Runxi Cheng

4 papers · 2025–2026 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (15)

Venues

ICML (2) ACL (1) EMNLP (1)

Top co-authors

Chun Yuan (2) Feng Xiong (2) Xiangxiang Chu (1) Ying Zhou (1) Xiaotian Ye (1) Zisheng Zhou (1) Zhumin Chen (1) Yuchen Guan (1) Mengqi Zhang (1) Yong Wang (1)

Research topics

Artificial Intelligence (4) Deep Learning (4) Core AI (4) Machine Learning (3) Optimization & Theory · Machine Learning (2) Optimization & Theory · Deep Learning (2) Natural Language Processing (1) Applications (1) Learning Types (1) Models (1) Resources & Methods (1) Techniques (1)

Keywords

sampling strategy (1) mathematical reasoning (1) test-time adaptation (1) model merging (1) weight perturbation (1) spectral analysis (1) reward model (1) ranking loss (1) task vector (1) sampling budget (1) linear subspace (1) difficulty estimation (1) large language model (1) self-taught reasoning (1) teacher logit (1) gradient scaling (1) logits distillation (1) boundary problem (1) budget reallocation (1) boundary-level problem (1)

Papers

Spectral Characterization and Mitigation of Sequential Knowledge Editing Collapse ACL 2026 Enhancing Logits Distillation with Plug&Play Kendall’s $τ$ Ranking Loss ICML 2025 HS-STaR: Hierarchical Sampling for Self-Taught Reasoners via Difficulty Estimation and Budget Reallocation EMNLP 2025 Whoever Started the interference Should End It: Guiding Data-Free Model Merging via Task Vectors ICML 2025