Beichen Zhang

mathematical reasoning (5) tool-augmented reasoning (2) large language model (2) neural architecture search (2) representation learning (2) process reward model (2) reasoning efficiency (2) tool use (2) monte carlo estimation (1) commonsense knowledge (1) adversarial learning (1) model architecture (1) response generation (1) dialogue generation (1) reinforcement learning (1) language model (1) knowledge graph (1) chain-of-thought reasoning (1) uncertainty sampling (1) message passing (1)