AI.info

Hao Li

Explore Hao Li on AI.info.

• Simple Domain Generalization for Strong Pixel-Level Image Tampering Detection in Modern VLMs
• PhysInOne: Visual Physics Learning and Reasoning in One Suite
• DiverseDiT: Towards Diverse Representation Learning in Diffusion Transformers
• Chain of World: World Model Thinking in Latent Motion
• RoboInter: A Holistic Intermediate Representation Suite Towards Robotic Manipulation
• Robo3R: Enhancing Robotic Manipulation with Accurate Feed-Forward 3D Reconstruction
• VAMOS-OCTA: Vessel-Aware Multi-Axis Orthogonal Supervision for Inpainting Motion-Corrupted OCT Angiography Volumes
• MetricAnything: Scaling Metric Depth Pretraining with Noisy Heterogeneous Sources
• Learning Sewing Patterns via Latent Flow Matching of Implicit Fields
• Agentic reinforcement learning empowers next-generation chemical language models for molecular design and synthesis
• Diff-MN: Diffusion Parameterized MoE-NCDE for Continuous Time Series Generation with Irregular Observations
• LLMRouterBench: A Massive Benchmark and Unified Framework for LLM Routing
• TexTailor: Inference-Time Textual Guidance Tailoring for Multimodal Diffusion Transformers
• Towards Generative Location Awareness for Disaster Response: A Probabilistic Cross-view Geolocalization Approach
• RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension
• FDP: A Frequency-Decomposition Preprocessing Pipeline for Unsupervised Anomaly Detection in Brain MRI
• Agentmandering: A Game-Theoretic Framework for Fair Redistricting via Large Language Model Agents
• Monocular absolute depth estimation from endoscopy via domain-invariant feature learning and latent consistency
• IGGT: Instance-Grounded Geometry Transformer for Semantic 3D Reconstruction
• From Spatial to Actions: Grounding Vision-Language-Action Model in Spatial Foundation Priors
• InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy
• ICL-Router: In-Context Learned Model Representations for LLM Routing
• NaViL: Rethinking Scaling Properties of Native Multimodal Large Language Models under Data Constraints