AnchorReasoning: A Visual Grounding and Causal Reasoning Dataset in Long-Tail Autonomous Driving Scenarios

arXiv:2609.28366 · cs.CV, cs.AI · Submitted 2026-09-23 · Read on arXiv

cs.CV, cs.AI

Submitted: 2026-09-23

Updated: 2026-09-23

Code: https://github.com/nvidia-cosmos/cosmos-reason2

Terminology

• Grounding — 32× in this paper · explained in 3 episodes
• Visual Grounding — 10× in this paper · explained in 2 episodes
• Accuracy — 8× in this paper · explained in 1 episode
• Ablation — 6× in this paper · explained in 1 episode
• Consistency — 6× in this paper · explained in 3 episodes
• Fine-Tuning — 6× in this paper · explained in 5 episodes
• Adaptation — 4× in this paper · explained in 1 episode
• Causal Reasoning — 4× in this paper · explained in 2 episodes
• Supervised Fine-Tuning — 4× in this paper
• Rater Feedback Score — 3× in this paper
• Structured Reasoning — 3× in this paper · explained in 3 episodes
• AI Foundation Model — 2× in this paper · explained in 1 episode
• Adam — 2× in this paper · explained in 2 episodes
• Benchmark — 2× in this paper · explained in 2 episodes
• Domain Adaptation — 2× in this paper · explained in 5 episodes
• Foundation Model — 2× in this paper · explained in 3 episodes
• Foundation Models — 2× in this paper · explained in 7 episodes
• Hallucination — 2× in this paper · explained in 3 episodes
• Vision-Language Models (VLMs) — 2× in this paper · explained in 6 episodes
• Action Space — 1× in this paper · explained in 1 episode
• Adaptive Reasoning — 1× in this paper · explained in 2 episodes
• Average Displacement Error — 1× in this paper
• Chain-of-Thought (CoT) — 1× in this paper · explained in 4 episodes
• Core — 1× in this paper · explained in 2 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Final Displacement Error — 1× in this paper
• Generative AI — 1× in this paper · explained in 2 episodes
• Human-in-the-Loop — 1× in this paper · explained in 3 episodes
• Instance Segmentation — 1× in this paper · explained in 3 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Segmentation Masks — 1× in this paper · explained in 2 episodes
• Supervised Fine-Tuning (SFT) — 1× in this paper · explained in 8 episodes
• Temporal Reasoning — 1× in this paper · explained in 2 episodes
• Unified Framework — 1× in this paper · explained in 5 episodes

Sources

• Qwen3-VL Technical Report
• Qwen2.5-VL Technical Report
• nuReasoning: A Reasoning-Centric Dataset and Benchmark for Long-Tail Autonomous Driving
• Alpamayo-R1: Bridging Reasoning and Action Prediction for Generalizable Autonomous Driving in the Long Tail

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models