XPENG-Peking University Collaborative Research Accepted by AAAI 2026: Introducing a Novel Visual Token Pruning Framework for Autonomous Driving
Rhea-AI Summary
XPENG (NYSE:XPEV) and Peking University announced that their paper "FastDriveVLA: Efficient End-to-End Driving via Plug-and-Play Reconstruction-based Token Pruning" was accepted to AAAI 2026. The research introduces FastDriveVLA, a reconstruction-based visual token pruning framework for Vision-Language-Action models that aims to focus on essential visual information and ignore irrelevant background.
Key metrics: AAAI received 23,680 submissions with a 17.6% acceptance rate; FastDriveVLA cut visual tokens from 3,249 to 812 and achieved a ~7.5x reduction in computational load on the nuScenes benchmark while preserving planning accuracy.
Positive
- ~7.5x reduction in computational load on nuScenes benchmark
- Visual tokens reduced from 3,249 to 812, enabling lighter onboard inference
- Paper accepted at AAAI 2026 with a 17.6% acceptance rate
Negative
- None.
Key Figures
Market Reality Check
Peers on Argus
XPEV gained 6.18%, outpacing Chinese EV peers like LI (+2.53%) and NIO (+4.08%), while others such as RIVN (-1.51%) and F (-0.19%) were down, suggesting a stock-specific reaction to the AI research news.
Historical Context
| Date | Event | Sentiment | Move | Catalyst |
|---|---|---|---|---|
| Dec 15 | Global expansion | Positive | -3.6% | Malaysia localized EV production and strong overseas growth metrics. |
| Dec 01 | Delivery update | Positive | -2.2% | Robust November deliveries and high overseas growth plus AI Day recap. |
| Nov 17 | Earnings release | Positive | -10.3% | Q3 2025 revenue, margin improvements, and strong delivery growth. |
| Nov 05 | Earnings preview | Neutral | -4.0% | Scheduling of Q3 2025 earnings call and access details for investors. |
| Oct 31 | Delivery update | Positive | +0.5% | Record October deliveries and expansion into seven new markets. |
Recent positive operational and financial updates often saw negative or muted next-day price reactions, indicating a tendency for the stock to fade good news.
Over the last few months, XPENG reported strong growth in deliveries, record monthly volumes, and significant international expansion, including localized production in Malaysia and entry into new markets across Europe and APAC. Q3 2025 results showed rapid revenue growth and improving margins, yet shares often traded lower after these updates. The current AAAI 2026 AI recognition builds on earlier AI Day and VLA 2.0 announcements, reinforcing XPENG’s focus on full-stack autonomous driving capabilities.
Market Pulse Summary
This announcement showcases XPENG’s AI depth, with its FastDriveVLA framework reportedly delivering a 7.5x reduction in computational load while maintaining planning accuracy, and acceptance at the selective AAAI 2026 conference. It builds on prior AI Day and VLA 2.0 disclosures, reinforcing a full-stack autonomy strategy. Investors may track how quickly such research is deployed into production vehicles and whether it supports future margin or performance improvements.
AI-generated analysis. Not financial advice.
- XPENG-PKU Research Breakthrough: XPENG, in collaboration with Peking University, has developed FastDriveVLA—a novel visual token pruning framework that enables autonomous driving AI to "drive like a human" by focusing only on essential information, achieving a 7.5x reduction in computational load.
- Top-Tier AI Recognition: The research has been accepted by AAAI 2026, one of the world's premier AI conferences, which had a highly selective acceptance rate of just
17.6% this year. - Accelerating L4 Autonomy: This achievement underscores XPENG's full-stack capabilities in AI-driven mobility and advances the industry toward efficient, scalable deployment of next-generation autonomous driving systems.
The paper introduces FastDriveVLA, an efficient visual token pruning framework specifically designed for end-to-end autonomous driving Vision-Language-Action (VLA) models. This work offers a new approach to visual token pruning by enabling AI to "drive like a human", focusing only on essential visual information while filtering out irrelevant data.
As AI large models evolve rapidly, VLA models are being widely adopted in end-to-end autonomous driving systems due to their strong capabilities in complex scene understanding and action reasoning. These models encode images into large numbers of visual tokens, which serve as the foundation for the model to "see" the world and make driving decisions. However, processing large numbers of tokens increases computational load onboard the vehicle, impacting inference speed and real-time performance.
While visual token pruning has been recognized as a viable method to accelerate VLA inference, existing approaches, whether based on text-visual attention or token similarity, have shown limitations in driving scenarios. To address this, XPENG and PKU developed FastDriveVLA, a novel reconstruction-based token pruning framework inspired by how human drivers focus on relevant foreground information while ignoring non-critical background areas.
The method introduces an adversarial foreground-background reconstruction strategy that enhances the model's ability to identify and retain valuable tokens. On the nuScenes autonomous driving benchmark, FastDriveVLA achieved state-of-the-art performance across various pruning ratios. When the number of visual tokens was reduced from 3,249 to 812, the framework achieved a nearly 7.5x reduction in computational load while maintaining high planning accuracy.
This is the second time this year that XPENG has been recognized at top-tier global AI conference. In June, XPENG was the only Chinese automaker invited to speak at CVPR WAD, where it shared advances in autonomous driving foundation models. At its AI Day in November, XPENG unveiled VLA 2.0 architecture, which removes the "language translation" step and enables direct Visual-to-Action generation, a breakthrough that redefines the conventional V-L-A pipeline.
These accomplishments reflect XPENG's full-stack in-house capabilities, from model architecture design and training to distillation and vehicle deployment. Looking ahead, XPENG remains committed to achieving L4 level autonomous driving to accelerate the integration of physical AI systems into vehicles, with the goal of delivering safe, efficient, and comfortable intelligent driving experiences to users around the world.
About XPENG
XPENG is committed to leading the transformation of future mobility through technological exploration, positioning itself as "Explorer of Future Mobility". Headquartered in
XPENG pursues a global strategy for research, development, and sales, with an R&D center in
On August 27, 2020, XPENG officially listed on the New York Stock Exchange (NYSE: XPEV), raising funds in an IPO that set a record at the time for the global new energy vehicle industry. On July 7, 2021, the company listed on the Hong Kong Stock Exchange (HKEX: 9868), becoming the first Chinese new-energy automaker to achieve dual primary listings in both
For more information, please visit https://www.xpeng.com/.
Contacts:
For Media Enquiries: Alison Liang, XPENG PR Department
Email: liangrq3@xiaopeng.com
View original content:https://www.prnewswire.com/news-releases/xpeng-peking-university-collaborative-research-accepted-by-aaai-2026-introducing-a-novel-visual-token-pruning-framework-for-autonomous-driving-302650038.html
SOURCE XPENG
FAQ
What did XPENG (XPEV) announce on December 29, 2025 about FastDriveVLA?
How could FastDriveVLA affect XPEV vehicle autonomy performance and costs?
When was the XPENG–Peking University paper accepted to AAAI and how selective was it?
What benchmark and metrics validated FastDriveVLA for XPEV research?
Does XPENG plan to use FastDriveVLA in production vehicles soon?
