Dianqi Li

6

Papers

267

Total Citations

Papers (6)

Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts

Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation

Florence-VL: Enhancing Vision-Language Models with Generative Vision Encoder and Depth-Breadth Fusion

DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agents

NeurIPS 2025arXiv

LangBridge: Interpreting Image as a Combination of Language Embeddings

ImageGen-CoT: Enhancing Text-to-Image In-context Learning with Chain-of-Thought Reasoning