Unverified50% confidenceFactExact time
LARC (Latent Reasoning in Continuous space) is a continuous-space latent reasoning framework that mitigates the token-level bottleneck by performing reasoning over high-dimensional hidden states.
1
Sources
50%
Confidence
Long-term
Relevance
11/2/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedLARC is still at the research stage, and its ideas have general reference value for reasoning enhancement of unified multimodal models.63% similarUnverifiedLatent space reasoning allows the model to complete thinking in a continuous vector space composed of hidden states, only decoding the result into text at the final stage.61% similarUnverifiedCOCONUT (Chain of Continuous Thought) propagates the reasoning chain directly in continuous latent space, feeding the hidden state produced by the previous reasoning step directly as input to the next, bypassing the encode-decode loop from hidden state to token and back to hidden state.60% similarUnverifiedStandard vector RAG is built on the distributional semantics hypothesis: texts with similar meanings are closer together in embedding space.60% similarUnverifiedSpatial-dynamic fusion (SDF) extracts spatial and temporal priors from a dynamic geometry encoder and, under semantic guidance, selectively integrates these priors into the intermediate-layer representations of the VLM.59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1125577API
curl https://kongchang.com/api/v1/knowledge/claims/1125577MCP
get_claim(id=1125577)