Multilinguality in Hybrid Attention LLMs

arXiv:2609.35378 · cs.CL, cs.AI · Submitted 2026-09-28 · Read on arXiv

cs.CL, cs.AI

Submitted: 2026-09-28

Updated: 2026-09-28

Code: https://github.com/ibm-granite/granite-4.0-language-models

Terminology

• Distillation — 22× in this paper · explained in 2 episodes
• Hybrid Models — 20× in this paper · explained in 2 episodes
• Alignment — 19× in this paper · explained in 1 episode
• Transformer — 17× in this paper · explained in 2 episodes
• Embeddings — 9× in this paper · explained in 2 episodes
• Interpretability — 9× in this paper · explained in 15 episodes
• Benchmark — 7× in this paper · explained in 2 episodes
• Cross-lingual Transfer — 7× in this paper · explained in 2 episodes
• Perplexity — 5× in this paper · explained in 3 episodes
• Tokenization — 3× in this paper · explained in 2 episodes
• Abstraction — 2× in this paper · explained in 1 episode
• Sparsity — 2× in this paper · explained in 4 episodes
• Transformer Models — 2× in this paper · explained in 2 episodes
• AI Agents — 1× in this paper · explained in 2 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Activation Patching — 1× in this paper · explained in 2 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Attention Mechanism — 1× in this paper · explained in 2 episodes
• Benchmarking — 1× in this paper · explained in 3 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Hybrid Architectures — 1× in this paper · explained in 3 episodes
• In-Context Learning — 1× in this paper · explained in 4 episodes
• Model Merging — 1× in this paper · explained in 2 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Trace — 1× in this paper · explained in 2 episodes

Sources

• What Attention Recalls and Recurrence Controls in Hybrid Language Models
• Neural Machine Translation by Jointly Learning to Align and Translate
• Longformer: The Long-Document Transformer
• OmnilingualGAIA2: Evaluating the Multilingual Gap in Frontier AI Agents
• Global PIQA: Evaluating Commonsense Reasoning Across 100+ Languages and Cultures
• DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
• RADLADS: Rapid Attention Distillation to Linear Attention Decoders at Scale
• Jet-Nemotron: Efficient Language Model with Post Neural Architecture Search
• Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale
• Language-Specific Latent Process Hinders Cross-Lingual Performance
• Every Step Evolves: Scaling Reinforcement Learning for Trillion-Scale Thinking Model
• MiniMax-01: Scaling Foundation Models with Lightning Attention
• NVIDIA Nemotron 3: Efficient and Open Intelligence
• Olmo 3
• The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale
• FineWeb2: One Pipeline to Scale Them All -- Adapting Pre-Training Data Processing to Every Language
• Rethinking the Role of Efficient Attention in Hybrid Architectures
• Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models
• Tiny Aya: Bridging Scale and Multilingual Depth
• Kimi Linear: An Expressive, Efficient Attention Architecture

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