Related papers: LoRE-Merging: Exploring Low-Rank Estimation For La…

Model merging is an effective strategy to merge multiple models for enhancing model performances, and more efficient than ensemble learning as it will not introduce extra computation into inference. However, limited research explores if the…

Reinforcement learning (RL) is central to post-training, particularly for agentic models that require specialized reasoning behaviors. In this setting, model merging offers a practical mechanism for integrating multiple RL-trained agents…

Supervised fine-tuning (SFT) is crucial for adapting Large Language Models (LLMs) to specific tasks. In this work, we demonstrate that the order of training data can lead to significant training imbalances, potentially resulting in…

With the productive evolution of large language models (LLMs) in the field of natural language processing (NLP), tons of effort has been made to effectively fine-tune common pre-trained LLMs to fulfill a variety of tasks in one or multiple…

As Large Language Models (LLMs) excel across tasks and specialized domains, scaling LLMs based on existing models has garnered significant attention, which faces the challenge of decreasing performance when combining disparate models.…

Pre-training Large Language Models (LLMs) on web-scale datasets becomes fundamental for advancing general-purpose AI. In contrast, enhancing their predictive performance on downstream tasks typically involves adapting their knowledge…

Weight-space model merging combines independently fine-tuned models without accessing original training data, offering a practical alternative to joint training. While merging succeeds in multitask settings, its behavior in multilingual…

In order to streamline the fine-tuning of foundation models, Low-Rank Adapters (LoRAs) have been substantially adopted across various fields, including instruction tuning and domain adaptation. The underlying concept of LoRA involves…

Reinforcement learning (RL) has been widely used in training large language models (LLMs) for preventing unexpected outputs, eg reducing harmfulness and errors. However, existing RL methods mostly adopt the instance-level reward, which is…

Generative depth estimation methods leverage the rich visual priors stored in pre-trained text-to-image diffusion models, demonstrating astonishing zero-shot capability. However, parameter updates during training lead to catastrophic…

Aligning large language models (LLMs) with human preferences usually requires fine-tuning methods such as RLHF and DPO. These methods directly optimize the model parameters, so they cannot be used in test-time to improve model performance,…

The scaling law of Large Language Models (LLMs) reveals a power-law relationship, showing diminishing return on performance as model scale increases. While training LLMs from scratch is resource-intensive, fine-tuning a pre-trained model…

Existing low-rank adaptation (LoRA) methods face challenges on sparse large language models (LLMs) due to the inability to maintain sparsity. Recent works introduced methods that maintain sparsity by augmenting LoRA techniques with…

Model merging has emerged as a promising technique for combining multiple fine-tuned models into a single multitask model without retraining. However, the factors that determine whether merging will succeed or fail remain poorly understood.…

State-of-the-art vision-and-language models consist of many parameters and learn from enormous datasets, surpassing the amounts of linguistic data that children are exposed to as they acquire a language. This paper presents our approach to…

Recent advances in reinforcement learning (RL) for large language model (LLM) fine-tuning show promise in addressing multi-objective tasks but still face significant challenges, including competing objective balancing, low training…

Parameter-Efficient Fine-Tuning (PEFT) methods like LoRA have significantly improved the adaptation of LLMs to downstream tasks in a resource-efficient manner. However, in multi-task scenarios, challenges such as training imbalance and the…

Model merging aims to integrate multiple expert models into a single model that inherits their complementary strengths without incurring the inference-time cost of ensembling. Recent progress has shown that merging can be highly effective…

This paper introduces Bayesian Hierarchical Low-Rank Adaption (BoRA), a novel method for finetuning multi-task Large Language Models (LLMs). Current finetuning approaches, such as Low-Rank Adaption (LoRA), perform exeptionally well in…

Vision-language alignment in multi-modal large language models (MLLMs) relies on supervised fine-tuning (SFT) or reinforcement learning (RL). To align multi-modal large language models (MLLMs) in the post-training stage, supervised…