← Back to People
Jiawei Zhao is a research scientist at Meta FAIR.
3
Mentions
3
Articles
2
Outlets
Aug 2025 — Jan 2026
Coverage
Associated Topics
Companies Covered
Coverage Patterns
How media typically covers Jiawei Zhao
Article Types
- research2
- announcement1
Media Angles
- technical3
Narrative Framing
- breakthrough3
Appears In
Associated AI Models
Qwen3-8B2Qwen 31GPT-OSS1
Writes About
Appears Alongside
Articles
Most recent firstArticles Written
Jiawei Zhao as author
Meta Introduces Deepconf, A Parallel Thinking Method That Improves Reasoning Efficiency With Only ~50 Lines Of Code
jiaweizzhao.github.ioannouncementpositiveAug 25, 2025
Meta's DeepConf method improves LLM reasoning to 99.9% accuracy on AIME 2025 while reducing generated tokens by 84.7%, requiring only ~50 lines of code with no model retraining.
“Co-author of the DeepConf research paper on parallel thinking methods for LLM reasoning”
LLMsAI ResearchReinforcement LearningFoundation Models
Parallel Thinking with Confidence
jiaweizzhao.github.ioresearchpositiveAug 25, 2025
DeepConf, a parallel thinking method using model-internal confidence signals, achieves 99.9% accuracy on AIME 2025 while reducing generated tokens by 84.7% compared to standard thinking approaches without requiring additional training.
“Co-author of the Deep Think with Confidence research paper”
LLMsAI ResearchReinforcement LearningFoundation Models
Also Mentioned In
Referenced in coverage
Deep Think with Confidence
arXivresearchpositiveJan 12, 2026
DeepConf, a test-time method leveraging model-internal confidence signals, improves LLM reasoning efficiency and achieves up to 99.9% accuracy on AIME 2025 while reducing generated tokens by 84.7%.
“Co-authored DeepThink with Confidence (DeepConf) paper on reducing LLM reasoning overhead.”
LLMsAI Inference OptimizationReasoning TasksTest-Time Scaling