7 papers
ELMP: Efficient Learning for Motion Planning via Analytical Policy Gradients
Yixiao Li, Tifanny Portela, Jordis Herrmann +2
Neural Motion Planners (NMPs) enable fast reactive motion generation, but adapting them to new environments typically requires recollecting large expert datasets, which is computat…
Controllable and Verifiable Tool-Use Data Synthesis for Agentic Reinforcement Learning
Siyuan Xu, Shiyang Li, Xin Liu +9
Existing synthetic tool-use corpora are primarily designed for offline supervised fine-tuning, yet reinforcement learning (RL) requires executable environments that support reward-…
Co-Diffusion: An Affinity-Aware Two-Stage Latent Diffusion Framework for Generalizable Drug-Target Affinity Prediction
Yining Qian, Pengjie Wang, Yixiao Li +4
Predicting drug-target affinity is fundamental to virtual screening and lead optimization. However, existing deep models often suffer from representation collapse in stringent cold…
NoWag: A Unified Framework for Shape Preserving Compression of Large Language Models
Lawrence Liu, Inesh Chakrabarti, Yixiao Li +3
Large language models (LLMs) exhibit remarkable performance across various natural language processing tasks but suffer from immense computational and memory demands, limiting thei…
EBGAN-MDN: An Energy-Based Adversarial Framework for Multi-Modal Behavior Cloning
Yixiao Li, Julia Barth, Thomas Kiefer +1
Multi-modal behavior cloning faces significant challenges due to mode averaging and mode collapse, where traditional models fail to capture diverse input-output mappings. This prob…
Finding Fantastic Experts in MoEs: A Unified Study for Expert Dropping Strategies and Observations
Ajay Jaiswal, Jianyu Wang, Yixiao Li +6
Sparsely activated Mixture-of-Experts (SMoE) has shown promise in scaling up the learning capacity of neural networks. However, vanilla SMoEs have issues such as expert redundancy…