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

Large language models (LLMs) rely on key-value (KV) caches for efficient autoregressive decoding; however, cache size grows linearly with context length and model depth, becoming a major bottleneck in long-context inference. Prior KV cache…

Audio-Visual Speech Recognition (AVSR) achieves robust speech recognition in noisy environments by combining auditory and visual information. However, recent Large Language Model (LLM) based AVSR systems incur high computational costs due…

Long-form video understanding remains challenging for Video Large Language Models (VideoLLMs), as the dense frame sampling introduces massive visual tokens while sparse sampling risks missing critical temporal evidence and leading to LLM…

Modern foundation models such as large language models (LLMs) and large multi-modal models (LMMs) require a massive amount of computational and memory resources. We propose a new framework to convert such LLMs/LMMs into a reduced-dimension…

Discrete audio tokens are compact representations that aim to preserve perceptual quality, phonetic content, and speaker characteristics while enabling efficient storage and inference, as well as competitive performance across diverse…

The reasoning abilities of Large Language Models (LLMs) can be improved by structurally denoising their weights, yet existing techniques primarily focus on denoising the feed-forward network (FFN) of the transformer block, and can not…

While Transformer-based models have shown impressive language modeling performance, the large computation cost is often prohibitive for practical use. Attention head pruning, which removes unnecessary attention heads in the multihead…

Large language models (LLMs) excel at complex reasoning, yet their efficiency is limited by the surging cognitive overhead of long thought traces. In this paper, we propose LightThinker, a method that enables LLMs to dynamically compress…

Recent years have seen a growing adoption of Transformer models such as BERT in Natural Language Processing and even in Computer Vision. However, due to their size, there has been limited adoption of such models within resource-constrained…

Large language models (LLMs) have recently emerged as powerful tools for tackling many language-processing tasks. Despite their success, training and fine-tuning these models is still far too computationally and memory intensive. In this…

Abstractive compression utilizes smaller langauge models to condense query-relevant context, reducing computational costs in retrieval-augmented generation (RAG). However,retrieved documents often include information that is either…

We introduce Speech Information Retrieval (SIR), a new long-context task for Speech Large Language Models (Speech LLMs), and present SPIRAL, a 1,012-sample benchmark testing models' ability to extract critical details from approximately…

The increasing prevalence of large language models (LLMs) such as GPT-4 in various applications has led to a surge in the size of prompts required for optimal performance, leading to challenges in computational efficiency. Prompt…

Prompt compression methods enhance the efficiency of Large Language Models (LLMs) and minimize the cost by reducing the length of input context. The goal of prompt compression is to shorten the LLM prompt while maintaining a high generation…

The prevalence of Transformer-based pre-trained language models (PLMs) has led to their wide adoption for various natural language processing tasks. However, their excessive overhead leads to large latency and computational costs. The…

Scaling the context size of large language models (LLMs) enables them to perform various new tasks, e.g., book summarization. However, the memory cost of the Key and Value (KV) cache in attention significantly limits the practical…

Visual token compression is critical for Large Vision-Language Models (LVLMs) to efficiently process high-resolution inputs. Existing methods that typically adopt fixed compression ratios cannot adapt to scenes of varying complexity, often…

Tokenizer is an essential component for large language models (LLMs), and a tokenizer with a high compression rate can improve the model's representation and processing efficiency. However, the tokenizer cannot ensure high compression rate…

Large language model (LLM) tokenizers act as structured compressors: by mapping text to discrete token sequences, they determine token count (and thus compute and context usage) and the statistical structure seen by downstream models.…

Large vision-language models (LVLMs) achieve strong multimodal understanding, but their inference cost grows rapidly with the number of visual tokens, especially for high-resolution images and long videos. Existing attention-based methods…