Trending Research
OpenELM: An Efficient Language Model Family with Open-source Training and Inference Framework
apple/corenet
•
•
To this end, we release OpenELM, a state-of-the-art open language model.
CyberSecEval 2: A Wide-Ranging Cybersecurity Evaluation Suite for Large Language Models
We present BenchmarkName, a novel benchmark to quantify LLM security risks and capabilities.
QLoRA: Efficient Finetuning of Quantized LLMs
internlm/xtuner
•
•
NeurIPS 2023
Our best model family, which we name Guanaco, outperforms all previous openly released models on the Vicuna benchmark, reaching 99. 3% of the performance level of ChatGPT while only requiring 24 hours of finetuning on a single GPU.
Improving Diffusion Models for Virtual Try-on
yisol/IDM-VTON
•
•
Finally, we present a customization method using a pair of person-garment images, which significantly improves fidelity and authenticity.
Ranked #1 on
Virtual Try-on
on VITON-HD
ID-Animator: Zero-Shot Identity-Preserving Human Video Generation
Based on this pipeline, a random face reference training method is further devised to precisely capture the ID-relevant embeddings from reference images, thus improving the fidelity and generalization capacity of our model for ID-specific video generation.
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.
Dynamic Generation of Personalities with Large Language Models
We propose a new metric to assess personality generation capability based on this evaluation method.
AutoCrawler: A Progressive Understanding Web Agent for Web Crawler Generation
We propose AutoCrawler, a two-stage framework that leverages the hierarchical structure of HTML for progressive understanding.
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.
SnapKV: LLM Knows What You are Looking for Before Generation
Specifically, SnapKV achieves a consistent decoding speed with a 3. 6x increase in generation speed and an 8. 2x enhancement in memory efficiency compared to baseline when processing inputs of 16K tokens.
