Unverified50% confidenceFactExact time
ClueFlow pushes credit assignment down from the turn granularity to the state-change granularity, enabling the model to learn which type of evidence-acquisition action leads to which type of state evolution.
1
Sources
50%
Confidence
Long-term
Relevance
10/20/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedClueFlow's attribution mechanism determines which decisions should be supervised in the SFT stage, learning only from state changes consistent with the gold standard and their original interaction contexts.71% similarUnverifiedDuring the inference stage, TRACE retrieves compact evidential prompts from the structure and feeds them to the model as additional information.70% similarVerifiedKnowledge distillation technology enables small models to extract a considerable proportion of capability from large models, undermining the validity of fixed compute thresholds as a proxy metric for capability.68% similarUnverifiedFlow matching models generate images by learning a continuous probability flow (ODE trajectory) from the noise distribution to the data distribution, and are generally more stable to train and require fewer inference steps.67% similarUnverifiedProbe guidance extracts guidance signals directly from the frozen internal states of existing models, eliminating the need for additional forward passes during inference.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1073988API
curl https://kongchang.com/api/v1/knowledge/claims/1073988MCP
get_claim(id=1073988)