Wei Wang

Yusheng Zheng, Tianyuan Wu, Quanzhi Fu et al.

AI agents increasingly run in production through harnesses, the software around the LLM, including an engine that enforces safety and effectiveness policies, e.g., 'run tests before committing.' Enforcing these policies requires bridging a semantic gap: policy intent is expressed in underspecified natural language, while enforcement must act on concrete system actions, e.g., which test to run. Many policies also define event ordering or data flow actions. Yet existing approaches fall short. Tool-call guardrails miss system actions that bypass the tool layer, while OS sandboxes control resource access instead of actions, returning opaque errors that confuse the agent. Our key insight is that policy context lives within the agent closest to the task, while enforcement must happen at the OS to cover all execution paths. We introduce ActPlane, a policy engine that lets agents declare policies and enforces them in the OS kernel with semantic feedback and isolation. ActPlane uses a simple information-flow control (IFC) DSL to support cross-event policies. We implement ActPlane with eBPF and evaluate it on policies from the empirical study, coding-task benchmarks, and safety benchmarks. ActPlane improves policy compliance, including on indirect execution paths that tool-call interception cannot observe, with 1.9%-8.4% overhead. ActPlane is at https://github.com/eunomia-bpf/ActPlane

Shikai Qiu, Xiaowen Xu, Benlei Cui et al.

General-purpose models often struggle to reliably identify and understand real-world multimodal risks, largely due to the inherent multimodal adversarial nature of content and AI safety. We present Yuvion VL, a family of multimodal large language models purpose-built for content and AI safety, with both instruction-tuned and reasoning-oriented variants. Yuvion VL addresses this gap by treating safety as an inherently adversarial and multimodal problem and designing the entire pipeline around adversarial robustness. For data construction, we develop an automated pipeline integrating adversarial-aware data synthesis with multi-stage quality control, producing large-scale, high-quality multimodal samples augmented with domain knowledge and reasoning annotations. For training, we adopt a three-stage pipeline that includes continued pretraining for risk-concept cross-modal alignment, instruct post-training for production-grade safety tasks, and reasoning post-training for enhanced interpretability and performance in complex tasks. We further introduce Confuse-then-Contrast Fine-Tuning, a contrastive framework that mines model-specific confusions and constructs multi-image contrastive groups to enforce explicit discrimination of fine-grained visual-semantic elements, enabling the model to distinguish between visually similar cases with different safety implications in adversarial safety tasks. To support rigorous evaluation, we further introduce Yuvion VL RiskEval (YVRE), a collection of benchmarks covering diverse open and internal evaluations, with a focus on content and AI safety, adversarial robustness, and real-world capability requirements. Experiments show that Yuvion VL-32B achieves industry-leading safety performance, surpassing comparably sized open-source models and best closed-source commercial models, while maintaining comparable general capabilities.

Lianghua Huang, Zhifan Wu, Wei Wang et al.

We present Wan-Streamer, a native-streaming, end-to-end interactive foundation model designed from the ground up for real-time, low-latency, full-duplex audio-visual interaction. Wan-Streamer seamlessly models language, audio, and video as both input and output within a single Transformer, where the sequence is represented as interleaved visual, audio, and text input tokens together with visual, audio, and text output tokens, coordinated by block-causal attention for incremental streaming. Unlike cascaded interactive systems that rely on separate VAD, ASR, language, TTS, audio-driven animation, or video-generation modules, Wan-Streamer does not rely on external language, speech, avatar, or video-generation modules: perception, reasoning, generation, response timing, turn management, and cross-modal synchronization are learned jointly within one unified model, reducing pipeline latency and error accumulation. To support natural audio-visual responsiveness, we redesign the entire stack around streamability, including causal encoders, causal decoders, block-causal attention, and low-latency multimodal token scheduling, enabling streaming units as short as 160 ms at 25 fps. Wan-Streamer achieves approximately 200 ms model-side response latency and approximately 550 ms total interaction latency when combined with 350 ms bidirectional network latency, supporting sub-second duplex audio-visual communication. These results position Wan-Streamer as a unified, end-to-end, multimodal interactive foundation model for low-latency streaming interaction.

Qiyang Lyu, Zhenyu Wu, Wei Wang et al.

Localization in challenging environments, such as GNSS-denied, geometrically repetitive, or textureless scenes commonly found in offices, hotels, and underground parking facilities, remains an open problem for reliable autonomous mobile robot (AMR) deployment. Single-modality localization methods are inherently limited by the constraints of individual sensors. Although multimodal fusion frameworks have shown improved robustness, most existing approaches still rely heavily on geometric or texture features, or on infrastructure-based beacons, which increase installation and maintenance costs while reducing deployment flexibility. Recently, ambient magnetic field (AMF)-based localization has attracted growing attention because it does not depend on geometric or texture features, nor does it require additional infrastructure, making it a promising complementary modality for AMR localization. However, existing studies have only explored such fusion in pedestrian scenarios using smartphone-mounted sensor suites, and practical solutions for AMR systems remain largely unexplored. To address this gap, this article proposes a magnetometer-inertial-LiDAR fused multimodal localization framework with a custom-designed sensor suite, termed MIL-LC, which provides reliable localization even when LiDAR suffers from geometric degeneration or when the magnetic map changes during long-term deployment. Extensive experiments in both simulation and real-world environments demonstrate that the proposed MIL-LC framework achieves robust and accurate localization performance.

Yuanhao Wang, Wei Wang

Let $n$ and $p$ denote the numbers of vertices and labels, respectively, in an undirected edge-labeled graph. Previous work showed that, under the Exponential Time Hypothesis (ETH), there is no deterministic algorithm with running time \[ (np)^{o\left(\frac{\log n}{(\log\log n)^2}\right)}. \] In this paper, we give a deterministic reduction that strengthens this conditional running-time lower bound to \[ (np)^{o\left(\frac{\log n}{\log\log n}\right)}. \]

Wei Wang, Enlin Gu, Antonio Loquercio et al.

AI copilots can substantially boost human performance through shared control, but excessive assistance can induce over-reliance and skill atrophy. This paper studies how an embodied AI agent can act as a coach that accelerates human motor-skill development. We argue that effective coaching requires strategic scaffolding and stepping back that are aligned with the learner's capability, allowing productive failures that drive learning. We formalize the interactive AI coaching process as a non-cooperative dynamic game in which the learner optimizes task performance while the coach targets the learner's independent competence. Building on this formalism, we develop a reinforcement learning framework combining adaptive shared control with probabilistic models of the coach's causal influence on skill evolution, enabling tractable training of coaching policies. A comprehensive user study (N=33) on first-person-view drone racing shows significant gains in human learning outcomes over state-of-the-art AI coaching baselines.