Ji Luo

Jakob Engel, Kiran Somasundaram, Michael Goesele et al. · mit

Egocentric, multi-modal data as available on future augmented reality (AR) devices provides unique challenges and opportunities for machine perception. These future devices will need to be all-day wearable in a socially acceptable form-factor to support always available, context-aware and personalized AI applications. Our team at Meta Reality Labs Research built the Aria device, an egocentric, multi-modal data recording and streaming device with the goal to foster and accelerate research in this area. In this paper, we describe the Aria device hardware including its sensor configuration and the corresponding software tools that enable recording and processing of such data.

Ling Team, Binwei Zeng, Chao Huang et al.

In this technical report, we tackle the challenges of training large-scale Mixture of Experts (MoE) models, focusing on overcoming cost inefficiency and resource limitations prevalent in such systems. To address these issues, we present two differently sized MoE large language models (LLMs), namely Ling-Lite and Ling-Plus (referred to as "Bailing" in Chinese, spelled Bǎilíng in Pinyin). Ling-Lite contains 16.8 billion parameters with 2.75 billion activated parameters, while Ling-Plus boasts 290 billion parameters with 28.8 billion activated parameters. Both models exhibit comparable performance to leading industry benchmarks. This report offers actionable insights to improve the efficiency and accessibility of AI development in resource-constrained settings, promoting more scalable and sustainable technologies. Specifically, to reduce training costs for large-scale MoE models, we propose innovative methods for (1) optimization of model architecture and training processes, (2) refinement of training anomaly handling, and (3) enhancement of model evaluation efficiency. Additionally, leveraging high-quality data generated from knowledge graphs, our models demonstrate superior capabilities in tool use compared to other models. Ultimately, our experimental findings demonstrate that a 300B MoE LLM can be effectively trained on lower-performance devices while achieving comparable performance to models of a similar scale, including dense and MoE models. Compared to high-performance devices, utilizing a lower-specification hardware system during the pre-training phase demonstrates significant cost savings, reducing computing costs by approximately 20%. The models can be accessed at https://huggingface.co/inclusionAI.

Zhaowei Wang, Lishu Luo, Haodong Duan et al.

Long-context modeling is becoming a core capability of modern large vision-language models (LVLMs), enabling sustained context management across long-document understanding, video analysis, and multi-turn tool use in agentic workflows. Yet practical training recipes remain insufficiently explored, particularly for designing and balancing long-context data mixtures. In this work, we present a systematic study of long-context continued pre-training for LVLMs, extending a 7B model from 32K to 128K context with extensive ablations on long-document data. We first show that long-document VQA is substantially more effective than OCR transcription. Building on this observation, our ablations further yield three key findings: i) for sequence-length distribution, balanced data outperforms target-length-focused data (e.g., 128K), suggesting that long-context ability requires generalizable key-information retrieval across various lengths and positions; ii) retrieval remains the primary bottleneck, favoring retrieval-heavy mixtures with modest reasoning data for task diversity; and iii) pure long-document VQA largely preserves short-context capabilities, suggesting that instruction-formatted long data reduces the need for short-data mixing. Based on these findings, we introduce MMProLong, obtained by long-context continued pre-training from Qwen2.5-VL-7B with only a 5B-token budget. MMProLong improves long-document VQA scores by 7.1% and maintains strong performance at 256K and 512K contexts beyond its 128K training window, without additional training. It further generalizes to webpage-based multimodal needle retrieval, long-context vision-text compression, and long-video understanding without task-specific supervision. Overall, our study establishes a practical LongPT recipe and an empirical foundation for advancing long-context vision-language models.

Ji Luo, Yaxuan Chen, Guangchi Zhang et al.

Enhancing user fairness in advanced multi-user systems like two-layer rate-splitting multiple access (RSMA) is a critical yet challenging task. This letter proposes a novel movable antenna (MA) approach to address this challenge. We formulate a max-min fairness problem, maximizing the minimum user rate, a key metric for fairness, through the joint optimization of the beamforming matrices, user clustering, common rate allocation, and the antenna position vector (APV). To solve this non-convex problem, we develop an efficient two-loop iterative algorithm. The outer-loop leverages the dynamic neighborhood pruning particle swarm optimization method to find a high-quality APV, while the inner-loop optimizes the remaining variables for a given APV. Simulation results validate our approach, demonstrating that the proposed scheme yields significant fairness gains over various benchmark schemes.

Yifan Li, Javad Sohankar, Ji Luo et al.

Quantifying and forecasting individual brain aging trajectories is critical for understanding neurodegenerative disease and the heterogeneity of aging, yet current approaches remain limited. Most models predict chronological age, an imperfect surrogate for biological aging, or generate synthetic MRIs that enhance data diversity but fail to capture subject-specific trajectories. Here, we present BrainPath, a 3D generative framework that learns longitudinal brain aging dynamics during training and, at inference, predicts anatomically faithful MRIs at arbitrary timepoints from a single baseline scan. BrainPath integrates an age calibration loss, a swap learning strategy, and an age perceptual loss to preserve subtle, biologically meaningful variations. Across held-out ADNI and an independent NACC dataset, BrainPath outperforms state-of-the-art reference models in structural similarity (SSIM), mean squared error (MSE), peak signal-to-noise ratio (PSNR), and MRI age-difference accuracy, while capturing realistic and temporally consistent aging patterns. Beyond methodological innovation, BrainPath enables personalized mapping of brain aging, synthetic follow-up scan prediction, and trajectory-based analyses, providing a foundation for precision modeling of brain aging and supporting research into neurodegeneration and aging interventions.

Ji Luo, Hui Cao, Jie Wang et al.

Voxel-based 3D object classification has been thoroughly studied in recent years. Most previous methods convert the classic 2D convolution into a 3D form that will be further applied to objects with binary voxel representation for classification. However, the binary voxel representation is not very effective for 3D convolution in many cases. In this paper, we propose a hybrid cascade architecture for voxel-based 3D object classification. It consists of three stages composed of fully connected and convolutional layers, dealing with easy, moderate, and hard 3D models respectively. Both accuracy and speed can be balanced in our proposed method. By giving each voxel a signed distance value, an obvious gain regarding the accuracy can be observed. Besides, the mean inference time can be speeded up hugely compared with the state-of-the-art point cloud and voxel based methods.

Shengyu Zhao, Tingfung Lau, Ji Luo et al.

3D medical image registration is of great clinical importance. However, supervised learning methods require a large amount of accurately annotated corresponding control points (or morphing), which are very difficult to obtain. Unsupervised learning methods ease the burden of manual annotation by exploiting unlabeled data without supervision. In this paper, we propose a new unsupervised learning method using convolutional neural networks under an end-to-end framework, Volume Tweening Network (VTN), for 3D medical image registration. We propose three innovative technical components: (1) An end-to-end cascading scheme that resolves large displacement; (2) An efficient integration of affine registration network; and (3) An additional invertibility loss that encourages backward consistency. Experiments demonstrate that our algorithm is 880x faster (or 3.3x faster without GPU acceleration) than traditional optimization-based methods and achieves state-of-theart performance in medical image registration.