Piji Li

R4: Nested Reasoning-Retrieval for Reward Modeling in Role-Playing Agents

Investigating Advanced Reasoning of Large Language Models via Black-Box Interaction

LSRS: Latent Scale Rejection Sampling for Visual Autoregressive Modeling

Group-Wise Optimization for Self-Extensible Codebooks in Vector Quantized Models

SaraCoder: Orchestrating Semantic and Structural Cues for Resource-Optimized Repository-Level Code Completion

Brain-Inspired fMRI-to-Text Decoding via Incremental and Wrap-Up Language Modeling

Language Reconstruction with Brain Predictive Coding from fMRI Data

Vector Segmented and Recombined Adaptation for Scalable and Efficient Model Tuning