相关论文: Learning Less Is More: Premature Upper-Layer Atten…

Large language models store biomedical facts with uneven strength after pretraining: some facts are present in the weights but are not reliably accessible under deterministic decoding (latent knowledge), while others are scarcely…

Although it is known that transformer language models (LMs) pass features from early layers to later layers, it is not well understood how this information is represented and routed by the model. We analyze a mechanism used in two LMs to…

Despite the huge progress in myriad generation tasks, pretrained language models (LMs) such as GPT2 still tend to generate repetitive texts with maximization-based decoding algorithms for open-ended generation. We attribute their…

Looped Transformers (LT) have emerged as a powerful architecture by iterating their layers multiple times before decoding the final token. However, pairing them with full attention retains quadratic complexity, making them computationally…

The Transformer architecture has significantly advanced deep learning, particularly in natural language processing, by effectively managing long-range dependencies. However, as the demand for understanding complex relationships grows,…

Transformers face quadratic complexity and memory issues with long sequences, prompting the adoption of linear attention mechanisms using fixed-size hidden states. However, linear models often suffer from limited recall performance, leading…

The Transformer is widely used in natural language processing tasks. To train a Transformer however, one usually needs a carefully designed learning rate warm-up stage, which is shown to be crucial to the final performance but will slow…

Machine unlearning in foundation models (e.g., language and vision transformers) is essential for privacy and safety; however, existing approaches are unstable and unreliable. A widely used strategy, the gradient difference method, applies…

Recently, Transformer-based language models have demonstrated remarkable performance across many NLP domains. However, the unsupervised pre-training step of these models suffers from unbearable overall computational expenses. Current…

The computational burden of attention in long-context language models has motivated two largely independent lines of work: sparse attention mechanisms that reduce complexity by attending to selected tokens, and gated attention variants that…

LLM decoding is bottlenecked for large batches and long contexts by loading the key-value (KV) cache from high-bandwidth memory, which inflates per-token latency, while the sequential nature of decoding limits parallelism. We analyze the…

The transformer is the most popular neural architecture for language modeling. The cornerstone of the transformer is its global attention mechanism, which lets the model aggregate information from all preceding tokens before generating the…

The capacity of neural networks like the widely adopted transformer is known to be very high. Evidence is emerging that they learn successfully due to inductive bias in the training routine, typically a variant of gradient descent (GD). To…

Large language models (LLMs) based on generative pre-trained Transformer have achieved remarkable performance on knowledge graph question-answering (KGQA) tasks. However, LLMs often produce ungrounded subgraph planning or reasoning results…

Large Language Models (LLMs) face significant computational bottlenecks during inference due to the quadratic complexity of self-attention mechanisms, particularly as context lengths increase. We introduce SpecAttn, a novel training-free…

Large language model (LLM) inference is increasingly bottlenecked by the Key-Value (KV) cache, yet the fine-grained structure of attention-head activations remains poorly understood. We show that pretrained Transformers exhibit a pervasive…

This work examines whether decoder-only Transformers such as LLaMA, which were originally designed for large language models (LLMs), can be adapted to the computer vision field. We first "LLaMAfy" a standard ViT step-by-step to align with…

Transformer attention computes a single softmax-weighted average over values -- a one-pass estimate that cannot correct its own errors. We introduce \emph{gradient-boosted attention}, which applies the principle of gradient boosting…

While the Self-Attention mechanism in the Transformer model has proven to be effective in many domains, we observe that it is less effective in more diverse settings (e.g. multimodality) due to the varying granularity of each token and the…

Transformer-based pretrained large language models (PLM) such as BERT and GPT have achieved remarkable success in NLP tasks. However, PLMs are prone to encoding stereotypical biases. Although a burgeoning literature has emerged on…