Virtual Head Attention

cs.CL, cs.AI

Submitted: 2026-10-13

Updated: 2026-10-13

Comments: Published as a main conference paper at NeurIPS 2026

Code: https://github.com/PaddlePaddle/VHA

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• Program Synthesis with Large Language Models
• Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
• Training Verifiers to Solve Math Word Problems
• Multi-Head Attention: Collaborate Instead of Concatenate
• Interleaved Head Attention
• The Llama 3 Herd of Models
• Measuring Massive Multitask Language Understanding
• Measuring Mathematical Problem Solving With the MATH Dataset
• DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
• Decoupled Weight Decay Regularization
• Low-Rank Key Value Attention
• Explicit Multi-head Attention for Inter-head Interaction in Large Language Models
• GPQA: A Graduate-Level Google-Proof Q&A Benchmark
• INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge
• Fast Transformer Decoding: One Write-Head is All You Need
• Talking-Heads Attention
• GTA: Grouped-head latenT Attention
• Llama 2: Open Foundation and Fine-Tuned Chat Models
• Qwen2 Technical Report
• Tensor Product Attention Is All You Need

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering