Astra: Toward General-Purpose Mobile Robots via Hierarchical Multimodal Learning

Modern robot navigation systems encounter difficulties in diverse and complex indoor environments. Traditional approaches rely on multiple modules with small models or rule-based systems and thus lack adaptability to new environments. To address this, we developed Astra, a comprehensive dual-model architecture, Astra-Global and Astra-Local, for mobile robot navigation. Astra-Global, a multimodal LLM, processes vision and language inputs to perform self and goal localization using a hybrid topological-semantic graph as the global map, and outperforms traditional visual place recognition methods. Astra-Local, a multitask network, handles local path planning and odometry estimation. Its 4D spatial-temporal encoder, trained through self-supervised learning, generates robust 4D features for downstream tasks. The planning head utilizes flow matching and a novel masked ESDF loss to minimize collision risks for generating local trajectories, and the odometry head integrates multi-sensor inputs via a transformer encoder to predict the relative pose of the robot. Deployed on real in-house mobile robots, Astra achieves high end-to-end mission success rate across diverse indoor environments.

LARES: Latent Reasoning for Sequential Recommendation

Sequential recommender systems have become increasingly important in real-world applications that model user behavior sequences to predict their preferences. However, existing sequential recommendation methods predominantly rely on non-reasoning paradigms, which may limit the model's computational capacity and result in suboptimal recommendation performance. To address these limitations, we present LARES, a novel and scalable LAtent REasoning framework for Sequential recommendation that enhances model's representation capabilities through increasing the computation density of parameters by depth-recurrent latent reasoning. Our proposed approach employs a recurrent architecture that allows flexible expansion of reasoning depth without increasing parameter complexity, thereby effectively capturing dynamic and intricate user interest patterns. A key difference of LARES lies in refining all input tokens at each implicit reasoning step to improve the computation utilization. To fully unlock the model's reasoning potential, we design a two-phase training strategy: (1) Self-supervised pre-training (SPT) with dual alignment objectives; (2) Reinforcement post-training (RPT). During the first phase, we introduce trajectory-level alignment and step-level alignment objectives, which enable the model to learn recommendation-oriented latent reasoning patterns without requiring supplementary annotated data. The subsequent phase utilizes reinforcement learning (RL) to harness the model's exploratory ability, further refining its reasoning capabilities. Comprehensive experiments on real-world benchmarks demonstrate our framework's superior performance. Notably, LARES exhibits seamless compatibility with existing advanced models, further improving their recommendation performance.

Action is All You Need: Dual-Flow Generative Ranking Network for Recommendation

We introduce the Dual-Flow Generative Ranking Network (DFGR), a two-stream architecture designed for recommendation systems. DFGR integrates innovative interaction patterns between real and fake flows within the QKV modules of the self-attention mechanism, enhancing both training and inference efficiency. This approach effectively addresses a key limitation observed in Meta's proposed HSTU generative recommendation approach, where heterogeneous information volumes are mapped into identical vector spaces, leading to training instability. Unlike traditional recommendation models, DFGR only relies on user history behavior sequences and minimal attribute information, eliminating the need for extensive manual feature engineering. Comprehensive evaluations on open-source and industrial datasets reveal DFGR's superior performance compared to established baselines such as DIN, DCN, DIEN, and DeepFM. We also investigate optimal parameter allocation strategies under computational constraints, establishing DFGR as an efficient and effective next-generation generate ranking paradigm.

UAV-Enabled Joint Sensing, Communication, Powering and Backhaul Transmission in Maritime Monitoring Networks

This paper addresses the challenge of energy-constrained maritime monitoring networks by proposing an unmanned aerial vehicle (UAV)-enabled integrated sensing, communication, powering and backhaul transmission scheme with a tailored time-division duplex frame structure. Within each time slot, the UAV sequentially implements sensing, wireless charging and uplink receiving with buoys, and lastly forwards part of collected data to the central ship via backhaul links. Considering the tight coupling among these functions, we jointly optimize time allocation, UAV trajectory, UAV-buoy association, and power scheduling to maximize the performance of data collection, with the practical consideration of sea clutter effects during UAV sensing. A novel optimization framework combining alternating optimization, quadratic transform and augmented first-order Taylor approximation is developed, which demonstrates good convergence behavior and robustness. Simulation results show that under sensing quality-of-service constraint, buoys are able to achieve an average data rate over 22bps/Hz using around 2mW harvested power per active time slot, validating the scheme's effectiveness for open-sea monitoring. Additionally, it is found that under the influence of sea clutters, the optimal UAV trajectory always keeps a certain distance with buoys to strike a balance between sensing and other multi-functional transmissions.

Generative Diffusion Model Driven Massive Random Access in Massive MIMO Systems

Massive random access is an important technology for achieving ultra-massive connectivity in next-generation wireless communication systems. It aims to address key challenges during the initial access phase, including active user detection (AUD), channel estimation (CE), and data detection (DD). This paper examines massive access in massive multiple-input multiple-output (MIMO) systems, where deep learning is used to tackle the challenging AUD, CE, and DD functions. First, we introduce a Transformer-AUD scheme tailored for variable pilot-length access. This approach integrates pilot length information and a spatial correlation module into a Transformer-based detector, enabling a single model to generalize across various pilot lengths and antenna numbers. Next, we propose a generative diffusion model (GDM)-driven iterative CE and DD framework. The GDM employs a score function to capture the posterior distributions of massive MIMO channels and data symbols. Part of the score function is learned from the channel dataset via neural networks, while the remaining score component is derived in a closed form by applying the symbol prior constellation distribution and known transmission model. Utilizing these posterior scores, we design an asynchronous alternating CE and DD framework that employs a predictor-corrector sampling technique to iteratively generate channel estimation and data detection results during the reverse diffusion process. Simulation results demonstrate that our proposed approaches significantly outperform baseline methods with respect to AUD, CE, and DD.

Cross-Link Interference Mitigation With Over-the-Air Pilot Forwarding for Dynamic TDD

Dynamic time-division duplex (D-TDD) aided mobile communication systems bear the potential to achieve significantly higher spectral efficiency than traditional static TDD based systems. However, strong cross-link interference (CLI) may be caused by different transmission directions between adjacent cells in D-TDD systems, thus degrading the performance. Most existing CLI mitigation schemes require sharing certain information among base stations (BSs) via backhaul links. This strategy is usually expensive and suffers high latency. Alternatively, we propose a pilot information sharing scheme based on over-the-air forwarding of the downlink pilot of the interfering BS to the interfered BS via a wireless terminal, along with a dedicated CLI channel estimation method. Simulation results demonstrate that thanks to the proposed pilot information sharing scheme the classic interference rejection combining (IRC) receiver achieves a signal detection performance highly comparable to that of the IRC detector with perfect pilot information, necessitating no information sharing among BSs via backhaul links. Furthermore, the proposed CLI channel estimation scheme reduces the impact of errors introduced by pilot forwarding, thereby improving the performance of both CLI channel estimation and signal detection.

SkyReels-V2: Infinite-length Film Generative Model

Recent advances in video generation have been driven by diffusion models and autoregressive frameworks, yet critical challenges persist in harmonizing prompt adherence, visual quality, motion dynamics, and duration: compromises in motion dynamics to enhance temporal visual quality, constrained video duration (5-10 seconds) to prioritize resolution, and inadequate shot-aware generation stemming from general-purpose MLLMs' inability to interpret cinematic grammar, such as shot composition, actor expressions, and camera motions. These intertwined limitations hinder realistic long-form synthesis and professional film-style generation. To address these limitations, we propose SkyReels-V2, an Infinite-length Film Generative Model, that synergizes Multi-modal Large Language Model (MLLM), Multi-stage Pretraining, Reinforcement Learning, and Diffusion Forcing Framework. Firstly, we design a comprehensive structural representation of video that combines the general descriptions by the Multi-modal LLM and the detailed shot language by sub-expert models. Aided with human annotation, we then train a unified Video Captioner, named SkyCaptioner-V1, to efficiently label the video data. Secondly, we establish progressive-resolution pretraining for the fundamental video generation, followed by a four-stage post-training enhancement: Initial concept-balanced Supervised Fine-Tuning (SFT) improves baseline quality; Motion-specific Reinforcement Learning (RL) training with human-annotated and synthetic distortion data addresses dynamic artifacts; Our diffusion forcing framework with non-decreasing noise schedules enables long-video synthesis in an efficient search space; Final high-quality SFT refines visual fidelity. All the code and models are available at https://github.com/SkyworkAI/SkyReels-V2.

BLIA: Detect model memorization in binary classification model through passive Label Inference attack

Model memorization has implications for both the generalization capacity of machine learning models and the privacy of their training data. This paper investigates label memorization in binary classification models through two novel passive label inference attacks (BLIA). These attacks operate passively, relying solely on the outputs of pre-trained models, such as confidence scores and log-loss values, without interacting with or modifying the training process. By intentionally flipping 50% of the labels in controlled subsets, termed "canaries," we evaluate the extent of label memorization under two conditions: models trained without label differential privacy (Label-DP) and those trained with randomized response-based Label-DP. Despite the application of varying degrees of Label-DP, the proposed attacks consistently achieve success rates exceeding 50%, surpassing the baseline of random guessing and conclusively demonstrating that models memorize training labels, even when these labels are deliberately uncorrelated with the features.

AFDM-Enabled Integrated Sensing and Communication: Theoretical Framework and Pilot Design

The integrated sensing and communication (ISAC) has been envisioned as one representative usage scenario of sixth-generation (6G) network. However, the unprecedented characteristics of 6G, especially the doubly dispersive channel, make classical ISAC waveforms rather challenging to guarantee a desirable performance level. The recently proposed affine frequency division multiplexing (AFDM) can attain full diversity even under doubly dispersive effects, thus becoming a competitive candidate for next-generation ISAC waveforms. Relevant investigations are still at an early stage, which involve only straightforward design lacking explicit theoretical analysis. This paper provides an in-depth investigation on AFDM waveform design for ISAC applications. Specifically, the closed-form Cr\'{a}mer-Rao bounds of target detection for AFDM are derived, followed by a demonstration on its merits over existing counterparts. Furthermore, we formulate the ambiguity function of the pilot-assisted AFDM waveform for the first time, revealing conditions for stable sensing performance. To further enhance both the communication and sensing performance of the AFDM waveform, we propose a novel pilot design by exploiting the characteristics of AFDM signals. The proposed design is analytically validated to be capable of optimizing the ambiguity function property and channel estimation accuracy simultaneously as well as overcoming the sensing and channel estimation range limitation originated from the pilot spacing. Numerical results have verified the superiority of the proposed pilot design in terms of dual-functional performance.

In-Memory Massive MIMO Linear Detector Circuit with Extremely High Energy Efficiency and Strong Memristive Conductance Deviation Robustness

The memristive crossbar array (MCA) has been successfully applied to accelerate matrix computations of signal detection in massive multiple-input multiple-output (MIMO) systems. However, the unique property of massive MIMO channel matrix makes the detection performance of existing MCA-based detectors sensitive to conductance deviations of memristive devices, and the conductance deviations are difficult to be avoided. In this paper, we propose an MCA-based detector circuit, which is robust to conductance deviations, to compute massive MIMO zero forcing and minimum mean-square error algorithms. The proposed detector circuit comprises an MCA-based matrix computing module, utilized for processing the small-scale fading coefficient matrix, and amplifier circuits based on operational amplifiers (OAs), utilized for processing the large-scale fading coefficient matrix. We investigate the impacts of the open-loop gain of OAs, conductance mapping scheme, and conductance deviation level on detection performance and demonstrate the performance superiority of the proposed detector circuit over the conventional MCA-based detector circuit. The energy efficiency of the proposed detector circuit surpasses that of a traditional digital processor by several tens to several hundreds of times.