Skip to content
Other

Inference-Time-Derisking-in-Masked-Diffusion

risk control for diffusion LLMs

2 min readupdated

Researchers at NYCU-MLLab released the code and two trained linear risk heads (compact modules attached on top of the main model) for REDACT (Risk-Evaluated Decoding At Commit-Time). The repository tackles text generation safety in masked diffusion language models (diffusion LLMs that reconstruct masked text step by step rather than writing strictly left to right). During decoding, REDACT scores the risk of top-K token candidates based on the current noise level and picks a safer path along a single generation trajectory. The checkpoints run on top of the base models GSAI-ML/LLaDA-8B-Base and GSAI-ML/LLaDA-8B-Instruct, whose weights need to be downloaded separately. This release is useful for AI safety researchers and engineers working with diffusion language models.

Key features

  • Two specialized modules: a dedicated toxicity checkpoint (for LLaDA-8B-Base) and an auxiliary jailbreak-resistance module (for LLaDA-8B-Instruct).
  • Ultra-lightweight architecture: each head contains only 4,385 trainable parameters, takes 4096-dimensional pooled backbone features, and uses 8 noise bins with a 32-dimensional embedding.
  • Built-in calibration: the checkpoints already include calibrated thresholds for each noise bin and output a scalar risk score via a softplus function.
  • Full reproducible archive: alongside the best and last weights, the release bundles source code, training logs, Hydra configs, and SHA256SUMS checksums.

What you can do

  • Reduce generation toxicity: attach the time_dependent_mlp_best.pt head to LLaDA-8B-Base to filter out unwanted tokens directly during diffusion decoding.
  • Strengthen filter-bypass defenses: pair the auxiliary time_dependent_linear_best.pt checkpoint with LLaDA-8B-Instruct in jailbreak-resistance evaluation pipelines.
  • Integrate into your own code: load the lightweight linear head directly via linear_head.runtime to get risk scores from precomputed model hidden states.

Example

import torch
from linear_head.runtime import load_linear_checkpoint

head, _ = load_linear_checkpoint("checkpoints/linear_heads/time_dependent_mlp_best.pt", device=torch.device("cpu"))
# features: [batch, 4096], rho_idx: [batch] из диапазона [0, 7]
with torch.no_grad():
    risk = head(features, rho_idx)["risk"]
Read moreDetails
Validation (at a target TPR of 0.95): for the toxicity checkpoint (epoch 23), macro_fpr_at_tpr = 0.0843; for the jailbreak module (epoch 59), it is 0.4660.
Environment: Linux, Python >= 3.12, CUDA 13.0 (targeted at Hopper/H200 GPUs, installed via uv sync --extra cu130).
Limitations: this is a research proxy tool and does not guarantee completely safe text; checkpoints for Dream and reward models are not included in the release.
License: the source code is distributed under MIT, while no separate license is specified for the weights in the archives.
Discuss Telegram 0

Will it run?

Runs in BF16

Fits without quantisation.

  • BF16weights 0.0 GB · ready files0.5 GB
  • FP8 / INT8recommendedweights 0.0 GB0.5 GB
  • 4-bitweights 0.0 GB0.5 GB

Tip: go 8-bit.FP8 / INT8 is within about a percent of full precision in quality, takes half the memory and runs faster on RTX 40/50 and H100. Full precision only pays off for fine-tuning.

What to get for this model

Massed ComputeOpen Massed Compute

Your own GPU: FP8 / INT8 — from RTX 2060 · BF16 — from RTX 2060

Massed Compute hourly prices, November 2026. The discounted price applies with the coupon at checkout.

Estimate: weights plus working memory. Long videos, high resolutions and long contexts need more.

Run it on Massed Compute

The script downloads the model to the rented machine. How to run it is in the model card.

  1. 1. Rent a machine with a fitting GPU

    Open Massed Compute
  2. 2. Paste the script into the machine's terminal

    Connect over SSH (the Massed Compute panel shows the command) or open a terminal on the machine's desktop.

    HF_TOKEN / CIVITAI_TOKENThe script starts with token lines: paste yours between the quotes. The Hugging Face token is for gated models, the Civitai one for Civitai models.

    # NYCU-MLLab/Inference-Time-Derisking-in-Masked-Diffusion
    mkdir -p ~/models
    curl -LsSf https://astral.sh/uv/install.sh | sh
    source "$HOME/.local/bin/env"
    uv tool install "huggingface_hub[cli]"
    hf download NYCU-MLLab/Inference-Time-Derisking-in-Masked-Diffusion --local-dir ~/models/Inference-Time-Derisking-in-Masked-Diffusion
    # The model is in ~/models. How to run it is in the model card (link above).
  3. 3. Use it

    The model is in ~/models. How to run it is in the model card (link above).

Stop the machine in the panel when you are done: it bills by the minute while it runs.

How to speed it up

Picked for this model type. Choose your hardware above to see what fits you exactly.

  • FlashAttention 44.0.0b40from November 18, 2026new release

    fastest exact attention on B200

    Kernels for Blackwell (beta). Exact attention without quantisation — fine for everything, LLMs included.

    How to enable: pip install flash-attn-4; vLLM and SGLang pick it up themselves.

    Earlier generations (2)
    • FlashAttention 3 — The Hopper (H100/H200) version with FP8.
    • FlashAttention 2 — The standard for RTX 30/40/50 and A100: exact attention without the memory cost of long contexts.
  • torch.compile2.15.0from October 28, 2026new release

    10–30% for free

    Compiles the model for your GPU. Slower first run, faster afterwards.

    How to enable: model = torch.compile(model); in ComfyUI the TorchCompileModel node.

Model family

New posts about versions of LLaDA-8B-Base (quants, finetunes, LoRAs) will show up under the bell.

Quantised versions 4All on Hugging Face
Fine-tunes 12All on Hugging Face
LoRAs and adapters 12All on Hugging Face

About the model

NYCU-MLLab/Inference-Time-Derisking-in-Masked-Diffusion
Author
NYCU-MLLab
Category
Other
Released
Posted

On NeyroLearn

Hugging Face

00

Ask AI about this model

Answered by Gemini 4 · the chat is kept only in this tab

Comments