Trending Research
InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models
We present InstantMesh, a feed-forward framework for instant 3D mesh generation from a single image, featuring state-of-the-art generation quality and significant training scalability.
Is Sora a World Simulator? A Comprehensive Survey on General World Models and Beyond
gigaai-research/general-world-models-survey
•
•
General world models represent a crucial pathway toward achieving Artificial General Intelligence (AGI), serving as the cornerstone for various applications ranging from virtual environments to decision-making systems.
EffiBench: Benchmarking the Efficiency of Automatically Generated Code
This paper presents EffiBench, a benchmark with 1, 000 efficiency-critical coding problems for assessing the efficiency of code generated by code generation models.
OpenVoice: Versatile Instant Voice Cloning
The voice styles are not directly copied from and constrained by the style of the reference speaker.
MemGPT: Towards LLMs as Operating Systems
Large language models (LLMs) have revolutionized AI, but are constrained by limited context windows, hindering their utility in tasks like extended conversations and document analysis.
Towards Realistic Scene Generation with LiDAR Diffusion Models
In this paper, we propose LiDAR Diffusion Models (LiDMs) to generate LiDAR-realistic scenes from a latent space tailored to capture the realism of LiDAR scenes by incorporating geometric priors into the learning pipeline.
Score-Guided Diffusion for 3D Human Recovery
statho/scorehmr
•
•
We present Score-Guided Human Mesh Recovery (ScoreHMR), an approach for solving inverse problems for 3D human pose and shape reconstruction.
Automating the Enterprise with Foundation Models
We conduct initial experiments showing that multimodal FMs can address the limitations of traditional RPA with (1) near-human-level understanding of workflows (93% accuracy on a workflow understanding task) and (2) instant set-up with minimal technical barrier (based solely on a natural language description of a workflow, ECLAIR achieves end-to-end completion rates of 40%).
ESRL: Efficient Sampling-based Reinforcement Learning for Sequence Generation
hiyouga/llama-efficient-tuning
•
•
Applying Reinforcement Learning (RL) to sequence generation models enables the direct optimization of long-term rewards (\textit{e. g.,} BLEU and human feedback), but typically requires large-scale sampling over a space of action sequences.
FREB-TQA: A Fine-Grained Robustness Evaluation Benchmark for Table Question Answering
To investigate these aspects, we create and publish a novel TQA evaluation benchmark in English.
