Related papers: Context Cascade Compression: Exploring the Upper L…

With the growing demand for long-context LLMs across a wide range of applications, the key-value (KV) cache has become a critical bottleneck for both latency and memory usage. Recently, KV-cache offloading has emerged as a promising…

Large Language Models (LLMs) have been widely adopted to process long-context tasks. However, the large memory overhead of the key-value (KV) cache poses significant challenges in long-context scenarios. Existing training-free KV cache…

Large language models are transforming systems research by automating the discovery of performance-critical algorithms for computer systems. Despite plausible codes generated by LLMs, producing solutions that meet the stringent correctness…

Standard Large Language Models (LLMs) struggle with handling dialogues with long contexts due to efficiency and consistency issues. According to our observation, dialogue contexts are highly structured, and the special token of…

Large language models (LLMs) are in need of sufficient contexts to handle many critical applications, such as retrieval augmented generation and few-shot learning. However, due to the constrained window size, the LLMs can only access to the…

Large language models (LMs) are currently trained to predict tokens given document prefixes, enabling them to directly perform long-form generation and prompting-style tasks which can be reduced to document completion. Existing pretraining…

Large Language Models (LLMs) achieve superior performance through Chain-of-Thought (CoT) reasoning, but these token-level reasoning chains are computationally expensive and inefficient. In this paper, we introduce Compressed Latent…

Large language models (LLMs) face significant token efficiency bottlenecks in code generation and logical reasoning tasks, a challenge that directly impacts inference cost and model interpretability. This paper proposes a formal framework…

Text compression for large language model (LLM) systems is usually framed as token deletion, retrieval, summarization, or exact reconstruction. We study a more aggressive but explicitly lossy setting: compress text into compact codes that…

The exponential growth of Large Multimodal Models (LMMs) has driven advancements in cross-modal reasoning but at significant computational costs. In this work, we focus on visual language models. We highlight the redundancy and inefficiency…

The increasing prevalence of Large Language Models (LLMs) demands effective safeguards for their operation, particularly concerning their tendency to generate out-of-context responses. A key challenge is accurately detecting when LLMs stray…

Video Large Language Models (Video LLMs) have shown remarkable progress in understanding and reasoning about visual content, particularly in tasks involving text recognition and text-based visual question answering (Text VQA). However,…

Context-aware processing mechanisms have increasingly become a critical area of exploration for improving the semantic and contextual capabilities of language generation models. The Context-Aware Semantic Recomposition Mechanism (CASRM) was…

Modern techniques in Content-based Recommendation (CBR) leverage item content information to provide personalized services to users, but suffer from resource-intensive training on large datasets. To address this issue, we explore the…

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…

Large language models (LLMs) and their multimodal variants can now process visual inputs, including images of text. This raises an intriguing question: can we compress textual inputs by feeding them as images to reduce token usage while…

Large Language Models (LLMs) have demonstrated exceptional capabilities across diverse tasks. However, their deployment in long context scenarios remains hindered by computational inefficiency and information redundancy. Context compression…

The rapid expansion of context window sizes in Large Language Models~(LLMs) has enabled them to tackle increasingly complex tasks involving lengthy documents. However, this progress comes at the cost of a substantial increase in memory…

Large Language Models (LLMs) are increasingly deployed across edge and cloud platforms for real-time question-answering and retrieval-augmented generation. However, processing lengthy contexts in distributed systems incurs high…

Unlike autoregressive models, which generate one token at a time, dLLMs denoise a chunk of [MASK] tokens jointly and sample one or more tokens per step; despite enabling parallel decoding, this process incurs substantial computational cost…