Related papers: SMITIN: Self-Monitored Inference-Time INtervention…

Instruction tuning increasingly relies on LLM-based prompt refinement, where prompts in the training corpus are selectively rewritten by an external refiner to improve clarity and instruction alignment. This motivates an instance-level…

We present a direct inverse modeling method named SURGIN, a SURrogate-guided Generative INversion framework tailed for subsurface multiphase flow data assimilation. Unlike existing inversion methods that require adaptation for each new…

In social networks, people influence each other through social links, which can be represented as propagation among nodes in graphs. Influence minimization (IMIN) is the problem of manipulating the structures of an input graph (e.g.,…

We consider the problem of inferring the total causal effect of a single variable intervention on a (response) variable of interest. We propose a certain marginal integration regression technique for a very general class of potentially…

We analyze a reversed-supervision strategy that searches over labelings of a large unlabeled set \(B\) to minimize error on a small labeled set \(A\). The search space is \(2^n\), and the resulting complexity remains exponential even under…

Deep neural networks often develop spurious bias, reliance on correlations between non-essential features and classes for predictions. For example, a model may identify objects based on frequently co-occurring backgrounds rather than…

Recent advancements in song generation have shown promising results in generating songs from lyrics and/or global text prompts. However, most existing systems lack the ability to model the temporally varying attributes of songs, limiting…

Diffusion models have become leading approaches for high-fidelity image generation. Recent DiT-based diffusion models, in particular, achieve strong prompt adherence while producing high-quality samples. We propose SHIFT, a simple but…

Backdoor attacks change a small portion of training data by introducing hand-crafted triggers and rewiring the corresponding labels towards a desired target class. Training on such data injects a backdoor which causes malicious inference in…

In this paper we propose a data-driven output-feedback controller synthesis method for discrete-time linear time-invariant systems in a specific autoregressive form. The synthesis goal is either to achieve dissipativity with respect to a…

We study unsupervised learning by developing introspective generative modeling (IGM) that attains a generator using progressively learned deep convolutional neural networks. The generator is itself a discriminator, capable of introspection:…

This paper presents a new dynamic approach to experiment design in settings where, due to interference or other concerns, experimental units are coarse. `Region-split' experiments on online platforms are one example of such a setting. The…

We present Text2midi-InferAlign, a novel technique for improving symbolic music generation at inference time. Our method leverages text-to-audio alignment and music structural alignment rewards during inference to encourage the generated…

Existing autoregressive large-scale text-to-speech (TTS) models have advantages in speech naturalness, but their token-by-token generation mechanism makes it difficult to precisely control the duration of synthesized speech. This becomes a…

Modern neural sequence generation models are built to either generate tokens step-by-step from scratch or (iteratively) modify a sequence of tokens bounded by a fixed length. In this work, we develop Levenshtein Transformer, a new partially…

Music mastering style transfer aims to model and apply the mastering characteristics of a reference track to a target track, simulating the professional mastering process. However, existing methods apply fixed processing based on a…

Inference-time steering methods offer a lightweight alternative to fine-tuning large language models (LLMs) and vision-language models (VLMs) by modifying internal activations at test time without updating model weights. However, most…

Auto-regressive sequence-to-sequence models with attention mechanism have achieved state-of-the-art performance in many tasks such as machine translation and speech synthesis. These models can be difficult to train. The standard approach,…

The dominant retrieve-then-rank pipeline in large-scale recommender systems suffers from mis-calibration and engineering overhead due to its architectural split and differing optimization objectives. While recent generative sequence models…

Large Language Models memorize vast amounts of training data, raising concerns regarding privacy, copyright infringement, and safety. Machine unlearning seeks to remove the influence of a targeted forget set while preserving model…