Publications (9)
Schema-Aware Multi-Task Learning for Complex Text-to-SQL
Yangjun Wu, Han Wang
Conventional text-to-SQL parsers are not good at synthesizing complex SQL queries that involve multiple tables or columns, due to the challenges inherent in identifying the correct…
TLM: Token-Level Masking for Transformers
Yangjun Wu, Kebin Fang, Dongxiang Zhang +3
Structured dropout approaches, such as attention dropout and DropHead, have been investigated to regularize the multi-head attention mechanism in Transformers. In this paper, we pr…
Seed1.5-Thinking: Advancing Superb Reasoning Models with Reinforcement Learning
ByteDance Seed, :, Jiaze Chen +267
We introduce Seed1.5-Thinking, capable of reasoning through thinking before responding, resulting in improved performance on a wide range of benchmarks. Seed1.5-Thinking achieves 8…
Perception, Verdict, and Evolution: Hindsight-Driven Self-Refining Forensics Agent for AI-Generated Image Detection
Yangjun Wu, Keyu Yan, Yu Liu +5
The rapid advancement of generative models presents a significant challenge to existing deepfake detection methods, particularly given the widespread dissemination of highly realis…
NNQS-Transformer: an Efficient and Scalable Neural Network Quantum States Approach for Ab initio Quantum Chemistry
Yangjun Wu, Chu Guo, Yi Fan +2
Neural network quantum state (NNQS) has emerged as a promising candidate for quantum many-body problems, but its practical applications are often hindered by the high cost of sampl…
A real neural network state for quantum chemistry
Yangjun Wu, Xiansong Xu, Dario Poletti +3
The restricted Boltzmann machine (RBM) has been successfully applied to solve the many-electron Schrdinger equation. In this work we propose a single-layer fully c…
FF2: A Feature Fusion Two-Stream Framework for Punctuation Restoration
Yangjun Wu, Kebin Fang, Yao Zhao +3
To accomplish punctuation restoration, most existing methods focus on introducing extra information (e.g., part-of-speech) or addressing the class imbalance problem. Recently, larg…
A Context-Aware Feature Fusion Framework for Punctuation Restoration
Yangjun Wu, Kebin Fang, Yao Zhao
To accomplish the punctuation restoration task, most existing approaches focused on leveraging extra information (e.g., part-of-speech tags) or addressing the class imbalance probl…
Solving Schrödinger Equation with a Language Model
Honghui Shang, Chu Guo, Yangjun Wu +2
Accurately solving the Schrödinger equation for intricate systems remains a prominent challenge in physical sciences. A paradigm-shifting approach to address this challenge involv…