Trending Research
Ouroboros3D: Image-to-3D Generation via 3D-aware Recursive Diffusion
However, training these two stages separately leads to significant data bias in the inference phase, thus affecting the quality of reconstructed results.
LLaVA-UHD: an LMM Perceiving Any Aspect Ratio and High-Resolution Images
To address the challenges, we present LLaVA-UHD, a large multimodal model that can efficiently perceive images in any aspect ratio and high resolution.
Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity
We design models based off T5-Base and T5-Large to obtain up to 7x increases in pre-training speed with the same computational resources.
Show, Don't Tell: Aligning Language Models with Demonstrated Feedback
SALT-NLP/demonstrated-feedback
•
•
Across our benchmarks and user study, we find that win-rates for DITTO outperform few-shot prompting, supervised fine-tuning, and other self-play methods by an average of 19% points.
Improving Alignment and Robustness with Circuit Breakers
Existing techniques aimed at improving alignment, such as refusal training, are often bypassed.
Generalizable Human Gaussians from Single-View Image
To this end, we propose single-view generalizable Human Gaussian model (HGM), a diffusion-guided framework for 3D human modeling from a single image.
CARES: A Comprehensive Benchmark of Trustworthiness in Medical Vision Language Models
Artificial intelligence has significantly impacted medical applications, particularly with the advent of Medical Large Vision Language Models (Med-LVLMs), sparking optimism for the future of automated and personalized healthcare.
L-MAGIC: Language Model Assisted Generation of Images with Coherence
intellabs/mmpano
•
•
CVPR 2024
However, the lack of global scene layout priors leads to subpar outputs with duplicated objects (e. g., multiple beds in a bedroom) or requires time-consuming human text inputs for each view.
ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimization
Moreover, given the same computational resources, a ReNO-optimized one-step model outperforms widely-used open-source models such as SDXL and PixArt-$\alpha$, highlighting the efficiency and effectiveness of ReNO in enhancing T2I model performance at inference time.
Pre-training Small Base LMs with Fewer Tokens
Here we show that smaller LMs trained utilizing some of the layers of GPT2-medium (355M) and GPT-2-large (770M) can effectively match the val loss of their bigger counterparts when trained from scratch for the same number of training steps on OpenWebText dataset with 9B tokens.
