Introduces Expanding Generative Flows (EFlows) and Expanding Flow Maps (EFMs) for generating outputs of varying sizes in continuous and discrete state spaces.

This paper introduces WanSong, a diffusion-based model for long-form, commercial-grade song generation that directly generates high-fidelity, multilingual songs up to 5 minutes and outputs dual stems,…

The paper introduces Drifting Preference Optimization (DrPO), an efficient online method for preference finetuning one-step text-to-image generators that avoids complex gradient calculations and model…

This paper proposes a data collection strategy using solver iterates to augment datasets for training generative models, improving the efficiency of the data-model-optimization loop in one-sided box-c…

The paper introduces the Insertion Process (IP), a novel stochastic generative model that learns variable-length, non-monotonic sequence generation by explicitly modeling the insertion order of tokens…

The paper introduces PRAXIS, a novel algorithm that efficiently approximates the computation of 'Rashomon sets' for decision trees, significantly reducing memory and runtime complexity.

This paper introduces GraphBU, a graph-native MILP instance generator whose unit is a local subproblem plus its interface, promoting coupling and preserving feasibility.

This paper introduces BBOmix, an open-source benchmark for unsupervised representation learning on real-world biological data.

This paper introduces an activation hierarchy and proves a Predictor-Impossibility Theorem, showing that no effective predictor family can determine all stage languages. It also establishes a slice th…

This paper proposes using offline reinforcement learning (RL) as an efficient alternative to online RL for post-training code-generating LLMs, demonstrating its effectiveness, especially for smaller m…

This book provides a compact, derivation-oriented mathematical primer that connects major families of generative AI models, showing their underlying structural relationships.

StepPRM-RTL is a novel framework that enhances LLM-based RTL code generation for digital hardware designs.

PhyGenHOI introduces a novel framework that generates physically accurate and visually faithful 4D Human-Object Interactions by coupling generative human motion with explicit physical object simulatio…

CubePart is a generative framework that enables the creation of complex 3D meshes by explicitly controlling and generating individual, semantically defined parts based on open-vocabulary text prompts.

This paper simplifies the proof of the bound on the target dimension for reducing the dimension of high-dimensional polygonal curves using random projections, extending it to various distance measures…

Introduce Deep Second-Order Stochastic Residual Method (D2SRM) for high-dimensional, Hessian-dependent fully nonlinear parabolic PDEs, establish well-posedness, and develop population-level convergenc…

The paper proposes a visual program synthesis framework using a VLM to generate accurate training data for semiconductor inspection, mitigating the sim-to-real gap by applying input binarization to st…

The paper introduces Conformal Generation (Conf-Gen), a novel framework that adapts conformal risk control to provide formal uncertainty guarantees for unsupervised generative models like LLMs and ima…

This paper studies the behavior and complexity of randomized algorithms that may terminate almost surely but run forever on exceptional random tapes. It provides bounds on the survival tail, Kolmogoro…

The paper introduces Grid Programs, a novel, Turing-complete model of computation where programs are two-dimensional arrangements of instructions, fundamentally departing from linear code structures.