Related papers: CRAFT: Forgetting-Aware Intervention-Based Adaptat…

While Multimodal Large Language Models (MLLMs) excel at generalizing across modalities and tasks, effectively adapting them to specific downstream tasks while simultaneously retaining both general and specialized knowledge remains…

Large Language Models (LLMs) exhibit strong general language capabilities. However, fine-tuning these models on domain-specific tasks often leads to catastrophic forgetting, where the model overwrites or loses essential knowledge acquired…

Large language models (LLMs) show an innate skill for solving language based tasks. But insights have suggested an inability to adjust for information or task-solving skills becoming outdated, as their knowledge, stored directly within…

End-to-end training of Spoken Language Models (SLMs) commonly involves adapting pre-trained text-based Large Language Models (LLMs) to the speech modality through multi-stage training on diverse tasks such as ASR, TTS and spoken question…

Continual Learning (CL) aims to incrementally update a trained model on new tasks without forgetting the acquired knowledge of old ones. Existing CL methods usually reduce forgetting with task priors, \ie using task identity or a subset of…

Recent advances in Large Language Models (LLMs) have exhibited remarkable proficiency across various tasks. Given the potent applications of LLMs in numerous fields, there has been a surge in LLM development. In developing LLMs, a common…

Large language models (LLMs) often require vast amounts of text to effectively acquire new knowledge. While continuing pre-training on large corpora or employing retrieval-augmented generation (RAG) has proven successful, updating an LLM…

Continual post-training (CPT) is a popular and effective technique for adapting foundation models like multimodal large language models to specific and ever-evolving downstream tasks. While existing research has primarily concentrated on…

We study Latent Recurrent Transformer (LRT), a lightweight augmentation of autoregressive transformers that reuses a high-level source-layer hidden state from the previous token as recurrent memory for the next token. Because this source…

Large language models (LLMs) exhibit in-context learning abilities which enable the same model to perform several tasks without any task-specific training. In contrast, traditional adaptation approaches, such as fine-tuning, modify the…

Multivariate time series forecasting often struggles to capture long-range dependencies due to fixed lookback windows. Retrieval-augmented forecasting addresses this by retrieving historical segments from memory, but existing approaches…

Instruction tuning is now a widely adopted approach to aligning large multimodal models (LMMs) to follow human intent. It unifies the data format of vision-language tasks, enabling multi-task joint training. However, vision-language tasks…

The deployment of large language models (LLMs) like ChatGPT and Gemini has shown their powerful natural language generation capabilities. However, these models can inadvertently learn and retain sensitive information and harmful content…

Continual learning aims to improve the ability of modern learning systems to deal with non-stationary distributions, typically by attempting to learn a series of tasks sequentially. Prior art in the field has largely considered supervised…

Continual learning (CL) has remained a persistent challenge for deep neural networks due to catastrophic forgetting (CF) of previously learned tasks. Several techniques such as weight regularization, experience rehearsal, and parameter…

Continual Learning (CL) involves training a machine learning model in a sequential manner to learn new information while retaining previously learned tasks without the presence of previous training data. Although there has been significant…

Continual learning (CL) aims to continually accumulate knowledge from a non-stationary data stream without catastrophic forgetting of learned knowledge, requiring a balance between stability and adaptability. Relying on the generalizable…

In dynamic open-world environments, autonomous agents often encounter novelties that hinder their ability to find plans to achieve their goals. Specifically, traditional symbolic planners fail to generate plans when the robot's planning…

Large Language Models (LLMs) have demonstrated strong performance in open-ended generation tasks. However, they often struggle to adapt content to users with differing cognitive capacities, leading to a phenomenon we term cognitive…

Reasoning capability plays a significantly critical role in the the broad applications of Large Language Models (LLMs). To enhance the reasoning performance of LLMs, diverse Reinforcement Learning (RL)-based fine-tuning approaches have been…