Stable-Layers: Fine-Tuning Image Layer Decomposition Models with VLM-Scored Reinforcement Learning

• URL: http://arxiv.org/abs/2605.30257v1
• Date: Thu, 28 May 2026 17:20:31 GMT
• Title: Stable-Layers: Fine-Tuning Image Layer Decomposition Models with VLM-Scored Reinforcement Learning
• Abstract summary: We present Stable-Layers, a reinforcement learning framework that eliminates the need for paired supervision.<n>We apply Flow-GRPO with LoRA adaptation, sampling multiple candidate decompositions per image, scoring them with a vision-language model (VLM)<n>We produce decompositions with stronger layer separation, fewer blank or artifact-heavy layers, and lower per-layer reconstruction error on the Crello dataset compared to the base model.
• Score: 11.163998944500323
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present Stable-Layers, a reinforcement learning framework that eliminates the need for paired supervision by fine-tuning a pretrained layer decomposition model using only feedback from a vision-language model (VLM). Starting from Qwen-Image-Layered, we apply Flow-GRPO with LoRA adaptation, sampling multiple candidate decompositions per image, scoring them with a VLM, and optimising the policy from group-relative advantages. The key challenge lies in designing a reliable reward signal: VLMs scoring samples in isolation tend to compress their judgements into a narrow band, leaving GRPO with little within-group variance to learn from. We address this with a two-stage evaluation pipeline that pairs structured per-sample scoring across five edit-centric criteria with a grid-based calibration step in which the VLM re-scores all candidates side-by-side. Stable-Layers produces decompositions with stronger layer separation, fewer blank or artifact-heavy layers, and lower per-layer reconstruction error on the Crello dataset compared to the base model.

Related papers

• Unsupervised Transfer Clustering for Mitigating Cold Start in Active Prompt Learning [1.5539424546888112]
  Vision-Language Models (VLMs) are able to achieve impressive zero-shot classification performance by aligning visual and textual representations.<n>Each new task still demands handcrafted prompts.<n>Active Prompt Learning (APL) combines Active Learning (AL) and Prompt Learning (PL) into a single framework.
  arXiv  Detail & Related papers  (2026-09-04T18:14:44Z)
• Semi-Supervised Adaptation of Vision-Language Models for Image Classification [2.526705939946147]
  Self-Evolutionary CLIP (SE- CLIP) is a semi-supervised framework for label mining in scene classification.<n>Results on the UCM and NWPU benchmarks indicate that SE-CLIP significantly outperforms existing semi-supervised approaches.
  arXiv  Detail & Related papers  (2026-08-26T07:54:50Z)
• Enhancing Gradient Inversion Attacks in Federated Learning via Hierarchical Feature Optimization [56.95448807869383]
  Federated Learning (FL) has emerged as a compelling paradigm for privacy-preserving distributed machine learning.<n>Recent studies find that the gradients exchanged in the FL system are also vulnerable to privacy leakage.<n>We propose textbfGradient textbfInversion over textbfFeature textbfDomains (GIFD)
  arXiv  Detail & Related papers  (2026-04-01T14:32:15Z)
• From Sparse to Dense: Multi-View GRPO for Flow Models via Augmented Condition Space [78.36537400975298]
  Group Relative Policy Optimization (GRPO) has emerged as a powerful framework for preference alignment in text-to-image (T2I) flow models.<n>We propose Multi-View GRPO, a novel approach that enhances relationship exploration by augmenting the condition space.<n>MV-GRPO achieves superior alignment performance over state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-03-13T04:35:13Z)
• ReCALL: Recalibrating Capability Degradation for MLLM-based Composed Image Retrieval [64.14282916266998]
  Composed Image Retrieval aims to retrieve target images based on a hybrid query comprising a reference image and a modification text.<n>We propose ReCALL, a model-agnostic framework that follows a diagnose-generate-refine pipeline.<n>Experiments on CIRR and FashionIQ show that ReCALL consistently recalibrates degraded capabilities and achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2026-02-02T04:52:54Z)
• Evaluating Embedding Generalization: How LLMs, LoRA, and SLERP Shape Representational Geometry [0.0]
  We study the extent to which spherical linear (SLERP) model-merging mitigates over-specialization introduced by task-specific adaptation.<n>We compare four families of models: non-LLM encoders trained from scratch or fine-tuned for embeddings, LLM-based encoders adapted with parameter-efficient methods (LoRA), LLM-based encoders with LoRA followed by model souping merging into the base weights, and the same LoRA-adapted LLMs merged using SLERP across checkpoints or stages.
  arXiv  Detail & Related papers  (2025-11-16T17:28:06Z)
• Reinforce-Ada: An Adaptive Sampling Framework for Reinforce-Style LLM Training [47.26632817047513]
  Reinforcement learning applied to large language models (LLMs) for reasoning tasks is often bottlenecked by unstable gradient estimates.<n>We propose Reinforce-Ada, an adaptive sampling framework for online RL post-training of LLMs.<n>Unlike conventional two-stage allocation methods, Reinforce-Ada interleaves estimation and sampling in an online successive elimination process.
  arXiv  Detail & Related papers  (2025-10-06T16:34:09Z)
• Improving the Reasoning of Multi-Image Grounding in MLLMs via Reinforcement Learning [28.111812077758845]
  Multimodal Large Language Models (MLLMs) excel at visual grounding in single-image scenarios with textual references.<n>However, their performance degrades when handling real-world applications that involve complex multi-image compositions and multi-modal instructions.<n>We adopt a Reinforcement Learning based post-training strategy to improve the reasoning of MLLMs in multi-image grounding tasks.
  arXiv  Detail & Related papers  (2025-07-01T13:48:57Z)
• Test-Time Adaptation with CLIP Reward for Zero-Shot Generalization in Vision-Language Models [76.410400238974]
  We propose TTA with feedback to rectify the model output and prevent the model from becoming blindly confident. A CLIP model is adopted as the reward model during TTA and provides feedback for the VLM. The proposed textitreinforcement learning with CLIP feedback(RLCF) framework is highly flexible and universal.
  arXiv  Detail & Related papers  (2023-05-29T11:03:59Z)
• Boosting Few-shot Fine-grained Recognition with Background Suppression and Foreground Alignment [53.401889855278704]
  Few-shot fine-grained recognition (FS-FGR) aims to recognize novel fine-grained categories with the help of limited available samples. We propose a two-stage background suppression and foreground alignment framework, which is composed of a background activation suppression (BAS) module, a foreground object alignment (FOA) module, and a local to local (L2L) similarity metric. Experiments conducted on multiple popular fine-grained benchmarks demonstrate that our method outperforms the existing state-of-the-art by a large margin.
  arXiv  Detail & Related papers  (2022-10-04T07:54:40Z)
• Contrastive Prototype Learning with Augmented Embeddings for Few-Shot Learning [58.2091760793799]
  We propose a novel contrastive prototype learning with augmented embeddings (CPLAE) model. With a class prototype as an anchor, CPL aims to pull the query samples of the same class closer and those of different classes further away. Extensive experiments on several benchmarks demonstrate that our proposed CPLAE achieves new state-of-the-art.
  arXiv  Detail & Related papers  (2021-01-23T13:22:44Z)
• Adaptive Adversarial Logits Pairing [65.51670200266913]
  An adversarial training solution Adversarial Logits Pairing (ALP) tends to rely on fewer high-contribution features compared with vulnerable ones. Motivated by these observations, we design an Adaptive Adversarial Logits Pairing (AALP) solution by modifying the training process and training target of ALP. AALP consists of an adaptive feature optimization module with Guided Dropout to systematically pursue fewer high-contribution features.
  arXiv  Detail & Related papers  (2020-05-25T03:12:20Z)

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.