ODEWorld: A Continuous Predictive Architecture via Physical-Time Flow

In the physical world we inhabit, space and time are fundamentally continuous. However, existing machine learning paradigms for world modeling are largely confined to discrete-time prediction, thereby exhibiting significant inefficiency in capturing the dynamics of physical world. We introduce Physical-Time Flow (\textbf{PT-Flow}), a novel approach that learns a continuous latent velocity field operating in physical time. Crucially, the underlying dynamics of sequential data are parameterized by an ordinary differential equation (ODE) embedded in a well-structured representation space. Under this paradigm, the prediction of future can be recast as temporal integration via an ODE solver in the compressed latent space. Building upon PT-Flow, we construct \textbf{ODEWorld}, a continuous-time latent world model that is both efficient and versatile. By extracting time-variant features and enforcing ODE properties on both the dynamical representation space and the latent velocity field, ODEWorld effectively addresses the long-standing representation collapse issue in latent world model literature. This also enables high-quality image reconstruction even after long-horizon prediction. Moreover, its continuous nature allows for arbitrary temporal resolution and even backward prediction, which is impossible for most discrete-time models. Lastly, ODEWorld can provide rich planning-oriented information to facilitate downstream policy learning. Comprehensive experiments demonstrate that ODEWorld successfully reconciles planning-conducive dynamics abstraction with visual realism, excelling in both video generation and robotic control. \href{https://dstate.github.io/odeworld_website/}{Project Website}.

SGTP: Sampling-based Game-Theoretic Planning for Real-Time Multi-Vehicle Autonomous Racing

Autonomous multi-vehicle racing requires real-time planning of diverse competitive behaviors in intense interactions. Existing planners often struggle to balance strategic diversity and computational efficiency. To address this challenge, we propose Sampling-based Game-Theoretic Planning (SGTP), a real-time framework that combines game-theoretic reasoning with GPU-accelerated sampling of control sequences and dynamics rollouts. Sampled trajectories are ranked using a game-aware cost to capture competitive interactions and generate diverse racing behaviors. Our planner then performs feasibility selection by explicitly enforcing track-boundary and dynamic collision-avoidance constraints, ensuring safe and reliable transitions between racing strategies. Extensive simulations on challenging tracks show that SGTP achieves a 95.24% win rate and a 99.35% task-completion ratio in highly interactive races, with a mean computational time of 0.095 s over multiple iterative solving steps. We also demonstrate the successful application of SGTP in large-scale scenarios with up to 10 agents. We release our code and provide an open-source benchmark of multi-agent autonomous racing algorithms to facilitate future research. Project page: https://sgtp-racing.github.io/.

RPG-VST: Robust Poisson-Gaussian Variance Stabilization for Blind RAW Denoising

Variance stabilization with the generalized Anscombe transform (GAT) enables frozen Gaussian denoisers to process Poisson--Gaussian (PG) RAW noise, but its reliability depends on fitted shot/read-noise parameters. In blind single-image deployment, these parameters are estimated from low-texture RAW statistics that are often corrupted by residual texture, clipping, defective pixels, and read-noise floors. Such contamination yields heavy-tailed log-variance residuals, making ordinary least-squares PG calibration brittle and causing severe tail failures despite favorable average PSNR. We propose RPG-VST, a robust no-reference variance-stabilization framework for blind RAW denoising. RPG-VST estimates PG parameters separately for each color filter array (CFA) plane using a Student-$t$ log-variance objective with robust tile statistics and physical constraints. It then estimates the stabilized-domain noise level $σ_z$ from tile variance ratios and uses it as a reliability signal. For each image, RPG-VST selects the robust fit or the conventional OLS fit according to which produces $σ_z$ closer to unit variance, requiring no clean reference or learned threshold. On SID Sony SID$50$, SIDD, and ELD with frozen SwinIR and Restormer denoisers, RPG-VST improves mean PSNR in all six dataset--backbone settings. It reduces severe tails, defined as cases whose PSNR gain over Direct is below $-1$ dB, in four settings and leaves them unchanged in the other two. On SIDD, it yields $+1.83/+1.92$ dB and reduces severe tails from $44/36$ to $7/4$. Ablations show that the $σ_z$ gate prevents regressions of ungated robust fitting on read-noise-dominated ELD captures.

Fashion-3DLR: A Controllable 3D Garment Generation Using Pairwise Fashion Elements for Intelligent Design

AI-generated content (AIGC) has made significant progress, with 2D generative models becoming ready-to-use tools for the digital fashion industry. However, 3D garment generation remains in its nascent stage, where in the realm of fashion, the semantic information of diverse design elements exhibits intricate coupling relationships in 3D representations, posing substantial challenges for generating diverse 3D garments. In this work, to handle the above problem, We introduce Fashion-3DLR, a novel 3D garment generation framework that utilizes diverse design elements to create high-quality, versatile 3D garment assets. Specifically, to bridge the semantic gaps between different fashion elements, we propose a Garment Feature Fusion Diffusion Transformer (GFF-DiT) module to integrate 2D fashion design elements, e.g., sketch and texture, into latent space. Within the latent space, we then employ a rectified flow transformer to generate geometry latents, which can be decoded into various 3D garment representations, including 3D Gaussians and meshes. Furthermore, we integrate Fashion-3DLR into downstream tasks, achieving the 3D Gaussian Splatting (3DGS)-driven cloth physical simulation and mesh-based virtual try-on. Experimental results indicate that Fashion-3DLR surpass the previous state-of-the-art methods, which verify that the proposed work can generate well-structured, non-watertight garments capable of physical simulation and virtual try-on, underscoring its potential as a versatile 3D garment design tool.

JEPA-CFM: A Joint Embedding Predictive Architecture-based Channel Foundation Model for Robust Fluid Antenna Systems

Fluid antenna systems (FAS) have emerged as a promising technology for sixth-generation (6G) wireless networks. By allowing antenna elements to move freely within a compact region, FAS can exploit rich spatial diversity without additional hardware. However, acquiring real-time channel state information (CSI), extrapolating channel values to unmeasured antenna ports, and determining accurate user positions remain major obstacles. These challenges stem mainly from strong spatial correlations within the limited aperture and the scarcity of observable data. To overcome these limitations, this paper introduces joint embedding predictive architecture (JEPA)-based channel foundation model (CFM) specifically designed for FAS. The model adopts JEPA to learn versatile representations by extracting high-level latent embeddings of masked or unobserved channel segments. Unlike conventional approaches that attempt pixel-by-pixel reconstruction of raw CSI coefficients, JEPA-CFM focuses on predicting abstract structures in a compact feature space. The pre-training objective combines three complementary loss terms: the standard masked autoencoder reconstruction loss, the JEPA latent prediction loss, and a sliced isotropic Gaussian regularization (SIGReg) term. Together, these components prevent representation collapse and significantly enhance robustness under severe spatial correlation and highly sparse observations. After pre-training, the encoder is frozen, and lightweight task-specific heads are attached: a decoder for channel extrapolation and a global average pooling layer followed by a multi-layer perceptron regression head for wireless positioning. Extensive simulations in the realistic DeepMIMO urban scenario demonstrate that JEPA-CFM substantially outperforms the conventional masked autoencoder baseline in channel extrapolation and wireless positioning.

Pailitao-MMSearch: Building Native E-Commerce Multimodal Search Foundation

The evolution of e-commerce has fundamentally transformed how users search for products, shifting from simple text-based keyword queries to complex multimodal interactions that seamlessly combine product images, natural language descriptions, and mixed-intent instructions. However, existing approaches face a critical dilemma: single-modal specialist models, deployed independently for text retrieval, visual search, and voice recognition, operate in isolation and cannot handle cross-modal queries, while general-purpose vision-language models lack the domain-specific knowledge necessary for fine-grained product understanding, user behavior modeling, and commercial intent reasoning. In this work, we present Pailitao-MMSearch, one native e-commerce multimodal search foundation model designed to bridge this gap. Our approach introduces three key innovations: (1)HybSID (Hybrid Semantic ID);(2)a two-stage continual pre-training strategy; and (3)a hybrid reasoning post-training pipeline. Built upon Qwen and deployed on Taobao's Pailitao multimodal search platform, Pailitao-MMSearch achieves substantial improvements in online A/B testing, including up to +13.61\% in Gross Merchandise Volume (GMV) and +8.21\% in transaction volume compared to traditional multi-modal search pipeline, demonstrating the effectiveness of our native e-commerce multimodal search large language models.

Semi-Supervised Conditional Diffusion via Label Augmentation

Conditional diffusion models have become a powerful and flexible framework for learning complex conditional distributions from labeled data. In practice, however, acquiring high-quality labels is costly and time-consuming, leaving large volumes of unlabeled data unused. To address this, we introduce label-augmented conditional diffusion (LACD), a simple and effective approach that incorporates unlabeled examples by assigning them a designated trivial label and performing joint denoising score matching over the augmented dataset. We provide sufficient conditions guaranteeing population-level identifiability of the target conditional distribution under this scheme. Moreover, we establish rigorous statistical guarantees: when sufficiently many unlabeled samples are available, the sampling distribution produced by LACD converges strictly faster than the purely supervised estimator in total variation distance, and at least as fast in Wasserstein-1 distance. Extensive experiments on synthetic, image, and tabular benchmarks corroborate our theory and show substantial gains in sample efficiency and generative performance compared with the purely supervised estimator.

CFM-Bench: A Unified Multi-Domain, Multi-Task Benchmark for Channel Foundation Models

Channel foundation models (CFMs) are developing rapidly, with recent studies reporting benefits from pretraining across downstream wireless tasks. Yet CFMs are commonly evaluated in model-specific pipelines with different data, radio configurations, partitions, adaptation procedures, task definitions, and metrics. Reported comparisons therefore tend to show that pretraining improves over supervised training from scratch within one pipeline, but neither rank CFMs nor compare them fairly with task-specific models. We release CFM-Bench, a unified multi-domain, multi-task benchmark designed to address this gap. It curates six channel configurations spanning 3GPP statistical simulation, two independent ray-tracing pipelines, industrial and aerial measurements, and synchronized vehicular multimodal simulation. Official partitions isolate complete trajectories, measurement sessions, vehicle links, simulation realizations, or buffered spatial regions. CFM-Bench does not prescribe an external pretraining corpus or strategy; no benchmark split may be used for foundation-model pretraining, and the official training split is reserved exclusively for downstream fine-tuning. The benchmark additionally requires disclosure of all data used during model development and prohibits training-stage use of official test units. Six task groups are organized along three CFM application dimensions: physical-layer (PHY) channel intelligence, radio-access-network (RAN) decision intelligence, and integrated sensing and communication (ISAC). They cover CSI feedback, frequency and temporal channel extrapolation, propagation-state classification, current- and future-beam prediction, and single-frame and temporal localization. CFM-Bench provides a common substrate for comparing the transferability of channel representations across models, domains, and tasks.

Conditional Generative Learning Enabled Wireless UAV Sensing and Tracking via Point Cloud Imaging

In this paper, we study an unmanned aerial vehicle (UAV) sensing and tracking problem, where a base station equipped with an antenna array continuously illuminates a flying UAV and exploits the reflected echoes for slot-wise point cloud imaging within its potential flight region. To accomplish this task, the imaging region for each slot is determined based on the prior of the historical UAV positions. Then, the UAV is represented by an electromagnetic point cloud in this region that contains its spatial information and electromagnetic properties (EPs), enabling the unified extraction of UAV position, attitude, and shape from the reconstructed point cloud. The EP point cloud imaging for the UAV based on echo signals is a complex inverse problem. To this end, we propose an Array-based Unified Generative UAV Sensing and Tracking (AUGUST) approach, which integrates a conditional channel encoding module and a generative decoding module. The encoding module incorporates position and signal-to-noise ratio embeddings to stabilize the UAV intrinsic feature extraction under fast UAV position and channel variations, and maps the encoded features to a latent space regularized by a learnable flow-based prior. The decoding module employs a diffusion model with a weighted training objective to reconstruct the UAV point cloud guided by the extracted features. The simulation results demonstrate that the reconstructed point clouds via the proposed AUGUST approach present higher fidelity compared to the benchmark schemes, thereby enabling a more accurate capture of the UAV attitude and shape information. The AUGUST approach also presents a substantial gain over the conventional model-based baseline in positioning performance.

Chat2Scenic: An Iterative RAG-Based Framework for Scenario Generation in Autonomous Driving

Validating autonomous driving systems requires diverse, regulation-compliant test scenarios. In simulation-based testing, scenarios are defined as executable scripts. Yet automatically generating such scripts from regulatory descriptions remains an open challenge, and existing approaches face fundamental trade-offs. Retrieval-assemble methods achieve reasonable compilation rates but lack scalability, whereas retrieval-based full-script generation suffers from low compilation success rates. We present Chat2Scenic, the first iterative retrieval-augmented framework to generate scenario scripts in Domain Specific Language (DSL). Specifically, Chat2Scenic provides a chatbot interface that supports interactive scenario refinement and integrates Retrieval-augmented Generation (RAG) to ground scenario generation in regulatory knowledge and DSL syntax. Furthermore, we propose an open benchmark for scenario generation comprising 123 scenarios from various regulations, including NHTSA and United Nations Vehicle Regulations, as well as other sources. Extensive evaluation with State-of-the-Art (SOTA) Large Language Models (LLMs) demonstrates that Chat2Scenic achieves 76.42% Compilation Success Rate (CSR) and 58.17% Framework Accuracy (FA), outperforming existing methods (Retrieval Assemble with 30.08% CSR, 11.03% FA and Retrieval full script generation with 16.26% CSR, 10.86% FA). To facilitate future research, we release our code as open source at https://github.com/TUM-AVS/chat2scenic.