Haichao Zhang
Source-listed: PhD candidate in Computer Engineering · Northeastern University
- Multimodal AI
- Language models
- Sequence models
Selected work
5- ThinkJEPA: Empowering Latent World Models with Large Vision-Language Reasoning ModelFirst author · 2026
- LinkedOut: Linking World Knowledge Representation Out of Video LLM for Next-Generation Video RecommendationFirst author · 2025
- Dense Video Understanding with Gated Residual TokenizationFirst author · 2025
- OOSTraj: Out-of-Sight Trajectory Prediction With Vision-Positioning DenoisingFirst author · 2024
- Layout Sequence Prediction From Noisy Mobile ModalityFirst author · 2023