Search Results for author:
Found 23 papers, 9 papers with code
LoRS: Efficient Low-Rank Adaptation for Sparse Large Language Model
Existing low-rank adaptation (LoRA) methods face challenges on sparse large language models (LLMs) due to the inability to maintain sparsity.
SLAM-Omni: Timbre-Controllable Voice Interaction System with Single-Stage Training
Recent advancements highlight the potential of end-to-end real-time spoken dialogue systems, showcasing their low latency and high quality.
Interleaved Speech-Text Language Models are Simple Streaming Text to Speech Synthesizers
This paper introduces Interleaved Speech-Text Language Model (IST-LM) for streaming zero-shot Text-to-Speech (TTS).
AlignFormer: Modality Matching Can Achieve Better Zero-shot Instruction-Following Speech-LLM
The AlignFormer can achieve a near 100% IFR with audio-first training and game-changing improvements from zero to non-zero IFR on some evaluation data with instruction-first training.
SAM Decoding: Speculative Decoding via Suffix Automaton
Speculative decoding (SD) has been demonstrated as an effective technique for lossless LLM inference acceleration.
P$^2$ Law: Scaling Law for Post-Training After Model Pruning
Pruning has become a widely adopted technique for reducing the hardware requirements of large language models (LLMs).
Learning to Generalize Unseen Domains via Multi-Source Meta Learning for Text Classification
In this paper, we study the multi-source Domain Generalization of text classification and propose a framework to use multiple seen domains to train a model that can achieve high accuracy in an unseen domain.
APTNESS: Incorporating Appraisal Theory and Emotion Support Strategies for Empathetic Response Generation
By incorporating emotional support strategies, we aim to enrich the model's capabilities in both cognitive and affective empathy, leading to a more nuanced and comprehensive empathetic response.
Balancing Information Perception with Yin-Yang: Agent-Based Information Neutrality Model for Recommendation Systems
While preference-based recommendation algorithms effectively enhance user engagement by recommending personalized content, they often result in the creation of ``filter bubbles''.
Streamlining Redundant Layers to Compress Large Language Models
This paper introduces LLM-Streamline, a pioneer work on layer pruning for large language models (LLMs).
LMDrive: Closed-Loop End-to-End Driving with Large Language Models
On the other hand, previous autonomous driving methods tend to rely on limited-format inputs (e. g. sensor data and navigation waypoints), restricting the vehicle's ability to understand language information and interact with humans.
$\rm SP^3$: Enhancing Structured Pruning via PCA Projection
Structured pruning is a widely used technique for reducing the size of pre-trained language models (PLMs), but current methods often overlook the potential of compressing the hidden dimension (d) in PLMs, a dimension critical to model size and efficiency.
Informative Scene Graph Generation via Debiasing
It integrates two components: Semantic Debiasing (SD) and Balanced Predicate Learning (BPL), for these imbalances.
Adapting Large Language Model with Speech for Fully Formatted End-to-End Speech Recognition
Most end-to-end (E2E) speech recognition models are composed of encoder and decoder blocks that perform acoustic and language modeling functions.
BHEISR: Nudging from Bias to Balance -- Promoting Belief Harmony by Eliminating Ideological Segregation in Knowledge-based Recommendations
This approach endeavors to transcend the constraints of the filter bubble, enrich recommendation diversity, and strike a belief balance among users while also catering to user preferences and system-specific business requirements.
A dynamic risk score for early prediction of cardiogenic shock using machine learning
We developed a deep learning-based risk stratification tool, called CShock, for patients admitted into the cardiac ICU with acute decompensated heart failure and/or myocardial infarction to predict onset of cardiogenic shock.
Code-Switching Text Generation and Injection in Mandarin-English ASR
Code-switching speech refers to a means of expression by mixing two or more languages within a single utterance.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Building High-accuracy Multilingual ASR with Gated Language Experts and Curriculum Training
We propose gated language experts and curriculum training to enhance multilingual transformer transducer models without requiring language identification (LID) input from users during inference.
The feasibility of Q-band millimeter wave on hand-gesture recognition for indoor FTTR scenario
The generalization for different scenarios and dif-ferent users is an urgent problem for millimeter wave gesture recognition for indoor fiber-to-the-room (FTTR) scenario.
From General to Specific: Informative Scene Graph Generation via Balance Adjustment
The scene graph generation (SGG) task aims to detect visual relationship triplets, i. e., subject, predicate, object, in an image, providing a structural vision layout for scene understanding.
ABEM: An Adaptive Agent-based Evolutionary Approach for Mining Influencers in Online Social Networks
A key step in influence maximization in online social networks is the identification of a small number of users, known as influencers, who are able to spread influence quickly and widely to other users.
Improving Transformer-based Speech Recognition Using Unsupervised Pre-training
Speech recognition technologies are gaining enormous popularity in various industrial applications.
Adversarial Examples for Electrocardiograms
For this model, we utilized a new technique to generate smoothed examples to produce signals that are 1) indistinguishable to cardiologists from the original examples and 2) incorrectly classified by the neural network.
