ALiBi bias is the expectation of positional LSH-induced block masks, yielding spectral and max-norm approximation bounds that reduce long-context biased attention to randomized short-context unbiased attention.
Journal of machine learning research , volume=
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
representative citing papers
Theoretical analysis of continual factual knowledge acquisition shows data replay stabilizes pretrained knowledge by shifting convergence dynamics while regularization only slows forgetting, leading to the STOC method for attention-based replay selection.
Synthetic pre-pre-training on structured data improves LLM robustness to noisy pre-training, matching baseline loss with up to 49% fewer natural tokens for a 1B model.
CogVideoX generates coherent 10-second text-to-video outputs at high resolution using a 3D VAE, expert adaptive LayerNorm transformer, progressive training, and a custom data pipeline, claiming state-of-the-art results.
NV-Embed achieves first place on the MTEB leaderboard across 56 tasks by combining a latent attention layer, causal-mask removal, two-stage contrastive training, and data curation for LLM-based embedding models.
SmolLM2 is a 1.7B-parameter language model that outperforms Qwen2.5-1.5B and Llama3.2-1B after overtraining on 11 trillion tokens using custom FineMath, Stack-Edu, and SmolTalk datasets in a multi-stage pipeline.
Conversational scenario modeling from user profiles and domain knowledge, combined with intent-keyword bridging, improves proactivity, fluency, and informativeness in target-guided proactive dialogue systems.
citing papers explorer
-
Positional LSH: Binary Block Matrix Approximation for Attention with Linear Biases
ALiBi bias is the expectation of positional LSH-induced block masks, yielding spectral and max-norm approximation bounds that reduce long-context biased attention to randomized short-context unbiased attention.
-
Towards Understanding Continual Factual Knowledge Acquisition of Language Models: From Theory to Algorithm
Theoretical analysis of continual factual knowledge acquisition shows data replay stabilizes pretrained knowledge by shifting convergence dynamics while regularization only slows forgetting, leading to the STOC method for attention-based replay selection.
-
Synthetic Pre-Pre-Training Improves Language Model Robustness to Noisy Pre-Training Data
Synthetic pre-pre-training on structured data improves LLM robustness to noisy pre-training, matching baseline loss with up to 49% fewer natural tokens for a 1B model.
-
CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer
CogVideoX generates coherent 10-second text-to-video outputs at high resolution using a 3D VAE, expert adaptive LayerNorm transformer, progressive training, and a custom data pipeline, claiming state-of-the-art results.
-
NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models
NV-Embed achieves first place on the MTEB leaderboard across 56 tasks by combining a latent attention layer, causal-mask removal, two-stage contrastive training, and data curation for LLM-based embedding models.
-
SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model
SmolLM2 is a 1.7B-parameter language model that outperforms Qwen2.5-1.5B and Llama3.2-1B after overtraining on 11 trillion tokens using custom FineMath, Stack-Edu, and SmolTalk datasets in a multi-stage pipeline.
-
Enhancing Target-Guided Proactive Dialogue Systems via Conversational Scenario Modeling and Intent-Keyword Bridging
Conversational scenario modeling from user profiles and domain knowledge, combined with intent-keyword bridging, improves proactivity, fluency, and informativeness in target-guided proactive dialogue systems.