English NewsSunday, 15 November 2026
Latest
Arrest warrant issued after absence from coastal statue caseTwo respondents summoned over alleged breach of online-posting orderLandslide alerts cover parts of seven districts until November 12 eveningUnregistered shop signs removed along Adampan main roadCocaine case involving three defendants set for January 25 pre-trial conferenceMirissa guide says viral boat video showed play between friendsWhat could a change of government in Israel mean for relations with India?Sri Lanka keeps electricity tariffs unchanged for final quarterFive-working-day business registration pilot begins in selected Sri Lanka divisionsDrone taxi project takes flight at Colombo Port CityPooja Hegde draws crowds at Colombo fashion-store openingMinistry explains private fuel price flexibility and plans 72 CPC stations
AI

XCoT-VLA: Executable Chain-of-Thought for Vision-Language-Action Driving

2026-08-11

XCoT-VLA: Executable Chain-of-Thought for Vision-Language-Action Driving. NOAA-L brochure, NOAA Observation of the Earth and its Environment Survey of Mis (PDM 1.0)

Authors/institution: XPeng Foundation Model Team, XPeng Inc. Venue/status: arXiv preprint, submitted 11 August 2026. Problem: verbose natural-language reasoning is slow and difficult to optimise for real-time driving control. Contribution: two-to-six executable reasoning tokens jointly condition fixed trajectory queries. Practical significance: compact intermediate representations may make VLA planners more efficient. Limitations: company-authored, unreproduced, dataset-specific metrics and no safety case or on-road deployment evidence. Paper

More AI technology news

More in AI

Autonomous driving research — XCoT-VLA

Autonomous driving research — XCoT-VLA

Research studies monitoring

Research studies monitoring

In-Context VLA argues robots should consume grounded language rather than generate free-form reasoning

In-Context VLA argues robots should consume grounded language rather than generate free-form reasoning

FlashVLA: Streaming Action Decoding for Fast and Asynchronous VLA Inference

FlashVLA: Streaming Action Decoding for Fast and Asynchronous VLA Inference

Text Capability Loss in Vision-Language Adaptation: An Attention-Sink Diagnosis

Text Capability Loss in Vision-Language Adaptation: An Attention-Sink Diagnosis