相关论文: Accelerating LLaMA Inference by Enabling Intermedi…

Large Language Models (LLMs), such as ChatGPT and GPT-4, have dramatically transformed natural language processing research and shown promising strides towards Artificial General Intelligence (AGI). Nonetheless, the high costs associated…

The popularity of LLaMA (Touvron et al., 2023a;b) and other recently emerged moderate-sized large language models (LLMs) highlights the potential of building smaller yet powerful LLMs. Regardless, the cost of training such models from…

Diffusion large language models (dLLMs) generate text via iterative denoising but consistently underperform on multi-step reasoning. We hypothesize this gap stems from a coordination problem: AR models build coherence token-by-token, while…

The inference demand for LLMs has skyrocketed in recent months, and serving models with low latencies remains challenging due to the quadratic input length complexity of the attention layers. In this work, we investigate the effect of…

Large Language Models (LLMs), with their increasing depth and number of parameters, have demonstrated outstanding performance across a variety of natural language processing tasks. However, this growth in scale leads to increased…

The rapid evolution of Large Language Model (LLM) inference systems has yielded significant efficiency improvements. However, our systematic analysis reveals that current evaluation methodologies frequently exhibit fundamental flaws, often…

Deploying large language models (LLMs) in real-world applications is often hindered by strict computational and latency constraints. While dynamic inference offers the flexibility to adjust model behavior based on varying resource budgets,…

This paper introduces a simple and scalable approach to improve the data efficiency of large language model (LLM) training by augmenting existing text data with thinking trajectories. The compute for pre-training LLMs has been growing at an…

The Large Language Model (LLM) is widely employed for tasks such as intelligent assistants, text summarization, translation, and multi-modality on mobile phones. However, the current methods for on-device LLM deployment maintain slow…

This paper focuses on extending the success of large language models (LLMs) to sequential decision making. Existing efforts either (i) re-train or finetune LLMs for decision making, or (ii) design prompts for pretrained LLMs. The former…

This work investigates distillation methods for large language models (LLMs) with the goal of developing compact models that preserve high performance. Several existing approaches are reviewed, with a discussion of their respective…

This work introduces EE-Tuning, a lightweight and economical solution to training/tuning early-exit large language models (LLMs). In contrast to the common approach of full-parameter pre-training, EE-Tuning augments any pre-trained (and…

Large Language Models (LLMs) have demonstrated remarkable performance on various tasks, yet their ability to extract and internalize deeper insights from domain-specific datasets remains underexplored. In this study, we investigate how…

The computational cost of training multimodal large language models (MLLMs) grows rapidly with the number of processed tokens. Existing efficiency methods mainly target inference via token reduction or merging, offering limited benefits…

Standard classification models often map inputs directly to labels without explicit reasoning, potentially limiting their performance, robustness, and interpretability. This paper introduces a novel two-stage approach to enhance text…

The self-improving ability of large language models (LLMs), enabled by prompting them to analyze and revise their own outputs, has garnered significant interest in recent research. However, this ability has been shown to be absent and…

Large language models (LLMs) are now used in multi-turn workflows, but we still lack a clear way to measure when iteration helps and when it hurts. We present an evaluation framework for iterative refinement that spans ideation, code, and…

Recent advances in text-based large language models (LLMs), particularly in the GPT series and the o1 model, have demonstrated the effectiveness of scaling both training-time and inference-time compute. However, current state-of-the-art TTS…

Diffusion-based large language models (dLLMs) refine token generations through iterative denoising, but answers often stabilize before all steps complete. We propose EDIT (Early Diffusion Inference Termination), an inference-time criterion…

Recent advancements have demonstrated that the performance of large language models (LLMs) can be significantly enhanced by scaling computational resources at test time. A common strategy involves generating multiple Chain-of-Thought (CoT)…