AI.info

Wei Liu

Explore Wei Liu on AI.info.

• Last Translation Benchmark
• On-Policy Self-Distillation in Diffusion Models
• FlowMimic: Mask-free Visual Editing and Generation with Pixel-pair Warped Flow Field for Online Video Editing Data Generation and Modality Mimicry
• RealWonder: Real-Time Physical Action-Conditioned Video Generation
• Benchmarking LLM Tool-Use in the Wild
• CoFEH: LLM-driven Feature Engineering Empowered by Collaborative Bayesian Hyperparameter Optimization
• Self-Play Only Evolves When Self-Synthetic Pipeline Ensures Learnable Information Gain
• Hunt Instead of Wait: Evaluating Deep Data Research on Large Language Models
• Seeing Is Believing? A Benchmark for Multimodal Large Language Models on Visual Illusions and Anomalies
• FutureMind: Equipping Small Language Models with Strategic Thinking-Pattern Priors via Adaptive Knowledge Distillation
• SP^2DPO: An LLM-assisted Semantic Per-Pair DPO Generalization
• RM-Distiller: Exploiting Generative LLM for Reward Model Distillation
• Docs2Synth: A Synthetic Data Trained Retriever Framework for Scanned Visually Rich Documents Understanding
• VideoASMR-Bench: Can AI-Generated ASMR Videos Fool VLMs and Humans?
• MRD: Multi-resolution Retrieval-Detection Fusion for High-Resolution Image Understanding
• SKEL-CF: Coarse-to-Fine Biomechanical Skeleton and Surface Mesh Recovery
• Rad-GS: Radar-Vision Integration for 3D Gaussian Splatting SLAM in Outdoor Environments
• ICLR: Inter-Chrominance and Luminance Interaction for Natural Color Restoration in Low-Light Image Enhancement
• Mixture of States: Routing Token-Level Dynamics for Multimodal Generation
• Environment Scaling for Interactive Agentic Experience Collection: A Survey
• Revisiting Entropy in Reinforcement Learning for Large Reasoning Models
• Isaac Lab: A GPU-Accelerated Simulation Framework for Multi-Modal Robot Learning
• The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution
• When Personalization Tricks Detectors: The Feature-Inversion Trap in Machine-Generated Text Detection