Profiles2019-2026
Ping Luo
The University of Hong Kong
Also published as P Luo
77Papers
41Last author
150Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers77
- Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action PoliciesAuthor 12 of 12ICML 2026 · 86 citations
- AutoBio: A Simulation and Benchmark for Robotic Automation in Digital Biology LaboratoryAuthor 15 of 18ICLR 2026 · 21 citations
- INT vs. FP: A Comprehensive Study of Fine-Grained Low-bit Quantization FormatsAuthor 13 of 14ICML 2026 · 21 citations
- Laytrol: Preserving Pretrained Knowledge in Layout Control for Multimodal Diffusion TransformersAuthor 3 of 4AAAI 2026 · 5 citations
- CLAP: Unsupervised 3D Representation Learning for Fusion 3D Perception via Curvature Sampling and Prototype LearningAuthor 7 of 7ICLR 2026 · 1 citation
- LithoGRPO: Fast Inverse Lithography via GRPO Reinforced Flow MatchingAuthor 10 of 10ICML 2026
- AnalogCoder: Analog Circuit Design via Training-Free Code GenerationAuthor 7 of 7AAAI 2025 · 105 citations
- FUDOKI: Discrete Flow-based Unified Understanding and Generation via Kinetic-Optimal VelocitiesAuthor 9 of 9NeurIPS 2025 · 45 citations
- AutoMMLab: Automatically Generating Deployable Models from Language Instructions for Computer Vision TasksAuthor 5 of 6AAAI 2025 · 18 citations
- GUIOdyssey: A Comprehensive Dataset for Cross-App GUI Navigation on Mobile DevicesAuthor 10 of 10ICCV 2025 · 7 citations
- TREND: Unsupervised 3D Representation Learning via Temporal Forecasting for LiDAR PerceptionAuthor 5 of 6NeurIPS 2025 · 4 citations
- DexHandDiff: Interaction-aware Diffusion Planning for Adaptive Dexterous ManipulationAuthor 8 of 9CVPR 2025
- EfficientQAT: Efficient Quantization-Aware Training for Large Language ModelsAuthor 7 of 7ACL 2025
- Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and GenerationAuthor 11 of 11CVPR 2025
- JiSAM: Alleviate Labeling Burden and Corner Case Problems in Autonomous Driving via Minimal Real-World DataAuthor 6 of 6CVPR 2025
- NADER: Neural Architecture Design via Multi-Agent CollaborationAuthor 5 of 6CVPR 2025
- Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video GenerationAuthor 10 of 10ICML 2025
- Unsupervised Continual Domain Shift Learning with Multi-Prototype ModelingAuthor 5 of 8CVPR 2025
- PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image SynthesisAuthor 9 of 11ICLR 2024 · 831 citations
- OmniQuant: Omnidirectionally Calibrated Quantization for Large Language ModelsAuthor 10 of 10ICLR 2024 · 395 citations
- MotionCtrl: A Unified and Flexible Motion Controller for Video GenerationAuthor 8 of 8SIGGRAPH 2024 · 123 citations
- BESA: Pruning Large Language Models with Blockwise Parameter-Efficient Sparsity AllocationAuthor 9 of 9ICLR 2024 · 52 citations
- MoLE: Enhancing Human-centric Text-to-image Diffusion via Mixture of Low-rank ExpertsAuthor 4 of 6NeurIPS 2024 · 17 citations
- Scalable and Effective Arithmetic Tree Generation for Adder and Multiplier DesignsAuthor 4 of 4NeurIPS 2024 · 14 citations
- Large Language Models as Automated Aligners for benchmarking Vision-Language ModelsAuthor 7 of 7ICLR 2024 · 10 citations
- Diagnosing the Compositional Knowledge of Vision Language Models from a Game-Theoretic ViewAuthor 7 of 7ICML 2024 · 6 citations
- SkillDiffuser: Interpretable Hierarchical Planning via Skill Abstractions in Diffusion-Based Task ExecutionAuthor 6 of 6CVPR 2024
- DiffusionDet: Diffusion Model for Object DetectionAuthor 4 of 4ICCV 2023 · 715 citations
- RAPHAEL: Text-to-Image Generation via Large Mixture of Diffusion PathsAuthor 7 of 8NeurIPS 2023 · 201 citations
- ChiPFormer: Transferable Chip Placement via Offline Decision TransformerAuthor 6 of 6ICML 2023 · 69 citations
Showing the 30 most recent indexed papers.
