Flatness Preserves Instruction Following in Vision-Language-Action Models

• URL: http://arxiv.org/abs/2606.23641v1
• Date: Mon, 22 Jun 2026 17:30:29 GMT
• Title: Flatness Preserves Instruction Following in Vision-Language-Action Models
• Abstract summary: Vision-language-action (VLA) models have the potential for open-world generalization by leveraging pretrained vision-language representations.<n>We show that simply applying sharpness-aware minimization during VLA finetuning significantly improves instruction following by over 60% across multiple simulation and real-world benchmarks.
• Score: 25.329212039294486
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vision-language-action (VLA) models have the potential for open-world generalization by leveraging pretrained vision-language representations, yet downstream finetuning on limited robot data often degrades these representations, leading to brittle policies that ignore language instructions in favor of visual shortcuts, a failure mode we term instruction blindness. We hypothesize that standard finetuning with limited data applies gradients to a sparse set of points, which manifests as a sharp loss landscape with high-curvature minima. We propose to address this directly through flatness-preserving optimization while finetuning on the exact same data, where learning a flatter landscape results in a model more robust to perturbations in the weight space. Specifically, we demonstrate that simply applying sharpness-aware minimization during VLA finetuning significantly improves instruction following by over 60% across multiple simulation and real-world benchmarks without additional data, architectural modification, or retraining. We further analyze the effect of selective sharpness, quantify its effects, and show that our approach is complementary to existing guidance techniques. Project page can be found at https://haochenz11.github.io/papers/flatness-vla/.

Related papers

• Information-Regularized Attention for Visual-Centric Reasoning [30.245558374164492]
  Vision-language models (VLMs) have become a paradigm for multimodal learning, yet remain unstable due to object hallucination, weak visual grounding, and catastrophic forgetting.<n>We introduce Information-Regularized Attention (IRA), a attention mechanism that explicitly regulates the amount of visual information injected into the hidden states of intermediate transformer layers.
  arXiv  Detail & Related papers  (2026-07-01T04:45:41Z)
• Power Reinforcement Post-Training of Text-to-Image Models with Super-Linear Advantage Shaping [66.25536973294726]
  Post-training methods for text-to-image (T2I) models are prone to reward hacking.<n>Super-Linear Advantage Shaping (SLAS) reshapes the local policy space.<n>SLAS consistently surpasses the DanceGRPO baseline across multiple backbones and benchmarks.
  arXiv  Detail & Related papers  (2026-05-11T17:59:25Z)
• Understanding Degradation with Vision Language Model [56.09241449206817]
  Understanding visual degradations is a critical yet challenging problem in computer vision.<n>We introduce DU-VLM, a multimodal chain-of-thought model trained with supervised fine-tuning and reinforcement learning.<n>We also introduce textbfDU-110k, a large-scale dataset comprising 110,000 clean-degraded pairs with grounded physical annotations.
  arXiv  Detail & Related papers  (2026-02-04T13:51:15Z)
• Graph Unlearning Meets Influence-aware Negative Preference Optimization [45.33243345077153]
  In this paper, we introduce textbfINPO, an textbfInfluence-aware textbfNegative textbfPreference textbfOptimization framework.<n>We first analyze that NPO has slower divergence speed and theoretically propose that unlearning high-influence edges can reduce impact of unlearning.<n>Experiments conducted on five real-world datasets demonstrate that INPO-based model achieves state-of-the-art performance on all forget quality metrics.
  arXiv  Detail & Related papers  (2025-10-22T11:18:00Z)
• Fine-Tuning Visual Autoregressive Models for Subject-Driven Generation [20.67671141789497]
  We propose the first VAR-based approach for subject-driven generation.<n>We find that the early stages have a greater influence on the generation of subject than the latter stages.<n>Based on this finding, we propose scale-wise weighted tuning, which prioritizes coarser resolutions for promoting the model to focus on the subject-relevant information.
  arXiv  Detail & Related papers  (2025-04-03T14:12:55Z)
• Fine-Grained Verifiers: Preference Modeling as Next-token Prediction in Vision-Language Alignment [57.0121616203175]
  We propose FiSAO, a novel self-alignment method that utilizes the model's own visual encoder as a fine-grained verifier to improve vision-language alignment.<n>By leveraging token-level feedback from the vision encoder, FiSAO significantly improves vision-language alignment, even surpassing traditional preference tuning methods that require additional data.
  arXiv  Detail & Related papers  (2024-10-18T03:34:32Z)
• LOBG:Less Overfitting for Better Generalization in Vision-Language Model [19.890629892640206]
  We propose a framework named LOBG for vision-language models. We use CLIP to filter out fine-grained foreground information that might cause overfitting, thereby guiding prompts with basic visual concepts. Our method significantly improves generalization capability and alleviates overfitting compared to state-of-the-art approaches.
  arXiv  Detail & Related papers  (2024-10-14T08:06:21Z)
• Enhancing Robustness of Vision-Language Models through Orthogonality Learning and Self-Regularization [77.62516752323207]
  We introduce an orthogonal fine-tuning method for efficiently fine-tuning pretrained weights and enabling enhanced robustness and generalization. A self-regularization strategy is further exploited to maintain the stability in terms of zero-shot generalization of VLMs, dubbed OrthSR. For the first time, we revisit the CLIP and CoOp with our method to effectively improve the model on few-shot image classficiation scenario.
  arXiv  Detail & Related papers  (2024-07-11T10:35:53Z)
• Low-rank finetuning for LLMs: A fairness perspective [54.13240282850982]
  Low-rank approximation techniques have become the de facto standard for fine-tuning Large Language Models. This paper investigates the effectiveness of these methods in capturing the shift of fine-tuning datasets from the initial pre-trained data distribution. We show that low-rank fine-tuning inadvertently preserves undesirable biases and toxic behaviors.
  arXiv  Detail & Related papers  (2024-05-28T20:43:53Z)
• Calibrated Self-Rewarding Vision Language Models [27.686545023186852]
  Large Vision-Language Models (LVLMs) have made substantial progress by integrating pre-trained large language models (LLMs) and vision models through instruction tuning. LVLMs often exhibit the hallucination phenomenon, where generated text responses appear linguistically plausible but contradict the input image. We propose the Calibrated Self-Rewarding (CSR) approach, which enables the model to self-improve by iteratively generating candidate responses, evaluating the reward for each response, and curating preference data for fine-tuning.
  arXiv  Detail & Related papers  (2024-05-23T14:30:33Z)
• Extrapolation for Large-batch Training in Deep Learning [72.61259487233214]
  We show that a host of variations can be covered in a unified framework that we propose. We prove the convergence of this novel scheme and rigorously evaluate its empirical performance on ResNet, LSTM, and Transformer.
  arXiv  Detail & Related papers  (2020-06-10T08:22:41Z)

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.