Related papers: Text-driven 3D Human Generation via Contrastive Pr…

Recent contrastive methods show significant improvement in self-supervised learning in several domains. In particular, contrastive methods are most effective where data augmentation can be easily constructed e.g. in computer vision.…

Evaluating text-to-image generation models requires alignment with human perception, yet existing human-centric metrics are constrained by limited data coverage, suboptimal feature extraction, and inefficient loss functions. To address…

Recent advances in text-to-3D generation have made significant progress. In particular, with the pretrained diffusion models, existing methods predominantly use Score Distillation Sampling (SDS) to train 3D models such as Neural RaRecent…

Recent advancements in text-to-speech (TTS) have shown that language model (LM)-based systems offer competitive performance to their counterparts. Further optimization can be achieved through preference alignment algorithms, which adjust…

Learning from preference feedback is a common practice for aligning large language models~(LLMs) with human value. Conventionally, preference data is learned and encoded into a scalar reward model that connects a value head with an LLM to…

The success of reinforcement learning from human feedback (RLHF) in language model alignment is strongly dependent on the quality of the underlying reward model. In this paper, we present a novel approach to improve reward model quality by…

3D human generation is an important problem with a wide range of applications in computer vision and graphics. Despite recent progress in generative AI such as diffusion models or rendering methods like Neural Radiance Fields or Gaussian…

Efficient text-to-image generation remains a challenging task due to the high computational costs associated with the multi-step sampling in diffusion models. Although distillation of pre-trained diffusion models has been successful in…

The ability to generate highly realistic 2D images from mere text prompts has recently made huge progress in terms of speed and quality, thanks to the advent of image diffusion models. Naturally, the question arises if this can be also…

The automatic generation of counter-speech (CS) is a critical strategy for addressing hate speech by providing constructive and informed responses. However, existing methods often fail to generate high-quality, impactful, and scalable CS,…

Score Distillation Sampling (SDS) has been pivotal for leveraging pre-trained diffusion models in downstream tasks such as inverse problems, but it faces two major challenges: $(i)$ mode collapse and $(ii)$ latent space inversion, which…

We present InstructHumans, a novel framework for instruction-driven {animatable} 3D human texture editing. Existing text-based 3D editing methods often directly apply Score Distillation Sampling (SDS). SDS, designed for generation tasks,…

Contrastive learning produces coherent semantic feature embeddings by encouraging positive samples to cluster closely while separating negative samples. However, existing contrastive learning methods lack principled guarantees on coverage…

Distilling 3D representations from pretrained 2D diffusion models is essential for 3D creative applications across gaming, film, and interior design. Current SDS-based methods are hindered by inefficient information distillation from…

Large language models have achieved remarkable capabilities, but aligning their outputs with human values and preferences remains a significant challenge. Existing alignment methods primarily focus on positive examples while overlooking the…

Image-based object pose estimation sounds amazing because in real applications the shape of object is oftentimes not available or not easy to take like photos. Although it is an advantage to some extent, un-explored shape information in 3D…

For image generation with diffusion models (DMs), a negative prompt n can be used to complement the text prompt p, helping define properties not desired in the synthesized image. While this improves prompt adherence and image quality,…

Deep Candidate Generation plays an important role in large-scale recommender systems. It takes user history behaviors as inputs and learns user and item latent embeddings for candidate generation. In the literature, conventional methods…

Recent innovations on text-to-3D generation have featured Score Distillation Sampling (SDS), which enables the zero-shot learning of implicit 3D models (NeRF) by directly distilling prior knowledge from 2D diffusion models. However, current…

Text-to-3D generation aims to create 3D assets from text-to-image diffusion models. However, existing methods face an inherent bottleneck in generation quality because the widely-used objectives such as Score Distillation Sampling (SDS)…