Scaling Latent Reasoning via Looped Language Models (pretrained)
Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation (CLAP), ICASSP 2023
SCOPE: Selective Cross-modal Orchestration of Visual Perception Experts, Preprint, 2025
STRICT: Stress Test of Rendering Images Containing Text, EMNLP 2025
MAP: Low-compute Model Merging with Amortized Pareto Fronts via Quadratic Approximation, ICLR 2025
VCR: A Task for Pixel-Level Complex Reasoning in Vision Language Models via Restoring Occluded Text, ICLR 2025
Background
Research interests include Latent Reasoning, LLM/VLM Reasoning and Planning, Agent-based Model Simulator, Multi-agent Reinforcement Learning, AI for Climate Change, etc. Previously worked as a quantitative researcher in financial engineering.