Related papers: PuzLM: Solving Jigsaw Puzzles with Sequence-to-Seq…

The advent of large language models (LLMs) has dramatically advanced the state-of-the-art in numerous natural language generation tasks. For LLMs to be applied reliably, it is essential to have an accurate measure of their confidence.…

Large language models (LLMs) have demonstrated potential in reasoning tasks, but their performance on linguistics puzzles remains consistently poor. These puzzles, often derived from Linguistics Olympiad (LO) contests, provide a minimal…

The puzzle method was introduced by Choi and Park as an effective method for finding non-singular characteristic maps over wedged simplicial complexes $K(J)$ obtained from a given simplicial complex $K$. We study further the mod 2 case of…

Algorithmic reasoning is a fundamental cognitive ability that plays a pivotal role in problem-solving and decision-making processes. Reinforcement Learning (RL) has demonstrated remarkable proficiency in tasks such as motor control,…

We present Pix2Seq, a simple and generic framework for object detection. Unlike existing approaches that explicitly integrate prior knowledge about the task, we cast object detection as a language modeling task conditioned on the observed…

With the evolution of large language models (LLMs), there is growing interest in leveraging their rich semantic understanding to enhance industrial recommendation systems (RecSys). Traditional RecSys relies on ID-based embeddings for user…

We present MeshLLM, a novel framework that leverages large language models (LLMs) to understand and generate text-serialized 3D meshes. Our approach addresses key limitations in existing methods, including the limited dataset scale when…

Recently, large language models (LLMs) have shown surprising performance in task-specific workloads as well as general tasks with the given prompts. However, to achieve unprecedented performance, recent LLMs use billions to trillions of…

Many recent prompting strategies for large language models (LLMs) query the model multiple times sequentially -- first to produce intermediate results and then the final answer. However, using these methods, both decoder and model are…

Recovering Computer-Aided Design (CAD) programs from 3D geometries is a widely studied problem. Recent advances in large language models (LLMs) have enabled progress in CAD program synthesis, but existing methods rely on supervised training…

The unsupervised visual inspection of defects in industrial products poses a significant challenge due to substantial variations in product surfaces. Current unsupervised models struggle to strike a balance between detecting texture and…

Reinforcement learning based post-training has recently emerged as a powerful paradigm for enhancing the alignment and reasoning capabilities of multimodal large language models (MLLMs). While vision-centric post-training is crucial for…

Post-training quantization (PTQ) is an effective technique for compressing large language models (LLMs). However, while uniform-precision quantization is computationally efficient, it often compromises model performance. To address this, we…

Text-to-SQL is a pivotal task that bridges natural language understanding and structured data access, yet it remains fundamentally challenging due to semantic ambiguity and complex compositional reasoning. While large language models (LLMs)…

This paper introduces the first deep neural network-based estimation metric for the jigsaw puzzle problem. Given two puzzle piece edges, the neural network predicts whether or not they should be adjacent in the correct assembly of the…

Autoformalization, which translates natural language mathematics into machine-verifiable formal statements, is critical for using formal mathematical reasoning to solve math problems stated in natural language. While Large Language Models…

We introduce a novel visual tokenization framework that embeds a provable PCA-like structure into the latent token space. While existing visual tokenizers primarily optimize for reconstruction fidelity, they often neglect the structural…

Continual Semantic Parsing (CSP) aims to train parsers to convert natural language questions into SQL across tasks with limited annotated examples, adapting to the real-world scenario of dynamically updated databases. Previous studies…

Huge numbers of new words emerge every day, leading to a great need for representing them with semantic meaning that is understandable to NLP systems. Sememes are defined as the minimum semantic units of human languages, the combination of…

The use of children's drawings to examining their conceptual understanding has been proven to be an effective method, but there are two major problems with previous research: 1. The content of the drawings heavily relies on the task, and…