AI.info

Jun Zhang

Explore Jun Zhang on AI.info.

• MeanFlowNFT: Bringing Forward-Process RL to Average-Velocity Generators
• DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos
• Distribution-Aligned Sequence Distillation for Superior Long-CoT Reasoning
• GaussianImage++: Boosted Image Representation and Compression with 2D Gaussian Splatting
• TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs
• WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling
• OPAL: Operator-Programmed Algorithms for Landscape-Aware Black-Box Optimization
• Experience-Evolving Multi-Turn Tool-Use Agent with Hybrid Episodic-Procedural Memory
• 3M-TI: High-Quality Mobile Thermal Imaging via Calibration-free Multi-Camera Cross-Modal Diffusion
• RoadBench: Benchmarking MLLMs on Fine-Grained Spatial Understanding and Reasoning under Urban Road Scenarios
• MoDES: Accelerating Mixture-of-Experts Multimodal Large Language Models via Dynamic Expert Skipping
• CAS-Spec: Cascade Adaptive Self-Speculative Decoding for On-the-Fly Lossless Inference Acceleration of LLMs
• End-to-end Listen, Look, Speak and Act
• PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model
• NTIRE 2025 Challenge on Low Light Image Enhancement: Methods and Results
• LinVideo: A Post-Training Framework towards O(n) Attention in Efficient Video Generation