Related papers: Crown, Frame, Reverse: Layer-Wise Scaling Variants…
Large language models (LLMs) targeting different deployment scales and sizes are currently produced by training each variant from scratch; this is extremely compute-intensive. In this paper, we investigate if pruning an existing LLM and…
To enhance the efficiency of the attention mechanism within large language models (LLMs), previous works primarily compress the KV cache or group attention heads, while largely overlooking redundancy between layers. Our comprehensive…
Pruning is a highly effective approach for compressing large language models (LLMs), significantly reducing inference latency. However, conventional training-free structured pruning methods often employ a heuristic metric that…
Recent advances in Multimodal Large Language Models (MLLMs) have shown remarkable capabilities in understanding both images and 3D data, yet these modalities face inherent limitations in comprehensively representing object geometry and…
Continual learning (CL) has emerged as a pivotal paradigm to enable large language models (LLMs) to dynamically adapt to evolving knowledge and sequential tasks while mitigating catastrophic forgetting-a critical limitation of the static…
Scaling laws play a central role in the success of Large Language Models (LLMs), enabling the prediction of model performance relative to compute budgets prior to training. While Transformers have been the dominant architecture, recent…
Multimodal Large Language Models (MLLMs) have demonstrated strong performance across a wide range of vision-language tasks, yet their internal processing dynamics remain underexplored. In this work, we introduce a probing framework to…
Continually pre-training a large language model on heterogeneous text domains, without replay or task labels, has remained an unsolved architectural problem at LLM scale. Existing methods rely on replay buffers, task identifiers,…
Self-supervised speech representation learning (SSL) has shown to be effective in various downstream tasks, but SSL models are usually large and slow. Model compression techniques such as pruning aim to reduce the model size and computation…
Vision-Language Models (VLMs) have rapidly advanced by leveraging powerful pre-trained Large Language Models (LLMs) as core reasoning backbones. As new and more capable LLMs emerge with improved reasoning, instruction-following, and…
Recent development in Large Language Models (LLMs) and Multi-modal Large Language Models (MLLMs) have leverage Attention-based Transformer architectures and achieved superior performance and generalization capabilities. They have since…
This paper reveals that large language models (LLMs), despite being trained solely on textual data, are surprisingly strong encoders for purely visual tasks in the absence of language. Even more intriguingly, this can be achieved by a…
Finetuning language models (LMs) is crucial for adapting the models to downstream data and tasks. However, full finetuning is usually costly. Existing work, such as parameter-efficient finetuning (PEFT), often focuses on \textit{how to…
In contrast to RNNs, which compress their history into a single hidden state, Transformers can attend to all past tokens directly. However, standard Transformers rely solely on the hidden state from the previous layer to represent the…
Large Language Models (LLMs) based on autoregressive, decoder-only Transformers generate text one token at a time, where a token represents a discrete unit of text. As each newly produced token is appended to the partial output sequence,…
Trans-dimensional random field language models (TRF LMs) where sentences are modeled as a collection of random fields, have shown close performance with LSTM LMs in speech recognition and are computationally more efficient in inference.…
Fine-tuning large language models (LLMs) for downstream tasks is an essential stage of modern AI deployment. Reinforcement learning (RL) has emerged as the dominant fine-tuning paradigm, underpinning many state-of-the-art LLMs. In contrast,…
For many fundamental physics applications, transformers, as the state of the art in learning complex correlations, benefit from pretraining on quasi-out-of-domain data. The obvious question is whether we can exploit Large Language Models,…
Low-resource languages (LRLs) face significant challenges in natural language processing (NLP) due to limited data. While current state-of-the-art large language models (LLMs) still struggle with LRLs, smaller multilingual models (mLMs)…
In this paper, we move towards combining large parametric models with non-parametric prototypical networks. We propose prototypical fine-tuning, a novel prototypical framework for fine-tuning pretrained language models (LM), which…