← Back to all news
arXiv Computer Vision By Ivan Listopadov, Maksim Nakhodnov, Aibek Alanov

Policy-Mask: Budget-Aware Adaptation of Diffusion Features to Discriminative Tasks

Read the original on arXiv Computer Vision →

Policy‑Mask is a budget‑aware policy that jointly selects a timestep, a diffusion block, and a subset of channels from a frozen diffusion model to optimize downstream discriminative tasks. By normalizing channel scores and training on the downstream objective, it outperforms fixed‑extraction baselines on segmentation, classification, and semantic correspondence, achieving state‑of‑the‑art results on ADE20K, CIFAR‑100, and SPair‑71k. The method also extends to diffusion transformers by mapping U‑Net channels to image‑token hidden dimensions.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv Machine Learning
Sep 10

Dense Structural Compression of Transformers via Gauge-Correct Channel Removal

The paper introduces GaugeLasso, a method that applies symmetric group‑lasso penalties to transformer channels during training, enabling entire tensor slices to be zeroed out while maintaining dense tensors for GPU efficiency. By calibrating channel penalties based on inference utility per compute, the network self‑organizes into depth‑dependent structural profiles that can be dramatically smaller than the original architecture, achieving up to 255‑fold compression on a polynomial division task and outperforming hand‑designed baselines on language modeling and autoencoding benchmarks. The approach also accelerates training and reveals over‑provisioned axes that guide subsequent design iterations.

By Jed A. Duersch, Na\"im Es-Sebbani, Nathana\"el Haas, Zied Bouraoui
llmsefficiency
More like this →
arXiv Machine Learning
Aug 31

Learned Relay Representations for Forward-Thinking Discrete Diffusion Models

The paper introduces Learned Relay Representations (Relay), a technique for Masked Diffusion Models (MDMs) that preserves and forwards internal latent information across denoising steps via a differentiable per-token channel trained with truncated backpropagation through time. Relay enables MDMs to be forward‑thinking, avoiding costly recomputation of internal representations and improving efficiency. Applied to Fast‑dLLM v2, Relay outperforms standard supervised fine‑tuning on coding tasks and reduces inference latency by up to 32%, demonstrating a clear performance‑latency advantage for diffusion language models.

By Benjamin Rozonoyer, Jacopo Minniti, Dhruvesh Patel, Neil Band, Avishek Joey Bose, Tim G. J. Rudner, Andrew McCallum
llmsdiffusionfine-tuningefficiencybenchmarks
More like this →
arXiv Machine Learning
Aug 5

Latent Reward Registers for Diffusion Preference Alignment

arXiv:2608. 03929v1 Announce Type: new Abstract: Aligning diffusion models with human preferences usually relies on a sparse terminal reward evaluated on the final generated samples, presenting a severe temporal credit-assignment challenge across the multi-step denoising process.

By Yuanshen Guan, Zipeng Feng, Zhiwei Xiong, Peiqin Sun
llmsdiffusionreinforcement-learningefficiencybenchmarkssafety
More like this →