相关论文: Copy-as-Decode: Grammar-Constrained Parallel Prefi…

Repository-level code completion remains a challenging task for existing code large language models (code LLMs) due to their limited understanding of repository-specific context and domain knowledge. While retrieval-augmented generation…

Low-latency decoding for large language models (LLMs) is crucial for applications like chatbots and code assistants, yet generating long outputs remains slow in single-query settings. Prior work on speculative decoding (which combines a…

Intermediate-layer predictions in large language models (LLMs) are informative but hard to decode accurately, especially at early layers. Existing lens-style methods typically rely on direct linear readout, which is simple but often drifts…

In this study, we aim to reduce generation latency for Named Entity Recognition (NER) with Large Language Models (LLMs). The main cause of high latency in LLMs is the sequential decoding process, which autoregressively generates all labels…

Integrating large language models (LLMs) as priors in reinforcement learning (RL) offers significant advantages but comes with substantial computational costs. We present a principled cache-efficient framework for posterior sampling with…

In edge-cloud speculative decoding (SD), edge devices equipped with small language models (SLMs) generate draft tokens that are verified by large language models (LLMs) in the cloud. A key bottleneck in such systems is the limited…

Speculative decoding and quantization effectively accelerate memory-bound inference of large language models. Speculative decoding mitigates the memory bandwidth bottleneck by verifying multiple tokens within a single forward pass, which…

Speculative decoding accelerates LLM inference by verifying candidate tokens from a draft model against a larger target model. Recent judge decoding boosts this process by relaxing verification criteria by accepting draft tokens that may…

Understanding code represents a core ability needed for automating software development tasks. While foundation models like LLMs show impressive results across many software engineering challenges, the extent of their true semantic…

Reasoning LLMs produce longer outputs, requiring speculative decoding drafters trained on extended sequences. Parallel drafting - predicting multiple tokens per forward pass - offers latency benefits over sequential generation, but training…

Publicly available, large pretrained LanguageModels (LMs) generate text with remarkable quality, but only sequentially from left to right. As a result, they are not immediately applicable to generation tasks that break the unidirectional…

Striking an optimal balance between minimal drafting latency and high speculation accuracy to enhance the inference speed of Large Language Models remains a significant challenge in speculative decoding. In this paper, we introduce Falcon,…

How to edit the knowledge in multi-step reasoning has become the major challenge in the knowledge editing (KE) of large language models (LLMs). The difficulty arises because the hallucinations of LLMs during multi-step reasoning often lead…

Large Language Models (LLMs) often generate repetitive and monotonous outputs, especially in tasks like story generation, due to limited creative diversity when given the same input prompt. To address this challenge, we propose a novel…

Diffusion large language models (dLLMs) generate text by iteratively denoising masked token sequences. Although dLLMs can predict all masked positions in parallel within each step, the large number of denoising iterations still makes…

In LLM-based code generation, multiple code candidates are often generated in parallel from the same prompt -- for example, in best-of-N sampling or multi-candidate code completion. These requests can share KV caches through a common…

Large Language Models (LLMs) achieve strong performance across many tasks but suffer from high inference latency due to autoregressive decoding. The issue is exacerbated in Large Reasoning Models (LRMs), which generate lengthy chains of…

One of the most striking findings in modern research on large language models (LLMs) is that scaling up compute during training leads to better results. However, less attention has been given to the benefits of scaling compute during…

Large Language Models (LLMs) are increasingly applied to complex tasks that require extended reasoning. In such settings, models often benefit from diverse chains-of-thought to arrive at multiple candidate solutions. This requires two…

Large language models (LLMs) have been increasingly used to analyze text. However, they are often plagued with contextual reasoning limitations when analyzing long documents. When long documents are processed sequentially, early or dominant…