Related papers: Efficient Training-Free Multi-Token Prediction via…
Modern large language models (LLMs) excel at tasks that require storing and retrieving knowledge, such as factual recall and question answering. Transformers are central to this capability because they can encode information during training…
Most state-of-the-art models in natural language processing (NLP) are neural models built on top of large, pre-trained, contextual language models that generate representations of words in context and are fine-tuned for the task at hand.…
Although current semi-supervised medical segmentation methods can achieve decent performance, they are still affected by the uncertainty in unlabeled data and model predictions, and there is currently a lack of effective strategies that can…
Modern sparse language models typically achieve sparsity through Mixture-of-Experts (MoE) layers, which dynamically route tokens to dense MLP "experts." However, dynamic hard routing has a number of drawbacks, such as potentially poor…
Reinforcement learning (RL) has emerged as a key paradigm for aligning and optimizing large language models (LLMs). Standard approaches treat the LLM as the policy and apply RL directly over the full vocabulary space. However, this…
Pretrained language models (LMs) are prone to arithmetic errors. Existing work showed limited success in probing numeric values from models' representations, indicating that these errors can be attributed to the inherent unreliability of…
Text representation plays a critical role in tasks like clustering, retrieval, and other downstream applications. With the emergence of large language models (LLMs), there is increasing interest in harnessing their capabilities for this…
Large language models (LLMs) achieve strong performance across diverse tasks but suffer from high inference latency due to their autoregressive generation. Speculative Decoding (SPD) mitigates this issue by verifying candidate tokens in…
Pre-training of Large Language Models is often prohibitively expensive and inefficient at scale, requiring complex and invasive modifications in order to achieve high data throughput. In this work, we present Token-Superposition Training…
Hyperscaling of data and parameter count in LLMs is yielding diminishing improvement when weighed against training costs, underlining a growing need for more efficient finetuning and inference without sacrificing performance. This is…
Transformer has been widely used for self-supervised pre-training in Natural Language Processing (NLP) and achieved great success. However, it has not been fully explored in visual self-supervised learning. Meanwhile, previous methods only…
Consistently scaling pre-trained language models (PLMs) imposes substantial burdens on model adaptation, necessitating more efficient alternatives to conventional fine-tuning. Given the advantage of prompting in the zero-shot setting and…
Prompt Tuning is emerging as a scalable and cost-effective method to fine-tune Pretrained Language Models (PLMs), which are often referred to as Large Language Models (LLMs). This study benchmarks the performance and computational…
In this paper, we introduce a novel and simple method for obtaining high-quality text embeddings using only synthetic data and less than 1k training steps. Unlike existing methods that often depend on multi-stage intermediate pre-training…
Unsupervised text embedding methods, such as Skip-gram and Paragraph Vector, have been attracting increasing attention due to their simplicity, scalability, and effectiveness. However, comparing to sophisticated deep learning architectures…
Pre-trained transformer models shine in many natural language processing tasks and therefore are expected to bear the representation of the input sentence or text meaning. These sentence-level embeddings are also important in…
Autoregressive decoding in large language models (LLMs) requires $\mathcal{O}(n)$ sequential steps for $n$ tokens, fundamentally limiting inference throughput. Recent diffusion-based LLMs (dLLMs) enable parallel token generation through…
We introduce SEE&TREK, the first training-free prompting framework tailored to enhance the spatial understanding of Multimodal Large Language Models (MLLMS) under vision-only constraints. While prior efforts have incorporated modalities…
Generative Large Language Models (LLMs) based on the Transformer architecture have recently emerged as a dominant foundation model for a wide range of Natural Language Processing tasks. Nevertheless, their application in real-time scenarios…
While Transformer language models (LMs) are state-of-the-art for information extraction, long text introduces computational challenges requiring suboptimal preprocessing steps or alternative model architectures. Sparse attention LMs can…