AI.info

Xin Liu

Explore Xin Liu on AI.info.

• Edge-Assisted Multi-Robot Visual-Inertial SLAM with Efficient Communication
• ABot-N0: Technical Report on the VLA Foundation Model for Versatile Embodied Navigation
• HeaPA: Difficulty-Aware Heap Sampling and On-Policy Query Augmentation for LLM Reinforcement Learning
• DASH: Deterministic Attention Scheduling for High-throughput Reproducible LLM Training
• Agentic Conversational Search with Contextualized Reasoning via Reinforcement Learning
• Videos are Sample-Efficient Supervisions: Behavior Cloning from Videos via Latent Representations
• Multi-agent Self-triage System with Medical Flowcharts
• C$^3$TG: Conflict-aware, Composite, and Collaborative Controlled Text Generation
• Enhancing Rotation-Invariant 3D Learning with Global Pose Awareness and Attention Mechanisms
• Focusing on Language: Revealing and Exploiting Language Attention Heads in Multilingual Large Language Models
• SynthWorlds: Controlled Parallel Worlds for Disentangling Reasoning and Knowledge in Language Models
• DeepPlanner: Scaling Planning Capability for Deep Research Agents via Advantage Shaping
• Logit Arithmetic Elicits Long Reasoning Capabilities Without Training
• FastUMI-100K: Advancing Data-driven Robotic Manipulation with a Large-scale UMI-style Dataset