Autoregressive video diffusion models provide a natural formulation for streaming and variable-length video generation by conditioning newly generated frames on previously generated content. However, extending these models to minute-level generation remains challenging: the limited KV-cache budget prevents the model from retaining the full history, while repeatedly conditioning on self-generated frames induces a context distribution shift that accumulates over time, leading to visual artifacts, quality degradation, and temporal drift.
Adversarial attacks on skeletal human action recognition have received significant attention. However, existing methods typically introduce noise-like perturbations that degrade motion quality post-attack, and thereby are inherently perceptible with recent advancements in S-HAR systems.
Parallel test-time scaling samples many reasoning traces and majority-votes their answers, improving LLM accuracy but requiring traces to run to completion, incurring substantial computational overhead. We observe that probing partial traces at intermediate checkpoints can extract current answers without disrupting generation, revealing an evolving aggregate vote.
Interleaved thinking, where a unified multimodal model alternates between textual reasoning and visual generation, has shown promise on spatial and physical tasks. However, in complex long-chain scenarios, we identify a fundamental failure mode: generated images diverge from the textual context while subsequent text ignores the visual evidence, causing the two modalities to alternate without genuinely informing each other.
arXiv:2606. 11534v1 Announce Type: cross Abstract: Urban heat is amplified by impermeable surfaces and heterogeneous built environments, yet street-level variability remains difficult to quantify because multi-sensor observations are rarely available in consistent, analysis-ready form at the necessary spatiotemporal scales.
By Jonathan Starfeldt, Maria J. Molina, Alexander Kerr, Adam Yang, Thomas R. H. Holmes, Christopher R. Hain
arXiv:2606. 11961v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as conditional generators for structured data, relying on in-context learning (ICL) to adapt to new distributions without parameter updates.
By Antonio Pelusi, Stefano Braghin, Alberto Trombetta
arXiv:2606. 11686v1 Announce Type: cross Abstract: End-to-end task-success is the dominant way to evaluate LLM agents, but one aggregate number tells you that an agent regressed, not where.
By Sawyer Zhang, Alexander Wang, Sophie Lei
arXiv:2602. 05746v2 Announce Type: replace-cross Abstract: Prompt injection is a critical vulnerability in LLM agents, yet the strongest methods still rely on human red-teamers and hand-crafted prompts.
By Xin Chen, Jie Zhang, Florian Tram\`er
arXiv:2606. 11857v1 Announce Type: cross Abstract: Multi-channel mixed-SNR training improves out-of-distribution (OOD) generalisation of deep learning channel estimators for IEEE 802.
By Simbarashe Aldrin Ngorima, Albert Helberg, Marelie H. Davel
arXiv:2606. 11898v1 Announce Type: cross Abstract: Research on Text-Attributed Graphs (TAGs) has gained significant attention recently due to its broad applications across various real-world data scenarios, such as citation networks, e-commerce platforms, social media, and web pages.
By Hengyi Feng, Zeang Sheng, Meiyi Qiang, Meiyi Qiang, Wentao Zhang
arXiv:2606. 12362v1 Announce Type: cross Abstract: We study multimodal learning under missing modalities, with particular motivation from bioscience applications in which heterogeneous modalities are often only partially available when decisions need to be made.
By Hui Wang, Tianyu Ren, Joseph Butler, Christopher Baker, Karen Rafferty, Simon McDade
arXiv:2606. 11556v1 Announce Type: cross Abstract: Continuous electrocardiography (ECG) monitoring could surface rhythm abnormalities before they escalate into cardiovascular events.
By Kaan Arda Akyol, Jakub Kacper Szel\k{a}g, Aydin Abadi, Maha Alghamdi, Ghadah Albalawi, Ghouse Ibrahim Kaleelullah, Hilal Tutus, Sarah Al Subaiei, Shardul Kapse, Syed Mohammed Raheeb, Mujeeb Ahmed, Rehmat Ullah
arXiv:2606. 11751v1 Announce Type: cross Abstract: Multi-turn image editing is essential for iterative design, yet current models often struggle with identity drift and error accumulation over successive steps.
By Hang Xu, Xiaoxiao Ma, Guohui Zhang, Yu Hu, Siming Fu, Jie Huang, Lin Song, Haoyang Huang, Nan Duan, Feng Zhao
arXiv:2602. 10392v2 Announce Type: replace Abstract: When designing new materials, it is often necessary to tailor the material design to have some desired properties.
By Shaan Pakala, Aldair E. Gongora, Brian Giera, Evangelos E. Papalexakis
arXiv:2506. 08473v4 Announce Type: replace Abstract: Fine-tuning large language models (LLMs) improves performance but introduces critical safety vulnerabilities: even minimal harmful data can severely compromise safety measures.
By Shuo Yang, Qihui Zhang, Yuyang Liu, Xiaojun Jia, Kunpeng Ning, Jiayu Yao, Jigang Wang, Hailiang Dai, Yibing Song, Li Yuan
arXiv:2601. 14031v2 Announce Type: replace-cross Abstract: Forecasting intermittent time series, which contain zeros, is a crucial challenge in supply chains as inventory policies require probabilistic forecasts to establish safety levels.
By Stefano Damato, Nicol\`o Rubattu, Dario Azzimonti, Giorgio Corani
arXiv:2602. 20958v2 Announce Type: replace-cross Abstract: Vision-based Unmanned Aerial Vehicles (UAVs) frameworks aid human search tasks by detecting and recognizing specific individuals, then tracking and following them while maintaining a safe distance.
By Luka \v{S}iktar, Branimir \'Caran, Bojan \v{S}ekoranja, Marko \v{S}vaco
arXiv:2606. 12392v1 Announce Type: cross Abstract: Recently, large language models (LLMs) have achieved promising progress in the fields of classical Chinese translation and the generation of classical poetry.
By Haotao Xie
arXiv:2606. 11605v1 Announce Type: cross Abstract: Predicting process-property relationships in manufacturing is often challenged by high experimental costs and the limited interpretability of complex 'black-box' models.
By Ge Song, Kiarash Naghavi Khanghah, Anandkumar Patel, Rajiv Malhotra, Hongyi Xu
arXiv:2606. 12397v1 Announce Type: cross Abstract: Router is the cornerstone component to the Mixture-of-Experts models.
By Songhao Wu, Ang Lv, Ruobing Xie, Yankai Lin