Related papers: DiffLOB: Diffusion Models for Counterfactual Gener…

Generative models such as diffusion models, excel at capturing high-dimensional distributions with diverse input modalities, e.g. robot trajectories, but are less effective at multi-step constraint reasoning. Task and Motion Planning (TAMP)…

Cross-modal garment synthesis and manipulation will significantly benefit the way fashion designers generate garments and modify their designs via flexible linguistic interfaces.Current approaches follow the general text-to-image paradigm…

Recent advances in latent diffusion models have demonstrated state-of-the-art performance in high-dimensional time-series data synthesis while providing flexible control through conditioning and guidance. However, existing methodologies…

Generating visual layouts is an essential ingredient of graphic design. The ability to condition layout generation on a partial subset of component attributes is critical to real-world applications that involve user interaction. Recently,…

Language diffusion models aim to improve sampling speed and coherence over autoregressive LLMs. We introduce Neural Flow Diffusion Models for language generation, an extension of NFDM that enables the straightforward application of…

Fashionable image generation aims to synthesize images of diverse fashion prevalent around the globe, helping fashion designers in real-time visualization by giving them a basic customized structure of how a specific design preference would…

Diffusion-based world models have demonstrated strong capabilities in synthesizing realistic long-horizon trajectories for offline reinforcement learning (RL). However, many existing methods do not directly generate actions alongside states…

Predictive process analytics focuses on predicting future states, such as the outcome of running process instances. These techniques often use machine learning models or deep learning models (such as LSTM) to make such predictions. However,…

In recent years, diffusion models have demonstrated remarkable potential across diverse domains, from vision generation to language modeling. Transferring its generative capabilities to modern end-to-end autonomous driving systems has also…

Generating multiple counterfactual explanations for different modes within a class presents a significant challenge, as these modes are distinct yet converge under the same classification. Diffusion probabilistic models (DPMs) have…

Model-based offline optimization with dynamics-aware policy provides a new perspective for policy learning and out-of-distribution generalization, where the learned policy could adapt to different dynamics enumerated at the training stage.…

Current language models demonstrate remarkable proficiency in text generation. However, for many applications it is desirable to control attributes, such as sentiment, or toxicity, of the generated language -- ideally tailored towards each…

Personalized text-to-image generation has gained significant attention for its capability to generate high-fidelity portraits of specific identities conditioned on user-defined prompts. Existing methods typically involve test-time…

We develop a new market-making model, from the ground up, which is tailored towards high-frequency trading under a limit order book (LOB), based on the well-known classification of order types in market microstructure. Our flexible…

Target-Oriented Dialogue (TOD) remains a significant challenge in the LLM era, where strategic dialogue planning is crucial for directing conversations toward specific targets. However, existing dialogue planning methods generate dialogue…

Stable diffusion models represent the state-of-the-art in data synthesis across diverse domains and hold transformative potential for applications in science and engineering, e.g., by facilitating the discovery of novel solutions and…

Controllable generation is a fundamental task in NLP with many applications, providing a basis for function calling to agentic communication. However, even state-of-the-art autoregressive Large Language Models (LLMs) today exhibit…

We introduce beta diffusion, a novel generative modeling method that integrates demasking and denoising to generate data within bounded ranges. Using scaled and shifted beta distributions, beta diffusion utilizes multiplicative transitions…

Many commonly used liquidity measures are based on snapshots of the state of the limit order book (LOB) and can thus only provide information about instantaneous liquidity, and not regarding the local liquidity regime. However, trading in…

We derive a continuous time model for the joint evolution of the mid price and the bid-ask spread from a multiscale analysis of the whole limit order book (LOB) dynamics. We model the LOB as a multiclass queueing system and perform our…