AI Paper Atlas

Research map / Vision-language and multimodal / Robot action and navigation

TaCo: A Benchmark for Lossless and Lossy Codecs of Heterogeneous Tactile Data

Zhengxue Cheng, Yan Zhao, Keyu Wang, Hengdi ZHANG, Li Song

ICLR 2026 · Vision-language and multimodal › Robot action and navigation · approach: Memory and subgoal-based manipulation · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
retrain DualComp-I on tactile data and scale to 96M parameters (TaCo-LL-96M)DualComp-I · TouchandGo losslessbits/Byte: 0.948 -> 0.447Improved
retrain DualComp-I on tactile data (TaCo-LL-96M)DualComp-I · ObjectFolder losslessbits/Byte: 3.126 -> 2.709Improved
increase TaCo-LL size from 12M to 96M parameters (ablation)TaCo-LL · TouchandGo losslessbits/Byte: 0.622 -> 0.447Improved
increase TaCo-LL size from 12M to 96M parameters (ablation)TaCo-LL · ObjTac losslessbits/Byte: 0.569 -> 0.360Improved
increase TaCo-LL size from 12M to 96M parameters (ablation)TaCo-LL · TouchandGo losslessspeed (FPS): 0.67 -> 0.34Hurt
retrain LALIC on tactile data (TaCo-L)LALIC · TouchandGo lossyBD-rate (%): -51.6% -> -61.8%Improved
retrain LALIC on tactile data (TaCo-L)LALIC · ObjTac lossyBD-rate (%): 32.8% -> -27.0%Improved
compress with TaCo-L instead of uncompressed dataSVM classifier · TouchandGo material classificationtop-1 accuracy (%): 76.63 -> 75.12No clear effect
compress with TaCo-L instead of uncompressed dataSVM classifier · ObjectFolder material classificationtop-1 accuracy (%): 44.11 -> 43.08No clear effect
compress with TaCo-L instead of LALICclassification · YCB-Slide SVMtop-1 accuracy (%): 95.67 -> 98.01Improved
compress with TaCo-L instead of VTM-Intragrasping · s_lift averagesuccess rate (%): 63.1 -> 62.2No clear effect
compress with TaCo-L instead of uncompressed tactile signalsgrasping · s_lift averagesuccess rate (%): 63.8 -> 62.2Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy