AI.info

Xin Jin

Explore Xin Jin on AI.info.

• Inter-X++: A Comprehensive Benchmark for Multimodal Human-Human Interaction Analysis
• WorldArena: A Unified Benchmark for Evaluating Perception and Functional Utility of Embodied World Models
• TP-Blend: Textual-Prompt Attention Pairing for Precise Object-Style Blending in Diffusion Models
• PvP: Data-Efficient Humanoid Robot Learning with Proprioceptive-Privileged Contrastive Representations
• Goal-Driven Reward by Video Diffusion Models for Reinforcement Learning
• Diff-ICMH: Harmonizing Machine and Human Vision in Image Compression with Generative Prior
• MFmamba: A Multi-function Network for Panchromatic Image Resolution Restoration Based on State-Space Model
• Distribution Matching Distillation Meets Reinforcement Learning
• InteractComp: Evaluating Search Agents With Ambiguous Queries
• MergeMix: A Unified Augmentation Paradigm for Visual and Multi-Modal Understanding
• OmniNWM: Omniscient Driving Navigation World Models
• Hybrid-grained Feature Aggregation with Coarse-to-fine Language Guidance for Self-supervised Monocular Depth Estimation
• UltraLED: Learning to See Everything in Ultra-High Dynamic Range Scenes