Taiqiang Wu

SWINGARENA: Adversarial Programming Arena for Long-context GitHub Issue Solving

Shadow-FT: Tuning Instruct Model via Training on Paired Base Model

LINA: Exploring Linear Autoregressive Image Generative Models with Continuous Tokens

Timber: Training-free Instruct Model Refining with Base via Effective Rank

PhyX: Does Your Model Have the "Wits" for Physical Reasoning?

LLaMA Decoder As Vision Transformer