Jet-Long: Efficient Long-Context Extension with Dynamic Bifocal RoPE

arXiv:2607.07740 · cs.LG, cs.AI · Submitted 2026-07-08 · Read on arXiv

cs.LG, cs.AI

Submitted: 2026-07-08

Updated: 2026-09-29

Code: https://github.com/jet-ai-projects/jet-long

Terminology

• Accuracy — 1× in this paper · explained in 1 episode
• Agentic Workflows — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Perplexity — 1× in this paper · explained in 3 episodes
• RAG — 1× in this paper · explained in 3 episodes
• Trace — 1× in this paper · explained in 2 episodes

Sources

• gpt-oss-120b & gpt-oss-20b Model Card
• Training-Free Long-Context Scaling of Large Language Models
• Why Does the Effective Context Length of LLMs Fall Short?
• NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model
• Longformer: The Long-Document Transformer
• Extending Context Window of Large Language Models via Positional Interpolation
• Rethinking Attention with Performers
• SELF: Self-Extend the Context Length With Logistic Growth Function
• FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning
• LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens
• Data Engineering for Scaling Language Models to 128K Context
• Retrieval-Augmented Generation for Large Language Models: A Survey
• Mamba: Linear-Time Sequence Modeling with Selective State Spaces
• Jet-Nemotron: Efficient Language Model with Post Neural Architecture Search
• RULER: What's the Real Context Size of Your Long-Context Language Models?
• SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
• LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning
• A Training-Free Length Extrapolation Approach for LLMs: Greedy Attention Logit Interpolation (GALI)
• DeepSeek-V3 Technical Report
• DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks