Probe and Skip: Self-Predictive Token Skipping for Efficient Long-Context LLM Inference
cs.CL, cs.LG
Submitted: 2026-01-19
Updated: 2026-10-13
Terminology
Sources
- Pangu Embedded: An Efficient Dual-system LLM Reasoner with Metacognition
- The Llama 3 Herd of Models
- FTP: A Fine-grained Token-wise Pruner for Large Language Models via Token Routing
- A Comprehensive Survey on Long Context Language Modeling
- ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference
- SlimInfer: Accelerating Long-Context LLM Inference via Dynamic Token Pruning
- Discovering the Gems in Early Layers: Accelerating Long-Context LLMs with 1000x Input Token Reduction
- CaliDrop: KV Cache Compression with Calibration
- Beyond the Limits: A Survey of Techniques to Extend the Context Length in Large Language Models
- HuggingFace's Transformers: State-of-the-art Natural Language Processing
- A Survey of Resource-efficient LLM and Multimodal Foundation Models
- A Survey of Large Language Models
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