Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

Instructions Before Actions: Prospective and Retrospective Language Supervision for Driving Vision-Language-Action Data

Angel Martinez-Sanchez, Ross Greer

Published

Nov 16, 2026

Citations

0

Trust level

Low

Usefulness score

25/100 (Low)

Extraction confidence

45% (Low)

Derived from extracted protocol signals and abstract evidence.

Rater population

Not reported

Signals refreshed

Nov 16, 2026

Should you rely on this paper?

This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.

Use this as background context only. Do not make protocol decisions from this page alone.

Best use

Background context only

Use if you need

A secondary eval reference to pair with stronger protocol papers.

What to verify

Validate the evaluation procedure and quality controls in the full paper before operational use.

Main weakness

The available metadata is too thin to trust this as a primary source.

Human feedback signal
Not explicit
Not explicit in abstract metadata
Evaluation signal
Detected
Eval setup described
Usefulness for eval research
25/100
Adjacent candidate

Treat as adjacent context, not a core eval-method reference.

Abstract

Driving vision-language-action (VLA) models can accept navigation instructions, yet predicting a driver's trajectory does not establish that a model follows the instruction. We study how driving-language supervision is collected and evaluated, distinguishing prospective instructions issued before an action from retrospective labels written after observing it. We develop ADVLAT-Engine to synchronize spoken instructions, road-scene video, and vehicle trajectories, and compare three navigation apps on 48 replayed routes. On 87 maneuvers announced by both Google Maps and a passenger, the passenger uses more scene-dependent language. We evaluate four open driving VLAs before and after fine-tuning on prospective navigation-app drives. Fine-tuning reduces passenger-drive trajectory error by 23-59%, but instruction effects remain inconsistent. At real intersections, counterfactual instructions reveal stronger responsiveness: fine-tuned Alpamayo~2 Super gains 31 and 18 accuracy points at 15 and 5~m, while Qwen-Drive follows alternative maneuvers more reliably with a discrete command than with a sentence. We additionally collected retrospective annotations from four people for the driving recordings and describe controlled comparisons of annotation content, timing, and downstream learning; those analyses are pending. Our findings separate maneuver prediction from instruction-following and establish a framework for comparing prospective and retrospective supervision.

What we could verify

These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.

Human Feedback Types

missing

None explicit

No explicit feedback protocol extracted.

"Driving vision-language-action (VLA) models can accept navigation instructions, yet predicting a driver's trajectory does not establish that a model follows the instruction."

Evaluation Modes

partial

Automatic Metrics

Includes extracted eval setup.

"Driving vision-language-action (VLA) models can accept navigation instructions, yet predicting a driver's trajectory does not establish that a model follows the instruction."

Quality Controls

missing

Not reported

No explicit QC controls found.

"Driving vision-language-action (VLA) models can accept navigation instructions, yet predicting a driver's trajectory does not establish that a model follows the instruction."

Benchmarks / Datasets

missing

Not extracted

No benchmark anchors detected.

"Driving vision-language-action (VLA) models can accept navigation instructions, yet predicting a driver's trajectory does not establish that a model follows the instruction."

Reported Metrics

partial

Accuracy

Useful for evaluation criteria comparison.

"At real intersections, counterfactual instructions reveal stronger responsiveness: fine-tuned Alpamayo~2 Super gains 31 and 18 accuracy points at 15 and 5~m, while Qwen-Drive follows alternative maneuvers more reliably with a discrete command than with a sentence."

Benchmarks and datasets

No benchmark or dataset names were extracted from the available abstract.

Reported metrics

accuracy
Human feedback details
Uses human feedback
No
Feedback types
None
Rater population
Not reported
Unit of annotation
Trajectory (inferred)
Expertise required
General
Evaluation details
Evaluation modes
Automatic Metrics
Agentic eval
Long Horizon
Quality controls
Not reported
Evidence quality
Low
Use this page as
Background context only

Research brief

Metadata summary

Driving vision-language-action (VLA) models can accept navigation instructions, yet predicting a driver's trajectory does not establish that a model follows the instruction.

Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.

Key takeaways

  • Driving vision-language-action (VLA) models can accept navigation instructions, yet predicting a driver's trajectory does not establish that a model follows the instruction.
  • We study how driving-language supervision is collected and evaluated, distinguishing prospective instructions issued before an action from retrospective labels written after observing it.
  • We develop ADVLAT-Engine to synchronize spoken instructions, road-scene video, and vehicle trajectories, and compare three navigation apps on 48 replayed routes.

Researcher actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Validate inferred eval signals (Automatic metrics) against the full paper.
  • Use related-paper links to find stronger protocol-specific references.

Caveats

  • Generated from abstract + metadata only; no PDF parsing.
  • Signals below are heuristic and may miss details reported outside the abstract.

Recommended queries

Contribution summary

  • Driving vision-language-action (VLA) models can accept navigation instructions, yet predicting a driver's trajectory does not establish that a model follows the instruction.
  • We study how driving-language supervision is collected and evaluated, distinguishing prospective instructions issued before an action from retrospective labels written after observing it.

Why it matters for eval

  • We evaluate four open driving VLAs before and after fine-tuning on prospective navigation-app drives.

Researcher checklist

  • Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Evaluation mode is explicit

    Detected: Automatic Metrics

  • Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Benchmark or dataset anchors are present

    No benchmark/dataset anchor extracted from abstract.

  • Metric reporting is present

    Detected: accuracy