Unverified50% confidenceBenchmarkExact time
On the D3IL benchmark, the trained Quantum-JEPA model is able to generate multiple obstacle-avoidance routes from the same starting point, without observing motion information.
1
Sources
50%
Confidence
Long-term
Relevance
10/21/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedQuantum-JEPA uses a conditional quantum Born prior to learn the distribution of future representations, introducing a trainable quantum component into JEPA.68% similarUnverifiedThe proposed approach consists of three steps: training a JEPA model in a physics simulation environment, allowing physical structure to emerge from JEPA representations, and feeding the frozen physical representations as conditioning signals into an LLM.67% similarUnverifiedThe core design of Quantum-JEPA is to use a quantum circuit to generate binary latent actions, where the bit strings of the measurement outputs are interpreted as latent actions, which are then mapped by a shared predictor to different future representations.66% similarUnverifiedQuantum-JEPA adopts a sampled energy objective to optimize the quantum prior, so that the generated latent actions can both produce valid future predictions and cover multiple possible continuations.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1079377API
curl https://kongchang.com/api/v1/knowledge/claims/1079377MCP
get_claim(id=1079377)