arXiv 2610.31574 · cs.LG · 2026-10-22
Rethinking Sequence Compression with Test-time Regression
Sihan Yang, Jie Huang, Hanxuan Li, Yifan Guo, Weigao Sun, Yiran Zhong, Weiyang Liu
CUHK SphereLab
In latest · #323 Added on 2026-10-26
One-line takeaway
TTR-Compressor treats sequence compression as test-time regression, using closed-form fitted coefficients as the compressed representation, and serves as the compressor for block-wise sparse attention and the visual token merger in multimodal LLMs.
TTR-Compressor 用测试时回归做序列压缩：把输入 token 视为一个回归问题，以闭式求出的系数作为压缩表示，可用于块稀疏注意力和多模态大模型的视觉 token 合并。
Read on arXiv PDF Hugging Face discussion Code Project page
Topics & disciplines
More on Efficient training & inference
- The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation ▲511
- Scaling Properties of Same-Family On-Policy Distillation ▲327
- Beyond Domain-Routed Supervision: Cross-Teacher Guarding for Multi-Teacher On-Policy Distillation ▲250
- On-Policy or Off-Policy Learning? A Systematic Study of Distillation Dynamics ▲205
- Beyond Teacher Assignment: Domain-Normalized Multi-Teacher On-Policy Distillation ▲181
More on LLMs
- Jeva: System One Models from First Principles 2026-10-13 · ▲371
- Post-Training Leaves Behavioral Shadows on Unrelated Decisions 2026-09-24 · ▲273
- WeVisOne-VL: Unified Visual Perception from Objects to Pixels 2026-10-22 · ▲247
- Thinking Inertia: LLMs Keep Thinking When Told Not To 2026-10-08 · ▲241
- OmniEdu: Open Foundation Models for Learning and Teaching 2026-09-19 · ▲240
About this data
Metadata from the arXiv API (verified); upvotes from Hugging Face Daily Papers; citations from Semantic Scholar. Last refreshed 2026-10-26.
The takeaway is written by AIMap from the abstract; the abstract itself is not reproduced — read the original.