Trending Research
CV-VAE: A Compatible Video VAE for Latent Generative Video Models
Moreover, since current diffusion-based approaches are often implemented using pre-trained text-to-image (T2I) models, directly training a video VAE without considering the compatibility with existing T2I models will result in a latent space gap between them, which will take huge computational resources for training to bridge the gap even with the T2I models as initialization.
RectifID: Personalizing Rectified Flow with Anchored Classifier Guidance
Our study shows that based on a recent rectified flow framework, the major limitation of vanilla classifier guidance in requiring a special classifier can be resolved with a simple fixed-point solution, allowing flexible personalization with off-the-shelf image discriminators.
Self-Exploring Language Models: Active Preference Elicitation for Online Alignment
Preference optimization, particularly through Reinforcement Learning from Human Feedback (RLHF), has achieved significant success in aligning Large Language Models (LLMs) to adhere to human intentions.
DiG: Scalable and Efficient Diffusion Models with Gated Linear Attention
hustvl/dig
•
•
In this paper, we aim to leverage the long sequence modeling capability of Gated Linear Attention (GLA) Transformers, expanding its applicability to diffusion models.
KAN: Kolmogorov-Arnold Networks
Inspired by the Kolmogorov-Arnold representation theorem, we propose Kolmogorov-Arnold Networks (KANs) as promising alternatives to Multi-Layer Perceptrons (MLPs).
GaussianFormer: Scene as Gaussians for Vision-Based 3D Semantic Occupancy Prediction
To address this, we propose an object-centric representation to describe 3D scenes with sparse 3D semantic Gaussians where each Gaussian represents a flexible region of interest and its semantic features.
SimPO: Simple Preference Optimization with a Reference-Free Reward
Our top-performing model, built on Llama3-8B-Instruct, achieves a remarkable 44. 7 length-controlled win rate on AlpacaEval 2 -- surpassing Claude 3 Opus on the leaderboard, and a 33. 8 win rate on Arena-Hard -- making it the strongest 8B open-source model.
Neighborhood-Enhanced Supervised Contrastive Learning for Collaborative Filtering
PeiJieSun/NESCL
•
•
Using the graph-based collaborative filtering model as our backbone and following the same data augmentation methods as the existing contrastive learning model SGL, we effectively enhance the performance of the recommendation model.
Ranked #1 on
Recommendation Systems
on Gowalla
Poseidon: Efficient Foundation Models for PDEs
Moreover, Poseidon scales with respect to model and data size, both for pretraining and for downstream tasks.
MoRA: High-Rank Updating for Parameter-Efficient Fine-Tuning
kongds/mora
•
•
Low-rank adaptation is a popular parameter-efficient fine-tuning method for large language models.
