ReNFT: Repairing Mode Collapse in Reward Post-Training via Internal Probability-Mass Recalibration

• URL: http://arxiv.org/abs/2609.00061v2
• Date: Sat, 05 Sep 2026 05:18:48 GMT
• Title: ReNFT: Repairing Mode Collapse in Reward Post-Training via Internal Probability-Mass Recalibration
• Abstract summary: Reward post-training inevitably concentrates probability mass on a few reward-favored modes, a mode collapse that erases within-prompt diversity.<n>We propose ReNFT, which repairs a high-reward, low-diversity adapter through internal probability-mass recalibration.<n>On PickScore and GenEval, ReNFT retains 98.9% and 99.0% of NFT's reward while improving DreamSim-Div by 58.8% and 55.0%, respectively.
• Score: 84.10540890311843
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reward post-training of diffusion generators inevitably concentrates probability mass on a few reward-favored modes, a mode collapse that erases within-prompt diversity. Existing methods for mitigating collapse rely on external signals or interfaces, augmenting the reward with perceptual objectives, adjusting reference regularization, or modifying the text encoder, but none repairs an adapter that has already collapsed while preserving the acquired reward. We observe that online post-training primarily reallocates probability mass over capabilities inherited from pretraining rather than learning new visual content. Collapse is therefore suppression, not deletion, and can be reversed from within the generator. We propose ReNFT, which repairs a high-reward, low-diversity adapter through internal probability-mass recalibration. Unconditional probes first prioritize "anti-hub" prompts where the prompt-independent bias is easiest to expose. Two policy-dominated mixed routes then generate matched counterfactual proposals from the same prompt and initial noise, one probing the frozen base direction for suppressed alternatives and the other exposing the post-trained unconditional tendency. Reward ranking with an adaptive flipping guard assigns pull and push roles, and a joint-and-paired NFT update realizes the repair. On PickScore and GenEval, ReNFT retains 98.9% and 99.0% of NFT's reward while improving DreamSim-Div by 58.8% and 55.0%, respectively, offering a complementary alternative to external interventions.

Related papers

• Scale-Consistent Posterior Dynamics for Diffusion Inverse Problems [16.685352002333225]
  Posterior sampling with a pretrained diffusion prior is governed by a conditional score whose likelihood component is generally intractable.<n>We show that a noise-conditioned path whose targets approach the clean posterior produces a continuous surrogate SDE.<n>Experiments on FFHQ and ImageNet with 100 score evaluations demonstrate competitive reconstruction fidelity for superresolution and deblurring.
  arXiv  Detail & Related papers  (2026-08-15T09:38:41Z)
• Sample-Adaptive Latent Rewards for Uncertainty-Guided Diffusion Post-Training [51.18425726646089]
  We propose textscSURE, a unified latent-space framework for image and video diffusion models.<n>It learns reward distributions and directly uses their reliability to guide dense post-training.<n>textscSURE-REFL achieves the highest VBench quality, semantic, and total scores among the evaluated methods.
  arXiv  Detail & Related papers  (2026-08-06T14:55:42Z)
• Between-User Collapse Under Popularity-Biased Feedback: A Centered-Covariance Theorem and Computable Phase Boundary [0.0]
  We study how popularity-biased BPR training reshapes the between-user geometry of collaborative-filtering embeddings.<n>We prove that under popularity-biased feedback with stationary items, $C$ converges to a steady state.<n>We then examine the limits of the effect.
  arXiv  Detail & Related papers  (2026-08-03T17:33:25Z)
• MARBLE: Multi-Aspect Reward Balance for Diffusion RL [71.6241143519038]
  Reinforcement learning has become the dominant approach for aligning diffusion models with human preferences.<n>Existing practice deal with multiple rewards by training one specialist model per reward.<n>We propose MARBLE, a gradient-space optimization framework that maintains independent advantage estimators for each reward.
  arXiv  Detail & Related papers  (2026-05-07T16:20:42Z)
• SOAR: Self-Correction for Optimal Alignment and Refinement in Diffusion Models [48.335262141752715]
  Post-training pipeline for diffusion models has two stages: supervised fine-tuning (SFT) on curated data and reinforcement learning (RL) with reward models.<n>We propose SOAR (Self-Correction for Optimal Alignment and Refinement), a bias-correction post-training method that fills this gap.<n>It is on-policy, reward-free, and provides dense per-time supervision with no credit-assignment problem.
  arXiv  Detail & Related papers  (2026-04-14T11:45:15Z)
• Improving Search Agent with One Line of Code [68.58667107354253]
  Tool-based Agentic Reinforcement Learning (TARL) has emerged as a promising paradigm for training search agents to interact with external tools.<n>We propose textbfSearch textbfAgent textbfPolicy textbfOptimization (textbfSAPO), which stabilizes training via a conditional token-level KL constraint.
  arXiv  Detail & Related papers  (2026-03-10T04:07:39Z)
• FAST-DIPS: Adjoint-Free Analytic Steps and Hard-Constrained Likelihood Correction for Diffusion-Prior Inverse Problems [2.9506605740700107]
  Training-free diffusion priors often rely on repeated derivatives or inner optimization/MCMC loops with conservative step sizes.<n>We propose a training-free solver that replaces these inner loops with a hard measurement-space feasibility constraint.<n>Experiments achieve competitive PSNR/SSIM/LPIPS with up to 19.5$times$ speedup, without hand-coded adjoints or inner MCMC.
  arXiv  Detail & Related papers  (2026-03-02T08:17:26Z)
• Reinforcement Learning with Verifiable yet Noisy Rewards under Imperfect Verifiers [90.50039419576807]
  Reinforcement Learning with Verifiable Rewards (RLVR) trains policies against automated verifiers to avoid costly human labeling.<n>To reduce vulnerability to verifier hacking, many RLVR systems collapse rewards to binary $0,1$ during training.<n>This choice carries a cost: it introduces textitfalse negatives (rejecting correct answers, FNs) and textitfalse positives (accepting incorrect ones, FPs)
  arXiv  Detail & Related papers  (2025-10-01T13:56:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.