Related papers: Inference-time Alignment in Continuous Space

Alignment with human preferences is commonly framed using a universal reward function, even though human preferences are inherently heterogeneous. We formalize this heterogeneity by introducing user types and examine the limits of the…

The goal of this paper is to enhance Text-to-Audio generation at inference, focusing on generating realistic audio that precisely aligns with text prompts. Despite the rapid advancements, existing models often fail to achieve a reliable…

Shared autonomy systems require principled methods for inferring user intent and determining appropriate assistance levels. This is a central challenge in human-robot interaction, where systems must be successful while being mindful of user…

This paper studies the maximization of the weighted sum energy efficiency (WSEE). We derive a first-order optimal algorithm applicable to a wide class of communication scenarios exhibiting very fast convergence. We also discuss how to…

Deep learning models in computer vision have achieved significant success but pose increasing concerns about energy consumption and sustainability. Despite these concerns, there is a lack of comprehensive understanding of their energy…

Personalized alignment is crucial for enabling Large Language Models (LLMs) to engage effectively in user-centric interactions. However, current methods face a dual challenge: they fail to infer users' deep implicit preferences (including…

Embedding-based methods have attracted increasing attention in recent entity alignment (EA) studies. Although great promise they can offer, there are still several limitations. The most notable is that they identify the aligned entities…

Intelligent software systems continuously analyze their surrounding environment and accordingly adapt their internal state. Depending on the criticality index of the situation, the system should dynamically focus or widen its analysis and…

Test-time scaling improves the inference performance of Large Language Models (LLMs) but also incurs substantial computational costs. Although recent studies have reduced token consumption through dynamic self-consistency, they remain…

Large language models (LLMs) have empowered AI agents to tackle increasingly complex tasks. However, most existing agents remain limited to static planning and brittle interactions, falling short of true collaboration or adaptive reasoning.…

An increasing number of applications require real-time reasoning under uncertainty with streaming input. The temporal (dynamic) Bayes net formalism provides a powerful representational framework for such applications. However, existing…

Large language models (LLMs) often struggle with context fidelity, producing inconsistent answers when responding to questions based on provided information. Existing approaches either rely on expensive supervised fine-tuning to generate…

Deep search agents, which aim to answer complex questions requiring reasoning across multiple documents, can significantly speed up the information-seeking process. Collecting human annotations for this application is prohibitively…

Although large language models rely on chain-of-thought for complex reasoning, the overthinking phenomenon severely degrades inference efficiency. Existing reinforcement learning methods compress reasoning chains by designing elaborate…

In this paper, we address the problem of interference alignment (IA) over MIMO interference channels with limited channel state information (CSI) feedback based on quantization codebooks. Due to limited feedback and hence imperfect IA,…

Learned sparse retrieval, which can efficiently perform retrieval through mature inverted-index engines, has garnered growing attention in recent years. Particularly, the inference-free sparse retrievers are attractive as they eliminate…

We consider the problem of efficient inference of the Average Treatment Effect in a sequential experiment where the policy governing the assignment of subjects to treatment or control can change over time. We first provide a central limit…

Reinforcement learning control algorithms face significant challenges due to out-of-distribution and inefficient exploration problems. While model-based reinforcement learning enhances the agent's reasoning and planning capabilities by…

Adaptive inference schemes reduce the cost of machine learning inference by assigning smaller models to easier examples, attempting to avoid invocation of larger models when possible. In this work we explore a simple, effective adaptive…

We propose MESA and DMESA as novel feature matching methods, which utilize Segment Anything Model (SAM) to effectively mitigate matching redundancy. The key insight of our methods is to establish implicit-semantic area matching prior to…