Related papers: Test-Time Instance-Specific Parameter Composition:…

Imagine generating a city's electricity demand pattern based on weather, the presence of an electric vehicle, and location, which could be used for capacity planning during a winter freeze. Such real-world time series are often enriched…

We present SlotAdapt, an object-centric learning method that combines slot attention with pretrained diffusion models by introducing adapters for slot-based conditioning. Our method preserves the generative power of pretrained diffusion…

Recently, text-to-image generation models have achieved remarkable advancements, particularly with diffusion models facilitating high-quality image synthesis from textual descriptions. However, these models often struggle with achieving…

In adaptive control, a controller is precisely designed for a certain model of the system, but that model's parameters are updated online by another mechanism called the adaptive update. This allows the controller to aim for the benefits of…

Diffusion models conditioned on identity embeddings enable the generation of synthetic face images that consistently preserve identity across multiple samples. Recent work has shown that introducing an additional negative condition through…

Generative models in molecular design tend to be richly parameterized, data-hungry neural models, as they must create complex structured objects as outputs. Estimating such models from data may be challenging due to the lack of sufficient…

Generative classifiers offer potential advantages over their discriminative counterparts, namely in the areas of data efficiency, robustness to data shift and adversarial examples, and zero-shot learning (Ng and Jordan,2002; Yogatama et…

In model-based reinforcement learning, generative and temporal models of environments can be leveraged to boost agent performance, either by tuning the agent's representations during training or via use as part of an explicit planning…

Transformer-based pre-trained models with millions of parameters require large storage. Recent approaches tackle this shortcoming by training adapters, but these approaches still require a relatively large number of parameters. In this…

Despite significant advances in deep models for music generation, the use of these techniques remains restricted to expert users. Before being democratized among musicians, generative models must first provide expressive control over the…

Collecting robotic manipulation data is expensive, making it impractical to acquire demonstrations for the combinatorially large space of tasks that arise in multi-object, multi-robot, and multi-environment settings. While recent generative…

Despite impressive recent advances in text-to-image diffusion models, obtaining high-quality images often requires prompt engineering by humans who have developed expertise in using them. In this work, we present NeuroPrompts, an adaptive…

LLM agents that store knowledge as natural language suffer steep retrieval degradation as condition count grows, often struggle to compose learned rules reliably, and typically lack explicit mechanisms to detect stale or adversarial…

Audio-driven talking-head generation has achieved remarkable progress with recent models such as AniTalker, FLOAT, and Sonic. Despite their success, most existing approaches rely on a single static reference image to condition the entire…

Materials design aims to discover novel compounds with desired properties. However, prevailing strategies face critical trade-offs. Conventional element-substitution approaches readily and adaptively incorporate various domain knowledge but…

Recent studies have demonstrated that many layers are functionally redundant in large language models (LLMs), enabling model compression by removing these layers to reduce inference cost. While such approaches can improve efficiency,…

Compositional generalization refers to correctly interpret novel combinations of known primitives, which remains a major challenge. Existing approaches often rely on supervised fine-tuning, which encourages models to imitate target outputs.…

Compositional generalization is a key ability of humans that enables us to learn new concepts from only a handful examples. Neural machine learning models, including the now ubiquitous Transformers, struggle to generalize in this way, and…

Advances in data collection are producing growing volumes of temporal count observations, making adapted modeling increasingly necessary. In this work, we introduce a generative framework for independent component analysis of temporal count…

The choices of hyperparameters have critical effects on the performance of machine learning models. In this paper, we present a general framework that is able to construct an adaptive optimizer, which automatically adjust the appropriate…