Blog by Jiaming WangJiaming Wang 的博客

Blog博客

Thoughts on robotics, AI, research, and technology.关于机器人、AI、研究与技术的思考。

CROSS: Our Most Robust Mapping Yet

Mapping through darkness, glare, fast motion and sharp turns: a 59-second CROSS demo with real robot footage and benchmark comparisons.

Your Critic May Learn to Give Up Before Your Robot Learns to Pick Up

A curriculum shapes the evidence a critic learns from. Train near the frontier of competence so progress remains distinguishable from failure.

Robot Policies Need the Right Memory, Not an 8K Context Window

RoboTTT, WAM-TTT, and RoboSSM show that long context matters only when history becomes usable state—through task-relevant information, aligned meta-training, and memory matched to its timescale.

How We Won IEEE ICRA Robotics Challenges Two Years in a Row

Lessons from winning ICRA navigation and manipulation challenges: start from the problem, decompose it from first principles, and test the assumptions that matter.

OpenGEN-1: Reconstructing GEN-1 from First Principles

A first-principles reconstruction of GEN-1 as a physical foundation model trained on streams of interaction, with a proposed architecture, objective, data scale, and real-time inference system.

VLA Is Not Dead—At Least Not Yet

DreamZero and WAM split robot policy learning into future-video prediction and inverse dynamics—opening a powerful path beyond VLA, but at a steep deployment cost.

Pi 0.6: Supervised Learning in RL's Clothing

How RECAP reveals that modern RL post-training is fundamentally supervised learning guided by value-based preference signals and environment interaction.

CFGRL: The Theory Behind pi0.6*

How CFGRL reframes RL policy improvement as optimality-conditioned inference, then implements it via classifier-free guidance at sampling time.