3 citations · 12 across the 16 of their papers we have counts for
16 papers
Scaling Near-Optimal SFT-RL Annotation Budget Allocation from Small to Large LLMs
Jingtan Wang, Arun Verma, Xiaoqiang Lin +4
How to divide a fixed annotation budget between supervised fine-tuning (SFT) and reinforcement learning (RL) during LLM post-training remains an open problem. Existing work charact…
MCP-Universe RL: A Framework for Training MCP Tool-Use Agents via Reinforcement Learning
Ziyang Luo, Yan Yang, Xiangru Jian +5
Reinforcement learning (RL) has become an effective way to improve the tool-use ability of large language models (LLMs), but most existing RL frameworks stop at the policy update.…
W&D:Scaling Parallel Tool Calling for Efficient Deep Research Agents
Xiaoqiang Lin, Jun Hao Liew, Silvio Savarese +1
Deep research agents have emerged as powerful tools for automating complex intellectual tasks through multi-step reasoning and web-based information seeking. While recent efforts h…
REFRAG: Rethinking RAG based Decoding
Xiaoqiang Lin, Aritra Ghosh, Bryan Kian Hsiang Low +2
Large Language Models (LLMs) have demonstrated remarkable capabilities in leveraging extensive external knowledge to enhance responses in multi-turn and agentic applications, such…
Uncovering Scaling Laws for Large Language Models via Inverse Problems
Arun Verma, Zhaoxuan Wu, Zijian Zhou +15
Large Language Models (LLMs) are large-scale pretrained models that have achieved remarkable success across diverse domains. These successes have been driven by unprecedented compl…
ActiveDPO: Active Direct Preference Optimization for Sample-Efficient Alignment
Xiaoqiang Lin, Arun Verma, Zhongxiang Dai +3
The recent success in using human preferences to align large language models (LLMs) has significantly improved their performance in various downstream tasks, such as question answe…
Active Human Feedback Collection via Neural Contextual Dueling Bandits
Arun Verma, Xiaoqiang Lin, Zhongxiang Dai +2
Collecting human preference feedback is often expensive, leading recent works to develop principled algorithms to select them more efficiently. However, these works assume that the…
Neural Dueling Bandits: Preference-Based Optimization with Human Feedback
Arun Verma, Zhongxiang Dai, Xiaoqiang Lin +2
Contextual dueling bandit is used to model the bandit problems, where a learner's goal is to find the best arm for a given context using observed noisy human preference feedback ov…
Data-Centric AI in the Age of Large Language Models
Xinyi Xu, Zhaoxuan Wu, Rui Qiao +16
This position paper proposes a data-centric viewpoint of AI research, focusing on large language models (LLMs). We start by making the key observation that data is instrumental in…
Helpful or Harmful Data? Fine-tuning-free Shapley Attribution for Explaining Language Model Predictions
Jingtan Wang, Xiaoqiang Lin, Rui Qiao +2
The increasing complexity of foundational models underscores the necessity for explainability, particularly for fine-tuning, the most widely used training method for adapting model…
Prompt Optimization with Human Feedback
Xiaoqiang Lin, Zhongxiang Dai, Arun Verma +3
Large language models (LLMs) have demonstrated remarkable performances in various tasks. However, the performance of LLMs heavily depends on the input prompt, which has given rise…
Prompt Optimization with EASE? Efficient Ordering-aware Automated Selection of Exemplars
Zhaoxuan Wu, Xiaoqiang Lin, Zhongxiang Dai +5
Large language models (LLMs) have shown impressive capabilities in real-world applications. The capability of in-context learning (ICL) allows us to adapt an LLM to downstream task…
DETAIL: Task DEmonsTration Attribution for Interpretable In-context Learning
Zijian Zhou, Xiaoqiang Lin, Xinyi Xu +3
In-context learning (ICL) allows transformer-based language models that are pre-trained on general text to quickly learn a specific task with a few "task demonstrations" without up…
Use Your INSTINCT: INSTruction optimization for LLMs usIng Neural bandits Coupled with Transformers
Xiaoqiang Lin, Zhaoxuan Wu, Zhongxiang Dai +5
Large language models (LLMs) have shown remarkable instruction-following capabilities and achieved impressive performances in various applications. However, the performances of LLM…
Federated Zeroth-Order Optimization using Trajectory-Informed Surrogate Gradients
Yao Shu, Xiaoqiang Lin, Zhongxiang Dai +1
Federated optimization, an emerging paradigm which finds wide real-world applications such as federated learning, enables multiple clients (e.g., edge devices) to collaboratively o…
Fair yet Asymptotically Equal Collaborative Learning
Xiaoqiang Lin, Xinyi Xu, See-Kiong Ng +2
In collaborative learning with streaming data, nodes (e.g., organizations) jointly and continuously learn a machine learning (ML) model by sharing the latest model updates computed…