AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

DreamSAC: Learning Hamiltonian World Models via Symmetry Exploration

Jinzhou Tang, Fan Feng, Minghao Fu, Wenjun Lin, Jing Yang, Biwei Huang, Keze Wang

CVPR 2026 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Invariance-based self-supervised learning · 1 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
add viewpoint-robustness contrastive loss (ablation)DreamSAC · Reacher (Unseen View)mean reward: 212.37 -> 321.90Improved
use G-invariant Lie Transformer Hamiltonian instead of MLP (ablation)DreamSAC · Walker (1.5x Gravity)MSE: 4.9673 -> 1.0044Improved
add SAVi object-centric encoder (ablation)DreamSAC · Avg. OODMSE: 0.9031 -> 0.7048Improved
replace random exploration with Symmetry Exploration (ablation)DreamSAC · FetchPush (H=8)image prediction MSE: 0.675 -> 0.302Improved
replace random exploration with Symmetry Exploration (ablation)DreamSAC · Cheetah (H=16)image prediction MSE: 0.1565 -> 0.4052Hurt
use Symmetry Exploration instead of RND exploration (with DreamerV3 world model swapped for Hamiltonian model)DreamSAC · FetchPush (H=8)image prediction MSE: 0.976 -> 0.302Improved
replace DreamerV3 with DreamSACDreamerV3+RND · Walker-walk (Unseen Gravity 1.5x)mean reward: 167.52 -> 499.91Improved
replace DreamerV3 with DreamSACDreamerV3+Policy · Cheetah-run (Unseen Friction 2.0x)mean reward: 118.79 -> 120.23No clear effect
replace DreamerV3+RND with DreamSACDreamerV3+RND · Hopper-hop (ID)mean reward: 389.142 -> 366.117Hurt
replace DreamerV3 with DreamSACDreamerV3+Policy · Walker-walk (ID)mean reward: 965.217 -> 996.502Improved
zero-shot (frozen) DreamSAC instead of fine-tuned (ablation)DreamSAC · Reacher-hard (Unseen View)mean reward: 321.90 -> 149.64Hurt

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