AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

ASSCG: Just-Right Gating over Chattering for Fast–Slow LLM Planning in Autonomous Driving

Sining Ang, Yuan Chen, Liu Haiyan, Xuanyao Mao, jason bao, Xuliang Xuliang, Bingchuan Sun, Yan Wang

ECCV 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Dense features and foundation priors · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add ASSCG gate to AsyncDriverAsyncDriver · nuPlan Hard20score: 65.00 -> 67.28Improved
add ASSCG gate to AsyncDriverAsyncDriver · nuPlan Hard20latency (s/frame): 0.80 -> 0.32Improved
replace fixed 5-frame schedule with learned ASSCG at equal latencyAsyncDriver · nuPlan Hard20score: 64.27 -> 67.28Improved
add RL fine-tuning (GRPO) after SFT (ablation)ASSCG · nuPlan Hard20score: 66.21 -> 67.28Improved
use GRPO instead of PPO (ablation)ASSCG · nuPlan Hard20score: 66.76 -> 67.28Improved
use RWKV instead of Transformer backbone (ablation)ASSCG · nuPlan Hard20last-frame gate latency (s): 0.06 -> 0.02Improved
use RWKV instead of Transformer backbone (ablation)ASSCG · nuPlan Hard20score: 67.21 -> 67.28No clear effect
add Drop action (ablation)ASSCG · nuPlan Hard20score: 66.71 -> 67.28Improved
raise query-cost weight lambda_call from 0.001 to 0.0020 (ablation)ASSCG · nuPlan Hard20score: 67.28 -> 65.61Hurt
lower query-cost weight lambda_call from 0.001 to 0.0005 (ablation)ASSCG · nuPlan Hard20score: 67.28 -> 67.25No clear effect
add confidence cue to gate input (ablation)ASSCG · nuPlan Hard20score: 67.28 -> 67.33No clear effect
delay every Query by 3 frames (ablation)ASSCG · nuPlan Hard20score: 67.28 -> 66.76Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy