AI.info

Yang Li

Explore Yang Li on AI.info.

• Cross-Sign Language Transfer Learning Using Domain Adaptation with Multi-scale Temporal Alignment
• ProactiveMobile: A Comprehensive Benchmark for Boosting Proactive Intelligence on Mobile Devices
• Kimi K2.5: Visual Agentic Intelligence
• BMAM: Brain-inspired Multi-Agent Memory Framework
• Video-MSR: Benchmarking Multi-hop Spatial Reasoning Capabilities of MLLMs
• Towards Open Environments and Instructions: General Vision-Language Navigation via Fast-Slow Interactive Reasoning
• AT$^2$PO: Agentic Turn-based Policy Optimization via Tree Search
• Student Guides Teacher: Weak-to-Strong Inference via Spectral Orthogonal Exploration
• DIP: Dynamic In-Context Planner For Diffusion Language Models
• UltraShape 1.0: High-Fidelity 3D Shape Generation via Scalable Geometric Refinement
• In Pursuit of Pixel Supervision for Visual Pre-training
• HiFi-Portrait: Zero-shot Identity-preserved Portrait Generation with High-fidelity Multi-face Fusion
• A Large-Scale Multimodal Dataset and Benchmarks for Human Activity Scene Understanding and Reasoning
• From Imitation to Discrimination: Toward A Generalized Curriculum Advantage Mechanism Enhancing Cross-Domain Reasoning Tasks
• Decomposed Trust: Privacy, Adversarial Robustness, Ethics, and Fairness in Low-Rank LLMs
• Thinker: Training LLMs in Hierarchical Thinking for Deep Search via Multi-Turn Interaction
• Attention Illuminates LLM Reasoning: The Preplan-and-Anchor Rhythm Enables Fine-Grained Policy Optimization
• Novel Class Discovery for Point Cloud Segmentation via Joint Learning of Causal Representation and Reasoning
• FastUMI-100K: Advancing Data-driven Robotic Manipulation with a Large-scale UMI-style Dataset