Related papers: BEAVER: A Training-Free Hierarchical Prompt Compre…

Large language models (LLMs) have shown remarkable capabilities in language understanding and generation. However, such impressive capability typically comes with a substantial model size, which presents significant challenges in both the…

Large Language Models (LLMs) have demonstrated exceptional performance across diverse tasks. However, their deployment in long-context scenarios faces high computational overhead and information redundancy. While soft prompt compression has…

We present Perceiver-VL, a vision-and-language framework that efficiently handles high-dimensional multimodal inputs such as long videos and text. Powered by the iterative latent cross-attention of Perceiver, our framework scales with…

Providing extensive context via prompting is vital for leveraging the capabilities of Large Language Models (LLMs). However, lengthy contexts significantly increase inference latency, as the computational cost of self-attention grows…

Large language models (LLMs) empowered by chain-of-thought reasoning have achieved impressive accuracy on complex tasks but suffer from excessive inference costs and latency when applied uniformly to all problems. We propose SABER…

Large language models (LLMs) can serve as the semantic-matching engine of a content-based publish/subscribe broker for agentic AI across the edge-cloud computing continuum, bridging the vocabulary and modality gaps that defeat keyword and…

Injecting world knowledge into pretrained multimodal large language models (MLLMs) is essential for domain-specific applications. Task-specific fine-tuning achieves this by tailoring MLLMs to high-quality in-domain data but encounters…

Large Language Models (LLMs) have demonstrated impressive capabilities in a wide range of natural language processing tasks when leveraging in-context learning. To mitigate the additional computational and financial costs associated with…

Scaling language models to longer contexts is essential for capturing rich dependencies across extended discourse. However, na\"ive context extension imposes significant computational and memory burdens, often resulting in inefficiencies…

To extend the context length of Transformer-based large language models (LLMs) and improve comprehension capabilities, we often face limitations due to computational resources and bounded memory storage capacity. This work introduces a…

While Large Language Models (LLMs) can theoretically support extensive context windows, their actual deployment is constrained by the linear growth of Key-Value (KV) cache memory. Prevailing compression strategies mitigate this through…

In this paper, we explore the idea of training large language models (LLMs) over highly compressed text. While standard subword tokenizers compress text by a small factor, neural text compressors can achieve much higher rates of…

Large language models (LLMs) enhanced with retrieval-augmented generation (RAG) have introduced a new paradigm for web search. However, the limited context awareness of LLMs degrades their performance on RAG tasks. Existing methods to…

The linear memory growth of the KV cache poses a significant bottleneck for LLM inference in long-context tasks. Existing static compression methods often fail to preserve globally important information. Although recent dynamic retrieval…

The rapid advancement of Large Language Models (LLMs) has inaugurated a transformative epoch in natural language processing, fostering unprecedented proficiency in text generation, comprehension, and contextual scrutiny. Nevertheless,…

While Large Language Models (LLMs) become ever more dominant, classic pre-trained word embeddings sustain their relevance through computational efficiency and nuanced linguistic interpretation. Drawing from recent studies demonstrating that…

In long context scenarios, large language models (LLMs) face three main challenges: higher computational cost, performance reduction, and position bias. Research indicates that LLM performance hinges on the density and position of key…

Volumetric data compression is critical in fields like medical imaging, scientific simulation, and entertainment. We introduce a structure-free neural compression method combining Fourierfeature encoding with selective voxel sampling,…

Large Language Models (LLMs) have demonstrated impressive quality when applied to predictive tasks such as relevance ranking and semantic search. However, deployment of such LLMs remains prohibitively expensive for industry applications…

Long-horizon language agents accumulate conversation history far faster than any fixed context window can hold, making memory management critical to both answer accuracy and serving cost. Existing approaches either expand the context window…