AI.info

Xiang Li

Explore Xiang Li on AI.info.

• Latent Action as Intention Enables Efficient Future Imagination for World Action Models
• XPolicyLab: A Unified Standard and Open Ecosystem for Robot Policy Evaluation and Deployment
• Improving the Trade-off Between Watermark Strength and Speculative Sampling Efficiency for Language Models
• Embodied Task Planning via Graph-Informed Action Generation with Large Language Models
• APEX: Academic Poster Editing Agentic Expert
• World In Your Hands: A Large-Scale and Open-Source Ecosystem for Learning Human-Centric Manipulation in the Wild
• Generalization of Diffusion Models Arises with a Balanced Representation Space
• VLSA: Vision-Language-Action Models with Plug-and-Play Safety Constraint Layer
• Cue3D: Quantifying the Role of Image Cues in Single-Image 3D Generation
• 3rd Place Solution to ICCV LargeFineFoodAI Retrieval
• Mitigating Privacy-Utility Trade-off in Decentralized Federated Learning via $f$-Differential Privacy
• ReefNet: A Large-Scale Dataset and Benchmark for Fine-Grained Coral Reef Recognition