Search Results for author:
Found 30 papers, 9 papers with code
How does BERT process disfluency?
Analysis on sentence embeddings of disfluent and fluent sentence pairs reveals that the deeper the layer, the more similar their representation (exp2).
Cross-Lingual Transfer with MAML on Trees
In meta-learning, the knowledge learned from previous tasks is transferred to new ones, but this transfer only works if tasks are related.
Cross-Lingual Natural Language Inference
Cross-Lingual Transfer
+1
Bayesian Optimization from Human Feedback: Near-Optimal Regret Bounds
Existing work, which adopts the Bradley-Terry-Luce (BTL) feedback model, provides regret bounds for the performance of several algorithms.
Towards a Foundation Model for Communication Systems
Artificial Intelligence (AI) has demonstrated unprecedented performance across various domains, and its application to communication systems is an active area of research.
Latent Flow Transformer
Transformers, the standard implementation for large language models (LLMs), typically consist of tens to hundreds of discrete layers.
Group Think: Multiple Concurrent Reasoning Agents Collaborating at Token Level Granularity
Recent advances in large language models (LLMs) have demonstrated the power of reasoning through self-generated chains of thought.
TASTE: Text-Aligned Speech Tokenization and Embedding for Spoken Language Modeling
To our knowledge, TASTE is the first end-to-end approach that utilizes a reconstruction objective to automatically learn a text-aligned speech tokenization and embedding suitable for spoken language modeling.
BreezyVoice: Adapting TTS for Taiwanese Mandarin with Enhanced Polyphone Disambiguation -- Challenges and Insights
We present BreezyVoice, a Text-to-Speech (TTS) system specifically adapted for Taiwanese Mandarin, highlighting phonetic control abilities to address the unique challenges of polyphone disambiguation in the language.
The Breeze 2 Herd of Models: Traditional Chinese LLMs Based on Llama with Vision-Aware and Function-Calling Capabilities
In addition to language modeling capabilities, we significantly augment the models with function calling and vision understanding capabilities.
Enhancing Function-Calling Capabilities in LLMs: Strategies for Prompt Formats, Data Integration, and Multilingual Translation
This research delves into enhancing the function-calling capabilities of LLMs by exploring different approaches, including prompt formats for integrating function descriptions, blending function-calling and instruction-following data, introducing a novel Decision Token for conditional prompts, leveraging chain-of-thought reasoning, and overcoming multilingual challenges with a translation pipeline.
FineWeb-zhtw: Scalable Curation of Traditional Chinese Text Data from the Web
The quality and size of a pretraining dataset significantly influence the performance of large language models (LLMs).
Exact, Tractable Gauss-Newton Optimization in Deep Reversible Architectures Reveal Poor Generalization
We exploit this novel setting to study the training and generalization properties of the GN optimizer.
RAD-Bench: Evaluating Large Language Models Capabilities in Retrieval Augmented Dialogues
In real-world applications with Large Language Models (LLMs), external retrieval mechanisms - such as Search-Augmented Generation (SAG), tool utilization, and Retrieval-Augmented Generation (RAG) - are often employed to enhance the quality of augmented generations in dialogues.
Let's Fuse Step by Step: A Generative Fusion Decoding Algorithm with LLMs for Multi-modal Text Recognition
We introduce "Generative Fusion Decoding" (GFD), a novel shallow fusion framework, utilized to integrate Large Language Models (LLMs) into multi-modal text recognition systems such as automatic speech recognition (ASR) and optical character recognition (OCR).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Breeze-7B Technical Report
Breeze-7B is an open-source language model based on Mistral-7B, designed to address the need for improved language comprehension and chatbot-oriented capabilities in Traditional Chinese.
Advancing the Evaluation of Traditional Chinese Language Models: Towards a Comprehensive Benchmark Suite
In an effort to advance the evaluation of language models in Traditional Chinese and stimulate further research in this field, we have open-sourced our benchmark and opened the model for trial.
Generative Diffusion Models for Radio Wireless Channel Modelling and Sampling
In this paper, we propose a diffusion model based channel sampling approach for rapidly synthesizing channel realizations from limited data.
Zero-shot Domain-sensitive Speech Recognition with Prompt-conditioning Fine-tuning
In this work, we propose a method to create domain-sensitive speech recognition models that utilize textual domain information by conditioning its generation on a given text prompt.
Image generation with shortest path diffusion
We compute the shortest path according to this metric, and we show that it corresponds to a combination of image sharpening, rather than blurring, and noise deblurring.
Extending the Pre-Training of BLOOM for Improved Support of Traditional Chinese: Models, Methods and Results
In this paper we present the multilingual language model BLOOM-zh that features enhanced support for Traditional Chinese.
Flexible Multiple-Objective Reinforcement Learning for Chip Placement
Recently, successful applications of reinforcement learning to chip placement have emerged.
Improved Convergence Rates for Sparse Approximation Methods in Kernel-Based Learning
Kernel-based models such as kernel ridge regression and Gaussian processes are ubiquitous in machine learning applications for regression and optimization.
Uniform Generalization Bounds for Overparameterized Neural Networks
As a byproduct of our results, we show the equivalence between the RKHS corresponding to the NT kernel and its counterpart corresponding to the Mat\'ern family of kernels, showing the NT kernels induce a very general class of models.
Optimal Order Simple Regret for Gaussian Process Bandits
Consider the sequential optimization of a continuous, possibly non-convex, and expensive to evaluate objective function $f$.
Towards a Universal NLG for Dialogue Systems and Simulators with Future Bridging
In light of the recent success of data-driven approaches, we propose the novel future bridging NLG (FBNLG) concept for dialogue systems and simulators.
How to distribute data across tasks for meta-learning?
We show that: 1) If tasks are homogeneous, there is a uniform optimal allocation, whereby all tasks get the same amount of data; 2) At fixed budget, there is a trade-off between number of tasks and number of data points per task, with a unique solution for the optimum; 3) When trained separately, harder task should get more data, at the cost of a smaller number of tasks; 4) When training on a mixture of easy and hard tasks, more data should be allocated to easy tasks.
Meta-Learning with MAML on Trees
We show that TreeMAML improves the state of the art results for cross-lingual Natural Language Inference.
Cross-Lingual Natural Language Inference
Cross-Lingual Transfer
+2
Model agnostic meta-learning on trees
In meta-learning, the knowledge learned from previous tasks is transferred to new ones, but this transfer only works if tasks are related, and sharing information between unrelated tasks might hurt performance.
Optimal allocation of data across training tasks in meta-learning
They are tested on benchmarks with a fixed number of data-points for each training task, and this number is usually arbitrary, for example, 5 instances per class in few-shot classification.
Cyclic orthogonal convolutions for long-range integration of features
We propose a novel architecture that allows flexible information flow between features $z$ and locations $(x, y)$ across the entire image with a small number of layers.
