Related papers: Efficient Conditional Generation on Scale-based Vi…
We introduce Efficient Motion Diffusion Model (EMDM) for fast and high-quality human motion generation. Current state-of-the-art generative diffusion models have produced impressive results but struggle to achieve fast generation without…
Accurate and high-resolution Earth system model (ESM) simulations are essential to assess the ecological and socio-economic impacts of anthropogenic climate change, but are computationally too expensive to be run at sufficiently high…
In this work, we first revisit the sampling issues in current autoregressive (AR) image generation models and identify that image tokens, unlike text tokens, exhibit lower information density and non-uniform spatial distribution.…
Classifier-free guidance (CFG) has become a widely adopted and practical approach for enhancing generation quality and improving condition alignment. Recent studies have explored guidance mechanisms for unconditional generation, yet these…
While transformer models have been highly successful, they are computationally inefficient. We observe that for each layer, the full width of the layer may be needed only for a small subset of tokens inside a batch and that the "effective"…
The efficiency of large language models (LLMs) is fundamentally limited by their sequential, token-by-token generation process. We argue that overcoming this bottleneck requires a new design axis for LLM scaling: increasing the semantic…
Autoregressive models have emerged as a powerful approach for visual generation but suffer from slow inference speed due to their sequential token-by-token prediction process. In this paper, we propose a simple yet effective approach for…
An environment representation (ER) is a substantial part of every autonomous system. It introduces a common interface between perception and other system components, such as decision making, and allows downstream algorithms to deal with…
Autoregressive (AR) models have achieved unified and strong performance across both visual understanding and image generation tasks. However, removing undesired concepts from AR models while maintaining overall generation quality remains an…
Generative models (e.g., GANs, diffusion models) learn the underlying data distribution in an unsupervised manner. However, many applications of interest require sampling from a particular region of the output space or sampling evenly over…
Recent advances in motion diffusion models have substantially improved the realism of human motion synthesis. However, existing approaches either rely on full-sequence diffusion models with bidirectional generation, which limits temporal…
Understanding brain function represents a fundamental goal in neuroscience, with critical implications for therapeutic interventions and neural engineering applications. Computational modeling provides a quantitative framework for…
Conditional discrete generative models struggle to faithfully compose multiple input conditions. To address this, we derive a theoretically-grounded formulation for composing discrete probabilistic generative processes, with masked…
Conditional discrete generative models struggle to faithfully compose multiple input conditions. To address this, we derive a theoretically-grounded formulation for composing discrete probabilistic generative processes, with masked…
Modern distributed training relies heavily on communication compression to reduce the communication overhead. In this work, we study algorithms employing a popular class of contractive compressors in order to reduce communication overhead.…
Consistency Models (CMs) have showed a promise in creating visual content efficiently and with high quality. However, the way to add new conditional controls to the pretrained CMs has not been explored. In this technical report, we consider…
Generative models that satisfy hard constraints are critical in many scientific and engineering applications, where physical laws or system requirements must be strictly respected. Many existing constrained generative models, especially…
Content is created for a well-defined purpose, often described by a metric or signal represented in the form of structured information. The relationship between the goal (metrics) of target content and the content itself is non-trivial.…
Auto-Regressive (AR) models have achieved impressive results in 2D image generation by modeling joint distributions in the grid space. While this approach has been extended to the 3D domain for powerful shape generation, it still has two…
Neural language models can be successfully trained on source code, leading to applications such as code completion. However, their versatile autoregressive self-supervision objective overlooks important global sequence-level features that…