Related papers: Fast Inference of Visual Autoregressive Model with…

As an agent moves through the world, the apparent motion of scene elements is (usually) inversely proportional to their depth. It is natural for a learning agent to associate image patterns with the magnitude of their displacement over…

In this paper, we propose an efficient frontier detector method based on adaptive Rapidly-exploring Random Tree (RRT) for autonomous robot exploration. Robots can achieve real-time incremental frontier detection when they are exploring…

We present Locality-aware Parallel Decoding (LPD) to accelerate autoregressive image generation. Traditional autoregressive image generation relies on next-patch prediction, a memory-bound process that leads to high latency. Existing works…

Depth-adaptive neural networks can dynamically adjust depths according to the hardness of input words, and thus improve efficiency. The main challenge is how to measure such hardness and decide the required depths (i.e., layers) to conduct.…

Recently, prompt learning has demonstrated remarkable success in adapting pre-trained Vision-Language Models (VLMs) to various downstream tasks such as image classification. However, its application to the downstream Image-Text Retrieval…

Speculative decoding accelerates autoregressive large language model (LLM) inference by using a lightweight draft model to propose candidate tokens that are then verified in parallel by the target model. The speedup is significantly…

Diffusion Transformers (DiTs) achieve state-of-the-art generation quality but require long sequential denoising trajectories, leading to high inference latency. Recent speculative inference methods enable lossless parallel sampling in…

Recently, autoregressive (AR) image models have demonstrated remarkable generative capabilities, positioning themselves as a compelling alternative to diffusion models. However, their sequential nature leads to long inference times,…

Accurately predicting the future trajectories of traffic agents is essential in autonomous driving. However, due to the inherent imbalance in trajectory distributions, tail data in natural datasets often represents more complex and…

Large Language Models (LLMs) exhibit high inference latency due to their autoregressive decoding nature. While the draft head in speculative decoding mitigates this issue, its full potential remains unexplored. In this paper, we introduce…

Despite impressive advancements in Autonomous Driving Systems (ADS), navigation in complex road conditions remains a challenging problem. There is considerable evidence that evaluating the subjective risk level of various decisions can…

Diffusion models have achieved outstanding image generation by reversing a forward noising process to approximate true data distributions. During training, these models predict diffusion scores from noised versions of true samples in a…

Flow models are effective at progressively generating realistic images, but they generally struggle to capture long-range dependencies during the generation process as they compress all the information from previous time steps into a single…

Self-supervised learning methods based on image patch reconstruction have witnessed great success in training auto-encoders, whose pre-trained weights can be transferred to fine-tune other downstream tasks of image understanding. However,…

Prompt learning has recently become a very efficient transfer learning paradigm for Contrastive Language Image Pretraining (CLIP) models. Compared with fine-tuning the entire encoder, prompt learning can obtain highly competitive results by…

The process of estimating and counting tree density using only a single aerial or satellite image is a difficult task in the fields of photogrammetry and remote sensing. However, it plays a crucial role in the management of forests. The…

Autoregressive (AR) image models have recently demonstrated remarkable generative capability, but their sequential nature results in significant inference latency. Existing training-free acceleration methods typically verify tokens…

This paper introduces Multimodal Speculative Decoding (MSD) to accelerate Multimodal Large Language Models (MLLMs) inference. Speculative decoding has been shown to accelerate Large Language Models (LLMs) without sacrificing accuracy.…

Convolutional neural networks can automatically learn features via deep network architectures and given input samples. However, the robustness of obtained models may face challenges in varying scenes. Bigger differences in network…

Although current Video-LLMs achieve impressive performance in video understanding tasks, their autoregressive decoding efficiency remains constrained by the massive number of video tokens. Visual token pruning can partially ease this…