Related papers: FlowCut: Rethinking Redundancy via Information Flo…

Large language models (LLMs) process entire input contexts indiscriminately, which is inefficient when the information required to answer a query is localized within the context. We present dynamic context cutoff, a novel method enabling…

Vision-Language-Action (VLA) models have achieved significant breakthroughs by leveraging Large Vision Language Models (VLMs) to jointly interpret instructions and visual inputs. However, the substantial increase in visual tokens,…

Large Vision-Language Models (LVLMs) incur substantial inference costs due to the processing of a vast number of visual tokens. Existing methods typically struggle to model progressive visual token reduction as a multi-step decision process…

High-resolution Multimodal Large Language Models (MLLMs) face prohibitive computational costs during inference due to the explosion of visual tokens. Existing acceleration strategies, such as token pruning or layer sparsity, suffer from…

Robotic manipulation with Vision-Language-Action models requires efficient inference over long-horizon multi-modal context, where attention to dense visual tokens dominates computational cost. Existing methods optimize inference speed by…

Multimodal large language models (MLLMs) demonstrate strong performance across visual tasks, but their efficiency is hindered by significant computational and memory demands from processing long contexts in multimodal inputs. To address…

Value flow analysis that tracks the flow of values via data dependence is a widely used technique for detecting a broad spectrum of software bugs. However, the scalability issue often deteriorates when high precision (i.e.,…

Large Language Models (LLMs) rely on generating extensive intermediate reasoning units (e.g., tokens, sentences) to enhance final answer quality across a wide range of complex tasks. While this approach has proven effective, it inevitably…

Efficient vision-language understanding of large Remote Sensing Images (RSIs) is meaningful but challenging. Current Large Vision-Language Models (LVLMs) typically employ limited pre-defined grids to process images, leading to information…

Current high-resolution vision-language models encode images as high-resolution image tokens and exhaustively take all these tokens to compute attention, which significantly increases the computational cost. To address this problem, we…

Large multimodal models (LMMs) often suffer from severe inference inefficiency due to the large number of visual tokens introduced by image encoders. While recent token compression methods, such as pruning and merging, have shown promise in…

Recent Multimodal Large Language Models(MLLMs) often use a large number of visual tokens to compensate their visual shortcoming, leading to excessive computation and obvious visual redundancy. In this paper, we investigate what kind of…

Vision-Language Models (VLMs) have demonstrated strong performance on multimodal reasoning tasks, but their deployment remains challenging due to high inference latency and computational cost, particularly when processing high-resolution…

Large Multimodal Models (LMMs) have proven effective on various tasks. They typically encode visual inputs into Original Model sequences of tokens, which are then concatenated with textual tokens and jointly processed by the language model.…

Vision-language models (VLMs) could power real-time assistants and autonomous agents, but they face a critical challenge: understanding near-infinite video streams without escalating latency and memory usage. Processing entire videos with…

Growing evidence suggests that layer attention mechanisms, which enhance interaction among layers in deep neural networks, have significantly advanced network architectures. However, existing layer attention methods suffer from redundancy,…

Deploying Vision-Language Models (VLMs) under aggressive low-bit inference remains challenging because inference cost is dominated by the long visual-token prefix during prefill and the growing KV cache during autoregressive decoding. Token…

Real world deployments often expose modern object recognition models to domain shifts that precipitate a severe drop in accuracy. Such shifts encompass (i) variations in low level image statistics, (ii) changes in object pose and viewpoint,…

Video Large Language Models (Video LLMs) incur high inference latency due to a large number of visual tokens provided to LLMs. To address this, training-free visual token pruning has emerged as a solution to reduce computational costs;…

This paper investigates how to efficiently deploy vision transformers on edge devices for small workloads. Recent methods reduce the latency of transformer neural networks by removing or merging tokens, with small accuracy degradation.…