ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Haitao Mi

Haitao Mi

Topic trends: 32,543 papers · similarity ≥ 0.4 · year ≥ 2024 · Data sourced from Semantic Scholar

34,598 papers | Abstracts: 31,650 (91.5%) | Citations: 34,598 (100.0%) | arXiv: 26,074 (75.4%)

Built: Feb 15, 2026, 11:26 AM AMS

5

papers

71

total citations

papers (5)

Iterative Nash Policy Optimization: Aligning LLMs with General Preferences via No-Regret Learning

Trust, But Verify: A Self-Verification Approach to Reinforcement Learning with Verifiable Rewards

NEURIPS 2025arXiv

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training

NEURIPS 2025arXiv

LiteSearch: Efficient Tree Search with Dynamic Exploration Budget for Math Reasoning

UniGist: Towards General and Hardware-aligned Sequence-level Long Context Compression

NEURIPS 2025arXiv