WORL
Collection
4 items • Updated
Feature Extraction
Transformers
Safetensors
qwen3_vl
worl
nvrm
reward-model
video-reward-model
qwen3-vl
# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModel
processor = AutoProcessor.from_pretrained("Efficient-Large-Model/WORL-NVRM")
model = AutoModel.from_pretrained("Efficient-Large-Model/WORL-NVRM", device_map="auto")Quick Links
WORL-NVRM
Next-Video Reward Model (NVRM) scores a candidate video continuation in the context of preceding video and a text prompt. It provides a relative preference signal for reinforcement learning of video world models.
Related policy releases: WORL-Helios and WORL-Lingbot.
Model details
| Field | Description |
|---|---|
| Base model | Qwen3-VL-4B-Instruct |
| Base revision | ebb281ec70b05090aa6165b016eac8ec08e71b17 |
| Architecture | 36-layer Qwen3-VL backbone with a one-dimensional reward head |
| Release format | Merged BF16 backbone and separate scalar head, all in Safetensors |
| Input | Text prompt, preceding video context and candidate continuation |
| Output | One unnormalized scalar reward; higher indicates stronger relative preference |
| Intended use | Video preference research and reward evaluation in video RL |
The training LoRA is already merged into the backbone. The reward head is in
nvrm_head.safetensors, under key rm_head.weight. This is a reward model,
not a text-generation model; loading it as a generic chat model does not produce
the documented reward.
Training data and method
NVRM uses pairwise video preferences with a Bradley–Terry objective. The WORL manuscript describes approximately 312.4K preference pairs drawn from Sekai Real Walking, Sekai Game, OmniWorld, Object-centric Revisiting, OpenScene and General categories. Preference construction uses automated multimodal judgments, order-consistency checks and graph-based filtering.
The team reports that initial scene imagery for its self-created OpenScene data was generated with gpt-image. This repository distributes model artifacts; the full preference corpus is not bundled with the weights.
Download and use
hf download Efficient-Large-Model/WORL-NVRM --local-dir artifacts/WORL-NVRM
Use the WORL NVRM reward runtime, which loads the merged Qwen3VLModel backbone
and the separate scalar head. The complete chat formatting and preprocessing
contract is required; a generic Transformers pipeline is not a replacement for
that runtime. The WORL source release is being prepared separately.
| Preprocessing / scoring | Release contract |
|---|---|
| Candidate continuation | 5 seconds |
| Frame sampling | 1 FPS |
| Resize | Height 360 |
| Frame encoding | JPEG quality 85 |
| Image pixel bounds | 1,024–76,800 |
| Thinking / hidden-state normalization | Disabled / disabled |
| Reward | Last-token scalar, raw BF16 logit |
The source runtime profile uses Transformers 4.57.6, Accelerate 1.13.0,
qwen-vl-utils 0.0.14 and FlashAttention 2.7.4.post1. The artifact does not require
trust_remote_code. Pin a Hub revision for reproducible use and verify the
files against worl-bundle.json or RELEASE_MANIFEST.json.
Files and provenance
The repository contains three backbone shards, the reward head, tokenizer and processor assets, figures, license notices and integrity manifests.
Weights and model/processor configurations are unchanged from
qyoo/NVRM-world at 03f850630c0b.
Documentation and release manifests were updated for this repository.
RELEASE_MANIFEST.json records the source revision and checksums.
The source release reports matching preprocessing tensors and raw BF16 reward output against its inference fixture. That is a conversion/runtime check, not a measure of general reward quality. This publication adds no new model-quality or hardware benchmark.
Limitations
Rewards are relative and distribution-dependent, not calibrated probabilities. The model can miss physical or temporal errors, learn superficial preferences, and be vulnerable to reward hacking. Biases in the base model, candidate videos and preference judgments can affect rankings. Behavior beyond the documented preprocessing profile is not established by this release.
NVRM is intended for research and comparative reward evaluation. Its output does not establish factual correctness, content safety or suitability for safety-critical decisions.
License
This release retains the source model's Apache License 2.0. Preserve NOTICE.txt when redistributing it. The merged Qwen3-VL backbone is also distributed under Apache-2.0.
- Downloads last month
- 20
Model tree for Efficient-Large-Model/WORL-NVRM
Base model
Qwen/Qwen3-VL-4B-Instruct
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="Efficient-Large-Model/WORL-NVRM")