AI.info

Xin Li

Explore Xin Li on AI.info.

• BooM-VVT: Boosting Mask-Free Video Virtual Try-On with Image-Level Pseudo Data
• Beyond the Stability-Exploration Dilemma: Environmental Regularization for LLM Policy Optimization
• RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance
• ActFovea: Runtime Safeguarding for VLA Policies via Spatiotemporal Visual-Action Consistency
• RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Model
• MASFactory: A Graph-centric Framework for Orchestrating LLM-Based Multi-Agent Systems with Vibe Graphing
• InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery
• Retrieval-Infused Reasoning Sandbox: A Benchmark for Decoupling Retrieval and Reasoning Capabilities
• TiMem: Temporal-Hierarchical Memory Consolidation for Long-Horizon Conversational Agents
• Beyond Itinerary Planning-A Real-World Benchmark for Multi-Turn and Tool-Using Travel Tasks
• Evaluating Large Language Models on Multimodal Chemistry Olympiad Exams
• Diff-ICMH: Harmonizing Machine and Human Vision in Image Compression with Generative Prior
• UniFit: Towards Universal Virtual Try-on with MLLM-Guided Semantic Alignment
• FIA-Edit: Frequency-Interactive Attention for Efficient and High-Fidelity Inversion-Free Text-Guided Image Editing
• COIG-Writer: A High-Quality Dataset for Chinese Creative Writing with Thought Processes
• AutoMLGen: Navigating Fine-Grained Optimization for Coding Agents