XPENG–Peking College Collaborative Analysis Accepted By AAAI 2026: Introducing A Novel Visible Token Pruning Framework For Autonomous Driving

Help CleanTechnica’s work by means of a Substack subscription or on Stripe.

• XPENG-PKU Analysis Breakthrough: XPENG, in collaboration with Peking College, has developed FastDriveVLA—a novel visible token pruning framework that permits autonomous driving AI to “drive like a human” by focusing solely on important data, reaching a 7.5x discount in computational load.
• Prime-Tier AI Recognition: The analysis has been accepted by AAAI 2026, one of many world’s premier AI conferences, which had a extremely selective acceptance fee of simply 17.6% this yr.
• Accelerating L4 Autonomy: This achievement underscores XPENG’s full-stack capabilities in AI-driven mobility and advances the trade towards environment friendly, scalable deployment of next-generation autonomous driving programs.

GUANGZHOU, China – XPENG, in collaboration with Peking College, has had its paper “FastDriveVLA: Environment friendly Finish-to-Finish Driving by way of Plug-and-Play Reconstruction-based Token Pruning” accepted by AAAI 2026, one of many world’s prime conferences in synthetic intelligence. AAAI 2026 obtained 23,680 submissions, with solely 4,167 papers accepted, an acceptance fee of simply 17.6%.

The paper introduces FastDriveVLA, an environment friendly visible token pruning framework particularly designed for end-to-end autonomous driving Imaginative and prescient-Language-Motion (VLA) fashions. This work presents a brand new method to visible token pruning by enabling AI to “drive like a human”, focusing solely on important visible data whereas filtering out irrelevant information.

As AI massive fashions evolve quickly, VLA fashions are being extensively adopted in end-to-end autonomous driving programs attributable to their robust capabilities in advanced scene understanding and motion reasoning. These fashions encode pictures into massive numbers of visible tokens, which function the muse for the mannequin to “see” the world and make driving choices. Nonetheless, processing massive numbers of tokens will increase computational load onboard the car, impacting inference velocity and real-time efficiency.

Whereas visible token pruning has been acknowledged as a viable technique to speed up VLA inference, current approaches, whether or not based mostly on text-visual consideration or token similarity, have proven limitations in driving eventualities. To handle this, XPENG and PKU developed FastDriveVLA, a novel reconstruction-based token pruning framework impressed by how human drivers concentrate on related foreground data (e.g., lanes, automobiles, pedestrians) whereas ignoring non-critical background areas.

The strategy introduces an adversarial foreground-background reconstruction technique that enhances the mannequin’s capability to determine and retain worthwhile tokens. On the nuScenes autonomous driving benchmark, FastDriveVLA achieved state-of-the-art efficiency throughout varied pruning ratios. When the variety of visible tokens was decreased from 3,249 to 812, the framework achieved a virtually 7.5x discount in computational load whereas sustaining excessive planning accuracy.

That is the second time this yr that XPENG has been acknowledged at a top-tier world AI convention. In June, XPENG was the one Chinese language automaker invited to talk at CVPR WAD, the place it shared advances in autonomous driving basis fashions. At its Tech Day in November, XPENG unveiled its VLA 2.0 structure, which removes the “language translation” step and allows direct Visible-to-Motion technology, a breakthrough that redefines the traditional V-L-A pipeline.

These accomplishments mirror XPENG’s full-stack in-house capabilities, from mannequin structure design and coaching to distillation and car deployment. Trying forward, XPENG stays dedicated to reaching L4 degree autonomous driving. We’ll proceed to spend money on AI massive mannequin know-how to speed up the mixing of bodily AI programs into automobiles, with the aim of delivering protected, environment friendly, and comfy clever driving experiences to customers all over the world.

About XPENG

XPENG is dedicated to main the transformation of future mobility by means of technological exploration, positioning itself as “Explorer of Future Mobility”. Headquartered in Guangzhou, China, the corporate operates R&D facilities in Beijing, Shanghai, Shenzhen, Zhaoqing, and Yangzhou, and has established clever manufacturing bases in Zhaoqing and Guangzhou.
XPENG pursues a world technique for analysis, growth, and gross sales, with an R&D middle in the US and subsidiaries throughout a number of European international locations. The corporate adheres to full-stack in-house growth of clever driver-assistance software program and the event of core {hardware}, delivering an distinctive clever driving and driving expertise for customers.
On August 27, 2020, XPENG formally listed on the New York Inventory Alternate (NYSE: XPEV), elevating funds in an IPO that set a file on the time for the worldwide new vitality car trade. On July 7, 2021, the corporate listed on the Hong Kong Inventory Alternate (HKEX: 9868), changing into the primary Chinese language new-energy automaker to realize twin major listings in each Hong Kong and New York.

For extra data, please go to https://www.xpeng.com/.