Safe autonomous driving requires both accurate HD map construction and persistent awareness of traffic rules, even when their associated signs are no longer visible. However, existing methods either focus solely on geometric elements or treat rules as temporary classifications, failing to capture their persistent effectiveness across extended driving sequences. In this paper, we present PAMR (Persistent Autoregressive Mapping with Traffic Rules), a novel framework that performs autoregressive co-construction of lane vectors and traffic rules from visual observations. Our approach introduces two key mechanisms: Map-Rule Co-Construction for processing driving scenes in temporal segments, and Map-Rule Cache for maintaining rule consistency across these segments. To properly evaluate continuous and consistent map generation, we develop MapDRv2, featuring improved lane geometry annotations. Extensive experiments demonstrate that PAMR achieves superior performance in joint vector-rule mapping tasks, while maintaining persistent rule effectiveness throughout extended driving sequences.

Human-Scene Interaction (HSI) seeks to generate realistic human behaviors within complex environments, yet it faces significant challenges in handling long-horizon, high-level tasks and generalizing to unseen scenes. To address these limitations, we introduce FantasyHSI, a novel HSI framework centered on video generation and multi-agent systems that operates without paired data. We model the complex interaction process as a dynamic directed graph, upon which we build a collaborative multi-agent system. This system comprises a scene navigator agent for environmental perception and high-level path planning, and a planning agent that decomposes long-horizon goals into atomic actions. Critically, we introduce a critic agent that establishes a closed-loop feedback mechanism by evaluating the deviation between generated actions and the planned path. This allows for the dynamic correction of trajectory drifts caused by the stochasticity of the generative model, thereby ensuring long-term logical consistency. To enhance the physical realism of the generated motions, we leverage Direct Preference Optimization (DPO) to train the action generator, significantly reducing artifacts such as limb distortion and foot-sliding. Extensive experiments on our custom SceneBench benchmark demonstrate that FantasyHSI significantly outperforms existing methods in terms of generalization, long-horizon task completion, and physical realism.

Recent advances in audio-driven portrait animation have demonstrated impressive capabilities. However, existing methods struggle to align with fine-grained human preferences across multiple dimensions, such as motion naturalness, lip-sync accuracy, and visual quality. This is due to the difficulty of optimizing among competing preference objectives, which often conflict with one another, and the scarcity of large-scale, high-quality datasets with multidimensional preference annotations. To address these, we first introduce Talking-Critic, a multimodal reward model that learns human-aligned reward functions to quantify how well generated videos satisfy multidimensional expectations. Leveraging this model, we curate Talking-NSQ, a large-scale multidimensional human preference dataset containing 410K preference pairs. Finally, we propose Timestep-Layer adaptive multi-expert Preference Optimization (TLPO), a novel framework for aligning diffusion-based portrait animation models with fine-grained, multidimensional preferences. TLPO decouples preferences into specialized expert modules, which are then fused across timesteps and network layers, enabling comprehensive, fine-grained enhancement across all dimensions without mutual interference. Experiments demonstrate that Talking-Critic significantly outperforms existing methods in aligning with human preference ratings. Meanwhile, TLPO achieves substantial improvements over baseline models in lip-sync accuracy, motion naturalness, and visual quality, exhibiting superior performance in both qualitative and quantitative evaluations.

Large-scale map construction is foundational for critical applications such as autonomous driving and navigation systems. Traditional large-scale map construction approaches mainly rely on costly and inefficient special data collection vehicles and labor-intensive annotation processes. While existing satellite-based methods have demonstrated promising potential in enhancing the efficiency and coverage of map construction, they exhibit two major limitations: (1) inherent drawbacks of satellite data (e.g., occlusions, outdatedness) and (2) inefficient vectorization from perception-based methods, resulting in discontinuous and rough roads that require extensive post-processing. This paper presents a novel generative framework, UniMapGen, for large-scale map construction, offering three key innovations: (1) representing lane lines as discrete sequence and establishing an iterative strategy to generate more complete and smooth map vectors than traditional perception-based methods. (2) proposing a flexible architecture that supports multi-modal inputs, enabling dynamic selection among BEV, PV, and text prompt, to overcome the drawbacks of satellite data. (3) developing a state update strategy for global continuity and consistency of the constructed large-scale map. UniMapGen achieves state-of-the-art performance on the OpenSatMap dataset. Furthermore, UniMapGen can infer occluded roads and predict roads missing from dataset annotations.

High-Definition Maps (HD maps) are essential for the precise navigation and decision-making of autonomous vehicles, yet their creation and upkeep present significant cost and timeliness challenges. The online construction of HD maps using on-board sensors has emerged as a promising solution; however, these methods can be impeded by incomplete data due to occlusions and inclement weather, while their performance in distant regions remains unsatisfying. This paper proposes PriorDrive to address these limitations by directly harnessing the power of various vectorized prior maps, significantly enhancing the robustness and accuracy of online HD map construction. Our approach integrates a variety of prior maps uniformly, such as OpenStreetMap's Standard Definition Maps (SD maps), outdated HD maps from vendors, and locally constructed maps from historical vehicle data. To effectively integrate such prior information into online mapping models, we introduce a Hybrid Prior Representation (HPQuery) that standardizes the representation of diverse map elements. We further propose a Unified Vector Encoder (UVE), which employs fused prior embedding and a dual encoding mechanism to encode vector data. To improve the UVE's generalizability and performance, we propose a segment-level and point-level pre-training strategy that enables the UVE to learn the prior distribution of vector data. Through extensive testing on the nuScenes, Argoverse 2 and OpenLane-V2, we demonstrate that PriorDrive is highly compatible with various online mapping models and substantially improves map prediction capabilities. The integration of prior maps through PriorDrive offers a robust solution to the challenges of single-perception data, paving the way for more reliable autonomous driving.

Generative recommendation with large language models (LLMs) reframes prediction as sequence generation, yet existing LLM-based recommenders remain limited in leveraging geographic signals that are crucial in mobility and local-services scenarios.Here, we present REA-SONING OVER SPACE (ROS), a framework that utilizes geography as a vital decision variable within the reasoning process.ROS introduces a Hierarchical Spatial Semantic ID (SID) that discretizes coarse-to-fine locality and POI semantics into compositional tokens, and endows LLM with a three-stage Mobility Chain-of-Thought (CoT) paradigm that models user personality, constructs an intent-aligned candidate space, and performs locality informed pruning.We further align the model with real world geography via spatial-guided Reinforcement Learning (RL).Experiments on three widely used location-based social network (LBSN) datasets show that ROS achieves over 10% relative gains in hit rate over strongest LLM-based baselines and improves cross-city transfer, despite using a smaller backbone model.‡

With the rapid evolution of 3D generation algorithms, the cost of producing 3D humanoid character models has plummeted, yet the field is impeded by the lack of a comprehensive dataset for automatic rigging—a pivotal step in character animation. Addressing this gap, we present HumanRig, the first large-scale dataset specifically designed for 3D humanoid character rigging, encompassing 11,434 meticulously curated T-posed meshes adhered to a uniform skeleton topology. Capitalizing on this dataset, we introduce an innovative, data-driven automatic rigging framework, which overcomes the limitations of GNNbased methods in handling complex AI-generated meshes. Our approach integrates a Prior-Guided Skeleton Estimator (PGSE) module, which uses 2D skeleton joints to provide a preliminary 3D skeleton, and a Mesh-Skeleton Mutual Attention Network (MSMAN) that fuses skeleton features with 3D mesh features extracted by a U-shaped point transformer. This enables a coarse-to-fine 3D skeleton joint regression and a robust skinning estimation, surpassing previous methods in quality and versatility. This work not only remedies the dataset deficiency in rigging research but also propels the animation industry towards more efficient and automated character rigging pipelines.

Accurate lane topology is essential for autonomous driving, yet traditional methods struggle to model the complex, non-linear structures-such as loops and bidirectional lanes-prevalent in real-world road structure. We present SeqGrowGraph, a novel framework that learns lane topology as a chain of graph expansions, inspired by human map-drawing processes. Representing the lane graph as a directed graph $G=(V,E)$, with intersections ($V$) and centerlines ($E$), SeqGrowGraph incrementally constructs this graph by introducing one vertex at a time. At each step, an adjacency matrix ($A$) expands from $n \times n$ to $(n+1) \times (n+1)$ to encode connectivity, while a geometric matrix ($M$) captures centerline shapes as quadratic Bézier curves. The graph is serialized into sequences, enabling a transformer model to autoregressively predict the chain of expansions, guided by a depth-first search ordering. Evaluated on nuScenes and Argoverse 2 datasets, SeqGrowGraph achieves state-of-the-art performance.

Autoregressive transformers have revolutionized generative models in language processing and shown substantial promise in image and video generation. However, these models face significant challenges when extended to 3D generation tasks due to their reliance on next-token prediction to learn token sequences, which is incompatible with the unordered nature of 3D data. Instead of imposing an artificial order on 3D data, in this paper, we introduce G3PT, a scalable, coarse-to-fine 3D native generative model with cross-scale vector quantization and cross-scale autoregressive modeling. The key is to map point-based 3D data into discrete tokens with different levels of detail, naturally establishing a sequential relationship across a variety of scales suitable for autoregressive modeling. Remarkably, our method connects tokens globally across different levels of detail without manually specified ordering. Benefiting from this approach, G3PT features a versatile 3D generation pipeline that effortlessly supports the generation of 3D shapes under diverse conditional modalities. Extensive experiments demonstrate that G3PT achieves superior generation quality and generalization ability compared to previous baselines. Most importantly, for the first time in 3D generation, scaling up G3PT reveals distinct power-law scaling behaviors.

Creating a realistic animatable avatar from a single static portrait remains challenging. Existing approaches often struggle to capture subtle facial expressions, the associated global body movements, and the dynamic background. To address these limitations, we propose a novel framework that leverages a pretrained video diffusion Transformer model to generate high-fidelity, coherent talking portraits with controllable motion dynamics. At the core of our work is a dual-stage audio-visual alignment strategy. In the first stage, we employ a clip-level training scheme to establish coherent global motion by aligning audio-driven dynamics across the entire scene, including the reference portrait, contextual objects, and background. In the second stage, we refine lip movements at the frame level using a lip-tracing mask, ensuring precise synchronization with audio signals. To preserve identity without compromising motion flexibility, we replace the commonly used reference network with a lightweight cross-attention module that effectively maintains facial consistency throughout the video. Furthermore, we integrate a motion intensity modulation module that explicitly controls facial keypoints and body joint trajectories, enabling fine-grained manipulation of portrait movements beyond mere lip motion. Extensive experimental results show that our proposed approach achieves higher quality with better realism, coherence, motion intensity, and identity preservation. Our demo, code, models can be found on this page: https://fantasy-amap.github.io/fantasy-talking/.

Vision–Language–Action (VLA) models are increasingly used for end-to-end driving due to their world knowledge and reasoning ability. Most prior work, however, inserts textual chains-of-thought (CoT) as intermediate steps tailored to the current scene. Such symbolic compressions can blur spatio-temporal relations and discard fine visual cues, creating a cross-modal gap between perception and planning. We propose FSDrive, a visual spatio-temporal CoT framework that enables VLAs to think in images. The model first acts as a world model to generate a unified future frame that overlays coarse but physically-plausible priors—future lane dividers and 3D boxes—on the predicted future image. This unified frame serves as the visual CoT, capturing both spatial structure and temporal evolution. The same VLA then functions as an inverse-dynamics model, planning trajectories from current observations and the visual CoT. To equip VLAs with image generation while preserving understanding, we introduce a unified pre-training paradigm that expands the vocabulary to include visual tokens and jointly optimizes VQA (for semantics) and future-frame prediction (for dynamics). A progressive easy-to-hard scheme first predicts lane/box priors to enforce physical constraints, then completes full future frames for fine details. On nuScenes and NAVSIM, FSDrive improves trajectory accuracy and reduces collisions under both ST-P3 and UniAD metrics, and attains competitive FID for future-frame generation despite using lightweight autoregression. It also advances scene understanding on DriveLM. Together, these results indicate that visual CoT narrows the cross-modal gap and yields safer, more anticipatory planning. Code is available at https://github.com/MIV-XJTU/FSDrive.

Neural radiance fields (NeRF) have recently been applied to render large-scale scenes. However, their limited model capacity typically results in blurred rendering results. Existing large-scale NeRFs primarily address this limitation by partitioning the scene into blocks, which are subsequently handled by separate sub-NeRFs. These sub-NeRFs, trained from scratch and processed independently, lead to inconsistencies in geometry and appearance across the scene. Consequently, the rendering quality fails to exhibit significant improvement despite the expansion of model capacity. In this work, we present global-guided focal neural radiance field (GF-NeRF) that achieves high-fidelity rendering of large-scale scenes. Our proposed GF-NeRF utilizes a two-stage (Global and Focal) architecture and a global-guided training strategy. The global stage obtains a continuous representation of the entire scene while the focal stage decomposes the scene into multiple blocks and further processes them with distinct sub-encoders. Leveraging this two-stage architecture, sub-encoders only need fine-tuning based on the global encoder, thus reducing training complexity in the focal stage while maintaining scene-wide consistency. Spatial information and error information from the global stage also benefit the sub-encoders to focus on crucial areas and effectively capture more details of large-scale scenes. No-tably, our approach does not rely on any prior knowledge about the target scene, attributing GF-NeRF adaptable to various large-scale scene types, including street-view and aerial-view scenes. We demonstrate that our method achieves high-fidelity, natural rendering results on various types of large-scale datasets. Our project page: https://shaomq2187.github.io/GF-NeRF/

It is desirable for dialog systems to have capability to express specific emotions during a conversation, which has a direct, quantifiable impact on improvement of their usability and user satisfaction.After a careful investigation of real-life conversation data, we found that there are at least two ways to express emotions with language.One is to describe emotional states by explicitly using strong emotional words; another is to increase the intensity of the emotional experiences by implicitly combining neutral words in distinct ways.We propose an emotional dialogue system (EmoDS) that can generate the meaningful responses with a coherent structure for a post, and meanwhile express the desired emotion explicitly or implicitly within a unified framework.Experimental results showed EmoDS performed better than the baselines in BLEU, diversity and the quality of emotional expression.

A lack of labeled corpora obstructs the research progress on implicit discourse relation recognition (DRR) for Chinese, while there are some available discourse corpora in other languages, such as English. In this paper, we propose a cross-lingual implicit DRR framework that exploits an available English corpus for the Chinese DRR task. We use machine translation to generate Chinese instances from a labeled English discourse corpus. In this way, each instance has two independent views: Chinese and English views. Then we train two classifiers in Chinese and English in a co-training way, which exploits unlabeled Chinese data to implement better implicit DRR for Chinese. Experimental results demonstrate the effectiveness of our method.

Compared with single-modal sensorimotor task, cross-modal sensorimotor tasks such as Tai Chi are more complex because they require simultaneous control of joint motion and respiration. In this paper, we compared the performance of single and multi-sensory cues in single-modal and cross-modal tasks. The experimental results showed that for single-modal task of two joint motions, the performance of using both audio and vibrotactile cues was slightly worse than that of using single-sensory cues where both joints were guided by vibrotactile cues, which implied that the single-sensory cue was more suitable for the single-modal motor tasks while the multi-sensory cues might produce distraction to participants. For simultaneous control of joint motion and respiration, the multiple sensory cues produced better performance than the single sensory cues. The results implied that multi-sensory cues were more effective than single sensory cues in reducing mental workload when learning complex cross-modal motor tasks.

Simultaneous motion control of multiple joints has many potential applications such as Tai Chi, Yoga etc. The capability of vibrotactile cues to assist this kind of motor task has not been well explored. In this paper, we studied the effect of vibrotactile cues for guiding procedural motion of two joints on human's upper limbs. By mounting eight vibrotactile motors on two arms, we performed two experiments to measure human's perception and motor performance in response to the vibrotactile commands. In the first experiment, we measured perceptual performance of correctly identifying the location of two active vibrotactile cues. The difference between sustained, pulsed and hybrid vibration conditions was compared. To explore the possible reasons leading to the wrong perception results, the correct rate was ranked among different combinations of cues. In the second experiment, the correct rate of procedural motion control of two joints was measured, while vibrotactile cues were used as guidance signals to produce the motion command. The results showed that average correct rate of two cues localization on upper limbs was as high as 98%, while the average correct rate of procedural motion control of two joints was only 86%. Further analysis revealed that low correct rate of procedural motion control was caused by the unnatural motion pattern, i.e. two joints on a same arm and rotate in opposite directions.

Auditory or visual stimulation has been widely used for brainwave entrainment, i.e. to modulate brain electroencephalograms (EEG) signals into a specific target frequency band. In this work, we study whether similar phenomena exists with haptic stimulation. By using a Phantom desktop to provide a sinusoidal force stimulation to a human subject's hand, and using a Nexus EEG device for real-time brain signal monitoring, we test how the Sensory Motor Rhythm (SMR) signal and the Alpha signal of the subject responds to the haptic stimulation. Our experiments show that the energy level of SMR signal tends to increase considerably (on average 10~30% of 8 human subjects) after 10-15 minutes of haptic stimulation with a 15Hz stimulation signal, and the energy level of Alpha signal tends to decrease considerably (on average 10~30% of 8 human subjects) after 10-15 minutes of haptic stimulation with a 10Hz stimulation signal. These results may have potential application in training human concentration and/or relaxation skills.

Many applications meet certain programming patterns like pipeline, fork-join, do-all etc. While tools such as OS threads and OpenMP allow programmers only to express task or data parallelism, special support for programming patterns is distinctly lacking. Intel threading building blocks (TBB) is developed to address this problem, but its scheduler is general and not optimized for any of its parallel algorithms which include pipeline specially. In this paper, we provide a non-blocking framework for pipeline application on multi-core platform. We target linear pipeline in which each filter has one entrance and one exit. We design a novel work-stealing scheduler optimized specially for pipeline application: first, priority based stealing, priority is calculated for each filter in pipeline so that a worker can find the optimal "victim" easily when it needs to steal, second, multiple tasks can be stolen at a time so that much stealing time is reduced. A non-block queue is used to store intermediate result to reduce lock overhead and increase scalability. We apply our framework to four case studies, including text filter, two fish, ferret, ded up. And our framework reduces execution time of TBB by 72% in best case and 20% on average on an 8 core machine.

A family of flexible-core chip multiprocessors (FCMPs) has been recently proposed to allow simple, identical physical cores to be aggregated dynamically to form larger and more powerful logical processors. However, such flexible-core architecture faces a new significant scheduling problem in the operating system, which traditionally assumes only fixed-number and fixed-granularity processors. This paper proposes a framework, called FACRA, that employs low-level runtime software to simplify OS resource allocation and process scheduling on FCMPs. Through exporting a simple, uniform processor abstraction on flexible-core chip resource, FACRA provides a set of functions with uniform interface for system-level scheduling on FCMPs. To verify the design, FACRA is built on TFlex (a typical FCMP) in our experiments, and two well known process schedulers, round-robin and dynamic-priority scheduler of Linux 2.6.11, are modified to schedule on TFlex. The evaluation results demonstrate that FACRA can efficiently simplify OS resource allocation and process scheduling on FCMPs with negligible performance loss.

The Cell Broadband Engine is a typical heterogeneous chip multiprocessor which provides potential high performance for computing-intensive applications. Our researches focus on how to use Cell to speed up block cryptography applications. In this paper, we propose a mapping framework for block cryptography working in ECB mode and corresponding optimizing strategy. We take four algorithms(RC5, 3DES, AES, and Twofish) as benchmark and implement these four algorithms using Cell programming language. In order to enhance the performance, we present an optimizing strategy and evaluate the effects of the optimizing methods including compiler optimization, dual buffering, vectorization, and loop unrolling. The experiments indicate that all these four algorithms can obtain 5-20 times speedup compared with traditional processors, which shows that our mapping framework and optimizing strategy are effective for the block cryptography algorithms.