You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Target-Language DFS with Visual Ambiguity Guard: Runtime Weights

Gated organizer delivery for the SE team DialNav Challenge entry Target-Language DFS with Visual Ambiguity Guard.

The submitted controller does not train or fine-tune a new model. The archive contains the exact frozen runtime checkpoints used for final inference:

official RAINbow DST Navigator;
official RAINbow LANA question generator;
official RAINbow LANA answer generator;
official RAINbow GTL localizer;
OpenAI CLIP ViT-B/16.

Main file:

se_team_target_language_dfs_visual_guard_weights.tar
bytes: 8231567360
sha256: 5cc6461607384990b33b3335c2a42e1e2520c2db01d5c8589c14b4659fb8de5c

WEIGHTS_MANIFEST.json records the source, role, byte size, and SHA256 of each checkpoint. WEIGHTS_CHECKSUMS.sha256 can be used after extracting the archive.

This gated repository is provided only for challenge reproduction and organizer audit. Access is manually controlled. Recipients must comply with the upstream RAINbow, RAIN, RAINbow-data, Matterport3D, and OpenAI CLIP terms. Do not redistribute the archive publicly.

Code and reproduction instructions: https://github.com/neilyysun-ui/dialnav-target-language-dfs-visual-guard

Frozen code commit: 02def7f39f0f54877420ef64bddc18a164121648.

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support