World Engine generates realistic safety-critical driving variations from logs for reinforcement post-training, reducing benchmark failures more than data scaling and showing collision reductions plus on-road gains in a production system.
Clip model is an efficient continual learner
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
AREA stabilizes attribute extraction with principal geodesic analysis on hyperspherical space and aggregation with lightweight task experts plus variational bottleneck and optimal transport routing, outperforming SOTA in CLIP-based CIL.
NoFA-BC proposes a non-forgetting allocator using recursive least-squares and bi-level competition for improved knowledge allocation in class-incremental learning.
GR4CIL introduces gap-compensated routing to enable reliable task-aware knowledge routing in CLIP-based class incremental learning while preserving zero-shot generalization.
citing papers explorer
-
World Engine: Towards the Era of Post-Training for Autonomous Driving
World Engine generates realistic safety-critical driving variations from logs for reinforcement post-training, reducing benchmark failures more than data scaling and showing collision reductions plus on-road gains in a production system.
-
AREA: Attribute Extraction and Aggregation for CLIP-Based Class-Incremental Learning
AREA stabilizes attribute extraction with principal geodesic analysis on hyperspherical space and aggregation with lightweight task experts plus variational bottleneck and optimal transport routing, outperforming SOTA in CLIP-based CIL.
-
Non-Forgetting Knowledge Allocation with Bi-level Competition for Class-Incremental Learning
NoFA-BC proposes a non-forgetting allocator using recursive least-squares and bi-level competition for improved knowledge allocation in class-incremental learning.
-
GR4CIL: Gap-compensated Routing for CLIP-based Class Incremental Learning
GR4CIL introduces gap-compensated routing to enable reliable task-aware knowledge routing in CLIP-based class incremental learning while preserving zero-shot generalization.