Related papers: One-Level Prosodic Morphology
Large language models may encounter factual knowledge during pre-training yet fail to reliably use that knowledge after fine-tuning. Despite growing empirical evidence that MLP layers store factual associations and fine-tuning affects…
We present an integrated architecture for word-level and sentence-level processing in a unification-based paradigm. The core of the system is a CLP implementation of a unification engine for feature structures supporting relational values.…
As a cornerstone in language modeling, tokenization involves segmenting text inputs into pre-defined atomic units. Conventional statistical tokenizers often disrupt constituent boundaries within words, thereby corrupting semantic…
In this work, Yoshikawa's manipulability index is used to investigate reinforcement learning (RL) as a framework for morphology optimization in planar robotic manipulators. A 2R manipulator tracking a circular end-effector path is first…
This review is an extended version of the Seoul ICM 2014 proceedings.It is a short overview of the "topological recursion", a relation appearing in the asymptotic expansion of many integrable systems and in enumerative problems. We recall…
Spatial functional organization is a hallmark of biological brains: neurons are arranged topographically according to their response properties, at multiple scales. In contrast, representations within most machine learning models lack…
We present a novel metric for the evaluation of the morphological plausibility of subword segmentation. Unlike the typically used morpheme boundary or retrieval F-score, which requires gold segmentation data that is either unavailable or of…
Multimodal Language Analysis is a demanding area of research, since it is associated with two requirements: combining different modalities and capturing temporal information. During the last years, several works have been proposed in the…
Modal logics have proved useful for many reasoning tasks in symbolic artificial intelligence (AI), such as belief revision, spatial reasoning, among others. On the other hand, mathematical morphology (MM) is a theory for non-linear analysis…
Large language models have exhibited intriguing in-context learning capability, achieving promising zero- and few-shot performance without updating the parameters. However, conventional in-context learning is usually restricted by length…
Post-training methods, especially Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL), play an important role in improving large language models' (LLMs) complex reasoning abilities. However, the dominant two-stage pipeline (SFT…
This paper investigates the inverse capabilities and broader utility of multimodal latent spaces within task-specific AI (Artificial Intelligence) models. While these models excel at their designed forward tasks (e.g., text-to-image…
Federated learning and analytics are often described as collections of separate protocols, even when they share the same mathematical form: client-local tensor computation, mergeable aggregation into shared state, and shared-only…
A major drawback of reasoning models is their excessive token usage, inflating computational cost, resource demand, and latency. We show this verbosity stems not from deeper reasoning but from reinforcement learning loss minimization when…
Text-driven image style transfer has seen remarkable progress with methods leveraging cross-modal embeddings for fast, high-quality stylization. However, most existing pipelines assume a \emph{single} textual style prompt, limiting the…
Vision-language models (VLMs) have made significant progress in image classification by training with large-scale paired image-text data. Their performances largely depend on the prompt quality. While recent methods show that visual…
How do typological properties such as word order and morphological case marking affect the ability of neural sequence models to acquire the syntax of a language? Cross-linguistic comparisons of RNNs' syntactic performance (e.g., on…
Abstraction is key to scaling up reinforcement learning (RL). However, autonomously learning abstract state and action representations to enable transfer and generalization remains a challenging open problem. This paper presents a novel…
In English, prosody adds a broad range of information to segment sequences, from information structure (e.g. contrast) to stylistic variation (e.g. expression of emotion). However, when learning to control prosody in text-to-speech voices,…
Pretrained vision-language models (VLMs), such as CLIP, achieve remarkable zero-shot performance, yet their downstream potential hinges on effective fine-tuning. Most adaptation methods typically focus on refining representation from…