Related papers: ProFuser: Progressive Fusion of Large Language Mod…
Fine-tuning BERT-based models is resource-intensive in memory, computation, and time. While many prior works aim to improve inference efficiency via compression techniques, e.g., pruning, these works do not explicitly address the…
The immense computational cost of training Large Language Models (LLMs) presents a major barrier to innovation. While FP8 training offers a promising solution with significant theoretical efficiency gains, its widespread adoption has been…
Achieving consensus in group decision-making often involves overcoming significant challenges, particularly in reconciling diverse perspectives and mitigating biases that hinder agreement. Traditional methods relying on human facilitators…
While the numerous parameters in Large Language Models (LLMs) contribute to their superior performance, this massive scale makes them inefficient and memory-hungry. Thus, they are hard to deploy on commodity hardware, such as one single…
Reinforcement learning with verifiable rewards (RLVR) has improved the reasoning ability of large language models, yet training remains costly because many rollouts contribute little to optimization, considering the amount of computation…
Humans generally acquire new skills without compromising the old; however, the opposite holds for Large Language Models (LLMs), e.g., from LLaMA to CodeLLaMA. To this end, we propose a new post-pretraining method for LLMs with an expansion…
Developing effective multimodal data fusion strategies has become increasingly essential for improving the predictive power of statistical machine learning methods across a wide range of applications, from autonomous driving to medical…
Large language models such as GPT and Llama are trained with a next-token prediction loss. In this work, we suggest that training language models to predict multiple future tokens at once results in higher sample efficiency. More…
The recent popularity of text-to-image diffusion models (DM) can largely be attributed to the intuitive interface they provide to users. The intended generation can be expressed in natural language, with the model producing faithful…
Recently, the release of INSTRUCTEVAL has provided valuable insights into the performance of large language models (LLMs) that utilize encoder-decoder or decoder-only architecture. Interestingly, despite being introduced four years ago,…
Training large language models (LLMs) and multimodal LLMs necessitates significant computing resources, and existing publicly available LLMs are typically pre-trained on diverse, privately curated datasets spanning various tasks. For…
Large language models (LLMs) have revolutionized Natural Language Processing (NLP), but their size creates computational bottlenecks. We introduce a novel approach to create accurate, sparse foundational versions of performant LLMs that…
Recent advancements in joint speech-text models show great potential for seamless voice interactions. However, existing models face critical challenges: temporal resolution mismatch between speech tokens (25Hz) and text tokens (~3Hz)…
This paper presents a study on strategies to enhance the translation capabilities of large language models (LLMs) in the context of machine translation (MT) tasks. The paper proposes a novel paradigm consisting of three stages: Secondary…
We introduce Dream 7B, the most powerful open diffusion large language model to date. Unlike autoregressive (AR) models that generate tokens sequentially, Dream 7B employs discrete diffusion modeling to refine sequences in parallel through…
Large language models (LLMs) have demonstrated remarkable capabilities across various tasks. However, their widespread application is hindered by the resource-intensive decoding process. To address this challenge, current approaches have…
Fine-tuning pre-trained language models has become the prevalent paradigm for building downstream NLP models. Oftentimes fine-tuned models are readily available but their training data is not, due to data privacy or intellectual property…
Language models with recurrent depth, also referred to as universal or looped when considering transformers, are defined by the capacity to increase their computation through the repetition of layers. Recent efforts in pretraining have…
Large language models (LLMs) achieve high accuracy on many reasoning benchmarks but remain brittle under structural perturbations of rule-based systems. We introduce a diagnostic framework with four stress tests -- redundant vs. essential…
Large language models (LLMs) are susceptible to persuasion, which can pose risks when models are faced with an adversarial interlocutor. We take a first step towards defending models against persuasion while also arguing that defense…