Related papers: Training Optimal Large Diffusion Language Models

In recent years, large language models (LLMs) have witnessed remarkable advancements, with the test-time scaling law consistently enhancing the reasoning capabilities. Through systematic evaluation and exploration of a diverse spectrum of…

Masked diffusion models (MDMs) have shown promise in language modeling, yet their scalability and effectiveness in core language tasks, such as text generation and language understanding, remain underexplored. This paper establishes the…

Diffusion language models (DLMs) have emerged as a promising alternative to autoregressive models for faster inference via parallel token generation. We provide a rigorous foundation for this advantage by formalizing a model of parallel…

Fine-tuning large language models (LLMs) for reasoning tasks using reinforcement learning methods like Group Relative Policy Optimization (GRPO) is computationally expensive. To address this, we propose a predictive framework that models…

We propose DiFFPO, Diffusion Fast and Furious Policy Optimization, a unified framework for training masked diffusion large language models (dLLMs) to reason not only better (furious), but also faster via reinforcement learning (RL). We…

The scaling law, a cornerstone of Large Language Model (LLM) development, predicts improvements in model performance with increasing computational resources. Yet, while empirically validated, its theoretical underpinnings remain poorly…

Recent advances in large language models (LLMs) have shown remarkable capabilities across textual and multimodal domains. In parallel, diffusion-based language models have emerged as a promising alternative to the autoregressive paradigm,…

Large language models (LLMs) have been widely employed across various application domains, yet their black-box nature poses significant challenges to understanding how these models process input data internally to make predictions. In this…

Large Language Models (LLMs) have drawn a lot of attention due to their strong performance on a wide range of natural language tasks, since the release of ChatGPT in November 2022. LLMs' ability of general-purpose language understanding and…

Diffusion Language Models (DLMs) have emerged as a promising new paradigm for text generative modeling, potentially addressing limitations of autoregressive (AR) models. However, current DLMs have been studied at a smaller scale compared to…

Large language models (LLMs) have attracted significant attention due to their impressive general capabilities across diverse downstream tasks. However, without domain-specific optimization, they often underperform on specialized knowledge…

Large language models have achieved remarkable success under the autoregressive paradigm, yet high-quality text generation need not be tied to a fixed left-to-right order. Existing alternatives still struggle to jointly achieve generation…

We introduce Chunk-Distilled Language Modeling (CD-LM), an approach to text generation that addresses two challenges in current large language models (LLMs): the inefficiency of token-level generation, and the difficulty of adapting to new…

This work studies the general principles of improving the learning of language models (LMs), which aims at reducing the necessary training steps for achieving superior performance. Specifically, we present a theory for the optimal learning…

Diffusion Language Models (DLMs) offer a promising parallel generation paradigm but suffer from slow inference due to numerous refinement steps and the inability to use standard KV caching. We introduce CDLM (Consistency Diffusion Language…

Large Language Models (LLMs) have revolutionized many areas of artificial intelligence (AI), but their substantial resource requirements limit their deployment on mobile and edge devices. This survey paper provides a comprehensive overview…

Large language models (LLMs) have made remarkable advances in recent years, with scaling laws playing a critical role in this rapid progress. In this paper, we empirically investigate how a critical hyper-parameter, i.e., the global batch…

Training compute is increasingly outpacing the availability of high-quality data. This shifts the central challenge from optimal compute allocation to extracting maximum value from limited data. The widely adopted Chinchilla scaling law…

Diffusion large language models (dLLMs) have emerged as a compelling alternative to autoregressive (AR) LLMs, owing to their capacity for parallel token generation. This paradigm is particularly well-suited for code generation, where…

This paper investigates scaling laws for local SGD in LLM training, a distributed optimization algorithm that facilitates training on loosely connected devices. Through extensive experiments, we show that local SGD achieves competitive…