74 citations · 84 across the 8 of their papers we have counts for
8 papers
Beyond Perfect APIs: A Comprehensive Evaluation of LLM Agents Under Real-World API Complexity
Doyoung Kim, Zhiwei Ren, Jie Hao +11
We introduce WildAGTEval, a benchmark designed to evaluate large language model (LLM) agents' function-calling capabilities under realistic API complexity. Unlike prior work that a…
MMPlanner: Zero-Shot Multimodal Procedural Planning with Chain-of-Thought Object State Reasoning
Afrina Tabassum, Bin Guo, Xiyao Ma +2
Multimodal Procedural Planning (MPP) aims to generate step-by-step instructions that combine text and images, with the central challenge of preserving object-state consistency acro…
MEND: Meta dEmonstratioN Distillation for Efficient and Effective In-Context Learning
Yichuan Li, Xiyao Ma, Sixing Lu +3
Large Language models (LLMs) have demonstrated impressive in-context learning (ICL) capabilities, where a LLM makes predictions for a given test input together with a few input-out…
Asking Complex Questions with Multi-hop Answer-focused Reasoning
Xiyao Ma, Qile Zhu, Yanlin Zhou +2
Asking questions from natural language text has attracted increasing attention recently, and several schemes have been proposed with promising results by asking the right question…
Distilled One-Shot Federated Learning
Yanlin Zhou, George Pu, Xiyao Ma +2
Current federated learning algorithms take tens of communication rounds transmitting unwieldy model weights under ideal circumstances and hundreds when data is poorly distributed.…
A Batch Normalized Inference Network Keeps the KL Vanishing Away
Qile Zhu, Jianlin Su, Wei Bi +4
Variational Autoencoder (VAE) is widely used as a generative model to approximate a model's posterior on latent variables by combining the amortized variational inference and deep…
Improving Question Generation with Sentence-level Semantic Matching and Answer Position Inferring
Xiyao Ma, Qile Zhu, Yanlin Zhou +2
Taking an answer and its context as input, sequence-to-sequence models have made considerable progress on question generation. However, we observe that these approaches often gener…
Adaptive Leader-Follower Formation Control and Obstacle Avoidance via Deep Reinforcement Learning
Yanlin Zhou, Fan Lu, George Pu +5
We propose a deep reinforcement learning (DRL) methodology for the tracking, obstacle avoidance, and formation control of nonholonomic robots. By separating vision-based control in…