Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

CoRL 2026

AI overview

Sign in and the AI will write an overview from our coverage.

Headlines · 4

  1. Huawei Noah's The North Star Wins BEHAVIOR-1K Challenge 2026

    Huawei Noah's embodied intelligence team The North Star reportedly won BEHAVIOR-1K Challenge 2026 among 57 participating teams using the HiPhys-RSI framework, with a reported Q-score of about 0.683 and a 48.2% full-task success rate across 100 household tasks. HiPhys-RSI uses frozen programming agents and vision-language models to build, test, and revise executable robot pipelines, storing improvements as structured knowledge. The results come largely from the team's technical report, and hidden tests showed score declines on most tasks, along with sampling variation across only 10 instances per task.

    机器之心 · 🔥 0
  2. BAIR Details Its Research Schedule at CoRL 2026

    BAIR Blog says UC Berkeley faculty, postdocs and students will present 33 main-conference papers at CoRL 2026, along with four late-breaking-results posters and 10 oral or spotlight presentations. The conference runs November 9–12 in Austin, with Negar Mehr scheduled to deliver an Early Career Keynote. The schedule lists session windows rather than individual presentation times, and late-breaking-result coverage may still grow.

    BAIR Blog · 🔥 0
  3. CoRL 2026 reports a sharp jump in accepted papers

    雷峰网 AI reports that CoRL 2026 accepted 687 papers, up from 263 in 2025 and roughly 200 per year historically. Its analysis finds that China’s institutional participation rose from 5.9% in 2021 to 37.5% in 2026, while Tsinghua University led 2026 contributors with 58 papers. However, standardized affiliation data covers only 480 of the 687 papers, so the institutional rankings remain provisional.

    雷峰网 AI · 🔥 0
  4. SafeDriveVLA decouples navigation-conflict reasoning from driving actions

    A paper accepted at CoRL 2026 and submitted to arXiv on 14 October (arXiv:2610.20609) proposes SafeDriveVLA, a driving vision-language-action model that explicitly predicts a three-level navigation-compliance mode to decouple conflict reasoning from action generation, and uses navigation-conditioned world-model dreaming to determine when following the navigation signal is safe. The authors also present a benchmark suite that evaluates navigation following, conflict awareness and adversarial robustness together, reporting that existing VLAs fall short on both, with SimLingo completing no language-instructed lane change in closed loop. They report SafeDriveVLA reaching 88.16 Driving Score and 68.64% Success Rate on Bench2Drive, lifting closed-loop language following by 49.3% and cutting collisions under unsafe instructions from 60 to 38 versus the best SimLingo variant.

    Hugging Face · Papers · 🔥 0

Experience and discussion from the community

Share my CoRL 2026 experienceAsk about CoRL 2026

Nobody has shared their experience with CoRL 2026 yet.