Related papers: How Does Fine-tuning Affect the Geometry of Embedd…

Prompt tuning is a promising method to fine-tune a pre-trained language model without retraining its large-scale parameters. Instead, it attaches a soft prompt to the input text, whereby downstream tasks can be well adapted by merely…

Finetuning provides a scalable and cost-effective means of customizing language models for specific tasks or response styles, with greater reliability than prompting or in-context learning. In contrast, the conventional wisdom is that…

We propose a new finetuning method to provide pre-trained large language models (LMs) the ability to scale test-time compute through the diffusion framework. By increasing the number of diffusion steps, we show our finetuned models achieve…

Augmenting large language models (LLMs) with external tools is a promising approach to enhance their capabilities, especially for complex tasks. Synthesizing tool-use data through real-world simulations is an effective way to achieve this.…

We discover the emergence of \textit{basins} in the loss landscape of large language models. As model scale increases, LLMs become progressively more resilient to random perturbations in the parameter space, giving rise to expansive…

Finetuning pretrained models occurs in a low-dimensional subspace of the full parameter space. Prior work has focused on characterizing this optimization subspace, but largely ignored the complementary question: why do certain directions…

The ability for robots to transfer their learned knowledge to new tasks -- where data is scarce -- is a fundamental challenge for successful robot learning. While fine-tuning has been well-studied as a simple but effective transfer approach…

In natural language processing, it has been observed recently that generalization could be greatly improved by finetuning a large-scale language model pretrained on a large unlabeled corpus. Despite its recent success and wide adoption,…

This paper presents a significant improvement on the previous conference paper known as DefSent. The prior study seeks to improve sentence embeddings of language models by projecting definition sentences into the vector space of dictionary…

The rise of deep learning has marked significant progress in fields such as computer vision, natural language processing, and medical imaging, primarily through the adaptation of pre-trained models for specific tasks. Traditional…

Contemporary Vision-Language Models (VLMs) achieve strong performance on a wide range of tasks by pairing a vision encoder with a pre-trained language model, fine-tuned for visual-text inputs. Yet despite these gains, it remains unclear how…

Speech language models align with human brain responses to natural language to an impressive degree. However, current models rely heavily on low-level speech features, indicating they lack brain-relevant semantics which limits their utility…

When large language models are aligned via supervised fine-tuning, they may encounter new factual information that was not acquired through pre-training. It is often conjectured that this can teach the model the behavior of hallucinating…

As an important metric for mesh quality evaluation, the isotropy property holds significant value for applications such as texture UV-mapping, physical simulation, and discrete geometric analysis. Classical isotropy remeshing methods adjust…

It is challenging to train a good intent classifier for a task-oriented dialogue system with only a few annotations. Recent studies have shown that fine-tuning pre-trained language models with a small amount of labeled utterances from…

Intermediate feature representations represent the backbone for the expressivity and adaptability of deep neural networks. However, their geometric structure remains poorly understood. In this submission, we provide indirect insights into…

Pre-trained speech Transformers have facilitated great success across various speech processing tasks. However, fine-tuning these encoders for downstream tasks require sufficiently large training data to converge or to achieve…

State-of-the-art embedding models are increasingly derived from decoder-only Large Language Model (LLM) backbones adapted via contrastive learning. Given the emergence of reasoning models trained via Reinforcement Learning with Verifiable…

Since their introduction, Transformer architectures have dominated Natural Language Processing (NLP). However, recent research has highlighted an inherent anisotropy phenomenon in these models, presenting a significant challenge to their…

Extensive fine-tuning on Large Language Models does not always yield better results. Oftentimes, models tend to get better at imitating one form of data without gaining greater reasoning ability and may even end up losing some intelligence.…