AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

ViterbiPlanNet: Injecting Procedural Knowledge via Differentiable Viterbi for Planning in Instructional Videos

Luigi Seminara, Davide Moltisanti, Antonino Furnari

CVPR 2026 · Reinforcement learning › Visual and representation RL · approach: RL for combinatorial routing · 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 differentiable Viterbi layer during training (ablation)ViterbiPlanNet base model · CrossTask (T=3)Success Rate (%): 32.47 -> 38.09 (VD inference)Improved
add Viterbi decoding or DVL only at inference to a model trained without DVL (ablation)base model · CrossTask (T=3)Success Rate (%): 32.47 -> 32.99 / 32.09 / 30.77No clear effect
use emissions directly (argmax) at inference after DVL training (ablation)ViterbiPlanNet · CrossTask (T=3)Success Rate (%): 38.09 -> 20.05Hurt
add standard Viterbi decoding on top of DVL soft plan (ablation)ViterbiPlanNet · CrossTask (T=3)Success Rate (%): 37.66 -> 38.45No clear effect
enable PKG via guided training rather than conditioning or post-processing (ablation)ViterbiPlanNet vs KEPP/PlanLLM/SCHEMA · CrossTask (T=3)SR gain from PKG (%): +5.98 vs +2.56, +1.97, +3.31Improved
add PKG into LLM prompt (ablation)Qwen3-30B · CrossTask (T=3)Success Rate (%): 23.37 -> 23.31No clear effect
train with DVL and PKG instead of transformer planner (SCHEMA) at small training fractions (ablation)ViterbiPlanNet · CrossTask (T=3, training data fraction)Success Rate (%)Improved
ViterbiPlanNet vs SCHEMA when trained on T=6, tested on T=3ViterbiPlanNet · CrossTask cross-horizonSuccess Rate (%): 16.12 -> 27.77Improved
ViterbiPlanNet vs MTID under MTID protocolViterbiPlanNet · CrossTask (T=3)Success Rate (%): 40.45 -> 39.75No clear effect
ViterbiPlanNet vs best baseline on mIoUViterbiPlanNet · CrossTask (T=3)mIoU (%): -0.05 ± 0.27 (CrossTask mIoU)No clear effect

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