Search Results for author:
Found 53 papers, 18 papers with code
Diffusion-Driven Semantic Communication for Generative Models with Bandwidth Constraints
This paper introduces a diffusion-driven semantic communication framework with advanced VAE-based compression for bandwidth-constrained generative model.
Integrated Push-and-Pull Update Model for Goal-Oriented Effective Communication
This paper studies decision-making for goal-oriented effective communication.
Sequential Editing for Lifelong Training of Speech Recognition Models
Automatic Speech Recognition (ASR) traditionally assumes known domains, but adding data from a new domain raises concerns about computational inefficiencies linked to retraining models on both existing and new domains.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
DEM: Distribution Edited Model for Training with Mixed Data Distributions
Training with mixed data distributions is a common and important part of creating multi-task and instruction-following models.
Numeric Reward Machines
We compare our new approaches to a baseline reward machine in the Craft domain, where the numeric feature is the agent-to-target distance.
Semantic-Aware Remote Estimation of Multiple Markov Sources Under Constraints
This paper studies semantic-aware communication for remote estimation of multiple Markov sources over a lossy and rate-constrained channel.
Adaptive Federated Learning Over the Air
In contrast, an Adam-like algorithm converges at the $\mathcal{O}( 1/T )$ rate, demonstrating its advantage in expediting the model training process.
MAGID: An Automated Pipeline for Generating Synthetic Multi-modal Datasets
Development of multimodal interactive systems is hindered by the lack of rich, multimodal (text, images) conversational data, which is needed in large quantities for LLMs.
Eliciting Better Multilingual Structured Reasoning from LLMs through Code
xSTREET exposes a gap in base LLM performance between English and non-English reasoning tasks.
Semantic Text Transmission via Prediction with Small Language Models: Cost-Similarity Trade-off
We obtain $(\bar{c}, \bar{s})$ pairs for neural language and first-order Markov chain-based small language models (SLM) for prediction, using both a threshold policy that transmits a word if its cosine similarity with that predicted/completed at the destination is below a threshold, and a periodic policy, which transmits words after a specific interval and predicts/completes the words in between, at the destination.
Version age-based client scheduling policy for federated learning
Motivated by this, we introduce the novel concept of Version Age of Information (VAoI) to FL.
DeAL: Decoding-time Alignment for Large Language Models
Current work focuses on alignment at model training time, through techniques such as Reinforcement Learning with Human Feedback (RLHF).
Goal-Oriented Communication, Estimation, and Control over Bidirectional Wireless Links
This status information, such as dynamic plant state and Markov Process-based context information, is then received/estimated by the controller for remote control.
Value of Information and Timing-aware Scheduling for Federated Learning
Federated Learning (FL) offers a solution by preserving data privacy during training.
Goal-oriented Estimation of Multiple Markov Sources in Resource-constrained Systems
The destination is tasked with source reconstruction for actuation.
Analysis of Age of Information in Non-terrestrial Networks
Our work fills a gap in the literature by providing a comprehensive analysis of AoI in NTN and offers new insights into the performance of LEO satellite networks.
Experimental Study of Transport Layer Protocols for Wireless Networked Control Systems
In contrast, in WNCSs, the efficiency of the network is measured by its ability to facilitate control applications, and the data transmission rate should be limited to avoid network congestion.
Measuring and Mitigating Constraint Violations of In-Context Learning for Utterance-to-API Semantic Parsing
In executable task-oriented semantic parsing, the system aims to translate users' utterances in natural language to machine-interpretable programs (API calls) that can be executed according to pre-defined API specifications.
Pre-training Intent-Aware Encoders for Zero- and Few-Shot Intent Classification
Intent classification (IC) plays an important role in task-oriented dialogue systems.
Conversation Style Transfer using Few-Shot Learning
Conventional text style transfer approaches focus on sentence-level style transfer without considering contextual information, and the style is described with attributes (e. g., formality).
Backward Compatibility During Data Updates by Weight Interpolation
This method interpolates between the weights of the old and new model and we show in extensive experiments that it reduces negative flips without sacrificing the improved accuracy of the new model.
Dialog2API: Task-Oriented Dialogue with API Description and Example Programs
The conversational model interacts with the environment by generating and executing programs triggering a set of pre-defined APIs.
Goal-Oriented Semantic Communications for 6G Networks
In this article, we propose a generic goal-oriented semantic communication framework for various tasks with diverse data types, which incorporates both semantic level information and effectiveness-aware performance metrics.
Modeling Context With Linear Attention for Scalable Document-Level Translation
Document-level machine translation leverages inter-sentence dependencies to produce more coherent and consistent translations.
On-Demand AoI Minimization in Resource-Constrained Cache-Enabled IoT Networks with Energy Harvesting Sensors
We consider a resource-constrained IoT network, where multiple users make on-demand requests to a cache-enabled edge node to send status updates about various random processes, each monitored by an energy harvesting sensor.
ABC: Attention with Bounded-memory Control
One way to improve the efficiency is to bound the memory size.
Finetuning Pretrained Transformers into RNNs
Specifically, we propose a swap-then-finetune procedure: in an off-the-shelf pretrained transformer, we replace the softmax attention with its linear-complexity recurrent alternative and then finetune.
Ranked #2 on
Machine Translation
on WMT2017 Chinese-English
Random Feature Attention
RFA can be used as a drop-in replacement for conventional softmax attention and offers a straightforward way of learning with recency bias through an optional gating mechanism.
Ranked #27 on
Machine Translation
on IWSLT2014 German-English
Autonomous Maintenance in IoT Networks via AoI-driven Deep Reinforcement Learning
Internet of Things (IoT) with its growing number of deployed devices and applications raises significant challenges for network maintenance procedures.
Robot Trajectory Planning With QoS Constrained IRS-assisted Millimeter-Wave Communications
We present a solution to the optimization problem that exploits mm-wave channel characteristics to decouple beamforming and trajectory optimizations.
Trajectory Planning
Networking and Internet Architecture
Plug and Play Autoencoders for Conditional Text Generation
Text autoencoders are commonly used for conditional generation tasks such as style transfer.
Multilevel Text Alignment with Cross-Document Attention
Text alignment finds application in tasks such as citation recommendation and plagiarism detection.
Grounded Compositional Outputs for Adaptive Language Modeling
To our knowledge, the result is the first word-level language model with a size that does not depend on the training vocabulary.
Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention
Transformers achieve remarkable performance in several tasks but due to their quadratic complexity, with respect to the input's length, they are prohibitively slow for very long sequences.
Ranked #5 on
Offline RL
on D4RL
Deep Encoder, Shallow Decoder: Reevaluating Non-autoregressive Machine Translation
We show that the speed disadvantage for autoregressive baselines compared to non-autoregressive methods has been overestimated in three aspects: suboptimal layer allocation, insufficient speed measurement, and lack of knowledge distillation.
Learning-Based Link Scheduling in Millimeter-wave Multi-connectivity Scenarios
Multi-connectivity is emerging as a promising solution to provide reliable communications and seamless connectivity for the millimeter-wave frequency range.
Optimizing Information Freshness in a Multiple Access Channel with Heterogeneous Devices
We formulate an optimization problem that aims at minimizing the average age of information (AoI) of the EH node subject to the queue stability condition of the grid-connected node.
Information Theory Networking and Internet Architecture Information Theory
Regularization Advantages of Multilingual Neural Language Models for Low Resource Domains
In this study, we propose a multilingual neural language model architecture, trained jointly on the domain-specific data of several low-resource languages.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
Deep Residual Output Layers for Neural Language Generation
Many tasks, including language generation, benefit from learning the structure of the output space, particularly when the space of output labels is large and the data is sparse.
Ranked #12 on
Language Modelling
on Penn Treebank (Word Level)
Integrating Weakly Supervised Word Sense Disambiguation into Neural Machine Translation
We show that the concatenation of these vectors, and the use of a sense selection mechanism based on the weighted average of sense vectors, outperforms several baselines including sense-aware ones.
Document-Level Neural Machine Translation with Hierarchical Attention Networks
Neural Machine Translation (NMT) can be improved by including document-level contextual information.
Beyond Weight Tying: Learning Joint Input-Output Embeddings for Neural Machine Translation
The model is a generalized form of weight tying which shares parameters but allows learning a more flexible relationship with input word embeddings and allows the effective capacity of the output layer to be controlled.
GILE: A Generalized Input-Label Embedding for Text Classification
This forces their parametrization to be dependent on the label set size, and, hence, they are unable to scale to large label sets and generalize to unseen ones.
Self-Attentive Residual Decoder for Neural Machine Translation
Neural sequence-to-sequence networks with attention have achieved remarkable performance for machine translation.
Multilingual Hierarchical Attention Networks for Document Classification
Hierarchical attention networks have recently achieved remarkable performance for document classification in a given language.
The SUMMA Platform Prototype
We present the first prototype of the SUMMA Platform: an integrated platform for multilingual media monitoring.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
Explicit Document Modeling through Weighted Multiple-Instance Learning
Representing documents is a crucial component in many NLP tasks, for instance predicting aspect ratings in reviews.
Multilingual Visual Sentiment Concept Matching
The impact of culture in visual emotion perception has recently captured the attention of multimedia research.
Visual Affect Around the World: A Large-scale Multilingual Visual Sentiment Ontology
Our work expressly focuses on the uniqueness of culture and language in relation to human affect, specifically sentiment and emotion semantics, and how they manifest in social multimedia.
