AI.info

Chi Zhang

Explore Chi Zhang on AI.info.

• WNM-3D: A World Navigation Model with 3D Scene Conditioning for Closed-Loop VLN
• Instruction-based Image Editing: A Survey on Data, Models, Evaluation, and Applications
• Budget-Constrained Step-Level Diffusion Caching
• Free Lunch for Stabilizing Rectified Flow Inversion
• InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery
• Learning Physics-Grounded 4D Dynamics with Neural Gaussian Force Fields
• Spectral Characterization and Mitigation of Sequential Knowledge Editing Collapse
• QwenStyle: Content-Preserving Style Transfer with Qwen-Image-Edit
• Mitigating Long-Tailed Anomaly Score Distributions with Importance-Weighted Loss
• SlicerOrbitSurgerySim: An Open-Source Platform for Virtual Registration and Quantitative Comparison of Preformed Orbital Plates
• Aetheria: A multimodal interpretable content safety framework based on multi-agent debate and collaboration
• Fast3Dcache: Training-free 3D Geometry Synthesis Acceleration
• Knowledge Completes the Vision: A Multimodal Entity-aware Retrieval-Augmented Generation Framework for News Image Captioning
• CAS-Spec: Cascade Adaptive Self-Speculative Decoding for On-the-Fly Lossless Inference Acceleration of LLMs
• Adaptive Stochastic Coefficients for Accelerating Diffusion Sampling
• FAPO: Flawed-Aware Policy Optimization for Efficient and Reliable Reasoning
• A Parameter-Efficient Mixture-of-Experts Framework for Cross-Modal Geo-Localization
• Heterogeneous Adversarial Play in Interactive Environments