Related papers: Vector Space Morphology with Linear Discriminative…

We propose a novel structured discriminative block-diagonal dictionary learning method, referred to as scalable Locality-Constrained Projective Dictionary Learning (LC-PDL), for efficient representation and classification. To improve the…

Recent Multi-Modal Large Language Models (MLLMs) have demonstrated strong capabilities in learning joint representations from text and images. However, their spatial reasoning remains limited. We introduce 3DFroMLLM, a novel framework that…

Morphologically rich languages accentuate two properties of distributional vector space models: 1) the difficulty of inducing accurate representations for low-frequency word forms; and 2) insensitivity to distinct lexical relations that…

In this paper, we investigate how model distillation impacts the development of reasoning features in large language models (LLMs). To explore this, we train a crosscoder on Qwen-series models and their fine-tuned variants. Our results…

This paper introduces diffusion protein language model (DPLM), a versatile protein language model that demonstrates strong generative and predictive capabilities for protein sequences. We first pre-train scalable DPLMs from…

The concept of Label Distribution Learning (LDL) is a technique to stabilize classification and regression problems with ambiguous and/or imbalanced labels. A prototypical use-case of LDL is human age estimation based on profile images.…

Spatial reasoning is a fundamental aspect of human cognition, enabling intuitive understanding and manipulation of objects in three-dimensional space. While foundation models demonstrate remarkable performance on some benchmarks, they still…

We propose a segmental neural language model that combines the generalization power of neural networks with the ability to discover word-like units that are latent in unsegmented character sequences. In contrast to previous segmentation…

Diffusion models (DMs) have achieved state-of-the-art results for image synthesis tasks as well as density estimation. Applied in the latent space of a powerful pretrained autoencoder (LDM), their immense computational requirements can be…

Understanding the latent space geometry of large language models (LLMs) is key to interpreting their behavior and improving alignment. Yet it remains unclear to what extent LLMs linearly organize representations related to semantic…

Large language models (LLMs) have made significant advancements in natural language understanding. However, through that enormous semantic representation that the LLM has learnt, is it somehow possible for it to understand images as well?…

Supervised dictionary learning (SDL) is a classical machine learning method that simultaneously seeks feature extraction and classification tasks, which are not necessarily a priori aligned objectives. The goal of SDL is to learn a…

Based on its great successes in inference and denosing tasks, Dictionary Learning (DL) and its related sparse optimization formulations have garnered a lot of research interest. While most solutions have focused on single layer…

While Large Language Models (LLMs) excel at reasoning on text and Vision-Language Models (VLMs) are highly effective for visual perception, applying those models for visual instruction-based planning remains a widely open problem. In this…

Considering the challenges faced by large language models (LLMs) in logical reasoning and planning, prior efforts have sought to augment LLMs with access to external solvers. While progress has been made on simple reasoning problems,…

Large language models (LLMs) have demonstrated rapid progress across a wide array of domains. Owing to the very large number of parameters and training data in LLMs, these models inherently encompass an expansive and comprehensive materials…

Latent diffusion models offer an attractive alternative to discrete diffusion for non-autoregressive text generation by operating on continuous text representations and denoising entire sequences in parallel. The major challenge in latent…

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…

Large language models (LLMs) have demonstrated impressive capabilities across diverse tasks, yet their ability to perform structured symbolic planning remains limited, particularly in domains requiring formal representations like the…

Discovering the symbols and rules that can be used in long-horizon planning from a robot's unsupervised exploration of its environment and continuous sensorimotor experience is a challenging task. The previous studies proposed learning…