CORTEXA
← Browse
arxivcs.LG2026-07-20

DiFA: Inference-Time Forward-Process Alignment for Diffusion Models

Shigui Li, Delu Zeng

The prevailing inference framework for diffusion models formulates generation fundamentally as a problem of numerical integration. This perspective casts the model as an exact estimator, neglecting the inherent statistical uncertainty of the denoising process. In this work, we propose Forward-Process Aligned Diffusion prediction (\textbf{DiFA}), a training-free framework that reframes inference-time data prediction refinement as a sequential state estimation problem. Rather than reusing past outputs solely for numerical integration, DiFA treats iterative data predictions along the reverse trajectory as correlated observations to build a forward-aligned temporal consensus. Inspired by Kalman filtering, this consensus aggregates historical predictions according to structural consistency and noise-level compatibility. To counteract the over-smoothing tendency of temporal consensus, we introduce a deviation guidance mechanism to adaptively preserve residual details. Empirically, DiFA yields significant improvements on CIFAR-10 and ImageNet across the evaluated metrics, including FID, IS, and FD-DINOv2, demonstrating that aligning inference with the forward statistical structure substantially improves generative fidelity.

View free PDFSource page

Related papers

arxivcs.ARcs.LG2026-07-23

DRC-Aid: Design-Rule Correction via Agentic Framework utilizing Inference-Time Large Language Models

Anushka Mukherjee, Kang He, Kaushik Roy

Resolving Design Rule Violations (DRVs) in layouts entails an iterative loop of geometric edits and verification. We present DRC-Aid, a closed-loop agentic framework that automates local DRC repair by formulating it as verification-in-the-loop search. To constrain the combinatori…

View free PDFSource page
arxivcs.LGcs.AIcs.CL2026-07-02

Safe Inference-Time Alignment via Lagrangian Reward Augmentation

Yaswanth Chittepu, Ativ Joshi, Sohini Chintala, Scott Niekum

Inference-time alignment steers a frozen language model during decoding using auxiliary reward signals, avoiding the cost of repeated weight updates. However, existing inference-time alignment methods typically optimize a single scalar score, so explicit safety constraints must e…

View free PDFSource page
arxivcs.LGcs.CL2026-07-13

HyperSafe: Inference-Time Safety Recovery for Fine-Tuned Language Models

Aznaur Aliev, Carlos Hinojosa, Abdelrahman Eldesokey, Bang An, Bernard Ghanem, Yibo Yang

Safety alignment in large language models can be fragile under fine-tuning, as even benign task adaptation may increase harmful compliance. Existing defenses mainly follow two directions: they either intervene during or after fine-tuning through retraining or weight modification,…

View free PDFSource page
arxivstat.MLcs.AIcs.LGeess.SYmath.OC2026-07-07

EHR-MPC: Inference-Time Control for Sepsis Treatment with Generative Patient Digital Twins

Joshua Pickard, Wei Qi, Na Li, Ann Woolley, Lisa Cosimi, Roy Kishony, et al.

Sepsis is a leading cause of mortality, yet optimal treatment policies remain contested. Existing reinforcement learning (RL) approaches learn fixed strategies for sepsis treatment, limiting adaptability to changing clinical objectives during inference. We propose EHRMPC, a frame…

View free PDFSource page
arxivcs.CVcs.LG2026-07-16

MeanFlowNFT: Bringing Forward-Process RL to Average-Velocity Generators

Yushi Huang, Xiangxin Zhou, Jun Zhang, Liefeng Bo, Tianyu Pang

MeanFlow generators achieve fast few-step sampling by predicting average velocities over time intervals, making them attractive for efficient generation. Reinforcement learning (RL) has become a powerful way to align diffusion and flow models with human preferences and task-speci…

View free PDFSource page