🏢 Tsinghua University

LLaMA-Mesh: Unifying 3D mesh generation with LLMs by directly representing meshes as text, enabling efficient text-to-3D conversion within a single model.

Sharingan extracts user action sequences from desktop recordings using novel VLM-based methods, achieving 70-80% accuracy and enabling RPA.

JanusFlow harmonizes autoregression and rectified flow for unified multimodal understanding and generation, achieving state-of-the-art results on standard benchmarks.

DimensionX generates photorealistic 3D and 4D scenes from a single image via controllable video diffusion, enabling precise manipulation of spatial structure and temporal dynamics.

WEBRL: A self-evolving online curriculum reinforcement learning framework empowers open LLMs to excel as high-performing web agents, surpassing proprietary models.

Researchers discovered predictable scaling laws for activation sparsity in LLMs, showing how data, architecture, and model size influence sparsity, paving the way for more efficient and interpretable …

DeeR-VLA dynamically adjusts the size of a multimodal large language model based on task difficulty, significantly reducing computational cost and memory usage in robotic control without compromising …

Constraint Back-translation enhances complex instruction following in LLMs by leveraging inherent constraints in existing datasets for efficient high-quality data creation.

ANDROIDLAB, a novel framework, systematically benchmarks Android autonomous agents, improving LLM and LMM success rates on 138 tasks via a unified environment and open-source dataset.