Writing study: SimScale: Learning to Drive via Real-World Simulation at Scale

CVPR overviewCorpus atlasBy contribution typeVisual galleryRules & templateWriting patternsPaper studies

← CVPR 2026 oral writing corpus

Haochen Tian, Tianyu Li, Haochen Liu, Jiazhi Yang, Yihang Qiu, Guang Li, junli wang, Yinfeng Gao, Zhang Zhang, Liang Wang, Hangjun Ye, Long Chen, Hongyang Li · Official CVPR 2026 oral record

Observed writing choices, not acceptance rules. This study examines the inspected manuscript version. It does not establish why the paper was accepted or that its presentation choices should be copied unchanged.

Figure, table and section ledger

Editorial contribution type: Datasets, benchmarks & measurement (primary).

Layout extraction, not a required paper template. Counts are distinct caption labels; a multi-panel figure counts once. Section spans are estimated from heading positions, including floats and whitespace. Method and limitations.

Canonical PDF

10 physical pages

Before references / appendix

≈ 8.16 page-equivalents

Main figures / tables

5 / 4

Attached appendix figures / tables

0 / 0

Attached appendix span

Separate file recorded below; not in this PDF total

Before references / appendix: ≈ 81.6%References / intervening material: ≈ 18.4%Estimated layout envelopes, not text/artwork area. Unresolved appendix boundaries remain within the undivided post-body material.

Extraction notes: No attached appendix boundary detected. Zero means no recognized caption, not independently verified absence.

Section-by-section lengths and source pages

The title/abstract/front matter precede the first numbered heading. A span ends at the next detected top-level heading, not at the last sentence; end-page whitespace is included. References and statements are listed separately. These are not measurements of text-only or artwork area.

Top-level heading	Starts on PDF page	Estimated span	Share of entire PDF
1. Real-World Data	1	≈ 0.06 pp.	0.6%
2. Scalable Simulation Data	1	≈ 0.52 pp.	5.2%
3. Vocabulary Scoring	1	≈ 7.04 pp.	70.4%
4. Conclusion	8	≈ 0.28 pp.	2.8%
Acknowledgments	9	≈ 0.11 pp.	1.1%
References	9	≈ 1.84 pp.	18.4%

All detected figure and table locations

Main text

• Figure 1 · p. 1
• Figure 2 · p. 3
• Figure 3 · p. 5
• Table 1 · p. 6
• Table 2 · p. 6
• Figure 4 · p. 7
• Figure 5 · p. 7
• Table 3 · p. 8
• Table 4 · p. 8

Attached appendix

No recognized caption labels.

Separate source files—excluded from canonical-PDF totals

A separate author version may repeat main text and references. Whole-file lengths and counts are not extra appendix material and are never added to the canonical PDF totals. Read the study's source scope for which sections received substantive reading versus layout inspection.

Additional source 1

Separate PDF (or ZIP containing it): whole-file layout of 13 physical pages; 9 detected figures and 6 tables. These may include overlapping main-text material.

Located appendix only: starts on physical p.1; ≈ 12.94 page-equivalents, 9 figure labels and 6 table labels. This interval is distinct from the whole file.

Detected heading	PDF page	Estimated span
Supplementary Material	1	≈ 0.02 pp.
A. Related Work	1	≈ 0.04 pp.
B. Extended Implementation Details	1	≈ 0.03 pp.
C. Extended Experimental Results	1	≈ 0.04 pp.
D. Additional Experimental Results	1	≈ 0.04 pp.
E. Limitations and Broader Impact	1	≈ 0.04 pp.
F. License of Assets	1	≈ 8.77 pp.
References	10	≈ 3.95 pp.

• Figure 1 · p. 2
• Table 1 · p. 2
• Table 2 · p. 2
• Table 3 · p. 3
• Table 4 · p. 3
• Figure 2 · p. 4
• Table 5 · p. 4
• Figure 3 · p. 5
• Figure 4 · p. 5
• Table 6 · p. 5
• Figure 5 · p. 7
• Figure 6 · p. 7
• Figure 7 · p. 8
• Figure 8 · p. 8
• Figure 9 · p. 9

Argument and organization

1. 2. Methodology

   Defines simulation, pseudo-expert trajectories, and co-training.

2. 3. Experiments

   Moves from fixed leaderboard protocols to scaling, intervention ablations, and scene examples.

Problem, claim and contribution

Missing rare driving states motivates expanding data coverage rather than claiming a new planner architecture.

§1; Figure 1 · Main paper · Additional source 2

Argument and section order

Pseudocode exposes perturbation, reactive rollout, sensor simulation, and filtering; recovery-based and planner-based experts are separately explained.

Algorithm 1 and §2.3 p. 4 · Main paper · Additional source 2

Figures, captions and visual explanation

Four matched scaling plots compare planners and supervision choices; scene strips pair trajectory maps with rendered camera views.

Figures 4–5 p. 7 · Main paper · Additional source 2

Tables, comparisons and evidence

Leaderboard captions distinguish privileged symbolic inputs, pseudo-expert supervision, and reward scoring; reactive/nonreactive tests probe the data-generation mechanism.

Tables 1–4 pp. 6,8 · Main paper · Additional source 2

Appendix and reproducibility

A table of contents maps extended experiments, limitations, and licenses; further tests vary real-data amount and rendering fidelity.

Supplement §§B–F · Main paper · Additional source 2

Clarity and writing conventions

The text calls the curves fitted log-quadratic trends and discusses plateaus/degradation, useful restraint around a scaling headline.

§3.3 p. 7 · Main paper · Additional source 2

What to reuse—and what not to infer

Transferable lesson: A data-scaling study should show how samples are produced, what supervision they contain, and where measured gains saturate.

Boundary: Fitted trends over examined scales are not universal scaling laws or a real-world safety guarantee.

Apply this lesson using the argument and evidence worksheet.

Inspection record and sources

Checked

2026-09-26

Reading status

Writing-focused manuscript scan + selected visuals inspected

Main text

Manuscript-wide writing scan of main PDF pp. 1–8: framing, section structure, method exposition, figure/table captions, evaluation organization and conclusions; not an exhaustive technical proof audit or reproduction.

Appendix / supplement

Scanned the 13-page supplement's outline, implementation tables, full results, further scaling and fidelity experiments, qualitative sequences, limitations, and asset-license section.

Visually inspected PDF pages

4, 7

This is a writing-focused scan of the manuscript and the stated supplementary scope: framing, organization, visual explanation, evidence presentation and wording. It is not a line-by-line proof audit, reproduction of results or exhaustive scientific review.

• Official CVPR 2026 CVF proceedings PDF; retrieved 2026-09-26 · 10 pages
• Official CVPR 2026 separate supplementary PDF; retrieved 2026-09-26 · 13 pages