Related papers: ROSA-Tuning: Enhancing Long-Context Modeling via S…
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…
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…
As large language models increasingly gain popularity in real-world applications, processing extremely long contexts, often exceeding the model's pre-trained context limits, has emerged as a critical challenge. While existing approaches to…
Fine-tuning helps large language models (LLM) recover degraded information and enhance task performance. Although Low-Rank Adaptation (LoRA) is widely used and effective for fine-tuning, we have observed that its scaling factor can limit or…
Extending context window sizes allows large language models (LLMs) to process longer sequences and handle more complex tasks. Rotary Positional Embedding (RoPE) has become the de facto standard due to its relative positional encoding…
This paper presents a context key/value compression method for Transformer language models in online scenarios, where the context continually expands. As the context lengthens, the attention process demands increasing memory and…
Retrieval-Augmented Generation (RAG) has significantly advanced large language models (LLMs) by grounding their outputs in external tools and knowledge sources. However, existing RAG systems are typically constrained to static, single-turn…
Reasoning language models such as DeepSeek-R1 produce long chain-of-thought traces during inference time which make them costly to deploy at scale. We show that using compression techniques such as neural network pruning produces greater…
Long contexts improve capabilities of large language models but pose serious hardware challenges: compute and memory footprints grow linearly with sequence length. Particularly, the decoding phase continuously accesses massive KV cache,…
Large Language Models (LLMs) have garnered widespread attention due to their remarkable performance across various tasks. However, to mitigate the issue of hallucinations, LLMs often incorporate retrieval-augmented pipeline to provide them…
Large Language Models (LLMs) excel across a variety of language tasks yet are constrained by limited input lengths and high computational costs. Existing approaches\textemdash such as relative positional encodings (e.g., RoPE, ALiBi) and…
Large Language Models (LLMs) have demonstrated remarkable capabilities across various applications, but their performance on long-context tasks is often limited by the computational complexity of attention mechanisms. We introduce a novel…
Utilizing large-scale pretrained models is a well-known strategy to enhance performance on various target tasks. It is typically achieved through fine-tuning pretrained models on target tasks. However, na\"{\i}ve fine-tuning may not fully…
Large language models (LLMs) have achieved substantial progress in processing long contexts but still struggle with long-context reasoning. Existing approaches typically involve fine-tuning LLMs with synthetic data, which depends on…
Although Transformers with fully connected self-attentions are powerful to model long-term dependencies, they are struggling to scale to long texts with thousands of words in language modeling. One of the solutions is to equip the model…
Long-context large language models (LLMs) hold promise for tasks such as question-answering (QA) over long documents, but they tend to miss important information in the middle of context documents (arXiv:2307.03172v3). Here, we introduce…
The quadratic cost of attention limits the scalability of long-context LLMs, especially under limited hardware memory budgets. While attention is often sparse, existing static sparse methods cannot adapt to task- or input-dependent…
Transformer-based large language models face severe scalability challenges in long-context generation due to the computational and memory costs of full-context attention. Under practical computation and memory constraints, many…
Dot-product attention has wide applications in computer vision and natural language processing. However, its memory and computational costs grow quadratically with the input size. Such growth prohibits its application on high-resolution…
Training and serving long-context large language models (LLMs) incurs substantial overhead. To address this, two critical steps are often required: a pretrained LLM typically undergoes a separate stage for context length extension by…