Related papers: Overcoming Sparsity Artifacts in Crosscoders to In…

While language models are increasingly more proficient at code generation, they still frequently generate incorrect programs. Many of these programs are obviously wrong, but others are more subtle and pass weaker correctness checks such as…

Understanding code represents a core ability needed for automating software development tasks. While foundation models like LLMs show impressive results across many software engineering challenges, the extent of their true semantic…

During the pretraining phase, large language models (LLMs) acquire vast amounts of knowledge from extensive text corpora. Nevertheless, in later stages such as fine-tuning and inference, the model may encounter knowledge not covered in the…

We propose a method to teach multiple large language models (LLM) to collaborate by interleaving their generations at the token level. We model the decision of which LLM generates the next token as a latent variable. By optimizing the…

We propose MisMatch, a novel consistency-driven semi-supervised segmentation framework which produces predictions that are invariant to learnt feature perturbations. MisMatch consists of an encoder and a two-head decoders. One decoder…

Recent advances in large language models (LLMs) have led to the development of thinking language models that generate extensive internal reasoning chains before producing responses. While these models achieve improved performance,…

The recent phenomenal success of language models has reinvigorated machine learning research, and large sequence models such as transformers are being applied to a variety of domains. One important problem class that has remained relatively…

Vision-language retrieval is an important multi-modal learning topic, where the goal is to retrieve the most relevant visual candidate for a given text query. Recently, pre-trained models, e.g., CLIP, show great potential on retrieval…

Chatter detection has become a prominent subject of interest due to its effect on cutting tool life, surface finish and spindle of machine tool. Most of the existing methods in chatter detection literature are based on signal processing and…

State-of-the-art performance on language understanding tasks is now achieved with increasingly large networks; the current record holder has billions of parameters. Given a language model pre-trained on massive unlabeled text corpora, only…

Aligned representations across languages is a desired property in multilingual large language models (mLLMs), as alignment can improve performance in cross-lingual tasks. Typically alignment requires fine-tuning a model, which is…

During the finetuning stage of text generation tasks, standard cross-entropy loss treats all tokens equally. This can lead models to overemphasize high-frequency, low-information tokens, neglecting lower-frequency tokens crucial for…

How do neural language models keep track of number agreement between subject and verb? We show that `diagnostic classifiers', trained to predict number from the internal states of a language model, provide a detailed understanding of how,…

Existing research has shown that a multilingual pre-trained language model fine-tuned with one (source) language also performs well on downstream tasks for non-source languages, even though no fine-tuning is done on these languages.…

Large language models (LLMs) have demonstrated significant progress in multilingual language understanding and generation. However, due to the imbalance in training data, their capabilities in non-English languages are limited. Recent…

Recent research in the design of end to end communication system using deep learning has produced models which can outperform traditional communication schemes. Most of these architectures leveraged autoencoders to design the encoder at the…

Transfer learning is beneficial by allowing the expressive features of models pretrained on large-scale datasets to be finetuned for the target task of smaller, more domain-specific datasets. However, there is a concern that these…

Diffusion models have achieved great success in modeling continuous data modalities such as images, audio, and video, but have seen limited use in discrete domains such as language. Recent attempts to adapt diffusion to language have…

Fashion content generation is an emerging area at the intersection of artificial intelligence and creative design, with applications ranging from virtual try-on to culturally diverse design prototyping. Existing methods often struggle with…

Supervised fine-tuning (SFT) plays a critical role for pretrained large language models (LLMs), notably enhancing their capacity to acquire domain-specific knowledge while preserving or potentially augmenting their general-purpose…