Related papers: EvoEdit: Evolving Null-space Alignment for Robust …

Large language models (LLMs) have made impressive progress in natural language processing. These models rely on proper human instructions (or prompts) to generate suitable responses. However, the potential of LLMs are not fully harnessed by…

Model editing aims to correct outdated or erroneous knowledge in large language models (LLMs) without the need for costly retraining. Lifelong model editing is the most challenging task that caters to the continuous editing requirements of…

Large language models (LLMs) exhibit remarkable capabilities across diverse tasks, yet aligning them efficiently and effectively with human expectations remains a critical challenge. This thesis advances LLM alignment by introducing novel…

Knowledge editing is a technique for efficiently and accurately updating the knowledge of large language models (LLMs) to alleviate obsolescence and correct errors. However, most existing methods overfit to specific models, causing edited…

While large language models (LLMs) excel at static scientific reasoning, they struggle to model the temporal structure of dynamic physical processes. We present EvoMD-LLM (Evolutionary Molecular Dynamics Large Language Model), a framework…

In-context knowledge editing (IKE) enables efficient modification of large language model (LLM) outputs without parameter changes and at zero-cost. However, it can be misused to manipulate responses opaquely, e.g., insert misinformation or…

Large Language Models (LLMs) have significantly advanced natural language processing, demonstrating strong capabilities in tasks such as text generation, summarization, and reasoning. Recently, their potential for automating precise text…

Neural language models (LMs) have been extensively trained on vast corpora to store factual knowledge about various aspects of the world described in texts. Current technologies typically employ knowledge editing methods or specific prompts…

We introduce EvoLib, a test-time learning framework that enables large language models to accumulate, reuse, and evolve knowledge across problem instances without parameter updates or external supervision. Instead of adapting model…

Knowledge Editing (KE) aims to adjust a Large Language Model's (LLM) internal representations and parameters to correct inaccuracies and improve output consistency without incurring the computational expense of re-training the entire model.…

Large language models (LLMs) require constant updates to remain aligned with evolving real-world knowledge. Model editing offers a lightweight alternative to retraining, but sequential editing often destabilizes representations and induces…

Knowledge editing has become a promising approach for efficiently and precisely updating knowledge embedded in large language models (LLMs). In this work, we focus on Same-Subject Editing, which involves modifying multiple attributes of a…

Speculative decoding accelerates Large Language Model inference via a draft-then-verify paradigm, yet the output projection layer becomes a bottleneck as vocabulary sizes scale. While existing static pruning methods effectively reduce this…

Lip synchronization and audio-visual editing have emerged as fundamental challenges in multimodal learning, underpinning a wide range of applications, including film production, virtual avatars, and telepresence. Despite recent progress,…

Robot imitation learning relies on 4D multi-view sequential images. However, the high cost of data collection and the scarcity of high-quality data severely constrain the generalization and application of embodied intelligence policies like…

Most real-world image editing tasks require multiple sequential edits to achieve desired results. Current editing approaches, primarily designed for single-object modifications, struggle with sequential editing: especially with maintaining…

Text-guided image editing, a pivotal task in modern multimedia content creation, has seen remarkable progress with training-free methods that eliminate the need for additional optimization. Despite recent progress, existing methods are…

As large language models (LLMs) are trained on massive datasets, they have raised significant privacy and ethical concerns due to their potential to inadvertently retain sensitive information. Unlearning seeks to selectively remove specific…

Diffusion models have significantly improved text-to-image generation, producing high-quality, realistic images from textual descriptions. Beyond generation, object-level image editing remains a challenging problem, requiring precise…

The discovery of symbolic solutions -- mathematical expressions, logical rules, and algorithmic structures -- is fundamental to advancing scientific and engineering progress. However, traditional methods often struggle with search…