Ji, Ziwei
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
2025/07/07 by Gheorghe Comanici, Comanici, Gheorghe, Eric Bieber +6844 · 8 voices · 1358 citations
#cs.CL #cs.AI
- Think before you speak: Training Language Models With Pause Tokens
2023/10/03 by Sachin Goyal, Ziwei Ji, Goyal, Sachin +9 · 3 voices · 53 citations
Computer Science · #Topic Modeling #Natural Language Processing Techniques #Speech and dialogue systems
- A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity
2023/02/08 by Yejin Bang, Bang, Yejin, Samuel Cahyawijaya +23 · 2 voices · 43 citations
Computer Science · #Natural Language Processing Techniques #Text Readability and Simplification #Topic Modeling #cs.AI #cs.CL
- Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation
2025/07/14 by Sangmin Bae, Bae, Sangmin, Yujin Kim +19 · 6 voices · 29 citations
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #cs.CL #cs.LG
- Gradient descent aligns the layers of deep linear networks
2018/10/04 by Ziwei Ji, Matus Telgarsky, Ji, Ziwei +1 · 16 citations
Engineering · Computer Science · Medicine · #Sparse and Compressive Sensing Techniques #Stochastic Gradient Optimization Techniques #Advanced Neuroimaging Techniques and Applications
- Directional convergence and alignment in deep learning
2020/06/11 by Ziwei Ji, Ji, Ziwei, Matus Telgarsky +1 · 16 citations
Computer Science · #Stochastic Gradient Optimization Techniques #Domain Adaptation and Few-Shot Learning #Adversarial Robustness in Machine Learning
- Relaxed Recursive Transformers: Effective Parameter Sharing with Layer-wise LoRA
2024/10/28 by Sangmin Bae, Bae, Sangmin, Adam Fisch +10 · 2 voices · 10 citations
Engineering · Computer Science · #cs.CL #cs.LG
- CrossNER: Evaluating Cross-Domain Named Entity Recognition
2020/12/08 by Zihan Liu, Yan Xu, Liu, Zihan +13 · 8 citations
Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Natural Language Processing Techniques #Topic Modeling
- LLM Internal States Reveal Hallucination Risk Faced With a Query
2024/07/03 by Ziwei Ji, Ji, Ziwei, Delong Chen +11 · 1 voice · 14 citations
#cs.CL
- Negative Object Presence Evaluation (NOPE) to Measure Object Hallucination in Vision-Language Models
2023/10/09 by Lovenia, Holy, Dai, Wenliang, Cahyawijaya, Samuel +2 · 9 citations
#Computation and Language (cs.CL) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences
- HalluLens: LLM Hallucination Benchmark
2025/04/24 by Yejin Bang, Bang, Yejin, Ziwei Ji +12 · 27 citations
Psychology · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Psychedelics and Drug Studies
- Towards Mitigating Hallucination in Large Language Models via Self-Reflection
2023/10/10 by Ji, Ziwei, Yu, Tiezheng, Xu, Yan +3 · 9 citations
#Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences
- Gradient descent follows the regularization path for general losses
2020/06/19 by Ziwei Ji, Miroslav Dudı́k, Ji, Ziwei +5 · 4 citations
Computer Science · Engineering · #Advancements in Semiconductor Devices and Circuit Design #Adversarial Robustness in Machine Learning #FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Optimization and Control (math.OC) #Stochastic Gradient Optimization Techniques
- Calibrating Verbal Uncertainty as a Linear Feature to Reduce Hallucinations
2025/03/18 by Ji, Ziwei, Yu, Lei, Koishekenov, Yeskendir +6 · 13 citations
#Computation and Language (cs.CL) #FOS: Computer and information sciences
- Polylogarithmic width suffices for gradient descent to achieve arbitrarily small test error with shallow ReLU networks
2019/09/26 by Ji, Ziwei, Telgarsky, Matus · 3 citations
#FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Optimization and Control (math.OC)
- Plausible May Not Be Faithful: Probing Object Hallucination in Vision-Language Pre-training
2022/10/14 by Wenliang Dai, Dai, Wenliang, Zihan Liu +7 · 4 citations
Computer Science · Medicine · #Multimodal Machine Learning Applications #COVID-19 diagnosis using AI
- RHO (ρ): Reducing Hallucination in Open-domain Dialogues with Knowledge Grounding
2022/12/03 by Ziwei Ji, Ji, Ziwei, Zihan Liu +11 · 5 citations
Computer Science · #Topic Modeling #Text Readability and Simplification #Natural Language Processing Techniques
- Generalization bounds via distillation
2021/04/12 by Daniel Hsu, Hsu, Daniel, Ziwei Ji +5 · 3 citations
Computer Science · Engineering · #FOS: Computer and information sciences #Face and Expression Recognition #Machine Learning (cs.LG) #Sparse and Compressive Sensing Techniques #Stochastic Gradient Optimization Techniques
- Reproducibility in Optimization: Theoretical Framework and Limits
2022/02/09 by Kwangjun Ahn, Prateek Jain, Ahn, Kwangjun +9 · 3 citations
Computer Science · Engineering · Decision Sciences · #Stochastic Gradient Optimization Techniques #Sparse and Compressive Sensing Techniques #Advanced Bandit Algorithms Research
- Efficient Document Ranking with Learnable Late Interactions
2024/06/25 by Ji, Ziwei, Jain, Himanshu, Veit, Andreas +6 · 5 citations
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Information Retrieval (cs.IR) #Machine Learning (cs.LG) #Machine Learning (stat.ML)
- Early-stopped neural networks are consistent
2021/06/10 by Ziwei Ji, Justin D. Li, Ji, Ziwei +3 · 2 citations
Computer Science · #Adversarial Robustness in Machine Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and Algorithms #Stochastic Gradient Optimization Techniques
- Actor-critic is implicitly biased towards high entropy optimal policies
2021/10/21 by Yuzheng Hu, Hu, Yuzheng, Ziwei Ji +3 · 2 citations
Computer Science · Physics and Astronomy · #Adversarial Robustness in Machine Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Model Reduction and Neural Networks #Reinforcement Learning in Robotics
- NusaCrowd: Open Source Initiative for Indonesian NLP Resources
2022/12/19 by Samuel Cahyawijaya, Cahyawijaya, Samuel, Holy Lovenia +91 · 3 citations
Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Speech Recognition and Synthesis #Speech and dialogue systems
- ANAH-v2: Scaling Analytical Hallucination Annotation of Large Language Models
2024/07/05 by Gu, Yuzhe, Ji, Ziwei, Zhang, Wenwei +3 · 3 citations
#Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences
- Risk and parameter convergence of logistic regression
2018/03/20 by Ji, Ziwei, Telgarsky, Matus · 1 citation
#FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Optimization and Control (math.OC)
- Neural tangent kernels, transportation mappings, and universal approximation
2019/10/15 by Ziwei Ji, Ji, Ziwei, Matus Telgarsky +3 · 1 citation
Computer Science · Physics and Astronomy · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Model Reduction and Neural Networks #Neural Networks and Applications #Stochastic Gradient Optimization Techniques
- Planning with Reasoning using Vision Language World Model
2025/09/02 by Delong Chen, Théo Moutakanni, Chen, Delong +11 · 11 citations
Social Sciences · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Geographic Information Systems Studies
- WorldPrediction: A Benchmark for High-level World Modeling and Long-horizon Procedural Planning
2025/06/04 by Chen, Delong, Chung, Willy, Bang, Yejin +2 · 5 citations
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences
- ANAH: Analytical Annotation of Hallucinations in Large Language Models
2024/05/30 by Ji, Ziwei, Gu, Yuzhe, Zhang, Wenwei +3 · 1 citation
#Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences