Wenqi Shao

InternSpatial: A Comprehensive Dataset for Spatial Reasoning in Vision-Language Models

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

Fine-grained Contrastive Learning for ECG-Report Alignment with Waveform Enhancement

Enhance-A-Video: Better Generated Video for Free

CPGD: Toward Stable Reinforcement Learning for Language Models

VTPerception-R1: Enhancing Multimodal Reasoning via Explicit Visual and Textual Perceptual Grounding

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

UniFork: Exploring Modality Alignment for Unified Multimodal Understanding and Generation

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

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

More Than One Teacher: Adaptive Multi-Guidance Policy Optimization for Diverse Exploration

UniPruning: Unifying Local Metric and Global Feedback for Scalable Sparse LLMs

CoSMo-RL: Towards Trustworthy LMRMs via Joint Safety and Stability

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

Dynamic Multimodal Evaluation with Flexible Complexity by Vision-Language Bootstrapping

Lumina-T2X: Scalable Flow-based Large Diffusion Transformer for Flexible Resolution Generation

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

EMOS: Embodiment-aware Heterogeneous Multi-robot Operating System with LLM Agents

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

LLaMA Decoder As Vision Transformer

SAMRefiner: Taming Segment Anything Model for Universal Mask Refinement

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

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

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

TP-Eval: Tap Multimodal LLMs' Potential in Evaluation by Customizing Prompts

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

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

ZipVL: Efficient Large Vision-Language Models with Dynamic Token Sparsification and KV Cache Compression

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

EfficientQAT: Efficient Quantization-Aware Training for Large Language Models

PrefixQuant: Static Quantization Beats Dynamic through Prefixed Outliers in LLMs