Robbyant 开源触觉模型 LingBot-Touch，采用 Apache 2.0 协议
做机器人或具身智能的可以关注，Robbyant 把触觉编码这条链路开源了，Apache 20 随便商用。技术上选 JEPA 而不是 MAE/VAE 的原因讲得很清楚，稀疏触觉数据的训练细节直接能抄作业。
Robbyant 发布开源触觉模型 LingBot-Touch，采用 Apache 2.0 协议，把机器人指尖传感器的原始读数转换成控制软件可用的信号，解决摄像头无法感知抓握力度和打滑的问题。模型包含三个同规模编码器，每个 5.46M 参数，用同一批触觉数据训练。
训练 4,000 小时后，JEPA 版本在触觉到视频检索任务上取得 49.3% top-5 成绩，而 MAE 版本在 9% 以下，VAE 则跌到 3.1%。原因在于触觉数据高度稀疏且信噪比低：指尖只按压少数位置，大部分帧接近零值，重建式方法被迫复制无法预测的零和噪声，而 JEPA 只需在潜空间预测表征，可以跳过这些部分。掩码比例也从 40% 在前 300 步逐步升到 80%，目标由 EMA 编码器在四个深度产生，做法沿用 V-JEPA 2.1。
多源数据实验显示，固定目标传感器自身数据、只加入其他模态后，八个传感器-任务对中的七个获得提升，说明异构传感器数据能直接反哺单个传感器。
Looks like a brilliant open source release for robotics.
A great problem of robotics is that a camera can’t tell a robot how hard it’s squeezing or whether a grip is slipping, but a fingertip sensor can.
Robbyant released LingBot-Touch, an open-source model (Apache 2.0) that gives robots a sense of touch by turning fingertip sensor readings into signals their control software can use.
Robbyant trained three same-size encoders (5.46M parameters each) on the same touch data for LingBot-Touch. At 4,000 hours, the JEPA version, which predicts the masked parts in latent space, got 49.3% top-5 on tactile→video retrieval. MAE stayed under 9%. The VAE got 3.1%, worse than it did at 1,000 hours.
I think the reason is the data itself. A finger only presses a few spots, so most of every frame is close to zero, and the readings that aren't zero are noisy. Redrawing that means copying zeros and noise nobody can predict, and a JEPA only predicts the representation, so it can leave both out. The paper names the sparsity and the low signal-to-noise ratio as the reasons they went with JEPA.
The sparsity shaped training too. With 80% of taxels masked from step one, a lot of clips had no contact left to see and the gradients blew up, so they ramp the mask from 40% to 80% over the first 300 steps. Targets come from an EMA encoder at four depths, following V-JEPA 2.1.
To isolate the effect of multi-source data, they hold each sensor's own data fixed and add only the other modalities. With the target sensor's data unchanged, the multi-source model improves on seven of the eight sensor-task pairs, indicating that data from heterogeneous sensors directly benefits each individual sensor.
本条情报归属 AITOP「模型」核心栏目，重点聚焦中国 AI 产业与国产大模型生态。在跨区域产业观察坐标中，该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」「中美大模型技术代差与商业化对照」研究主线，反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括：LingBot-Touch、Robbyant、JEPA、机器人，读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。
信源核验说明：本文原始线索采编自「rohanpaul_ai」（@rohanpaul_ai），经 AITOP 多维评分管线结构化提炼。
