Peiwen Yuan

Diagnosing and Mitigating Systemic Reward Bias in Self-Rewarding RL

PatternKV: Flattening KV Representation Expands Quantization Headroom

Every Rollout Counts: Optimal Resource Allocation for Efficient Test-Time Scaling

Silencer: From Discovery to Mitigation of Self-Bias in LLM-as-Benchmark-Generator

Mind the Quote: Enabling Quotation-Aware Dialogue in LLMs via Plug-and-Play Modules

UniCBE: An Uniformity-driven Comparing Based Evaluation Framework with Unified Multi-Objective Optimization

Stitch and Tell: A Structured Data Augmentation Method for Spatial Understanding

InsBank: Evolving Instruction Subset for Ongoing Alignment

Beyond One-Size-Fits-All: Tailored Benchmarks for Efficient Model Evaluation