Related papers: SAFE-Pruner: Semantic Attention-Guided Future-Awar…

Vision-Language Models suffer severe KV cache pressure at inference, as a single image often encodes into thousands of tokens. Most existing methods exploit token sparsity through token pruning, but permanently discarding visual content…

Recent work has begun to equip vision-language-action (VLA) policies with explicit intermediate reasoning. In embodied control, however, textual chain-of-thought is a poor fit: irrelevant or weakly textual information can interfere with…

Several recent studies have demonstrated the promise of deep visuomotor policies for robot manipulator control. Despite impressive progress, these systems are known to be vulnerable to physical disturbances, such as accidental or…

Pruning is a promising approach to compress deep learning models in order to deploy them on resource-constrained edge devices. However, many existing pruning solutions are based on unstructured pruning, which yields models that cannot…

Large language models (LLMs) face significant deployment challenges due to their massive computational demands. % While pruning offers a promising compression solution, existing methods suffer from two critical limitations: (1) They neglect…

Visual Language Models require substantial computational resources for inference due to the additional input tokens needed to represent visual information. However, these visual tokens often contain redundant and unimportant information,…

Multimodal Large Language Models (MLLMs) have shown strong performance in vision-language tasks, but their inference efficiency is severely limited by the exponential growth of visual tokens in complex scenarios such as high-resolution…

Deep spiking neural networks (SNNs) have emerged as a potential alternative to traditional deep learning frameworks, due to their promise to provide increased compute efficiency on event-driven neuromorphic hardware. However, to perform…

Visual token pruning methods effectively mitigate the quadratic computational growth caused by processing high-resolution images and video frames in vision-language models (VLMs). However, existing approaches rely on predefined pruning…

Recent advancements in vision-language-action (VLA) models have shown promise in robotic manipulation, yet they continue to struggle with long-horizon, multi-step tasks. Existing methods lack internal reasoning mechanisms that can identify…

Large Vision Language Models (LVLMs) have achieved significant success across multi-modal tasks. However, the computational cost of processing long visual tokens can be prohibitively expensive on resource-limited devices. Previous methods…

Linear attention offers a computationally efficient yet expressive alternative to softmax attention. However, recent empirical results indicate that the hidden state of trained linear attention models often exhibits a low-rank structure,…

In multimodal large language models (MLLMs), the length of input visual tokens is often significantly greater than that of their textual counterparts, leading to a high inference cost. Many works aim to address this issue by removing…

Vision-Language-Action (VLA) models rely on current observations, including images, language instructions, and robot states, to predict actions and complete tasks. While accurate visual perception is crucial for precise action prediction…

Vision-Language-Action (VLA) models excel in robotic manipulation but suffer from significant inference latency due to processing dense visual tokens. Existing token reduction methods predominantly rely on attention magnitude as a static…

Transformer-based models have achieved dominant performance in numerous NLP tasks. Despite their remarkable successes, pre-trained transformers such as BERT suffer from a computationally expensive self-attention mechanism that interacts…

Vision-Language-Action (VLA) models have gained much attention from the research community thanks to their strength in translating multimodal observations with linguistic instructions into robotic actions. Despite their recent advancements,…

In this paper, we introduce PruneVid, a visual token pruning method designed to enhance the efficiency of multi-modal video understanding. Large Language Models (LLMs) have shown promising performance in video tasks due to their extended…

Vision-Language-Action (VLA) models improve action generation by conditioning policies on rich vision-language information. However, current auto-regressive policies are constrained by three bottlenecks: (1) architectural bias drives models…

While excellent in transfer learning, Vision-Language models (VLMs) come with high computational costs due to their large number of parameters. To address this issue, removing parameters via model pruning is a viable solution. However,…