FREE: Fast and Robust Vision Language Models with Early Exits

• URL: http://arxiv.org/abs/2506.06884v1
• Date: Sat, 07 Jun 2025 18:26:58 GMT
• Title: FREE: Fast and Robust Vision Language Models with Early Exits
• Authors: Divya Jyoti Bajpai, Manjesh Kumar Hanawal,
• Abstract summary: We introduce FREE, an adversarial training approach within a GAN-based framework.<n>Our method focuses on performing input-adaptive inference that increases inference speed with minimal drop in performance.<n>We experimentally validate that our method speeds up the inference process by more than 1.51x while retaining comparable performance.
• Score: 5.402030962296633
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In recent years, Vision-Language Models (VLMs) have shown remarkable performance improvements in Vision-Language tasks. However, their large size poses challenges for real-world applications where inference latency is a concern. To tackle this issue, we propose employing Early Exit (EE) strategies in VLMs. However, training exit classifiers in VLMs is challenging, particularly with limited labeled training data. To address this, we introduce FREE, an adversarial training approach within a GAN-based framework. Here, each exit consists of a transformer layer and a classifier. The transformer layer is adversarially trained to produce feature representations similar to the final layer, while a feature classifier serves as the discriminator. Our method focuses on performing input-adaptive inference that increases inference speed with minimal drop in performance. Experimental results demonstrate the effectiveness of our approach in enhancing accuracy and model robustness by mitigating overthinking and the phenomenon of mid-crisis that we highlight. We experimentally validate that our method speeds up the inference process by more than 1.51x while retaining comparable performance. The source code is available at https://github.com/Div290/FREE.

Related papers

• ONLY: One-Layer Intervention Sufficiently Mitigates Hallucinations in Large Vision-Language Models [67.75439511654078]
  Large Vision-Language Models (LVLMs) have introduced a new paradigm for understanding and reasoning about image input through textual responses.<n>They face the persistent challenge of hallucination, which introduces practical weaknesses and raises concerns about their reliable deployment in real-world applications.<n>We propose ONLY, a training-free decoding approach that requires only a single query and a one-layer intervention during decoding, enabling efficient real-time deployment.
  arXiv  Detail & Related papers  (2025-07-01T16:01:08Z)
• Skip-Vision: Efficient and Scalable Acceleration of Vision-Language Models via Adaptive Token Skipping [13.846838416902575]
  A key bottleneck stems from the proliferation of visual tokens required for fine-grained image understanding.<n>We propose Skip-Vision, a unified framework addressing both training and inference inefficiencies in vision-language models.<n> Experimental results demonstrate that Skip-Vision reduces training time by up to 35%, inference FLOPs by 75%, and latency by 45%.
  arXiv  Detail & Related papers  (2025-03-26T04:16:48Z)
• PLADIS: Pushing the Limits of Attention in Diffusion Models at Inference Time by Leveraging Sparsity [9.092404060771306]
  Diffusion models have shown impressive results in generating high-quality conditional samples.<n>However, existing methods often require additional training or neural function evaluations (NFEs)<n>We propose a novel and efficient method, termed PLADIS, which boosts pre-trained models by leveraging sparse attention.
  arXiv  Detail & Related papers  (2025-03-10T07:23:19Z)
• Underlying Semantic Diffusion for Effective and Efficient In-Context Learning [113.4003355229632]
  Underlying Semantic Diffusion (US-Diffusion) is an enhanced diffusion model that boosts underlying semantics learning, computational efficiency, and in-context learning capabilities.<n>We present a Feedback-Aided Learning (FAL) framework, which leverages feedback signals to guide the model in capturing semantic details.<n>We also propose a plug-and-play Efficient Sampling Strategy (ESS) for dense sampling at time steps with high-noise levels.
  arXiv  Detail & Related papers  (2025-03-06T03:06:22Z)
• Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think [72.48325960659822]
  One main bottleneck in training large-scale diffusion models for generation lies in effectively learning these representations.<n>We study this by introducing a straightforward regularization called REPresentation Alignment (REPA), which aligns the projections of noisy input hidden states in denoising networks with clean image representations obtained from external, pretrained visual encoders.<n>The results are striking: our simple strategy yields significant improvements in both training efficiency and generation quality when applied to popular diffusion and flow-based transformers, such as DiTs and SiTs.
  arXiv  Detail & Related papers  (2024-10-09T14:34:53Z)
• Visual Prompt Tuning in Null Space for Continual Learning [51.96411454304625]
  Existing prompt-tuning methods have demonstrated impressive performances in continual learning (CL) This paper aims to learn each task by tuning the prompts in the direction orthogonal to the subspace spanned by previous tasks' features. In practice, an effective null-space-based approximation solution has been proposed to implement the prompt gradient projection.
  arXiv  Detail & Related papers  (2024-06-09T05:57:40Z)
• BECLR: Batch Enhanced Contrastive Few-Shot Learning [1.450405446885067]
  Unsupervised few-shot learning aspires to bridge this gap by discarding the reliance on annotations at training time. We propose a novel Dynamic Clustered mEmory (DyCE) module to promote a highly separable latent representation space. We then tackle the, somehow overlooked yet critical, issue of sample bias at the few-shot inference stage.
  arXiv  Detail & Related papers  (2024-02-04T10:52:43Z)
• Accelerating LLaMA Inference by Enabling Intermediate Layer Decoding via Instruction Tuning with LITE [62.13435256279566]
  Large Language Models (LLMs) have achieved remarkable performance across a wide variety of natural language tasks. However, their large size makes their inference slow and computationally expensive. We show that it enables these layers to acquire 'good' generation ability without affecting the generation ability of the final layer.
  arXiv  Detail & Related papers  (2023-10-28T04:07:58Z)
• Planning for Sample Efficient Imitation Learning [52.44953015011569]
  Current imitation algorithms struggle to achieve high performance and high in-environment sample efficiency simultaneously. We propose EfficientImitate, a planning-based imitation learning method that can achieve high in-environment sample efficiency and performance simultaneously. Experimental results show that EI achieves state-of-the-art results in performance and sample efficiency.
  arXiv  Detail & Related papers  (2022-10-18T05:19:26Z)
• Activation to Saliency: Forming High-Quality Labels for Unsupervised Salient Object Detection [54.92703325989853]
  We propose a two-stage Activation-to-Saliency (A2S) framework that effectively generates high-quality saliency cues. No human annotations are involved in our framework during the whole training process. Our framework reports significant performance compared with existing USOD methods.
  arXiv  Detail & Related papers  (2021-12-07T11:54:06Z)

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.