Ping Luo

Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding

AutoBio: A Simulation and Benchmark for Robotic Automation in Digital Biology Laboratory

SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer

Fast-dLLM v2: Efficient Block-Diffusion LLM

RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation

CLAP: Unsupervised 3D Representation Learning for Fusion 3D Perception via Curvature Sampling and Prototype Learning

Scaling Law for Quantization-Aware Training

Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policies

Compose Your Policies! Improving Diffusion-based or Flow-based Robot Policies via Test-time Distribution-level Composition

From Denoising to Refining: A Corrective Framework for Vision-Language Diffusion Model

Dynamic Mixture of Progressive Parameter-Efficient Expert Library for Lifelong Robot Learning

LINA: Exploring Linear Autoregressive Image Generative Models with Continuous Tokens

Aligning Latent Spaces with Flow Priors

MM-PRM: Enhancing Multimodal Mathematical Reasoning with Scalable Step-Level Supervision

DriveE2E: Closed-Loop Benchmark for End-to-End Autonomous Driving through Real-to-Simulation

MM-Eureka: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning

Agent2World: A Unified LLM-based Multi-Agent Framework for Symbolic World-Model Generation

Truly Assessing Fluid Intelligence of Large Language Models through Dynamic Reasoning Evaluation

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control

PhyX: Does Your Model Have the "Wits" for Physical Reasoning?

Object-AVEdit: An Object-level Audio-Visual Editing Model

INT v.s. FP: A Comprehensive Study of Fine-Grained Low-bit Quantization Formats

TREND: Unsupervised 3D Representation Learning via Temporal Forecasting for LiDAR Perception

OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation

Dynamic Multimodal Evaluation with Flexible Complexity by Vision-Language Bootstrapping

BOOD: Boundary-based Out-Of-Distribution Data Generation

OWMM-Agent: Open World Mobile Manipulation With Multi-modal Agentic Data Synthesis

FUDOKI: Discrete Flow-based Unified Understanding and Generation via Kinetic-Optimal Velocities

Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation

IDA-VLM: Towards Movie Understanding via ID-Aware Large Vision-Language Model

WorldWeaver: Generating Long-Horizon Video Worlds via Rich Perception

SAMRefiner: Taming Segment Anything Model for Universal Mask Refinement

LLaMA Decoder As Vision Transformer

MMIU: Multimodal Multi-image Understanding for Evaluating Large Vision-Language Models

BOOD: Boundary-based Out-Of-Distribution Data Generation

CompGS: Unleashing 2D Compositionality for Compositional Text-to-3D via Dynamically Optimizing 3D Gaussians

Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation

An Empirical Study of Multiple Masking in Masked Autoencoder

Diffree: Text-Guided Shape Free Object Inpainting with Diffusion Model

HRVMamba: High-Resolution Visual State Space Model for Dense Prediction

Task-Oriented Diffusion Inversion for High-Fidelity Text-based Editing

DriveE2E: Benchmarking Closed-Loop End-to-End Autonomous Driving Based-on Real-World Traffic Scenarios

MatchMask: Mask-Centric Generative Data Augmentation for Label-Scarce Semantic Segmentation

PrefixQuant: Static Quantization Beats Dynamic through Prefixed Outliers in LLMs

EfficientQAT: Efficient Quantization-Aware Training for Large Language Models