Hao Chen

14 papers Harbin Institute of Technology

• DICEPTION: A Generalist Diffusion Model for Visual Perceptual Tasks
• EPA: Boosting Event-based Video Frame Interpolation with Perceptually Aligned Learning
• Enforcing Hard Linear Constraints in Deep Learning Models with Decision Rules
• Evaluating Program Semantics Reasoning with Type Inference in System $F$
• Fast-in-Slow: A Dual-System VLA Model Unifying Fast Manipulation within Slow Reasoning
• From Pretraining to Pathology: How Noise Leads to Catastrophic Inheritance in Medical Models
• Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System Collaboration
• On Fairness of Unified Multimodal Large Language Model for Image Generation
• ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation
• Rethinking Optimal Verification Granularity for Compute-Efficient Test-Time Scaling
• Role-aware Multi-agent Reinforcement Learning for Coordinated Emergency Traffic Control
• Toward Engineering AGI: Benchmarking the Engineering Design Capabilities of LLMs
• Unleashing Hour-Scale Video Training for Long Video-Language Understanding
• Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations