proomt

Search

Search posts, papers, and topics

All posts

Hugging Face Daily PapersElizaveta Kovtun, Matvey Konovalov, Andrey Sakhovskiy1 min readpaperadvanced

Tactile-JEPA: Topology-Aware Self-Supervised Representation Learning for Distributed Tactile Sensors

Read on arxiv.org

Summary

Tactile-JEPA is a self‑supervised pre‑training technique that leverages the irregular graph layout of distributed tactile skins to learn richer representations. Experiments show it reduces force and orientation estimation errors and improves downstream policy learning across diverse sensor types.

  • Tactile-JEPA predicts embeddings of masked taxels using a sensor connectivity graph, making the SSL objective topology‑aware.
  • Dual‑scale masking forces the encoder to capture fine‑grained contact details and the global state of the tactile surface.
  • Across three datasets, pre‑training cuts force estimation error by 6.3% and in‑hand orientation error by 20.8% versus prior SOTA.
  • Method works for both magnetic and piezoresistive skins, and for single‑sensor as well as paired‑sensor robot setups.

Robotics engineers building manipulation systems should care because better tactile encoders directly translate into more accurate force/pose estimation and more reliable policies.

8/10
roboticsrepresentation learningtactile sensingself supervised learninggraph neural networks

Related reading

  1. D-JEPA: A Decision-Aligned Latent World Model

    D-JEPA is a latent world model designed to bridge the gap between predicted outcomes and actual decision success in robotics. It learns decision-relevant relationships from executed actions, improving action selection by aligning latent space geometry with real-world results.

    Hugging Face Daily Papersarxiv.org1 minpaper

  2. JEPA-Anything: Learning Predictive Models across Different Worlds

    JEPA-Anything extends joint‑embedding predictive architectures with orthogonal predictive factorization, letting a single model learn complementary latent factors that can be recombined for prediction across disparate domains. The paper shows consistent performance gains on ten dynamics tasks, molecular simulations, and clinical event forecasting, plus experimental validation of a biologically‑de…

    Hugging Face Daily Papersarxiv.org1 minpaper

  3. Fingers as Legs: Learning Self-Supported Locomotion and Manipulation with an Anthropomorphic Hand

    The authors train an anthropomorphic robotic hand to crawl, steer, and recover from falls using its fingers for both support and manipulation, via a reinforcement‑learning reward formulation tuned to the hand's asymmetry. Sim‑to‑real experiments show faster locomotion than quadruped‑style rewards and successful untethered tasks without onboard vision.

    Hugging Face Daily Papersarxiv.org1 minpaper

  4. Breaking the Vision-Action Shortcut: Latent Interface Training for Generalizable Robotics Foundation Models

    Latent Interface Training (LIT) first learns a goal‑conditioned action prior without visual input, then adds a pose‑supervised latent interface as the only visual conditioning path. Applied to several vision‑language‑action models, LIT cuts vision‑action shortcuts and lifts LIBERO‑Plus success by 3.9–10.7 points and real‑world task success by 13.3–16.7 points under distribution shifts.

    Hugging Face Daily Papersarxiv.org1 minpaper

  5. Article: Architecting Secure and Scalable Facial Verification Systems

    A real‑world post‑mortem of a high‑volume face verification service that moved from a naïve synchronous API to an async, layered pipeline (edge validation, preprocessing, decoupled detection/verification, decision engine) to achieve 8.5k rpm, p99 < 1.8 s, 30 % cost savings, and strict privacy controls.

    InfoQinfoq.com15 min

  6. Introducing System One Models and Jev

    TypeSafe AI announced its first “System One” model, Jev, a non‑text‑generating LLM that outputs type‑safe structured decisions with calibrated probabilities. It claims 40‑200× lower latency (70‑500 ms) and 100‑500× lower cost versus frontier LLMs, no hallucinations, and parallel sampling. The post includes a side‑by‑side demo, a custom “workflow” benchmark comparing Jev to GPT‑5.6/6 and other mod…

    Hacker News front pagetypesafe.ai9 minHN1824480lobste.rs26