Gen Luo

ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data

Out of the Memory Barrier: A Highly Memory-Efficient Training System for LLMs with Million-Token Contexts

MM-HELIX: Boosting Multimodal Long-Chain Reflective Reasoning with Holistic Platform and Adaptive Hybrid Policy Optimization

SpaCE-10: A Comprehensive Benchmark for Multimodal Large Language Models in Compositional Spatial Intelligence

MetaCaptioner: Towards Generalist Visual Captioning with Open-source Suites

Vlaser: Vision-Language-Action Model with Synergistic Embodied Reasoning

GenExam: A Multidisciplinary Text-to-Image Exam

Sequential Diffusion Language Models

Blend-Aware Latent Diffusion: Mitigating Stitched Seams in Image Inpainting

ViCO: A Training Strategy towards Semantic Aware Dynamic High-Resolution

Beyond Proxy Metrics: A New Evaluation Framework for LLM Compression by Directly Measuring Generative Faithfulness

NaViL: Rethinking Scaling Properties of Native Multimodal Large Language Models under Data Constraints

Spotlight Attention: Towards Efficient LLM Generation via Non-linear Hashing-based KV Cache Retrieval

$\gamma-$MoD: Exploring Mixture-of-Depth Adaptation for Multimodal Large Language Models

Feast Your Eyes: Mixture-of-Resolution Adaptation for Multimodal Large Language Models

Weakly-supervised 3D Referring Expression Segmentation

Mono-InternVL: Pushing the Boundaries of Monolithic Multimodal Large Language Models with Endogenous Visual Pre-training