be order free and adaptable to any variable budget. To ensure the model can generalize to longer sequence lengths it uses a spectral circulant generator. This generator maintains the crucial orthogonal and commuting properties of the system. The result is a highly stable and mathematically grounded architecture for sequence processing.

---

### AdaMame: A Training Recipe for Adaptive Multilingual Reasoning

Authors: Dayeon Ki, Kevin Duh, Marine Carpuat
Published: 2026-06-13
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2606.15080v1

While Large Reasoning Models (LRMs) show strong performance in English, they often fail to reason in the language of the query, a phenomenon known as language collapse. Existing RL-based fixes typically add a binary language fidelity reward to the accuracy objective, yet still incur trade-off in accuracy, mid-trace code-switching, and excessive token usage. In this work, we propose AdaMame, a two-stage training recipe for multilingual mathematical reasoning that addresses these limitations by adaptively aligning the reasoning language to the query language without compromising accuracy. The first SFT stage fine-tunes on naturally occurring reasoning traces across five languages to establish multilingual reasoning capability. In the subsequent RL stage, we introduce AdaMame-GRPO, an adaptation of Group Relative Policy Optimization (GRPO) in which a query-conditioned alignment factor grows progressively during training, guiding the model to first explore diverse reasoning languages before exploiting reasoning in the query language. Evaluated across two benchmarks, two LRMs, and 12 languages, AdaMame-GRPO achieves Pareto-optimal performance across reasoning accuracy, language fidelity, and token efficiency over all baselines, with the strongest gains on out-of-domain, lower-resource languages.

---

### Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale

Authors: Ang Li, Ben Liu, Bin Han, Bin Hu, Bin Jing, Binbin Hu, Bing Li, Cai Chen, Caizhi Tang, Changxin Tian, Chao Huang, Chao Zhang et al.
Published: 2026-06-13
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2606.15079v1

Efficient and scalable agentic intelligence requires models that can deliver both low-latency responses and strong reasoning capabilities while remaining practical to train, serve, and deploy. In this report, we present Ling-2.6 and Ring-2.6, a family of models designed to address this challenge at scale. Ling-2.6 is optimized for instant response generation and high capability per output token, whereas Ring-2.6 is tailored for deeper reasoning and more advanced agentic workflows. Instead of training from scratch, we upgrade the Ling-2.0 base model through architectural migration pre-training and large-scale post-training. This upgrade is guided by a unified co-design of model architecture, optimization objectives, serving systems, and agent training environments, enabling improvements in both model capability and deployment efficiency. At the architectural level, we introduce a hybrid linear attention design that integrates Lightning Attention with MLA, improving the efficiency of long-context training and decoding. To further enhance token efficiency, we optimize capability per output token through Evolutionary Chain-of-Thought, Linguistic Unit Policy Optimization, bidirectional preference alignment, and shortest-correct-response distillation. For agentic capabilities, we propose KPop, a reinforcement learning framework designed to support stable training of Ring-2.6-1T on large-scale environment-grounded data. KPop improves training efficiency through asynchronous scheduling across coding, search, tool use, and workflow execution, enabling scalable learning from complex agent-environment interactions. Together, Ling-2.6 and Ring-2.6 provide a practical pathway toward efficient, scalable, and open agentic systems. We open-source all checkpoints in the 2.6 family to support further research and development in practical agentic intelligence.

---

### Cognitive Debt: AI as Intellectual Leverage and the Dynamics of Systemic Fragility

Authors: Shuchen Meng
Published: 2026-06-13
Categories: cs.AI, cs.GT, physics.soc-ph
arXiv: https://arxiv.org/abs/2606.15078v1

We develop a formal theory of cognitive debt: the stock of unverified reasoning obligations that accumulates when individuals use AI as a substitute rather than a complement for first-principles cognition. The model features two state variables per agent, cognitive capital and cognitive debt, and a multiplicative production technology in which cognitive capital functions as collateral that determines the return to AI adoption. We establish six propositions. Rational agents incur positive cognitive debt because the costs are deferred, partially external, and masked by short-run productivity gains. Tranquil periods lower subjective risk assessments, raise AI substitution intensity, and compound leverage, generating a cognitive Minsky moment in which subjective risk falls while true systemic fragility rises. Expected crisis losses are convex in aggregate leverage. Post-crisis, output-target pressure can produce a false-correction loop in which agents patch AI failures with more AI. The decentralised equilibrium over-adopts substitutive AI relative to the social optimum because of systemic risk, cognitive public goods, and arms-race externalities. In a two-type heterogeneous-agent economy, high-cognitive-capital agents adopt AI more intensively and may eventually erode their unaided cognitive capital below that of initially lower-skilled agents.

---

### Risk-Aware LLM Agents for Geospatial Data Retrieval: Design and Preliminary Adversarial Evaluation

Authors: Kyle Gao, Joel Cumming, Jonathan Li, Linlin Xu, David A. Clausi
Published: 2026-06-13
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2606.15077v1

We present an LLM-driven framework for retrieving remote sensing data from cloud-based geospatial catalogues using natural language queries. The system converts user intent into structured API calls, enabling efficient access to satellite imagery and environmental datasets. The architecture integrates three agents: Guardrail for safety and policy enforcement, General-QA for intent interpretation, and Recommender-Analyst for schema-aware API call generation. This coordinated design ensures reliable, semantically aligned interaction with external data services. The modular framework is portable across platforms through API schema substitution and supports applications in environmental monitoring, disaster response, and climate analysis. It establishes a scalable interface between user intent and geospatial infrastructure, enabling streamlined and automated Earth observation workflows. Preliminary experiments under adversarial multi-turn settings show that prompt-level safety instructions improve robustness, although rare high-impact failures persist in API manipulation scenarios and highlight the need for adaptive, system-level defenses that balance safety, usability, and cost efficiency, which motivates the use of our intercept-level Guardrail agent.

---

### TriAdReview: Triangular Adversarial Review Architecture for Multi-Model Technical Document Generation

Authors: Zhiqiang Zhou, Junliang Dai, Xu Ling
Published: 2026-06-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2606.15074v1

Large language models (LLMs) are increasingly used for technical document generation, yet single-model outputs often suffer from over-engineering, security blind spots, and incomplete coverage. We propose TriAdReview, a triangular adversarial review architecture that employs two independent reviewer models (engineering and boundary perspectives) and a triangular judging mechanism to iteratively improve a generator model's output. We evaluate TriAdReview across five benchmark tasks - architecture design, code generation, proposal review, security audit, and requirements analysis - using three configurations: single model (baseline), dual model (single review), and triple model (full system). Results across 75 experiments (n=5 per cell) show that the triple model configuration achieves a 10.1% overall improvement over the single model baseline (26.2 vs. 23.8 out of 50; p<0.05, paired t-test), with particularly strong gains on security audit (+27.6%), code generation (+20.8%), and architecture design (+15.6%). A second scorer (mimo-v2.5-pro) confirms the direction with a smaller effect (+2.7%), suggesting moderate inter-rater agreement. However, the system shows a -7.5% degradation on requirements analysis, revealing that adversarial review architectures have a structural bias toward simplification that is counterproductive for completeness-oriented tasks. We analyze this boundary condition through a task-type framework and demonstrate that reviewer prompt adaptation partially mitigates the issue. Our findings provide the first empirical characterization of when multi-model adversarial review helps versus harms, with implications for the design of collaborative AI systems.

---

### Texture-Shape Bias Balancing for Robust Synthetic-to-Real Semantic Segmentation in Automotive NIR Imagery

Authors: Felix Stillger, Ben Hamscher, Lukas Hahn, Annika Mütze, Tobias Meisen, Kira Maag
Published: 2026-06-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2606.15072v1

Semantic segmentation is a fundamental component of visual perception in modern automotive systems, enabling pixel-level scene understanding. Near-Infrared imaging (NIR) offers stable detection under difficult illumination conditions, but the development of domain-specific semantic segmentation models remains challenging due to the lack of high-quality annotated data from real-world scenarios. Synthetic datasets offer a scalable alternative, but models trained on synthetic images often suffer performance degradation when transferred to real domains. We present the first systematic study on synthetic to real domain adaptation for semantic segmentation in NIR images in the automotive domain. We propose a generative augmentation framework that transforms synthetic images into realistic NIR-style variants via our introduced target style adaptation (TSA). TSA fine-tunes a latent diffusion model via low-rank adaptation on a small curated set of real NIR images and applies it to synthetic training data using structure-preserving multi-signal conditioning. To reduce texture bias and improve segmentation robustness, we further apply a Voronoi-based style diversification strategy (VSD) that modifies the original textures while preserving scene geometry. Experiments with multiple model architectures on NIR data from vehicle interiors and street scenes show that balancing inductive bias during training leads to noticeably more robust semantic segmentation and effectively reduces the domain gap in our real-world scenarios by up to 63.6% on exterior and 28.4% on interior data. The code is available at GitHub.

---

### Stop When Further Reasoning Won't Help: Attention-State Adaptive Generation in Reasoning Models

Authors: Jiakai Li, Ke Qin, Rongzheng Wang, Yizhuo Ma, Qizhi Chen, Muquan Li, Shuang Liang
Published: 2026-06-13
Categories: cs.CL
arXiv: https://arxiv.org/abs/2606.15070v1

By incorporating test-time compute scaling, large reasoning models (LRMs) can solve complex problems through explicit chain-of-thought (CoT) reasoning processes. However, they often suffer from overthinking, resulting in redundant token outputs and degraded accuracy. Current methods to mitigate this issue remain limited: training-based approaches require substantial computational resources, while training-free methods rely on well-crafted prompts or unreliable confidence signals. In this work, we investigate early stopping from the perspective of attention distributions and propose a simple method, ASAG, which infers the model's reasoning state and adaptively adjusts the generation strategy. The proposed framework is training-free and plug-and-play, enabling seamless integration into existing LRMs. Extensive experiments on nine benchmarks demonstrate consistent improvements across mainstream LRMs with varying parameter scales, including the DeepSeek-R1-Distill and Qwen3 series. Specifically, ASAG improves average accuracy by 3.2% while reducing the number of generated tokens by nearly 40% across all reasoning tasks on Qwen3-8B.

---

### CoCoGEC: Counterfactual Generation for Robust Grammatical Error Correction

Authors: Qianyu Wang, Xiaoman Wang, Yuanyuan Liang, Xinyuan Li, Yunshi Lan
Published: 2026-06-13
Categories: cs.CL
arXiv: https://arxiv.org/abs/2606.15069v1

Grammatical error correction (GEC) systems are usually trained and evaluated on GEC benchmarks, but their performance often drops sharply once the surrounding context is slightly perturbed or extended. This indicates that the existing GEC models usually fail to understand the error patterns in the varying contexts. In this paper, we thoroughly investigate the counterfactuals for GEC tasks, where the subtle changes to the contexts could lead to the label flipping issue. We propose CoCoGEC, a counterfactual generation framework that creates copies of training instances with error-irrelevant contexts altered. Our framework systematically generates counterfactuals by (1) generating intra- and inter-sentence counterfactuals that maintain the error patterns as well as syntax of the original instances by altering the word-level and sentence-level contexts; (2) revising the generated counterfactuals by selecting the instances with flipped labels and high GEC Mutual Information (MI) coefficient. Extensive experiments show that our method substantially improves the stability of GEC models, outperforming a set of data augmentation baselines. Particularly, it could achieve absolute F0.5 gains of +9.9, +11.3, and +20.8 points on the perturbed BEA-19*,CoNLL-14*, and TEM-8* data set.Our code is released at https://github.com/Quinnok/CoCoGEC

---

### Phase-Localized Curation Does Not Help: A Negative Result on Per-Phase Metric Selection for Demonstration Filtering

Authors: Aarav Bedi
Published: 2026-06-13
Categories: cs.LG, cs.RO
arXiv: https://arxiv.org/abs/2606.15064v1

Manipulation demonstrations have temporal phase structure, and a natural hypothesis is that demonstration-curation metrics should be applied within phases rather than globally. The idea is to segment each trajectory into phases, score each phase with the metric that is locally most informative, and then aggregate. This follows directly from prior work showing that a single global metric can be the best detector of a defect and yet the worst curator of the resulting policy. We test the per-phase hypothesis on three contact-rich LIBERO pick-and-place tasks with a controlled early-release structural defect, comparing phase-gated curation against the same metrics applied uniformly and against a strong single global metric. Across all three tasks and five random seeds per condition, phase-gated curation is never the best curation strategy, and it is the worst of the three on two of the three tasks (Task 1: 86.0 vs. 92.0 for global; Task 3: 22.7 vs. 48.0 for uniform). We trace the failure to a concrete mechanism. When the defect signal is concentrated in a single phase, rank-aggregating across phases dilutes that signal with uninformative scores from defect-free phases, selecting a worse demonstration subset than simply applying the defect-informative metric everywhere. We further show that the per-phase metric selection does not transfer across tasks, since no phase shares a winning metric between any two tasks, so the selection cannot be reused and must be re-derived per task from a noisy sweep. These results bound a plausible and previously untested method, and they argue that practitioners should prefer identifying a single defect-informative metric over decomposing curation by phase. We release the full pipeline, all metric implementations, and per-seed results.

---

### A Practical Evaluation Method for Long-Form Simultaneous Speech-to-Speech Translation

Authors: Yulin Xue, Siqi Ouyang, Lei Li
Published: 2026-06-13
Categories: cs.CL
arXiv: https://arxiv.org/abs/2606.15059v1

Simultaneous speech-to-speech translation (SimulS2ST) enables real-time cross-lingual communication, but existing evaluation has focused largely on short or pre-segmented speech rather than long-form, continuous input. Prior approaches are difficult to reproduce and make assumptions that do not hold for end-to-end systems. We present a practical evaluation method for long-form SimulS2ST. Given source speech, pre-segmented source transcripts, and reference translations, we run automatic speech recognition (ASR) and forced alignment on the generated target speech to recover token-level timestamps, then apply a sentence-embedding-based aligner to match the target text to its corresponding source sentences. This enables sentence-level computation of latency and quality metrics, including YAAL and xCOMET, which are then aggregated into final system-level scores. Experiments on representative SimulS2ST systems show that the method is effective in practice and reveal that current systems suffer from substantial latency accumulation on long speech.

---

### Machine Learning and the Random Walk Puzzle: Forecasting the CAD/USD Exchange Rate with Expanding Window Evaluation and SHAP Interpretability

Authors: Louis Agyekum, Edmund Fosu Agyemang, Obu-Amoah Ampomah, Kofi Acheampong, Emmanuel Boadi, Priscilla Yaa Amakye, Fafa Shalom Tchorly, Enock Adu Bonsu, Eric Nyarko
Published: 2026-06-13
Categories: cs.LG, stat.AP
arXiv: https://arxiv.org/abs/2606.15058v1

This study examines whether machine learning (ML) models can outperform the naive random walk benchmark in forecasting the monthly USD/CAD exchange rate. Using daily data from the Bank of Canada spanning January 2017 to May 2026, resampled into 113 monthly observations, five ML models are evaluated: linear regression, random forest, gradient boosting, XGBoost, and AdaBoost. These models are benchmarked against the naive random walk model and exponential smoothing with Holt-Winters seasonality (ETS). All models are evaluated using an expanding-window framework to maintain strict out-of-sample integrity, and forecast-accuracy differences are assessed using the Diebold-Mariano (DM) test. Structural break detection identifies four significant breakpoints in the series, corresponding to the escalation of the US-China trade war in 2018, the COVID-19 economic recovery in 2020, the peak of the Bank of Canada rate-hiking cycle in 2022, and the start of the Bank of Canada rate-cutting cycle in 2024. SHAP, or Shapley Additive Explanations, analysis is applied to interpret the drivers of the best-performing ML model. The results show that the naive random walk model remains a formidable benchmark. Linear regression is the only model that statistically outperforms the naive random walk model, with a DM statistic of 3.0585 and a p value of 0.0071, whereas the ML ensemble models show only marginal differences. Random Forest with an expanding-window framework achieves the lowest MAPE of 1.17 percent among all models except the random walk. SHAP analysis confirms that short-term lags, particularly lag1 and lag2, and recent rolling means dominate predictions, consistent with the near-random-walk behavior of exchange rates.

---

### AutoDojo: Adaptive Black-Box Attacks Reveal the Limits of IPI Defenses and Task-Specification Effects in LLM Agents

Authors: Xinhang Ma, Taoran Li, Chaowei Xiao, Zhiyuan Yu, Ning Zhang, Yevgeniy Vorobeychik
Published: 2026-06-13
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2606.15057v2

Indirect prompt injection (IPI) is a major security threat to LLM-powered agents. Thus, a growing body of work have proposed a variety of defensive approaches against IPI. These can be grouped into three broad categories: 1) prompt-based (using prompting as a way to prevent agents from following malicious instructions), 2) detection-based (identifying and filtering malicious instructions), and 3) system-level (using systems insights, such as control and data isolation, for defense). However, commonly used benchmarks for evaluating defense, such as AgentDojo, are \emph{inherently static}, generating a fixed distribution of IPI attacks. Consequently, static benchmarks do not usefully evaluate defense robustness to adaptive threats. We address this issue by developing AutoDojo, an adaptive extension of AgentDojo that optimizes IPI against a given defense. Using AutoDojo against state-of-the-art IPI defenses across three task suites and five target models, we make two key observations. First, many defenses offer only limited protection: a cheap, black-box adaptive attack using a frontier LLM to iteratively optimize the injection raises attack success rate (ASR) well above the level achieved by static injections against nearly all evaluated defenses. Against a filter that reduces static ASR to 0\%, AutoDojo recovers 28\% overall and 64\% on action-open tasks. Second, for prompt-level and filter-based defenses, ASR is substantially higher on \emph{action-open} tasks -- where the user's request delegates the action itself to attacker-controlled content -- than on precisely specified tasks. This is a structural limit: on such tasks the injection can pose as ordinary data rather than an explicit instruction, bypassing defenses that rely on detecting instruction-like text. AutoDojo is publicly available at https://github.com/xhOwenMa/AutoDojo.

---

### Bridging Geographic Bias in Urban Streetscape Inference via Lifelong Learning with Visual-Semantic Pivoting

Authors: Xinze Zhang
Published: 2026-06-13
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2606.15055v1

Visual perception of urban streetscapes underpins evidence-based decisions in landscape planning, public health, and place-making. Yet models trained on a few well-photographed metropolises systematically misjudge underrepresented districts, propagating geographic bias into downstream policy. We address this gap with HVSP-LL, a lifelong learning framework that couples a stratified visual-semantic pivoting module with an equity-aware rehearsal mechanism. The pivoting module organises landscape concepts along a three-tier ontology (macro structure, meso composition, micro element) and aligns image features to learnable semantic anchors at each tier, providing transferable representations that resist distributional drift. The lifelong adaptation component sequentially absorbs new urban regions while constraining inter-region perception gaps through a worst-region sample-reweighting objective and a structurally-aware exemplar buffer. We evaluate HVSP-LL on a panoramic streetscape benchmark assembled from twelve cities across four continents and seven perceptual dimensions. The framework attains 0.834 Spearman correlation on the held-out city sequence, an absolute 6.1 point improvement over the strongest continual baseline, and shrinks the inter-city perception gap to 0.094 -- a 38% reduction relative to the strongest continual baseline (0.151) and a 57% reduction relative to a representative regularisation baseline (0.218). Ablations confirm that each tier of the pivoting hierarchy contributes monotonically, and the equity-aware rehearsal converts mean backward transfer from -0.038 (without retention) to +0.013, eliminating catastrophic forgetting on the held-out sequence. Our results indicate that hierarchical anchoring is a practical pathway toward geographically equitable streetscape inference at city scale.

---

### Size Doesn't Matter: Cosine-Scored Sparse Autoencoders

Authors: Silen Naihin, Lev Stambler
Published: 2026-06-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2606.15054v2

Sparse autoencoders (SAEs) detect features via inner product, so a feature's activation scales with both its directional alignment and the input's norm. Features that fire on token norm therefore claim dictionary slots regardless of content alignment. This matters because sublayer normalization has already discarded the magnitude the score measures, so the encoder detects a quantity the model does not read. We replace the score with a learned blend of cosine similarity and input magnitude, letting the optimizer choose how much norm to use; a per-feature extension lets each feature decide independently. In both regimes, training is free to recover inner product but never does, with no feature ever choosing more than half-magnitude dependence. At matched reconstruction, the cosine encoder learns features that align with human-recognizable concepts far more often than standard, filling dictionary slots that inner product wastes on norm detectors. Loss reweighting that equalizes gradients barely closes the gap, confirming forward-pass score geometry as the lever. The advantage is not universal across tasks or depths, but we believe cosine scoring should be the default for dictionary learning on normalized representations.

---

### Physics-conforming Latent Twins

Authors: Matthias Chung, Yutong Bu, Deepanshu Verma
Published: 2026-06-13
Categories: cs.LG, math.NA
arXiv: https://arxiv.org/abs/2606.15053v2

Surrogate models are central to scientific machine learning, where they enable fast prediction, simulation, inference, and control for complex physical systems. For time-dependent problems, however, accurate interpolation of training trajectories is not sufficient: reliable surrogates should also respect the conservation laws, invariants, admissibility conditions, and dissipative structures that give those trajectories physical meaning. We introduce Physics-conforming Latent Twins, a framework for learning latent surrogate solution operators whose dynamics satisfy selected physical principles by design. The method builds on the Latent Twin formulation by jointly learning an encoder, a decoder, and a latent flow map between arbitrary time-indexed states, while constraining the latent dynamics to preserve or dissipate prescribed structural quantities. We develop a constraint-transfer viewpoint that connects physical structure in the original state space with compatible constraints in latent space, and prove structure-preservation bounds showing how latent enforcement improves control of physical defects after decoding. We also derive algebraic conditions for latent flow maps that preserve linear and quadratic invariants or enforce dissipative inequalities. Numerical experiments on representative ODE and PDE benchmarks demonstrate improved constraint satisfaction, structural fidelity, and qualitative long-time behavior while maintaining accurate surrogate prediction.

---

### PANDA: An LLM-Enhanced Performance-Driven Analog Design Framework Bridging Design Intent and Layout Generation

Authors: Haoyi Zhang, Weijian Fan, Xiaohan Gao, Bingyang Liu, Runsheng Wang, Yibo Lin
Published: 2026-06-13
Categories: cs.AR, cs.AI
arXiv: https://arxiv.org/abs/2606.15052v1

Traditional design of analog circuits heavily relies on manual interventions across topology, sizing, and layout, with prior automation addressing stages in isolation. In this work, we propose PANDA, an LLM-enhanced framework that bridges high-level design intent to final layout by actively managing cross-stage dependencies through guided topology synthesis, substructure-aware sizing, and constraint-driven layout generation. This shifts automation from algorithm-centric execution to intent-centric co-design, reducing turnaround time from days or weeks to hours while improving design performance.

---

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

Authors: Yunfan Li, Artem Shmelev, Himanshu Gupta
Published: 2026-06-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2606.15049v1

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

---

### Temporal Difference Learning for Diffusion Models

Authors: Qizhen Ying, Yangchen Pan, Victor Adrian Prisacariu, Junfeng Wen
Published: 2026-06-13
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2606.15048v1

Diffusion models are typically trained with objectives that focus on local denoising targets at individual time steps (or adjacent pairs), which do not enforce consistency between predictions along the denoising trajectory. This lack of cross-time consistency can degrade performance, especially for few-step samplers. We introduce a temporal difference (TD) objective that penalizes inconsistency of the model's multi-step progress along the denoising path. By reformulating the diffusion process as a Markov reward process and casting denoising as a policy evaluation problem in reinforcement learning, we derive a unified TD approach that applies to both discrete- and continuous-time diffusion formulations. We further propose a principled sample-based reweighting method that stabilizes training. Empirically, we show that using our TD training can significantly improve sample quality measured by FID, with stronger advantages when the number of sampling steps is small, highlighting its practical utility under low-computation-budget scenarios. We provide ablation studies to justify our design choices, including pairwise loss reweighting, regularization weight, and one-step stride. Overall, our TD approach can be a general drop-in that enforces cross-time consistency and improves generation quality across different diffusion generative models.

---

### Equity with Efficiency: An Empirical Study of Tokenizers for Multilingual Large Language Models

Authors: Kieron Seven Jun Wei Lee, Muhammad Reza Qorib, Andrew Ivan Soegeng, Hwee Tou Ng
Published: 2026-06-13
Categories: cs.CL
arXiv: https://arxiv.org/abs/2606.15044v1

Multilingual large language models (LLMs) depend on subword tokenization to bridge discrete text and continuous neural representation. State-of-the-art multilingual LLMs often use Byte-level Byte-Pair Encoding (BPE) tokenizers that structurally favor high-resource languages and Latin scripts. For speakers of underrepresented languages, particularly those across Southeast Asia, this bias inflates inference costs and widens cross-lingual capability gaps. We present the first systematic comparison of equitable tokenizers on a unified benchmark spanning 11 Southeast Asian languages. Beyond tokenizer-level analysis of compression efficiency and cross-lingual equity, we assess downstream task performance through controlled 1.5B-parameter language model training using the same training data. Our results show that Parity-aware BPE lies on the Pareto frontier of the efficiency-equity trade-off, achieving strong compression parity at competitive cost. Morphology-Driven Byte Encoding delivers the best semantic reasoning performance through morphologically richer representations, albeit at a higher computational expense. Byte Latent Transformer underperforms on downstream tasks, possibly because its architectural assumptions misalign with the constraints of limited low-resource training data. Together, our findings demonstrate that cross-lingual fairness and tokenization efficiency are not fundamentally at odds, and offer practical guidance for designing equitable multilingual models.

---

### Fusion is not one-size-fits-all: Cross-Modal Representation Alignment for Time-to-Event Modeling

Authors: Zhemin Zhang, Weijie Chen, David Le, Amara Tariq, Alex Wallace, Matthew Stib, Juan Maria Farina, Chadi Ayoub, Reza Arsanjani, Imon Banerjee
Published: 2026-06-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2606.15038v1

Accurate time-to-event (TTE) prediction from multimodal clinical data remains challenging due to modality imbalance and distribution shift. We introduce a foundation model-driven framework for cross-modal representation alignment between CT imaging and longitudinal EHR data, designed to generalize across tasks and institutions. CT and EHR modalities are encoded independently using domain-specific foundation models and aligned in a shared latent space through four principled fusion strategies: late fusion, contrastive alignment, cross-attention, and co-attention. We evaluate two clinically distinct TTE tasks: pulmonary embolism (PE) mortality and cardiovascular disease (CVD) outcomes, on large-scale multi-institutional cohorts (PE: N=3,099 train; 1,098 internal; 435 external; CVD: N=2,951 train; 837 internal; 682 external). Fusion consistently improves concordance index by 1.5-5.4% over unimodal baselines when modalities contribute comparably. Overall, contrastive multimodal fusion, particularly with CLMBR representations, provided the most consistent and statistically robust improvements, especially for PE mortality prediction. For MACE, cross-attention (one-hot) achieved the highest internal performance and image-guided co-attention achieved the best external performance. We therefore introduce a generalizable foundation model-based cross-modal alignment framework and provide the first systematic analysis of fusion behavior under modality imbalance in TTE prediction. Our results establish task-aware multimodal alignment as a necessary design principle for robust generalization and scalable clinical deployment.

---

### ReportQA: QA-Based Radiology Report Evaluation

Authors: Yiming Shi, Shaoshuai Yang, Xi Chen, Haolin Li, Hengyu Zhang, Che Jiang, Kaiwen Wang, Xun Zhu, Dong Xie, Fei Wang, Dejing Dou, Miao Li et al.
Published: 2026-06-13
Categories: cs.CL, cs.CV
arXiv: https://arxiv.org/abs/2606.15037v1

Radiology report evaluation is essential for advancing automated report generation. Natural language generation metrics have limited clinical relevance. Clinical efficacy (CE) metrics evaluate important medical findings, but focus mainly on presence and cover only a limited set of entities. Due to heavy reliance on manual annotations, it is difficult for CE metrics to extend clinical entities or attributes. In clinical practice, radiology reports serve as a medium for information transfer. Clinicians use them to perform downstream diagnostic tasks without directly inspecting images. Based on this insight, we propose ReportQA, a clinical-related and flexible radiology report evaluation framework, supporting detailed quantitative analysis of radiology report generation systems. We first collect datasets covering multiple imaging modalities and anatomical regions. We then construct knowledge trees of clinical entities and attributes with radiologist guidance, and use large language models (LLMs) to extract structured information from raw reports. Next, we generate QA pairs from predefined templates and apply quality control through self-filtering and report-based filtering. During evaluation, the report is treated as context, and an LLM acts as a judge model to answer the QA pairs. Based on the resulting QA accuracy, we introduce QAScore metric. Compared with existing metrics, QAScore shows better alignment with radiologist judgments. Experiments on multiple state-of-the-art vision-language models reveal that current report-based inference paradigms struggle to learn fine-grained clinical representations and exhibit strong negative prior biases. In contrast, question-driven inference provides a more effective alternative. For reproducibility and extensibility, we release the knowledge trees, structured reports, and QA pairs, along with the pipeline code for QA construction and evaluation.

---

### Transformers Learn the Mestre-Nagao Heuristic

Authors: Pranav Venkata Konda
Published: 2026-06-13
Categories: cs.LG, math.NT
arXiv: https://arxiv.org/abs/2606.15036v1

We train a two-layer transformer encoder to classify rational elliptic curves $E/\mathbb{Q}$ of conductor $\leq 10000$ as either rank 0 or rank 1 from the first 128 normalized Frobenius traces. We achieve >99% accuracy on both classes, and accuracy is essentially unchanged on test curves with no isogeny or quadratic-twist relative in the training set. We then apply techniques from mechanistic interpretability such as attention analysis, linear probing, activation patching, logit attribution, and neuron-level circuit analysis to reverse-engineer the algorithm the (centroid in function space) model learned. We find that a sparse circuit of 20 out of 512 layer-1 MLP neurons is sufficient for rank prediction under a linear probe with an AUROC of 0.992 at plateau, implementing a push-pull detector architecture of rank-0 and rank-1 detectors with a one-sided readout. However, we notice that the model has sub-optimal readout problems indicating a mismatch in rank-order between the readout pathway and the discriminative circuit. Critically, the learned input weights of the top discriminating neuron match the Mestre-Nagao sum heuristic weights $\log(p)/(p\cdot \log{B})$ with a Spearman coefficient $r = 0.997$ and Pearson coefficient $r = 0.952$: the model has learnt a result from analytic number theory from the Frobenius trace data alone. We additionally find that all 50 independently trained models concentrate CLS attention on prime positions at 2-50$\times$ the rate of composite positions. The CLS embedding encodes $\log{L(E,1)}$ with $R^2 = 0.962\pm 0.011$ across the 50 models (after controlling for the conductor). Activation patching analysis reveals that attention weights are dissociated from causal information flow. Additionally, the 50 solutions from training are near-identical in function space (with pairwise agreement $>$98.8%) despite large weight space barriers.

---

### OSGuard: A Benchmark for Safety in Computer-Use Agents

Authors: Mina Mohammadmirzaei, Jeffrey Flanigan
Published: 2026-06-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2606.15034v1

Computer-use agents are increasingly evaluated by whether they complete realistic desktop and web tasks. However, task success alone can miss failures in which an agent reaches the nominal goal through an unsafe shortcut. We introduce OSGuard, a dual-granularity benchmark suite for evaluating safety in computer-use agents under benign, unchanged user instructions. OSGuard contains an action-level benchmark for local guardrail decisions and a risk-augmented execution suite for end-to-end evaluation. The action-level benchmark consists of contextualized proposed actions labeled as allowed, unrelated, or unsafe, each judged relative to the original instruction and current interface state. The execution suite contains manually constructed OSWorld-derived task variants in which the original task remains achievable, but the environment is modified to introduce latent hazards such as destructive overwrites, etc. Each variant is paired with augmented evaluators that retain the original task-success criterion while adding explicit state-based safety invariants, allowing us to distinguish safe completions from unsafe completions that satisfy the nominal task objective. Our experimental results on OSGuard show that current multimodal guardrails can perform well on isolated action judgments, while risk-augmented execution exposes remaining gaps between local oversight and reliable end-to-end safety. This dual-granularity design enables more precise diagnosis of whether models can both recognize unsafe proposed actions and improve full-task safety when deployed as guardrails.

---

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

Authors: Matthew Flathers, Francesco Cipriani, John Torous
Published: 2026-06-13
Categories: cs.HC, cs.CL, cs.CY
arXiv: https://arxiv.org/abs/2606.15033v1

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

---

### How Should World Models Be Evaluated for Embodied Decision-Making? A Decision-Making-Centric Position

Authors: Yang Yu, Shiyuan Zhang, Yifei Sheng, Haoxiang Ren, Haoxin Lin
Published: 2026-06-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2606.15032v2

World models have become a central abstraction in modern AI. The term now refers to several different objects: action-conditioned environment models, latent imagination models, future-video predictors, interactive neural simulators, latent predictive representations, and synthetic-data engines. Evaluation has broadened along with the term. Recent papers measure video realism, perceptual similarity, instruction following, physical plausibility, policy ranking, executability, planning success, and downstream policy improvement. This produces both metric diversity and a recurring problem of claim/evidence mismatch: papers sometimes make a stronger claim about what their model is useful for than their evaluation can establish. This paper surveys the recent literature and argues that, for models presented as world models for embodied decision-making, the more decisive issue is not whether the model generates visually convincing videos, but whether it supports reliable interventional reasoning, policy evaluation, planning, and policy optimization under intervention, policy-induced distribution shift, and long-horizon rollout. We organize the survey using an L0--L7 ladder spanning visual plausibility to policy optimization utility, noting that the levels cut across several orthogonal axes and so form an evidential hierarchy rather than a single scalar. The framework foregrounds interventional action fidelity, closed-loop rollout validity, reward/value prediction, policy-ranking agreement, optimization lift, model exploitability, and uncertainty calibration, with a minimal feasible reporting set for real-robot settings.

---

### Energy Efficiency of Locally Deployed LLMs: A Preliminary Quantitative GPU Power Benchmark on Consumer Hardware

Authors: Philipp M. Zähl, Anika Hennig
Published: 2026-06-12
Categories: cs.AI, cs.ET, cs.PF
arXiv: https://arxiv.org/abs/2608.00008v1

The local deployment of large language models (LLMs) is gaining traction due to privacy concerns and the desire for on-premise inference. However, the energy costs on consumer hardware remain poorly characterized, as most benchmarks focus solely on accuracy. This paper presents a reproducible, hardware-level energy benchmark of nine open-source LLMs (1B to 7B parameters) executed on a single consumer GPU (RTX 4060Ti 16GB). Using the Ollama inference engine, GPU power draw was sampled at 2Hz via nvidia-smi across a fixed prompt set. We evaluate mean/peak power, total energy per prompt (J/prompt), energy per output token (J/token), and throughput (tok/s). Our findings suggest that factors beyond raw parameter count, including model architecture and quantization strategy, drive energy efficiency. Specifically, gemma3:1b and llama3.2:1b achieve the lowest energy cost (0.56 J/token and 0.65 J/token) and the highest throughput (>170 tok/s). In contrast, the 7B-Mistral model consumes up to 4.4x more energy per token than the most efficient model. Notably, qwen3.5:2b exhibits anomalously high per-prompt energy due to extended internal reasoning, highlighting the need to distinguish between token generation modes in efficiency metrics.

---

### Atmospheric Diffusion-Guided Spatio-Temporal Transformer for Nuclear Radiation Forecasting

Authors: Tengfei Lyu, Jindong Han, Hao Liu
Published: 2026-06-12
Categories: cs.AI
arXiv: https://arxiv.org/abs/2607.24774v1

Nuclear radiation, the energy released during atomic decay, poses persistent risks to public health and the environment, and concerns have only grown since the Fukushima accident and the recent commencement of treated-water discharge. Modern monitoring networks now record radiation levels and accompanying weather conditions at thousands of stations, opening the door to nationwide forecasting that can inform emergency response, agricultural advisories, and routine public-safety decisions. However, turning this abundance of monitoring data into reliable forecasts is difficult for three reasons. First, the time series at each station are highly non-stationary, shaped by radioactive decay, weather variability, and irregular human interventions. Second, monitoring stations are severely unevenly distributed in space. Roughly 78% of Japan's stations sit in less than 6% of the country, clustered near Fukushima, which breaks the assumptions of standard graph-based models. Third, radiation co-evolves with heterogeneous context such as wind, temperature, and humidity through atmospheric transport processes that purely data-driven models struggle to capture from observations alone. In this study, we introduce NRFormer+, a spatio-temporal Transformer for nationwide nuclear radiation forecasting. NRFormer+ couples non-stationary temporal attention and density-adaptive spatial attention with a new atmospheric diffusion module that estimates how meteorology drives radiation dispersion and injects this physical signal into the network as an architectural prior. NRFormer+ delivers state-of-the-art accuracy on both datasets across all 13 baselines, reducing sudden-change MAE by up to 19.1% over the strongest baseline at comparable inference latency. Our code and datasets are publicly available at https://github.com/tfeilyu/NRFormer_Plus.

---

### Right-sizing Recommendations (RSR): Cloud Workload Conformal Prediction for Virtual Machines in Data Center Operations

Authors: Mehryar Majd, Feng Cheng, Ali Pahlevan
Published: 2026-06-12
Categories: cs.AI
arXiv: https://arxiv.org/abs/2607.24773v1

Managing cloud infrastructure efficiently, especially in environments of large cloud providers or hyperscalers, requires optimizing the use of physical resources to minimize costs and maximize performance. Selecting the right virtual machine (VM) sizes is crucial to achieving cost efficiency in these dynamic environments. However, traditional VM allocation and scheduling approaches often fail to account for the fluctuating and unpredictable nature of VM utilization, leading to inefficiencies such as over- or under-provisioning of resources. High-quality interval prediction helps accurately capture uncertainty in cloud resource demand and supports cloud operators in efficient instance provisioning. As an effective and reliable framework for constructing prediction intervals (PIs), conformal prediction (CP) is used for mid- and long-term forecasting tasks in cloud computing environments. This study proposes a new data-driven PI construction approach using bootstrapping conformal prediction for modern, dynamic, data-driven Right-sizing Recommendations (RSR) to enhance provisioning for diverse application workloads on hyperscalers. By learning workload utilization patterns, identifying correlations across multiple time series, and predicting medium- to long-term utilization trends, this research seeks to improve the efficiency of cloud and data center operations through an AI/ML-based provisioning pipeline. Our study demonstrates that AI-driven models, powered by machine learning regression techniques and evaluated using backtesting, achieve promising forecasting results for cloud resource utilization. Additionally, we rank the selected models to identify top-performing approaches for long-life VM candidates. The proposed framework enhances right-sizing recommendations and supports more cost-effective resource allocation in dynamic cloud environments.

---

### Group Preference Collapse in Personalized Multimodal Large Language Models

Authors: Fan Lyu, Wenqi Zhang, Joost van de Weijer
Published: 2026-06-12
Categories: cs.AI
arXiv: https://arxiv.org/abs/2607.22603v1

Personalized multimodal large language models (MLLMs) aim to generate user-specific responses, but existing methods mainly rely on profile-level information and overlook diverse user preferences. We identify group preference collapse, where multi-user personalized MLLMs become insensitive to individual preferences and drift toward dominant population-level choices due to suppressed preference signals and unreliable preference use during generation. We propose PrefMoE, a preference-centric framework that separates stable profile information from preference-related representations. PrefMoE decomposes preferences into shared prototypes and personalized residuals, preserves individualized residuals with imbalance-aware learning, counterfactual pseudo-user augmentation, and residual decorrelation, and routes profile and preference factors through separate LoRA adaptation paths. Experiments across multiple MLLM backbones show that PrefMoE improves preference-sensitive personalization while substantially reducing preference collapse. Project page: https://prefmoe.github.io/.

---

### DeepLook: Deeper Thinking with Lookahead

Authors: Tingxin Yang, Zefeng Wang, Mengyue Wang, Xingcheng Zhou, Yunpu Ma
Published: 2026-06-12
Categories: cs.AI
arXiv: https://arxiv.org/abs/2607.22602v1

Inference-time scaling has emerged as a powerful paradigm for improving large language model reasoning, often delivering larger gains on difficult reasoning tasks than parameter scaling alone. However, existing approaches remain inefficient in how compute is allocated within a reasoning trace. Motivated by the observation that reasoning failures often exhibit an early onset of uncertainty before a wrong answer become explicit, we introduce DeepLook, a training-free monitor-and-intervene decoding framework that concentrates lookahead compute at uncertainty bottlenecks. DeepLook aggregates token-level confidence into segment-level signals, triggers when confidence drops relative to recent history, and explores candidate continuations with fixed-horizon lookahead. Branches are ranked by Average Lookahead Confidence (ALC), the average segment-level confidence over rollout continuations, then pruned and aggregated through voting. On four competition-style mathematics benchmarks across DeepSeek-R1-8B, Qwen3-32B, GPT-OSS-20B, and GPT-OSS-120B, DeepLook shifts the accuracy--token-cost Pareto frontier: it improves accuracy over DeepConf-low in 11 of 16 settings while reducing dataset-level token generation by 87.3% on average, including gains of +3.1 on AIME25 with Qwen3-32B and +8.8 on BRUMO25 with GPT-OSS-20B. These results show that selective, future-aware intervention yields substantially stronger accuracy--cost trade-offs than uniformly scaling complete reasoning trajectories. Code is available here.

---

### Chart Deception in Vision-Language Models: From Vulnerability to Mitigation

Authors: Ridwan Mahbub, Mohammed Saidul Islam, Md Tahmid Rahman Laskar, Mizanur Rahman, Mir Tafseer Nayeem, Enamul Hoque
Published: 2026-06-12
Categories: cs.AI
arXiv: https://arxiv.org/abs/2607.22600v1

Information visualizations are widely used to communicate patterns, trends, and outliers, yet deceptive design choices-such as truncated or inverted axes, distorted aspect ratios, inappropriate encodings, and misleading color mappings-can systematically alter interpretation while preserving the underlying data. As Vision-Language Models (VLMs) are increasingly used for chart understanding and analytical reasoning, assessing their robustness to such deceptive visualizations has become critical for trustworthy data analysis. We introduce VisDeception, the first controlled paired benchmark for evaluating the robustness of VLMs to misleading chart designs. The benchmark contains 1,600 paired faithful and misleading charts spanning eight major categories of deceptive visualization tactics, where each misleading chart is paired with a faithful counterpart generated from the same underlying data. To isolate deception-induced reasoning errors from baseline chart-understanding errors, we introduce the Deception Score, a paired evaluation metric that quantifies how misleading visualizations shift model responses away from the faithful interpretation of the data. Across 32,000 responses from 10 state-of-the-art VLMs, we find that even advanced models remain highly vulnerable to deceptive visual manipulations. To improve robustness, we further propose an inference-time multi-agent mitigation framework that grounds reasoning in structured chart metadata extracted from the visualization before answer generation, enabling models to reduce the influence of deceptive visual cues without requiring explicit user instructions. Together, our findings reveal important reliability gaps in current chart-understanding systems and establish benchmark-driven evaluation, deception-aware metrics, and structured reasoning as promising directions for developing more trustworthy VLMs for visual analytics.

---

### Differencing the Diffusion Trajectory toward Uncertain Components for Time Series Forecasting

Authors: Chen Su, Yuanhe Tian, Yan Song
Published: 2026-06-12
Categories: cs.AI
arXiv: https://arxiv.org/abs/2607.22599v1

Diffusion models have become a widely used framework for probabilistic time series forecasting, modeling the distribution of future values given an observed history. In time series forecasting, however, the future continues the observed history, creating an asymmetry the standard diffusion process leaves unaddressed, with slowly-varying content largely determined by the observed continuity while higher-frequency dynamics carry most of the residual uncertainty. Existing diffusion-based forecasters decouple this asymmetry through an external rule before generation, leaving the corruption trajectory blind to which parts of the target the history can already anchor. We propose DiffDiff, a diffusion framework that embeds this predictability asymmetry into the diffusion trajectory itself, so that a single end-to-end diffusion process becomes aware of which parts of the target the history can already anchor. DiffDiff makes the forward operator step-dependent so that the noisy intermediate state progressively shifts from the target itself toward its second-order differenced structure, while a conditioning pathway supplies the denoiser with both value-domain and differential history information balanced by a stage-adaptive gate at each diffusion step. The terminal distribution approaches a standard Gaussian, preserving compatibility with existing samplers. On seven benchmarks across four prediction horizons, DiffDiff outperforms six diffusion baselines, and our analysis confirms that DiffDiff concentrates the diffusion's generative effort on the most uncertain components of the target while relieving it from rebuilding the history-anchored content.

---

### A didactical-driven teacher assistant for a dimensional modeling course

Authors: Laurent Brisson, Maria Segarra, Grégory Smits
Published: 2026-06-12
Categories: cs.CY, cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2607.22598v1

Educational chatbots powered by large language models (LLMs) show promising effects on learning outcomes, yet most systems delegate pedagogical decisions such as content selection and didactic structuring implicitly to the LLM, making tutoring strategies difficult to trace, evaluate, and reproduce. This paper presents a didactical-driven teacher assistant for a French-language university course on dimensional modelling, operating without commercial LLM budget or GPU infrastructure. The architecture formalises the instructor's pedagogical reasoning into deterministic modules that handle intent detection, concept linking, and didactic approach selection before any text is generated; the LLM acts solely as a linguistic executor. Evaluation on 195 authentic student questions addresses two research questions. First, we show that standard semantic retrieval alone does not reliably recover the pedagogically required content, thereby justifying the upstream orchestration strategy adopted in our architecture (RQ1). Second, compared to free-tier LLMs whose detection performance varies widely across models and which produce errors silently, the deterministic pipeline achieves high pair precision (73%) with full traceability and explicit abstention, though its limited coverage confirms that the detection strategy requires further refinement (RQ2).

---

### HyCE-RAG: Hypergraph Chain-of-Evidence Retrieval-Augmented Generation for Explainable Multi-hop Question Answering

Authors: Hong-Yu An, Yun-Jian Zhang, Chen-Wei Liang, Tian-Yi Zhang, Jian Ding, Yi-Lun Wu, Ao-Bo Li, Wei-Cong Su, Saifullah, Mujiangshan Wang
Published: 2026-06-12
Categories: cs.AI
arXiv: https://arxiv.org/abs/2607.22597v1

Multi-hop question answering requires systems to retrieve evidence from multiple documents and connect scattered facts into a coherent reasoning process. Standard retrieval-augmented generation (RAG) mainly relies on semantic similarity between a query and text chunks, and therefore often fails to model structural relations among entities, facts, and evidence units. Graph-based RAG improves this by introducing graph-structured knowledge, but pairwise edges are still limited in representing higher-order associations involving multiple entities and contexts. We propose HyCE-RAG, a Hypergraph Chain-of-Evidence Retrieval-Augmented Generation framework for explainable multi-hop question answering. HyCE-RAG organizes entities, relations, and contextual evidence into hyperedges, builds a query-aware evidence hypergraph, and performs confidence propagation over entity--hyperedge incidence structures. It then uses confidence-guided evidence assembly to select, connect, and rank evidence paths before answer generation. The scoring process jointly considers semantic relevance, entity connectivity, evidence coverage, relation reliability, extraction confidence, and propagated confidence. By providing the language model with structured evidence chains rather than flat retrieved passages, HyCE-RAG supports more faithful and interpretable reasoning. Experiments on HotpotQA, 2WikiMultihopQA, MuSiQue, and two GraphRAG-Bench subsets show that HyCE-RAG consistently outperforms standard RAG and graph-based RAG baselines in answer accuracy, context relevance, and faithfulness. These results suggest that hypergraph-based evidence organization is a promising direction for post-retrieval reasoning in complex question answering.

---

### An Agentic Orchestration of Atomistic Simulations

Authors: Rahul Somasundaram, Adela Habib, Khanh Dang, Sachin Shivakumar, Ryley G. Hill, Golo Wimmer, Avanish Mishra, Aleksandra Pachalieva, Arthur Lui, Hari Viswanathan, Michael Grosskopf, Saryu Fensin et al.
Published: 2026-06-12
Categories: cs.AI, cond-mat.mtrl-sci
arXiv: https://arxiv.org/abs/2607.22596v1

Atomistic simulations are central to materials design, but their execution involves complex, multi-step workflows that require significant human expertise. Here, we present an agent-based system embedded within the URSA (Universal Research and Scientific Agent) framework that automates the design, execution, and validation of atomistic simulations, demonstrated using the Large-scale Atomic/Molecular Massively Parallel Simulator (LAMMPS) tool. Our system autonomously selects interatomic potentials, constructs and runs simulations, and performs iterative error recovery within a closed-loop workflow. We evaluate the scientific reliability of the agent by benchmarking its outputs against LAVA, a high-throughput toolkit for LAMMPS and the Vienna Ab initio Simulation Package (VASP) calculations. Our framework reduces manual intervention and trial-and-error, thereby improving the rigor, reproducibility, and scalability of atomistic modeling.

---

### Isolating LLM Alignment from Regex: Zero Coverage and Metric-Dependent Divergence Under Adversarial Mutation

Authors: Alexandre Cristovão Maiorano
Published: 2026-06-12
Categories: cs.AI, cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2607.20494v1

Production LLM applications commonly stack a regex filter in front of model-side alignment; prior work found no measurable coverage gain from adding a live Gemini backend behind an active regex filter. We ask whether that ceiling holds when the corpus is \emph{designed to bypass the regex}. We introduce $L_5$-no-regex -- identical to $L_4$-real (Gemini-2.5-flash, token-budget cap, rate limit, output scrub) but with the nine-pattern filter disabled -- and evaluate it against $N{=}45$ adversarial probes across three sub-corpora (carry-forward, regex-bypass, alignment-isolate), amplified by Gemini paraphrase and PAIR to ${\sim}1{,}555$ probe-run pairs over $N{=}5$ replications. Under the primary substring classifier, H1 is refuted: $L_5$ block rate is $0,%$ across all five OWASP LLM Top-10 categories ($Δ\text{pp}{=}0$ vs.\ $L_0$, $p{=}1.00$; Wilson upper bound ${<}5,%$). A secondary LLM-judge metric on PAIR variants shows $56$--$100,%$ block rates ($p{<}0.01$), revealing alignment does respond to adversarially-framed probes -- but produces refusals too nuanced for substring matching. The sub-corpus differential prediction is not supported ($p{=}1.00$). Alignment's contribution is \emph{metric-dependent}: on natural-language harmful-request probes, it adds zero observed coverage beyond the regex; on adversarially-framed variants, an LLM judge detects refusals the substring classifier misses. The locked corpus, mutation artifacts, and export scripts are released for replication.

---

### Attention-based Experience Replay Framework for Continual Learning of Agnostic Time Series Forecasting Models

Authors: Quentin Besnard, Nicolas Ragot
Published: 2026-06-12
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2607.20493v1

Deep learning has led to remarkable progress in artificial intelligence, particularly in robotics, imaging and sound processing. However, a major limitation of neural networks remains their strong dependence on large and stationary datasets. In many real-world applications, these conditions are rarely met due to evolving and dynamic environments where data distributions change over time. Continual learning aims to address this challenge by developing models capable of adapting incrementally while maintaining a balance between stability and plasticity under computational constraints. In this work, we introduce a novel framework for continual time series forecasting, designed to extend existing static forecasting models commonly used in the literature by incorporating an Experience Replay strategy guided by Attention mechanisms. This approach allows the model to adapt dynamically to new contexts while preserving prior knowledge, effectively mitigating catastrophic forgetting. The framework is evaluated on standard forecasting benchmarks as well as on a piezometric dataset exhibiting diverse temporal behaviors. Results show that our approach effectively increases or maintains predictive performance over time while reducing retraining costs and data requirements, thus facilitating the deployment of forecasting models in dynamic and real-world settings.

---

### Spectral-LSH: Sub-Quadratic Prompt Compression via Krylov-Projected Locality-Sensitive Hashing

Authors: Ali Mahdavi, Azaseh Zamanifar, Amirfarhad Farhadi, Omid Kashefi
Published: 2026-06-12
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2607.19368v1

Long-prompt inference remains expensive because prefill attention scales quadratically with sequence length. We propose Spectral-LSH, a training-free prompt compression method that operates before the prompt enters the language model. Spectral-LSH approximates the dominant components of an implicit attention-kernel operator using a Krylov subspace method together with random features, avoiding explicit $O(N^2)$ attention-kernel materialization. It then applies SimHash in the resulting attention eigenspace to group similar tokens and aggregate them into macro-tokens with causal positional assignments. We evaluate Mistral-7B-Instruct-v0.3, Qwen2.5-7B-Instruct, and Qwen2.5-14B-Instruct on C4. Our experiments reveal a compression-ratio phase transition. Below $ρ= 4 \times$, local token redundancy is low enough that lightweight chunking typically provides the best latency--quality trade-off. Above $ρ= 8 \times$, the spectral path preserves quality that chunking loses. At $ρ= 16 \times$, Qwen2.5-7B (adaptive) reduces the PPL ratio from 353.409 to 196.963, while Qwen2.5-14B (adaptive) reduces it from 9.533 to 3.427. On a small long-context structured stress test containing JSON-like, code-like, and table-like inputs, local LSH also improves every metric over chunking at $8 \times$. The adaptive backend captures both regimes by using the chunk path at low compression and spectral clustering at high compression, although chunking remains the fastest backend in total latency.

---