相关论文: NeuroLogic A*esque Decoding: Constrained Text Gene…

This paper proposes a structure-aware decoding method based on large language models to address the difficulty of traditional approaches in maintaining both semantic integrity and structural consistency in nested and overlapping entity…

This paper introduces MeLA, a Metacognitive LLM-Driven Architecture that presents a new paradigm for Automatic Heuristic Design (AHD). Traditional evolutionary methods operate directly on heuristic code; in contrast, MeLA evolves the…

The obvious way to use several admissible heuristics in A* is to take their maximum. In this paper we aim to reduce the time spent on computing heuristics. We discuss Lazy A*, a variant of A* where heuristics are evaluated lazily: only when…

Advancements in text-to-image generative AI with large multimodal models are spreading into the field of image compression, creating high-quality representation of images at extremely low bit rates. This work introduces novel components to…

Retrieval-Augmented Generation (RAG) has significantly enhanced Large Language Models' ability to access external knowledge, yet current graph-based RAG approaches face two critical limitations in managing hierarchical information: they…

While most research on controllable text generation has focused on steering base Language Models, the emerging instruction-tuning and prompting paradigm offers an alternate approach to controllability. We compile and release ConGenBench, a…

Graph Retrieval-Augmented Generation (GraphRAG) enhances factual reasoning in LLMs by structurally modeling knowledge through graph-based representations. However, existing GraphRAG approaches face two core limitations: shallow retrieval…

In unstructured environments like parking lots or construction sites, due to the large search-space and kinodynamic constraints of the vehicle, it is challenging to achieve real-time planning. Several state-of-the-art planners utilize…

Knowledge-intensive language tasks require NLP systems to both provide the correct answer and retrieve supporting evidence for it in a given corpus. Autoregressive language models are emerging as the de-facto standard for generating…

This paper addresses two limitations of large language models (LLMs) in solving complex problems: (1) their reasoning processes exhibit Bayesian-like stochastic generation, where each token is sampled from a context-dependent probability…

The A* algorithm is a graph search algorithm which has shown good results in terms of computational complexity for Maximum Likelihood (ML) decoding of tailbiting convolutional codes. The decoding of tailbiting codes with this algorithm is…

Autoregressive modeling has been a huge success in the field of natural language processing (NLP). Recently, autoregressive models have emerged as a significant area of focus in computer vision, where they excel in producing high-quality…

The Neural Contextual Reinforcement Framework introduces an innovative approach to enhancing the logical coherence and structural consistency of text generated by large language models. Leveraging reinforcement learning principles, the…

Text generation under constraints have seen increasing interests in natural language processing, especially with the rapidly improving capabilities of large language models. However, existing benchmarks for constrained generation usually…

The active efficient coding (AEC) framework parsimoniously explains the joint development of visual processing and eye movements, e.g., the emergence of binocular disparity selective neurons and fusional vergence, the disjunctive eye…

This paper presents Loops On Retrieval Augmented Generation (LoRAG), a new framework designed to enhance the quality of retrieval-augmented text generation through the incorporation of an iterative loop mechanism. The architecture…

The rapid advancement of AI-based music generation tools is revolutionizing the music industry but also posing challenges to artists, copyright holders, and providers alike. This necessitates reliable methods for detecting such AI-generated…

Computational Design approaches facilitate the generation of typographic design, but evaluating these designs remains a challenging task. In this paper, we propose a set of heuristic metrics for typographic design evaluation, focusing on…

Diffusion-based large language models offer a non-autoregressive alternative for text generation, but enabling them to perform complex reasoning remains challenging. Reinforcement learning has recently emerged as an effective post-training…

Developing the logic necessary to solve mathematical problems or write mathematical proofs is one of the more difficult objectives for large language models (LLMS). Currently, the most popular methods in literature consists of fine-tuning…