-
Native Parallel Reasoner: Reasoning in Parallelism via Self-Distilled Reinforcement Learning
Paper • 2512.07461 • Published • 78 -
RuleReasoner: Reinforced Rule-based Reasoning via Domain-aware Dynamic Sampling
Paper • 2506.08672 • Published • 30 -
ReflectEvo: Improving Meta Introspection of Small LLMs by Learning Self-Reflection
Paper • 2505.16475 • Published • 3
Yang
jacklanda
AI & ML interests
Reasoning, Mech Interp, Semantics
Recent Activity
authored
a paper
about 8 hours ago
LM-Lexicon: Improving Definition Modeling via Harmonizing Semantic Experts
commented on
a paper
about 9 hours ago
LM-Lexicon: Improving Definition Modeling via Harmonizing Semantic Experts
upvoted
a
paper
about 9 hours ago
LM-Lexicon: Improving Definition Modeling via Harmonizing Semantic Experts
Organizations
None yet
-
Native Parallel Reasoner: Reasoning in Parallelism via Self-Distilled Reinforcement Learning
Paper • 2512.07461 • Published • 78 -
RuleReasoner: Reinforced Rule-based Reasoning via Domain-aware Dynamic Sampling
Paper • 2506.08672 • Published • 30 -
ReflectEvo: Improving Meta Introspection of Small LLMs by Learning Self-Reflection
Paper • 2505.16475 • Published • 3
