相关论文: Multi-property Steering of Large Language Models w…

In this paper, we propose a novel framework, Combo, for harmonious co-speech holistic 3D human motion generation and efficient customizable adaption. In particular, we identify that one fundamental challenge as the…

We introduce Mechanistic Error Reduction with Abstention (MERA), a principled framework for steering language models (LMs) to mitigate errors through selective, adaptive interventions. Unlike existing methods that rely on fixed, manually…

Active learning is able to significantly reduce the annotation cost for data-driven techniques. However, previous active learning approaches for natural language processing mainly depend on the entropy-based uncertainty criterion, and…

Modern language models (LMs) have significantly advanced generative modeling in natural language processing (NLP). Despite their success, LMs often struggle with adaptation to new contexts in real-time applications. A promising approach to…

This paper proposes an iterative generative model for solving the automatic colorization problem. Although previous researches have shown the capability to generate plausible color, the edge color overflow and the requirement of the…

This paper assesses the potential for large language models (LLMs) to serve as assistive tools in the creative writing process, by means of a single, in-depth case study. In the course of the study, we develop interactive and multi-voice…

Activation steering has emerged as a cost-effective paradigm for modifying large language model (LLM) behaviors. Existing methods typically intervene at the block level, steering the bundled activations of selected attention heads,…

Although deep learning has achieved appealing results on several machine learning tasks, most of the models are deterministic at inference, limiting their application to single-modal settings. We propose a novel general-purpose framework…

Language models can be steered by modifying their internal representations to control concepts such as emotion, style, or truthfulness in generation. However, the conditions for an effective intervention remain unclear and are often…

Diffusion models have emerged as powerful tools for high-quality image generation and editing, but guiding these models to produce specific outputs remains a challenge. Conventional approaches rely on conditioning mechanisms, such as text…

Model steering, which involves intervening on hidden representations at inference time, has emerged as a lightweight alternative to finetuning for precisely controlling large language models. While steering efficacy has been widely studied,…

Model-based reinforcement learning is an appealing framework for creating agents that learn, plan, and act in sequential environments. Model-based algorithms typically involve learning a transition model that takes a state and an action and…

Creating large-scale datasets for training high-performance generative models is often prohibitively expensive, especially when associated attributes or annotations must be provided. As a result, merging existing datasets has become a…

Mechanistic Interpretability (MI) has emerged as a vital approach to demystify the opaque decision-making of Large Language Models (LLMs). However, existing reviews primarily treat MI as an observational science, summarizing analytical…

Recent advancements in large language models (LLMs) have resulted in increasingly anthropomorphic language concerning the ability of LLMs to reason. Whether reasoning in LLMs should be understood to be inherently different is, however,…

Current efficient fine-tuning methods (e.g., adapters, prefix-tuning, etc.) have optimized conditional text generation via training a small set of extra parameters of the neural language model, while freezing the rest for efficiency. While…

This paper presents a guided tour of some specific problems encountered in the stability analysis of linear dynamical systems including delays in their systems' representation. More precisely, we will address the characterization of…

Large language models (LLMs) have significantly advanced dialogue systems and role-playing agents through their ability to generate human-like text. While prior studies have shown that LLMs can exhibit distinct and consistent personalities,…

This paper addresses the limitations of a single agent in task decomposition and collaboration during complex task execution, and proposes a multi-agent architecture for modular task decomposition and dynamic collaboration based on large…

Guiding unconditional diffusion models typically requires either retraining with conditional inputs or per-step gradient computations (e.g., classifier-based guidance), both of which incur substantial computational overhead. We present a…