Related papers: Dynamik: Syntactically-Driven Dynamic Font Sizing …
The analysis of events in dynamic environments poses a fundamental challenge in the development of intelligent agents and robots capable of interacting with humans. Current approaches predominantly utilize visual models. However, these…
While Large Language Models (LLMs) have emerged with remarkable capabilities in complex tasks through Chain-of-Thought reasoning, practical resource constraints have sparked interest in transferring these abilities to smaller models.…
The goal of automatic dubbing is to perform speech-to-speech translation while achieving audiovisual coherence. This entails isochrony, i.e., translating the original speech by also matching its prosodic structure into phrases and pauses,…
Widespread digital learning has expanded access to education but has resulted in highly sedentary, click-based interaction, contributing to digital fatigue, reduced cognitive flexibility, and health risks associated with prolonged passive…
Why should computers interpret language incrementally? In recent years psycholinguistic evidence for incremental interpretation has become more and more compelling, suggesting that humans perform semantic interpretation before constituent…
Deep learning-based speech enhancement (SE) models have recently outperformed traditional techniques, yet their deployment on resource-constrained devices remains challenging due to high computational and memory demands. This paper…
Diffusion-based large language models (dLLMs) have emerged as a promising paradigm, utilizing simultaneous denoising to enable global planning and iterative refinement. While these capabilities are particularly advantageous for long-context…
Soft context compression reduces the computational workload of processing long contexts in LLMs by encoding long context into a smaller number of latent tokens. However, existing frameworks apply uniform compression ratios, failing to…
Recent multimodal models such as Contrastive Language-Image Pre-training (CLIP) have shown remarkable ability to align visual and linguistic representations. However, domains where small visual differences carry large semantic significance,…
Supervised fine-tuning with synthesized instructions has been a common practice for adapting LLMs to domain-specific QA tasks. However, the synthesized instructions deviate from real user questions and expected answers. This study proposes…
Inspired by the inductive transfer learning on computer vision, many efforts have been made to train contextualized language models that boost the performance of natural language processing tasks. These models are mostly trained on large…
Scientific documents often contain a large number of acronyms. Disambiguation of these acronyms will help researchers better understand the meaning of vocabulary in the documents. In the past, thanks to large amounts of data from English…
We introduce Dynamic Information Sub-Selection (DISS), a novel framework of AI assistance designed to enhance the performance of black-box decision-makers by tailoring their information processing on a per-instance basis. Blackbox…
Semantic web is the next generation web, which concerns the meaning of web documents It has the immense power to pull out the most relevant information from the web pages, which is also meaningful to any user, using software agents. In…
Speculative decoding accelerates LLM inference by letting a small drafter propose multiple tokens which a large target model verifies once per speculation step. As vocabularies scale past 10e5 tokens,verification cost in the target model is…
Queries to large language models (LLMs) can be divided into two parts: the instruction/question and the accompanying context. The context for retrieval-augmented generation (RAG) systems in most benchmarks comes from Wikipedia or…
Some methods of automatic simultaneous translation of a long-form speech allow revisions of outputs, trading accuracy for low latency. Deploying these systems for users faces the problem of presenting subtitles in a limited space, such as…
This paper introduces a novel approach to Visual Forced Alignment (VFA), aiming to accurately synchronize utterances with corresponding lip movements, without relying on audio cues. We propose a novel VFA approach that integrates a local…
Large language models encode impressively broad world knowledge in their parameters. However, the knowledge in static language models falls out of date, limiting the model's effective "shelf life." While online fine-tuning can reduce this…
Maintaining information in context is essential in successful real-time language comprehension, but maintenance is cognitively costly and can slow processing. We hypothesize that rational language users selectively maintain information that…