Related papers: HeadRouter: Dynamic Head-Weight Routing for Task-A…

Multimodal large language models (MLLMs) have shown remarkable performance for cross-modal understanding and generation, yet still suffer from severe inference costs. Recently, abundant works have been proposed to solve this problem with…

Video Large Language Models (VLLMs) incur substantial prefilling cost due to the large number of visual tokens. While attention-based token pruning offers a promising acceleration strategy, applying it at shallow decoder layers often causes…

Vision tokens in multimodal large language models often dominate huge computational overhead due to their excessive length compared to linguistic modality. Abundant recent methods aim to solve this problem with token pruning, which first…

In this work, we present FastAV, the first token pruning framework tailored for audio-visual large language models (AV-LLMs). While token pruning has been actively explored in standard large language models (LLMs) and vision-language models…

Key-Value (KV) caching is a common technique to enhance the computational efficiency of Large Language Models (LLMs), but its memory overhead grows rapidly with input length. Prior work has shown that not all tokens are equally important…

Large Language Models (LLMs) deliver state-of-the-art performance across many tasks but impose high computational and memory costs, limiting their deployment in resource-constrained or real-time settings. To address this, we propose…

Large Speech Language Models (LSLMs) typically operate at high token rates (tokens/s) to ensure acoustic fidelity, yet this results in sequence lengths that far exceed the underlying semantic content, incurring prohibitive inference costs.…

Large Audio-Language Models (LALMs) have set new benchmarks in speech processing, yet their deployment is hindered by the memory footprint of the Key-Value (KV) cache during long-context inference. While general KV cache compression…

Large Multimodal Models (LMMs) excel in visual-language tasks by leveraging numerous visual tokens for fine-grained visual information, but this token redundancy results in significant computational costs. Previous research aimed at…

Large Vision-Language Models (LVLMs) have advanced multimodal learning but face high computational costs due to the large number of visual tokens, motivating token pruning to improve inference efficiency. The key challenge lies in…

Recent advances in large language models (LLMs) have significantly boosted long-context processing. However, the increasing key-value (KV) cache size poses critical challenges to memory and execution efficiency. Most KV cache compression…

As the computational needs of Large Vision-Language Models (LVLMs) increase, visual token pruning has proven effective in improving inference speed and memory efficiency. Traditional pruning methods in LVLMs predominantly focus on attention…

Large Audio-Language Models (LALMs) often suffer from audio-textual attention imbalance, prioritizing text over acoustic information, particularly in the multi-modal fusion layers of the Transformer architecture. This bias hinders their…

Transformer-based models have become the state of the art across multiple domains, from natural language processing to machine listening, thanks to the attention mechanisms. However, the attention layers require a large number of parameters…

Long-term conversational agents must decide which turns to store in external memory, yet recent systems rely on autoregressive LLM generation at every turn to make that decision. We present MemRouter, a write-side memory router that…

Autoregressive Transformers adopted in Large Language Models (LLMs) are hard to scale to long sequences. Despite several works trying to reduce their computational cost, most of LLMs still adopt attention layers between all pairs of tokens…

Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities, yet they encounter significant computational bottlenecks due to the massive volume of visual tokens. Consequently, visual token pruning, which substantially…

In long-context decoding for LLMs and LMMs, attention becomes increasingly memory-bound because each decoding step must load a large amount of KV-cache data from GPU memory. Existing acceleration strategies often trade efficiency for…

Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities across a range of multimodal tasks. However, their inference efficiency is constrained by the large number of visual tokens processed during decoding. To address…

Omni-modal large language models have demonstrated remarkable potential in holistic multimodal understanding; however, the token explosion caused by high-resolution audio and video inputs remains a critical bottleneck for real-time…