Search Results for author:
Found 47 papers, 18 papers with code
SeaLLMs 3: Open Foundation and Chat Multilingual Large Language Models for Southeast Asian Languages
Large Language Models (LLMs) have shown remarkable abilities across various tasks, yet their development has predominantly centered on high-resource languages like English and Chinese, leaving low-resource languages underserved.
Apple Intelligence Foundation Language Models
We present foundation language models developed to power Apple Intelligence features, including a ~3 billion parameter model designed to run efficiently on devices and a large server-based language model designed for Private Cloud Compute.
Virtual Full-Duplex Wireless Communications with Zero-Interval Modulation and Sampling
In ZIMS-VFD, the transceiver inserts a zero-interval for each symbol in the transmit signal and provides self-interference (SI)-free intervals for itself.
Multi-Frequency Resonant Circuit Based Multi-User Emergency Through-the-Earth Communication with Magnetic Induction
Magnetic induction (MI) is an effective technique in emergency through-the-earth communications due to the higher penetration efficiency and lower propagation loss as compared with electromagnetic wave communication.
RIS-Based Self-Interference Cancellation for Full-Duplex Broadband Transmission
The problem is solved with alternate optimization (AO) algorithm in three cases: ideal case, where both the amplitude and phase of each RIS unit cell can be controlled independently and continuously, continuous phases, where the phase of each RIS unit cell can be controlled independently, while the amplitude is fixed to one, and discrete phases, where the RC of each RIS unit cell can only take discrete values and these discrete values are equally spaced on the unit circle.
Fast and Slow Generating: An Empirical Study on Large and Small Language Models Collaborative Decoding
Our research underscores that the fundamental distinction between System 1 and System 2 lies in the uncertainty of next token predictions, where interventions by System 2 are crucial to support System 1.
MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training
Through careful and comprehensive ablations of the image encoder, the vision language connector, and various pre-training data choices, we identified several crucial design lessons.
Ranked #68 on
Visual Question Answering
on MM-Vet
CoGenesis: A Framework Collaborating Large and Small Language Models for Secure Context-Aware Instruction Following
With the advancement of language models (LMs), their exposure to private data is increasingly inevitable, and their deployment (especially for smaller ones) on personal devices, such as PCs and smartphones, has become a prevailing trend.
Operators' cognitive performance under extreme hot-humid exposure and its physiological-psychological mechanism based on ECG, fNIRS, and Eye Tracking
The best performance in a suitable environment was due to more effective activation in the prefrontal cortex (PFC).
Momentum Approximation in Asynchronous Private Federated Learning
Asynchronous protocols have been shown to improve the scalability of federated learning (FL) with a massive number of clients.
Wasserstein Nonnegative Tensor Factorization with Manifold Regularization
Nonnegative tensor factorization (NTF) has become an important tool for feature extraction and part-based representation with preserved intrinsic structure information from nonnegative high-order data.
PLGSLAM: Progressive Neural Scene Represenation with Local to Global Bundle Adjustment
To this end, we introduce PLGSLAM, a neural visual SLAM system capable of high-fidelity surface reconstruction and robust camera tracking in real-time.
SeaLLMs -- Large Language Models for Southeast Asia
Despite the remarkable achievements of large language models (LLMs) in various tasks, there remains a linguistic bias that favors high-resource languages, such as English, often at the expense of low-resource and regional languages.
FedHyper: A Universal and Robust Learning Rate Scheduler for Federated Learning with Hypergradient Descent
The theoretical landscape of federated learning (FL) undergoes rapid evolution, but its practical application encounters a series of intricate challenges, and hyperparameter optimization is one of these critical challenges.
FedDisco: Federated Learning with Discrepancy-Aware Collaboration
However, based on our empirical observations and theoretical analysis, we find that the dataset size is not optimal and the discrepancy between local and global category distributions could be a beneficial and complementary indicator for determining aggregation weights.
Non-Line-of-Sight Imaging With Signal Superresolution Network
This paper proposes a general learning-based pipeline for increasing imaging quality with only a few scanning points.
Few-shot Non-line-of-sight Imaging with Signal-surface Collaborative Regularization
In this work, we propose a signal-surface collaborative regularization (SSCR) framework that provides noise-robust reconstructions with a minimal number of measurements.
Robust Manifold Nonnegative Tucker Factorization for Tensor Data Representation
Nonnegative Tucker Factorization (NTF) minimizes the euclidean distance or Kullback-Leibler divergence between the original data and its low-rank approximation which often suffers from grossly corruptions or outliers and the neglect of manifold structures of data.
Non-line-of-sight imaging with arbitrary illumination and detection pattern
Non-line-of-sight (NLOS) imaging aims at reconstructing targets obscured from the direct line of sight.
Where to Begin? On the Impact of Pre-Training and Initialization in Federated Learning
Surprisingly, we also find that starting federated learning from a pre-trained initialization reduces the effect of both data and system heterogeneity.
FedFM: Anchor-based Feature Matching for Data Heterogeneity in Federated Learning
This method attempts to mitigate the negative effects of data heterogeneity in FL by aligning each client's feature space.
Where to Begin? On the Impact of Pre-Training and Initialization in Federated Learning
Surprisingly, we also find that starting federated learning from a pre-trained initialization reduces the effect of both data and system heterogeneity.
On the Unreasonable Effectiveness of Federated Averaging with Heterogeneous Data
Motivated by this observation, we propose a new quantity, average drift at optimum, to measure the effects of data heterogeneity, and explicitly use it to present a new theoretical analysis of FedAvg.
Federated Learning under Distributed Concept Drift
Federated Learning (FL) under distributed concept drift is a largely unexplored area.
RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning
RLPrompt formulates a parameter-efficient policy network that generates the desired discrete prompt after training with reward.
FedLite: A Scalable Approach for Federated Learning on Resource-constrained Clients
In classical federated learning, the clients contribute to the overall training by communicating local updates for the underlying model on their private data to a coordinating server.
Personalized Federated Learning for Heterogeneous Clients with Clustered Knowledge Transfer
Personalized federated learning (FL) aims to train model(s) that can perform well for individual clients that are highly data and system heterogeneous.
A Field Guide to Federated Optimization
Federated learning and analytics are a distributed approach for collaboratively learning models (or statistics) from decentralized data, motivated by and designed for privacy protection.
DualVGR: A Dual-Visual Graph Reasoning Unit for Video Question Answering
However, existing graph-based methods fail to perform multi-step reasoning well, neglecting two properties of VideoQA: (1) Even for the same video, different questions may require different amount of video clips or objects to infer the answer with relational reasoning; (2) During reasoning, appearance and motion features have complicated interdependence which are correlated and complementary to each other.
Ranked #29 on
Visual Question Answering (VQA)
on MSRVTT-QA
Local Adaptivity in Federated Learning: Convergence and Consistency
Popular optimization algorithms of FL use vanilla (stochastic) gradient descent for both local updates at clients and global updates at the aggregating server.
Libri-adhoc40: A dataset collected from synchronized ad-hoc microphone arrays
We trained several multi-device speech recognition systems on both the Libri-adhoc40 dataset and a simulated dataset.
Deep NMF Topic Modeling
In this paper, we propose a deep NMF (DNMF) topic modeling framework to alleviate the aforementioned problems.
Client Selection in Federated Learning: Convergence Analysis and Power-of-Choice Selection Strategies
Federated learning is a distributed optimization paradigm that enables a large number of resource-limited client nodes to cooperatively train a model without data sharing.
Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization
In federated optimization, heterogeneity in the clients' local datasets and computation speeds results in large variations in the number of local updates performed by each client in each communication round.
Slow and Stale Gradients Can Win the Race
Distributed Stochastic Gradient Descent (SGD) when run in a synchronous manner, suffers from delays in runtime as it waits for the slowest workers (stragglers).
Overlap Local-SGD: An Algorithmic Approach to Hide Communication Delays in Distributed SGD
In this paper, we propose an algorithmic approach named Overlap-Local-SGD (and its momentum variant) to overlap the communication and computation so as to speedup the distributed training procedure.
Advances and Open Problems in Federated Learning
FL embodies the principles of focused data collection and minimization, and can mitigate many of the systemic privacy risks and costs resulting from traditional, centralized machine learning and data science approaches.
Deep topic modeling by multilayer bootstrap network and lasso
Specifically, we first apply multilayer bootstrap network (MBN), which is an unsupervised deep model, to reduce the dimension of documents, and then use the low-dimensional data representations or their clustering results as the target of supervised Lasso for topic word discovery.
SlowMo: Improving Communication-Efficient Distributed SGD with Slow Momentum
We provide theoretical convergence guarantees showing that SlowMo converges to a stationary point of smooth non-convex losses.
MATCHA: Speeding Up Decentralized SGD via Matching Decomposition Sampling
This paper studies the problem of error-runtime trade-off, typically encountered in decentralized training based on stochastic gradient descent (SGD) using a given network.
Bilateral Adversarial Training: Towards Fast Training of More Robust Models Against Adversarial Attacks
To generate the adversarial image, we use one-step targeted attack with the target label being the most confusing class.
Adaptive Communication Strategies to Achieve the Best Error-Runtime Trade-off in Local-Update SGD
Large-scale machine learning training, in particular distributed stochastic gradient descent, needs to be robust to inherent system variability such as node straggling and random communication delays.
Cooperative SGD: A unified Framework for the Design and Analysis of Communication-Efficient SGD Algorithms
Communication-efficient SGD algorithms, which allow nodes to perform local updates and periodically synchronize local models, are highly effective in improving the speed and scalability of distributed SGD.
Visual Concepts and Compositional Voting
We use clustering algorithms to study the population activities of the features and extract a set of visual concepts which we show are visually tight and correspond to semantic parts of vehicles.
Detecting Semantic Parts on Partially Occluded Objects
Our approach detects semantic parts by accumulating the confidence of local visual cues.
Unsupervised learning of object semantic parts from internal states of CNNs by population encoding
We address the key question of how object part representations can be found from the internal states of CNNs that are trained for high-level tasks, such as object classification.
Semantic Part Segmentation using Compositional Model combining Shape and Appearance
This is more challenging than standard object detection, object segmentation and pose estimation tasks because semantic parts of animals often have similar appearance and highly varying shapes.
