yelong shen

Beyond Pass@ 1: Self-Play with Variational Problem Synthesis Sustains RLVR

DenseMixer: Improving MoE Post-Training with Precise Router Gradient

Training Matryoshka Mixture-of-Experts for Elastic Inference-Time Expert Utilization

Mixture of Neuron Experts

R&D-Agent: An LLM-Agent Framework Towards Autonomous Data Science

PeRL: Permutation-Enhanced Reinforcement Learning for Interleaved Vision-Language Reasoning

Reinforcement Learning for Reasoning in Large Language Models with One Training Example

Routing Mamba: Scaling State Space Models with Mixture-of-Experts Projection

Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long Generation

Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling

SwS: Self-aware Weakness-driven Problem Synthesis in Reinforcement Learning for LLM Reasoning

SAS: Simulated Attention Score

OmniParser for Pure Vision Based GUI Agent

LoRC: Low-Rank Compression for LLMs KV Cache with a Progressive Compression Strategy

Riemannian Low-Rank Adaptation for Federated Fine-Tuning of Foundation Models