Related papers: Disentangling Reasoning Capabilities from Language…

Retrieval-Augmented Generation (RAG) systems are increasingly diverse, yet many suffer from monolithic designs that tightly couple core functions like query reformulation, retrieval, reasoning, and verification. This limits their…

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…

Logical frameworks and meta-languages form a common substrate for representing, implementing and reasoning about a wide variety of deductive systems of interest in logic and computer science. Their design, implementation and their use in…

The ability to learn and compose functions is foundational to efficient learning and reasoning in humans, enabling flexible generalizations such as creating new dishes from known cooking processes. Beyond sequential chaining of functions,…

With the powerful reasoning capabilities of large language models (LLMs) and vision-language models (VLMs), many recent works have explored using them for decision-making. However, most of these approaches rely solely on language-based…

Large Language Models (LLMs) are central to reasoning, writing, and decision-support workflows, yet users lack consistent control over how they reason and express outputs. Conventional prompt engineering relies on verbose natural-language…

In recent years, large pretrained models have been used in dialogue systems to improve successful task completion rates. However, lack of reasoning capabilities of dialogue platforms make it difficult to provide relevant and fluent…

Group Activity Recognition detects the activity collectively performed by a group of actors, which requires compositional reasoning of actors and objects. We approach the task by modeling the video as tokens that represent the multi-scale…

We present PartComposer: a framework for part-level concept learning from single-image examples that enables text-to-image diffusion models to compose novel objects from meaningful components. Existing methods either struggle with…

Large language models make remarkable progress in reasoning capabilities. Existing works focus mainly on deductive reasoning tasks (e.g., code and math), while another type of reasoning mode that better aligns with human learning, inductive…

The birth of Foundation Models brought unprecedented results in a wide range of tasks, from language to vision, to robotic control. These models are able to process huge quantities of data, and can extract and develop rich representations,…

We propose Neural Reasoner, a framework for neural network-based reasoning over natural language sentences. Given a question, Neural Reasoner can infer over multiple supporting facts and find an answer to the question in specific forms.…

Inspired by e-participation systems, in this paper we propose a new model to represent human debates and methods to obtain collective conclusions from them. This model overcomes drawbacks of existing approaches by allowing users to…

Conventional works generally employ a two-phase model in which a generator selects the most important pieces, followed by a predictor that makes predictions based on the selected pieces. However, such a two-phase model may incur the…

Humans intuitively solve complex problems by flexibly shifting among reasoning modes: they plan, execute, revise intermediate goals, resolve ambiguity through associative judgment, and apply formal procedures to well-specified subproblems.…

Transformers demonstrate impressive performance on a range of reasoning benchmarks. To evaluate the degree to which these abilities are a result of actual reasoning, existing work has focused on developing sophisticated benchmarks for…

A hallmark of human intelligence is the ability to construct self-contained chunks of knowledge and adequately reuse them in novel combinations for solving different yet structurally related problems. Learning such compositional structures…

Large Language Models (LLMs) excel in complex reasoning tasks but struggle with consistent rule application, exception handling, and explainability, particularly in domains like legal analysis that require both natural language…

Recognizing elementary underlying concepts from observations (disentanglement) and generating novel combinations of these concepts (compositional generalization) are fundamental abilities for humans to support rapid knowledge learning and…

Recent advancements in language models have significantly enhanced performance in multiple speech-related tasks. Existing speech language models typically utilize task-dependent prompt tokens to unify various speech tasks in a single model.…