Search Results for author:
Found 41 papers, 9 papers with code
Language Branch Gated Multilingual Neural Machine Translation
Knowledge transfer across languages is crucial for multilingual neural machine translation.
Improving the Sample and Communication Complexity for Decentralized Non-Convex Optimization: Joint Gradient Estimation and Tracking
Similarly, for online problems, the proposed method achieves an $\mathcal{O}(m \epsilon^{-3/2})$ sample complexity and an $\mathcal{O}(\epsilon^{-1})$ communication complexity, while the best existing bounds are $\mathcal{O}(m\epsilon^{-2})$ and $\mathcal{O}(\epsilon^{-2})$.
Medical Multimodal Foundation Models in Clinical Diagnosis and Treatment: Applications, Challenges, and Future Directions
Recent advancements in deep learning have significantly revolutionized the field of clinical diagnosis and treatment, offering novel approaches to improve diagnostic precision and treatment efficacy across diverse clinical domains, thus driving the pursuit of precision medicine.
Multilingual Large Language Models: A Systematic Survey
An important focus of this survey is on the evaluation of MLLMs.
Model and Deep learning based Dynamic Range Compression Inversion
Then, a model-based inversion is completed to restore the original audio signal.
Constrained Optimal Fuel Consumption of HEV:Considering the Observational Perturbation
We assume accurate observation of battery state of charge (SOC) and precise speed curves when addressing the constrained optimal fuel consumption (COFC) problem via constrained reinforcement learning (CRL).
CogDevelop2K: Reversed Cognitive Development in Multimodal Large Language Models
To this end, we propose CogDevelop2K, a comprehensive benchmark that spans 12 sub-concepts from primitive knowledge like object permanence and boundary to more complex abilities like intentionality understanding, structured via the developmental trajectory of a human mind.
MA-RLHF: Reinforcement Learning from Human Feedback with Macro Actions
However, token-level RLHF suffers from the credit assignment problem over long sequences, where delayed rewards make it challenging for the model to discern which actions contributed to successful outcomes.
Probing Mechanical Reasoning in Large Vision Language Models
Mechanical reasoning is a fundamental ability that sets human intelligence apart from other animal intelligence.
Vision Language Models See What You Want but not What You See
Knowing others' intentions and taking others' perspectives are two core components of human intelligence that are typically considered to be instantiations of theory-of-mind.
Vision Language Models Know Law of Conservation without Understanding More-or-Less
Conservation is a critical milestone of cognitive development considered to be supported by both the understanding of quantitative concepts and the reversibility of mental operations.
FuxiTranyu: A Multilingual Large Language Model Trained with Balanced Data
To mitigate this challenge, we present FuxiTranyu, an open-source multilingual LLM, which is designed to satisfy the need of the research community for balanced and high-performing multilingual capabilities.
Spatial-Division Augmented Occupancy Field for Bone Shape Reconstruction from Biplanar X-Rays
Although various deep learning models have been proposed to address this complex task, they suffer from two limitations: 1) They employ voxel representation for bone shape and exploit 3D convolutional layers to capture anatomy prior, which are memory-intensive and limit the reconstruction resolution.
ALPINE: Unveiling the Planning Capability of Autoregressive Learning in Language Models
Furthermore, our theoretical analysis of gradient-based learning dynamics reveals that LLMs can learn both the adjacency and a limited form of the reachability matrices.
Conifer: Improving Complex Constrained Instruction-Following Ability of Large Language Models
To address this challenge, we introduce Conifer, a novel instruction tuning dataset, designed to enhance LLMs to follow multi-level instructions with complex constraints.
Automated Deterministic Auction Design with Objective Decomposition
Identifying high-revenue mechanisms that are both dominant strategy incentive compatible (DSIC) and individually rational (IR) is a fundamental challenge in auction design.
Towards a Deep Understanding of Multilingual End-to-End Speech Translation
In this paper, we employ Singular Value Canonical Correlation Analysis (SVCCA) to analyze representations learnt in a multilingual end-to-end speech translation model trained over 22 languages.
Coordinated Dynamic Bidding in Repeated Second-Price Auctions with Budgets
To the best of our knowledge, we are the first to consider bidder coordination in online repeated auctions with constraints.
A Scalable Neural Network for DSIC Affine Maximizer Auction Design
AMenuNet is always DSIC and individually rational (IR) due to the properties of AMAs, and it enhances scalability by generating candidate allocations through a neural network.
Two-Bit RIS-Aided Communications at 3.5GHz: Some Insights from the Measurement Results Under Multiple Practical Scenes
In particular, we adopt a self-developed broadband intelligent communication system 40MHz-Net (BICT-40N) terminal in order to fully acquire the channel information.
Fine-grained Cross-modal Fusion based Refinement for Text-to-Image Synthesis
The proposed FF-Block integrates an attention block and several convolution layers to effectively fuse the fine-grained word-context features into the corresponding visual features, in which the text information is fully used to refine the initial image with more details.
Score-based Continuous-time Discrete Diffusion Models
Score-based modeling through stochastic differential equations (SDEs) has provided a new perspective on diffusion models, and demonstrated superior performance on continuous data.
Optimal Scaling for Locally Balanced Proposals in Discrete Spaces
Optimal scaling has been well studied for Metropolis-Hastings (M-H) algorithms in continuous spaces, but a similar understanding has been lacking in discrete spaces.
Annealed Training for Combinatorial Optimization on Graphs
However, learning neural networks for CO problems is notoriously difficult in lack of the labeled data as the training is easily trapped at local optima.
Discrete Langevin Sampler via Wasserstein Gradient Flow
It is known that gradient-based MCMC samplers for continuous spaces, such as Langevin Monte Carlo (LMC), can be derived as particle versions of a gradient flow that minimizes KL divergence on a Wasserstein manifold.
To Supervise or Not: How to Effectively Learn Wireless Interference Management Models?
We then provide a series of theoretical results to further understand the properties of the two approaches.
Multi-task Learning of Order-Consistent Causal Graphs
We consider the problem of discovering $K$ related Gaussian directed acyclic graphs (DAGs), where the involved graph structures share a consistent causal order and sparse unions of supports.
CycleFlow: Purify Information Factors by Cycle Loss
SpeechFlow is a powerful factorization model based on information bottleneck (IB), and its effectiveness has been reported by several studies.
Provable Learning-based Algorithm For Sparse Recovery
In this work, we propose PLISA (Provable Learning-based Iterative Sparse recovery Algorithm) to learn algorithms automatically from data.
Path Auxiliary Proposal for MCMC in Discrete Space
Energy-based Model (EBM) offers a powerful approach for modeling discrete structure, but both inference and learning of EBM are hard as it involves sampling from discrete distributions.
Learning to Continuously Optimize Wireless Resource in a Dynamic Environment: A Bilevel Optimization Perspective
However, it is often challenging for these approaches to learn in a dynamic environment.
Improving Learning to Branch via Reinforcement Learning
Branch-and-Bound~(B\&B) is a general and widely used algorithm paradigm for solving Mixed Integer Programming~(MIP).
Learning to Continuously Optimize Wireless Resource In Episodically Dynamic Environment
We propose to build the notion of continual learning (CL) into the modeling process of learning wireless systems, so that the learning model can incrementally adapt to the new episodes, {\it without forgetting} knowledge learned from the previous episodes.
Deep generative factorization for speech signal
Various information factors are blended in speech signals, which forms the primary difficulty for most speech information processing tasks.
On the Divergence of Decentralized Non-Convex Optimization
However, by constructing some counter-examples, we show that when certain local Lipschitz conditions (LLC) on the local function gradient $\nabla f_i$'s are not satisfied, most of the existing decentralized algorithms diverge, even if the global Lipschitz condition (GLC) is satisfied, where the sum function $f$ has Lipschitz gradient.
Substituting Gadolinium in Brain MRI Using DeepContrast
Together, these studies validate our hypothesis that a deep learning approach can potentially replace the need for GBCAs in brain MRI.
On Investigation of Unsupervised Speech Factorization Based on Normalization Flow
Speech signals are complex composites of various information, including phonetic content, speaker traits, channel effect, etc.
Improving the Sample and Communication Complexity for Decentralized Non-Convex Optimization: A Joint Gradient Estimation and Tracking Approach
Similarly, for online problems, the proposed method achieves an $\mathcal{O}(m \epsilon^{-3/2})$ sample complexity and an $\mathcal{O}(\epsilon^{-1})$ communication complexity, while the best existing bounds are $\mathcal{O}(m\epsilon^{-2})$ and $\mathcal{O}(\epsilon^{-2})$, respectively.
Alice's Adventures in the Markovian World
This paper proposes an algorithm Alice having no access to the physics law of the environment, which is actually linear with stochastic noise, and learns to make decisions directly online without a training phase or a stable policy as initial input.
Distributed Training with Heterogeneous Data: Bridging Median- and Mean-Based Algorithms
We show that these algorithms are non-convergent whenever there is some disparity between the expected median and mean over the local gradients.
Locating the boundaries of Pareto fronts: A Many-Objective Evolutionary Algorithm Based on Corner Solution Search
In this paper, an evolutionary many-objective optimization algorithm based on corner solution search (MaOEA-CS) was proposed.
