AI Paper Atlas

Research map / Benchmarks / NIV T=3

NIV T=3 leaderboard

10 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on NIV T=3. Best success rate: 32.37 (ViterbiPlanNet, CVPR 2026).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

NIV T=3 · success rate

10 papers, each with its best reported number for its own method; higher is better.

#success rate ↑MethodPaperTopic
132.37ViterbiPlanNetViterbiPlanNet: Injecting Procedural Knowledge via Differentiable Viterbi for Planning in Instructional Videos
CVPR 2026 · Table 3
Visual and representation RL
231.25PDPPPDPP:Projected Diffusion for Procedure Planning in Instructional Videos
CVPR 2023 · Table 4
Action recognition
328.94SCHEMA w/ VEDiT
SCHEMA
VEDIT: Latent Prediction Architecture For Procedural Video Representation Learning
ICLR 2025 · Procedure planning table
Video segmentation and tracking
428.52MTIDMasked Temporal Interpolation Diffusion for Procedure Planning in Instructional Videos
ICLR 2025 · Table 3
Action recognition
527.93SCHEMASCHEMA: State CHangEs MAtter for Procedure Planning in Instructional Videos
ICLR 2024 · Appendix NIV table
Agents, code and math
627.04PKDD (stdPDPP)
PDPP
Procedure Knowledge Decoupled Distillation Strategy for Procedure Planning in Instructional Videos
AAAI 2025 · Table 3
Knowledge distillation
726.74PlanLLM
Vicuna-7B
PlanLLM: Video Procedure Planning with Refinable Large Language Models
AAAI 2025 · Table 2
Agents, code and math
826.05E3P (Ours)Event-Guided Procedure Planning from Instructional Videos with Text Supervision
ICCV 2023 · Table 3
Action recognition
924.68P3IVP3IV: Probabilistic Procedure Planning From Instructional Videos With Weak Supervision
CVPR 2022 · Table: NIV and COIN results
Action recognition
1024.44KEPPWhy Not Use Your Textbook? Knowledge-Enhanced Procedure Planning of Instructional Videos
CVPR 2024 · Table 3
Human-AI and goal-conditioned

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.