arXiv subjects

Jason Lu

Publications and source records attributed to Jason Lu.

5 recordsLinked to original sources

arXiv2026

The Impact of Shared Autonomous Vehicles in Microtransit Systems: A Case Study in Atlanta

Microtransit systems represent an enhancement to solve the first- and last-mile problem, integrating traditional rail and bus networks with on-demand shuttles into a flexible, integrated system. This type of demand responsive transport provides greater accessibility and higher quality levels of service compared to conventional fixed-route transit services. Advances in technology offer further opportunities to enhance microtransit performance. In particular, shared autonomous vehicles (SAVs) have the potential to transform the mobility landscape by enabling more sustainable operations, enhanced user convenience, and greater system reliability. This paper investigates the integration of SAVs in microtransit systems, advancing the technological capabilities of on-demand shuttles. A shuttle dispatching optimization model is enhanced to accommodate for driver behavior and SAV functionalities. A model predictive control approach is proposed that dynamically rebalances on-demand shuttles towards areas of higher demand without relying on vast historical data. Scenario-driven experiments are conducted using data from the MARTA Reach microtransit pilot. The results demonstrate that SAVs can elevate both service quality and user experience compared to traditional on-demand shuttles in microtransit systems.

eess.SY↗

arXiv2025

Alpamayo-R1: Bridging Reasoning and Action Prediction for Generalizable Autonomous Driving in the Long Tail

End-to-end architectures trained via imitation learning have advanced autonomous driving by scaling model size and data, yet performance remains brittle in safety-critical long-tail scenarios where supervision is sparse and causal understanding is limited. We introduce Alpamayo-R1 (AR1), a vision-language-action model (VLA) that integrates Chain of Causation reasoning with trajectory planning for complex driving scenarios. Our approach features three key innovations: (1) the Chain of Causation (CoC) dataset, built through a hybrid auto-labeling and human-in-the-loop pipeline producing decision-grounded, causally linked reasoning traces aligned with driving behaviors; (2) a modular VLA architecture combining Cosmos-Reason, a vision-language model pre-trained for Physical AI, with a diffusion-based trajectory decoder that generates dynamically feasible trajectories in real time; (3) a multi-stage training strategy using supervised fine-tuning to elicit reasoning and reinforcement learning (RL) to enforce reasoning-action consistency and optimize reasoning quality. AR1 achieves up to a 12% improvement in planning accuracy on challenging cases compared to a trajectory-only baseline, with a 35% reduction in close encounter rate in closed-loop simulation. RL post-training improves reasoning quality by 45% and reasoning-action consistency by 37%. Model scaling from 0.5B to 7B parameters shows consistent improvements. On-vehicle road tests confirm real-time performance (99 ms latency) and successful urban deployment. By bridging interpretable reasoning with precise control, AR1 demonstrates a practical path towards Level 4 autonomous driving. Model weights are available at https://huggingface.co/nvidia/Alpamayo-R1-10B with inference code at https://github.com/NVlabs/alpamayo.

cs.RO↗

arXiv2025

Nemotron-H: A Family of Accurate and Efficient Hybrid Mamba-Transformer Models

As inference-time scaling becomes critical for enhanced reasoning capabilities, it is increasingly becoming important to build models that are efficient to infer. We introduce Nemotron-H, a family of 8B and 56B/47B hybrid Mamba-Transformer models designed to reduce inference cost for a given accuracy level. To achieve this goal, we replace the majority of self-attention layers in the common Transformer model architecture with Mamba layers that perform constant computation and require constant memory per generated token. We show that Nemotron-H models offer either better or on-par accuracy compared to other similarly-sized state-of-the-art open-sourced Transformer models (e.g., Qwen-2.5-7B/72B and Llama-3.1-8B/70B), while being up to 3$\times$ faster at inference. To further increase inference speed and reduce the memory required at inference time, we created Nemotron-H-47B-Base from the 56B model using a new compression via pruning and distillation technique called MiniPuzzle. Nemotron-H-47B-Base achieves similar accuracy to the 56B model, but is 20% faster to infer. In addition, we introduce an FP8-based training recipe and show that it can achieve on par results with BF16-based training. This recipe is used to train the 56B model. We are releasing Nemotron-H base model checkpoints with support in Hugging Face and NeMo.

cs.CL↗

arXiv2023

Semi-Supervised Learning with Multiple Imputations on Non-Random Missing Labels

Semi-Supervised Learning (SSL) is implemented when algorithms are trained on both labeled and unlabeled data. This is a very common application of ML as it is unrealistic to obtain a fully labeled dataset. Researchers have tackled three main issues: missing at random (MAR), missing completely at random (MCAR), and missing not at random (MNAR). The MNAR problem is the most challenging of the three as one cannot safely assume that all class distributions are equal. Existing methods, including Class-Aware Imputation (CAI) and Class-Aware Propensity (CAP), mostly overlook the non-randomness in the unlabeled data. This paper proposes two new methods of combining multiple imputation models to achieve higher accuracy and less bias. 1) We use multiple imputation models, create confidence intervals, and apply a threshold to ignore pseudo-labels with low confidence. 2) Our new method, SSL with De-biased Imputations (SSL-DI), aims to reduce bias by filtering out inaccurate data and finding a subset that is accurate and reliable. This subset of the larger dataset could be imputed into another SSL model, which will be less biased. The proposed models have been shown to be effective in both MCAR and MNAR situations, and experimental results show that our methodology outperforms existing methods in terms of classification accuracy and reducing bias.

cs.LG↗

arXiv2023

The Impact of Congestion and Dedicated Lanes on On-Demand Multimodal Transit Systems

Traffic congestion can have a detrimental effect on public transit systems, and understanding and mitigating these effects is of critical importance for effective public transportation. Implementing Dedicated Bus Lanes (DBLs) is a well-known intervention to achieve this goal. A DBL is a designated lane for bus transit, which avoids congestion and substantially lowers the travel time. This makes transit more attractive, encouraging more travelers to adopt public transportation. This paper studies the impact of congestion and DBLs on novel On-Demand Multimodal Transit Systems (ODMTS). ODMTS combine traditional rail and bus networks with on-demand shuttles. Previous case studies have shown that ODMTS may simultaneously improve travel time, reduce system cost, and attract new passengers. Those benefits were shown for an ideal world without traffic congestion, and this paper hypothesizes that the advantages of ODMTS can be even more pronounced in the real world. This paper explores this hypothesis by creating realistic congestion scenarios and solving bilevel optimization problems to design ODMTS under these scenarios. The impact of DBLs on ODMTS is evaluated with a comprehensive case study in the Metro Atlanta Area. The results show that DBLs can significantly improve travel times and are effective at increasing adoption of the system.

math.OC↗