Unverified50% confidenceFactExact time
Research teams from Perplexity and NVIDIA jointly proposed a post-training method called JOLT, which lets the same model play both the teacher and student roles and trains it with joint reinforcement learning.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/22/2026
First Seen
Valid until: 1/20/2027
Sources
Related Entities
Related Claims
UnverifiedPerplexity has invested noticeably in self-developed reasoning models in recent years, while NVIDIA has continued to build out its training infrastructure and model research.69% similarUnverifiedOmniVerifier-C1 adopts a decoupled reinforcement learning training strategy, splitting the optimization objective into two parts: sub-question-level binary judgment and global alignment scoring.63% similarUnverifiedAchieving a significant improvement in programming capabilities through post-training on the same base model provides a new model iteration approach for teams with limited computing resources.63% similarUnverifiedIn the reinforcement learning phase, Motif follows the general RL strategy from the Nemotron Ultra technical report: training multiple teacher models, then distilling all teachers using MOPD (Multi-Objective Policy Distillation).62% similarUnverifiedThe research team introduced Generalized Teacher Forcing (GTF) to stabilize DEER, making its iterative process controllable and convergent again.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1084756API
curl https://kongchang.com/api/v1/knowledge/claims/1084756MCP
get_claim(id=1084756)