No article text was recorded for this version.
cross-scale attention alignment
Version 1 of 114 papers21 conceptsfrozen 2026-10-04
Papers in this version
- Blog: A Stitch in Time Saves Nine: Small VLM is a Precise Guidance for Accelerating Large VLMs
- Blog: Draft-based Approximate Inference for LLMs
- Blog: SmallKV: Small Model Assisted Compensation of KV Cache Compression for Efficient LLM Inference
- Blog: Less Is More, but Where? Dynamic Token Compression via LLM-Guided Keyframe Prior
- Blog: Speculative Prefill: Turbocharging TTFT with Lightweight and Training-Free Token Importance Estimation
- Blog: AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution
- Blog: Sparse Token Transformer with Attention Back Tracking
- Blog: SpeechPrune: Context-aware Token Pruning for Speech Information Retrieval
- Blog: Cross-Family Speculative Prefill: Training-Free Long-Context Compression with Small Draft Models
- Blog: LEANCODE: Understanding Models Better for Code Simplification of Pre-trained Large Language Models
- Blog: bert2BERT: Towards Reusable Pretrained Language Models
- Blog: IAM: Efficient Inference through Attention Mapping between Different-scale LLMs
- Blog: Enhancing Elusive Clues in Knowledge Learning by Contrasting Attention of Language Models
- Blog: Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps
History & citation
Current · Permanent link
- This direction split from Cross-Scale Attention Alignment for Efficient Inference (71% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_cross_scale_attention_alignment_ed280434,
title = {cross-scale attention alignment},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/cross-scale-attention-alignment/rdr_ed280434e51d4160a2808d900904dc69},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-22},
}This exact version (version 1, frozen text):
@misc{lacuna_cross_scale_attention_alignment_ed280434_v1,
title = {cross-scale attention alignment},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/cross-scale-attention-alignment/rdr_ed280434e51d4160a2808d900904dc69/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-22},
}