Controllable Long-term Motion Generation with Extended Joint Targets

LaFiTe has been introduced as a novel framework for generating high-fidelity, seamless textures directly on 3D surfaces, addressing the limitations of traditional UV-based and multi-view projection methods. By utilizing a variational autoencoder (VAE), LaFiTe encodes complex surface appearances into a structured latent space, which is then decoded into a continuous color field, achieving unprecedented texture fidelity.

A new method for movie trailer generation, named SSMP, has been proposed, which utilizes self-paced and self-corrective masked prediction to enhance the quality of trailers by employing bi-directional contextual modeling. This approach addresses the limitations of traditional selection-then-ranking methods that often lead to error propagation in trailer creation.

A new Transformer-based architecture called Small Building Model (SBM) has been introduced for layout synthesis in Building Information Modeling (BIM) scenes. This model addresses the challenge of tokenizing buildings by integrating diverse architectural features into sequences while maintaining their compositional structure, utilizing a sparse attribute-feature matrix to represent room properties.

A new method called Sliding-Window Merging (SWM) has been proposed to enhance the efficiency of large language models (LLMs) by compacting patch-redundant layers. This technique identifies and merges consecutive layers based on their functional similarity, thereby maintaining performance while simplifying model architecture. Extensive experiments indicate that SWM outperforms traditional pruning methods in zero-shot inference performance.

Researchers have introduced FusedKV, a novel approach to reconstructing key-value (KV) caches in transformer models, enhancing their efficiency by fusing information from bottom and middle layers. This method addresses the significant memory demands of KV caches during long sequence processing, which has been a bottleneck in transformer performance. Preliminary findings indicate that this fusion retains essential positional information without the computational burden of rotary embeddings.

SimFlow introduces a simplified and end-to-end training method for Latent Normalizing Flows (NFs), addressing limitations in previous models that relied on complex noise addition and frozen VAE encoders. By fixing the variance to a constant, the model enhances the encoder's output distribution and stabilizes training, leading to improved image reconstruction and generation quality.

DynamicCity has introduced a groundbreaking 4D occupancy generation framework that enhances urban scene generation by focusing on the dynamic nature of real-world driving environments. This framework utilizes a VAE model and a novel Projection Module to create high-quality dynamic 4D scenes, significantly improving fitting quality and reconstruction accuracy.

A new method called Density-Informed VAE (DiVAE) has been introduced, which enhances the Variational Autoencoder (VAE) framework by aligning the log-prior probability with data-derived log-density estimates. This approach allows for better allocation of posterior mass in relation to data-space density and improves prior coverage, particularly in synthetic datasets and the MNIST dataset.