AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

DH-VLM: Dual-Horizon Cooperative Latent Reasoning for Autonomous Driving

Ziyi Song, Chen Xia, Hang Yu, Sheng Zhou, Zhisheng Niu

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Reinforcement learning for visual reasoning · 0 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 HLA (hierarchical latent aggregation) instead of MLP (ablation)DH-VLM · DAIR-V2Xavg L2 error (m): 2.31 -> 1.87Improved
add HLA instead of MLP (ablation)DH-VLM · DAIR-V2Xavg collision rate (%): 0.39 -> 0.19Improved
add IDLE instead of MLP (ablation)DH-VLM · DAIR-V2Xavg L2 error (m): 2.48 -> 1.87Improved
add IDLE instead of MLP (ablation)DH-VLM · DAIR-V2Xavg collision rate (%): 0.34 -> 0.19Improved
add fusion in infrastructure vision encoder (ablation)infrastructure VLM · DAIR-V2Xavg L2 error (m): 5.19 -> 3.92Improved
add fundamental scene understanding QA data (ablation)infrastructure VLM with fusion · DAIR-V2Xavg L2 error (m): 3.92 -> 2.52Improved
add ego-personalized comprehension QA data (ablation)infrastructure VLM with fusion and F QA · DAIR-V2Xavg L2 error (m): 2.52 -> 1.72Improved
fuse 8 intermediate layers instead of only the final layer (ablation)DH-VLM (5:1) · DAIR-V2Xavg L2 error (m): 2.06 -> 1.87Improved
increase fused layers from 8 to 16 (ablation)DH-VLM (5:1) · DAIR-V2Xavg L2 error (m): 1.87 -> 1.88No clear effect
reduce fused layers from 8 to 4 (ablation)DH-VLM (5:1) · DAIR-V2Xavg L2 error (m): 1.87 -> 1.93Hurt
lower communication frequency from 5:1 to 10:1 (ablation)DH-VLM (8 layers) · DAIR-V2Xavg L2 error (m): 1.87 -> 2.21Hurt
raise communication frequency from 5:1 to 1:1 (ablation)DH-VLM (8 layers) · DAIR-V2Xavg L2 error (m): 1.87 -> 1.80Improved

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