Ruobing Xie

Towards a Comprehensive Scaling Law of Mixture-of-Experts

Fast Data Mixture Optimization via Gradient Descent

LaSeR: Reinforcement Learning with Last-Token Self-Rewarding

HS-SFT: Hybrid Sparse Supervised Fine-tuning for Offline LLM KV Cache Eviction

Union-of-Experts: Experts in Mixture-of-Experts are Secretly Routers

PT$^2$-LLM: Post-Training Ternarization for Large Language Models

Proximal Supervised Fine-Tuning

CAUSAL REASONING WITH LARGE FOUNDATION MOD- ELS TO GUIDE DYNAMIC SYSTEM FORECASTING

More Expressive Attention with Negative Weights

The Climb Carves Wisdom Deeper Than the Summit: On the Importance of Reasoning Patterns

Internet of Agents: Weaving a Web of Heterogeneous Agents for Collaborative Intelligence

Advancing LLM Reasoning Generalists with Preference Trees

Flexible Realignment of Language Models

Autonomy-of-Experts Models

Scaling Laws for Floating–Point Quantization Training