MétaCan
Menu
Back to cohort
Record W4292937774 · doi:10.17760/d20429166

Improving instruction generation for vision-language navigation by reward designing

2021· dissertation· en· W4292937774 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

Venuenot available
Typedissertation
Languageen
FieldComputer Science
TopicMultimodal Machine Learning Applications
Canadian institutionsScience North
Fundersnot available
KeywordsComputer scienceGenerator (circuit theory)Function (biology)Artificial intelligenceLanguage modelHuman–computer interaction

Abstract

fetched live from OpenAlex

Language generation for data augmentation in Vision-Language Navigation (VLN) has been widely used. However, despite the effort of evaluating augmented data, generating visually-grounded navigational instructions has always been an auxiliary task. To push the boundary of instruction generation, we proposed a more sophisticated approach to train the generator with REINFORCE algorithm and reward function as the combination of BLEU, BERTScore, and VLN loss. Experimental results show that our approach is able to improve the generation model in terms of the reward function. This work also discusses the possibility of utilizing existing instruction-trajectory compatibility model for training the generation model.`--Author's abstract

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.868
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0010.001
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.009
GPT teacher head0.303
Teacher spread0.294 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Quick stats

Citations0
Published2021
Admission routes1
Has abstractyes

Explore more

Same topicMultimodal Machine Learning ApplicationsFrench-language works237,207