SomaStacks

company

https://somastacks.com/

AI & ML interests

None defined yet.

Team members 11
private

authored 5 papers 9 months ago

AI Alignment: A Comprehensive Survey

Paper • 2310.19852 • Published Oct 30, 2023

Aligner: Achieving Efficient Alignment through Weak-to-Strong Correction

Paper • 2402.02416 • Published Feb 4, 2024 • 4

Reward Generalization in RLHF: A Topological Perspective

Paper • 2402.10184 • Published Feb 15, 2024

Kimi k1.5: Scaling Reinforcement Learning with LLMs

Paper • 2501.12599 • Published Jan 22, 2025 • 132

DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models

Paper • 2512.02556 • Published Dec 2, 2025 • 273

yjze

authored a paper 10 months ago

TWIST2: Scalable, Portable, and Holistic Humanoid Data Collection System

Paper • 2511.02832 • Published Nov 4, 2025 • 10

yjze

authored a paper over 1 year ago

BEHAVIOR Robot Suite: Streamlining Real-World Whole-Body Manipulation for Everyday Household Activities

Paper • 2503.05652 • Published Mar 7, 2025 • 11

yjze

authored a paper almost 2 years ago

Generalizable Humanoid Manipulation with Improved 3D Diffusion Policies

Paper • 2410.10803 • Published Oct 14, 2024 • 7

yjze

authored 4 papers over 2 years ago

On Pre-Training for Visuo-Motor Control: Revisiting a Learning-from-Scratch Baseline

Paper • 2212.05749 • Published Dec 12, 2022 • 2

Visual Reinforcement Learning with Self-Supervised 3D Representations

Paper • 2210.07241 • Published Oct 13, 2022 • 1

DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization

Paper • 2310.19668 • Published Oct 30, 2023 • 3

3D Diffusion Policy

Paper • 2403.03954 • Published Mar 6, 2024 • 14

yjze

authored a paper almost 3 years ago

Unleashing the Power of Pre-trained Language Models for Offline Reinforcement Learning

Paper • 2310.20587 • Published Oct 31, 2023 • 18

authored 3 papers almost 3 years ago

BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset

Paper • 2307.04657 • Published Jul 10, 2023 • 6

Safe RLHF: Safe Reinforcement Learning from Human Feedback

Paper • 2310.12773 • Published Oct 19, 2023 • 28

Baichuan 2: Open Large-scale Language Models

Paper • 2309.10305 • Published Sep 19, 2023 • 22

yjze

authored a paper about 3 years ago

GNFactor: Multi-Task Real Robot Learning with Generalizable Neural Feature Fields

Paper • 2308.16891 • Published Aug 31, 2023 • 10