Search Results for author:
Found 57 papers, 28 papers with code
MOM: Memory-Efficient Offloaded Mini-Sequence Inference for Long Context Language Models
On Meta-Llama-3. 2-8B, MOM extends the maximum context length from 155k to 455k tokens on a single A100 80GB GPU, while keeping outputs identical and not compromising accuracy.
Algorithm Design and Prototype Validation for Reconfigurable Intelligent Sensing Surface: Forward-Only Transmission
By leveraging sensing results from the active elements, we propose communication enhancement and robust interference suppression schemes for both near-field and far-field models, implemented through the passive elements.
Low-Complexity Beamforming Design for Null Space-based Simultaneous Wireless Information and Power Transfer Systems
Simultaneous wireless information and power transfer (SWIPT) is a promising technology for the upcoming sixth-generation (6G) communication networks, enabling internet of things (IoT) devices and sensors to extend their operational lifetimes.
Reconfigurable Intelligent Sensing Surface enables Wireless Powered Communication Networks: Interference Suppression and Massive Wireless Energy Transfer
Recently, a novel structures of reconfigurable intelligent surface (RIS) integrating both passive and active elements, termed reconfigurable intelligent sensing surface (RISS), efficiently addresses challenges in RIS channel estimation and mitigates issues related to multiplicative path loss by processing the signal at the RISS.
Bedrock Models in Communication and Sensing: Advancing Generalization, Transferability, and Performance
Deep learning (DL) has emerged as a powerful tool for addressing the intricate challenges inherent in communication and sensing systems, significantly enhancing the intelligence of future sixth-generation (6G) networks.
CaseGen: A Benchmark for Multi-Stage Legal Case Documents Generation
To the best of our knowledge, CaseGen is the first benchmark designed to evaluate LLMs in the context of legal case document generation.
Finedeep: Mitigating Sparse Activation in Dense LLMs via Multi-Layer Fine-Grained Experts
Moreover, we find that Finedeep achieves optimal results when balancing depth and width, specifically by adjusting the number of expert sub-layers and the number of experts per sub-layer.
HeadInfer: Memory-Efficient LLM Inference by Head-wise Offloading
Extending the context length has disproportionately shifted the memory footprint of LLMs during inference to the key-value cache (KV cache).
DSMoE: Matrix-Partitioned Experts with Dynamic Routing for Computation-Efficient Dense LLMs
As large language models continue to scale, computational costs and resource consumption have emerged as significant challenges.
Benchmarking Graph Representations and Graph Neural Networks for Multivariate Time Series Classification
Multivariate Time Series Classification (MTSC) enables the analysis if complex temporal data, and thus serves as a cornerstone in various real-world applications, ranging from healthcare to finance.
Tensor-GaLore: Memory-Efficient Training via Gradient Tensor Decomposition
We present Tensor-GaLore, a novel method for efficient training of neural networks with higher-order tensor weights.
Towards Combating Frequency Simplicity-biased Learning for Domain Generalization
Given the theoretical justification of models' biased learning behavior on different spatial frequency components, which is based on the dataset frequency properties, we argue that the learning behavior on various frequency components could be manipulated by changing the dataset statistical structure in the Fourier domain.
SynFER: Towards Boosting Facial Expression Recognition with Synthetic Data
Facial expression datasets remain limited in scale due to privacy concerns, the subjectivity of annotations, and the labor-intensive nature of data collection.
CLIP Multi-modal Hashing for Multimedia Retrieval
Multi-modal hashing methods are widely used in multimedia retrieval, which can fuse multi-source data to generate binary hash code.
Optimizing Placement and Power Allocation in Reconfigurable Intelligent Sensing Surfaces for Enhanced Sensing and Communication Performance
In this letter, we investigate the design of multiple reconfigurable intelligent sensing surfaces (RISSs) that enhance both communication and sensing tasks.
Multi-SIGATnet: A multimodal schizophrenia MRI classification algorithm using sparse interaction mechanisms and graph attention networks
To effectively capture the topological information of brain neural networks, a novel multimodal graph attention network based on sparse interaction mechanism (Multi-SIGATnet) was proposed for SZ classification was proposed for SZ classification.
Mini-Sequence Transformer: Optimizing Intermediate Memory for Long Sequences Training
We introduce Mini-Sequence Transformer (MsT), a simple and effective methodology for highly efficient and accurate LLM training with extremely long sequences.
LeKUBE: A Legal Knowledge Update BEnchmark
Existing benchmarks for evaluating knowledge update methods are mostly designed for the open domain and cannot address the specific challenges of the legal domain, such as the nuanced application of new legal knowledge, the complexity and lengthiness of legal regulations, and the intricate nature of legal reasoning.
ISPO: An Integrated Ontology of Symptom Phenotypes for Semantic Integration of Traditional Chinese Medical Data
Methods: To construct an integrated ontology of symptom phenotypes (ISPO), we manually annotated classical TCM textbooks and large-scale Chinese electronic medical records (EMRs) to collect symptom terms with support from a medical text annotation system.
Enhancing Vision-Language Models Generalization via Diversity-Driven Novel Feature Synthesis
To address this, we propose a plug-and-play feature synthesis method called LDFS (Language-Guided Diverse Feature Synthesis) to synthesize new domain features and improve existing CLIP fine-tuning strategies.
NTIRE 2024 Challenge on Short-form UGC Video Quality Assessment: Methods and Results
This paper reviews the NTIRE 2024 Challenge on Shortform UGC Video Quality Assessment (S-UGC VQA), where various excellent solutions are submitted and evaluated on the collected dataset KVQ from popular short-form video platform, i. e., Kuaishou/Kwai Platform.
Multi-scale Dynamic and Hierarchical Relationship Modeling for Facial Action Units Recognition
Human facial action units (AUs) are mutually related in a hierarchical manner, as not only they are associated with each other in both spatial and temporal domains but also AUs located in the same/close facial regions show stronger relationships than those of different facial regions.
Ranked #3 on
Facial Action Unit Detection
on BP4D
Conversational Disease Diagnosis via External Planner-Controlled Large Language Models
We demonstrated that our system obtained impressive performance in both disease screening and differential diagnoses tasks.
Deep Prompt Multi-task Network for Abuse Language Detection
To address the problem, we propose a novel Deep Prompt Multi-task Network (DPMN) for abuse language detection.
Boosting Adversarial Transferability across Model Genus by Deformation-Constrained Warping
Adversarial examples generated by a surrogate model typically exhibit limited transferability to unknown target systems.
REACT 2024: the Second Multiple Appropriate Facial Reaction Generation Challenge
In dyadic interactions, humans communicate their intentions and state of mind using verbal and non-verbal cues, where multiple different facial reactions might be appropriate in response to a specific speaker behaviour.
IEKM: A Model Incorporating External Keyword Matrices
In this paper, we propose an incorporation external keywords matrices model (IEKM) to address these challenges.
Massive Wireless Energy Transfer without Channel State Information via Imperfect Intelligent Reflecting Surfaces
Intelligent Reflecting Surface (IRS) utilizes low-cost, passive reflecting elements to enhance the passive beam gain, improve Wireless Energy Transfer (WET) efficiency, and enable its deployment for numerous Internet of Things (IoT) devices.
RTP: Rethinking Tensor Parallelism with Memory Deduplication
In the evolving landscape of neural network models, one prominent challenge stand out: the significant memory overheads associated with training expansive models.
Joint Prediction of Audio Event and Annoyance Rating in an Urban Soundscape by Hierarchical Graph Representation Learning
Sound events in daily life carry rich information about the objective world.
CTP:A Causal Interpretable Model for Non-Communicable Disease Progression Prediction
The CTP model combines trajectory prediction and causal discovery to enable accurate prediction of disease progression trajectories and uncover causal relationships between features.
MRecGen: Multimodal Appropriate Reaction Generator
Verbal and non-verbal human reaction generation is a challenging task, as different reactions could be appropriate for responding to the same behaviour.
REACT2023: the first Multi-modal Multiple Appropriate Facial Reaction Generation Challenge
The Multi-modal Multiple Appropriate Facial Reaction Generation Challenge (REACT2023) is the first competition event focused on evaluating multimedia processing and machine learning techniques for generating human-appropriate facial reactions in various dyadic interaction scenarios, with all participants competing strictly under the same conditions.
ReactFace: Online Multiple Appropriate Facial Reaction Generation in Dyadic Interactions
To address these limitations, this paper reformulates the task as an extrapolation or prediction problem, and proposes an novel framework (called ReactFace) to generate multiple different but appropriate facial reactions from a speaker behaviour rather than merely replicating the corresponding listener facial behaviours.
Semi-Supervised RF Fingerprinting with Consistency-Based Regularization
As a promising non-password authentication technology, radio frequency (RF) fingerprinting can greatly improve wireless security.
Temporal Dynamic Synchronous Functional Brain Network for Schizophrenia Diagnosis and Lateralization Analysis
The available evidence suggests that dynamic functional connectivity (dFC) can capture time-varying abnormalities in brain activity in resting-state cerebral functional magnetic resonance imaging (rs-fMRI) data and has a natural advantage in uncovering mechanisms of abnormal brain activity in schizophrenia(SZ) patients.
Spatio-Temporal AU Relational Graph Representation Learning For Facial Action Units Detection
This paper presents our Facial Action Units (AUs) detection submission to the fifth Affective Behavior Analysis in-the-wild Competition (ABAW).
Shift from Texture-bias to Shape-bias: Edge Deformation-based Augmentation for Robust Object Recognition
Recent studies have shown the vulnerability of CNNs under perturbation noises, which is partially caused by the reason that the well-trained CNNs are too biased toward the object texture, i. e., they make predictions mainly based on texture cues.
GRATIS: Deep Learning Graph Representation with Task-specific Topology and Multi-dimensional Edge Features
Our framework is effective, robust and flexible, and is a plug-and-play module that can be combined with different backbones and Graph Neural Networks (GNNs) to generate a task-specific graph representation from various graph and non-graph data.
A Benchmarking Dataset with 2440 Organic Molecules for Volume Distribution at Steady State
Conclusions: To the best of our knowledge, this is the largest dataset for VDss, which can be used as the benchmark for computational studies of VDss.
SemFormer: Semantic Guided Activation Transformer for Weakly Supervised Semantic Segmentation
Recent mainstream weakly supervised semantic segmentation (WSSS) approaches are mainly based on Class Activation Map (CAM) generated by a CNN (Convolutional Neural Network) based image classifier.
Weakly supervised Semantic Segmentation
Weakly-Supervised Semantic Segmentation
Scale-free and Task-agnostic Attack: Generating Photo-realistic Adversarial Patterns with Patch Quilting Generator
\noindent Traditional L_p norm-restricted image attack algorithms suffer from poor transferability to black box scenarios and poor robustness to defense algorithms.
GAN-Based Multi-View Video Coding with Spatio-Temporal EPI Reconstruction
At the decoder side, we combine the SI and adjacent viewpoints to reconstruct intermediate views using the GAN generator.
Learning Multi-dimensional Edge Feature-based AU Relation Graph for Facial Action Unit Recognition
While the relationship between a pair of AUs can be complex and unique, existing approaches fail to specifically and explicitly represent such cues for each pair of AUs in each facial display.
Ranked #7 on
Facial Action Unit Detection
on DISFA
Modality-Balanced Embedding for Video Retrieval
This modality imbalanceresults from a) modality gap: the relevance between a query and a video text is much easier to learn as the query is also a piece of text, with the same modality as the video text; b) data bias: most training samples can be solved solely by text matching.
Frequency-driven Imperceptible Adversarial Attack on Semantic Similarity
Current adversarial attack research reveals the vulnerability of learning-based classifiers against carefully crafted perturbations.
Online Refinement of Low-level Feature Based Activation Map for Weakly Supervised Object Localization
In the first stage, an activation map generator produces activation maps based on the low-level feature maps in the classifier, such that rich contextual object information is included in an online manner.
PALRACE: Reading Comprehension Dataset with Human Data and Labeled Rationales
Each passage was read by at least 26 human readers, who labeled their rationales to answer the question.
Prediction, Selection, and Generation: Exploration of Knowledge-Driven Conversation System
The system includes modules such as dialogue topic prediction, knowledge matching and dialogue generation.
CrossoverScheduler: Overlapping Multiple Distributed Training Applications in a Crossover Manner
Distributed deep learning workloads include throughput-intensive training tasks on the GPU clusters, where the Distributed Stochastic Gradient Descent (SGD) incurs significant communication delays after backward propagation, forces workers to wait for the gradient synchronization via a centralized parameter server or directly in decentralized workers.
Let's be Humorous: Knowledge Enhanced Humor Generation
To our knowledge, this is the first attempt to generate punchlines with knowledge enhanced model.
Minority Oversampling for Imbalanced Time Series Classification
Many important real-world applications involve time-series data with skewed distribution.
Neural Document Expansion with User Feedback
This paper presents a neural document expansion approach (NeuDEF) that enriches document representations for neural ranking models.
Temporal Relational Ranking for Stock Prediction
Our RSR method advances existing solutions in two major aspects: 1) tailoring the deep learning models for stock ranking, and 2) capturing the stock relations in a time-sensitive manner.
Unbiased Learning to Rank with Unbiased Propensity Estimation
We find that the problem of estimating a propensity model from click data is a dual problem of unbiased learning to rank.
The Dependent Random Measures with Independent Increments in Mixture Models
One of the propositions of the dependent random measures is that the atoms of the posterior distribution are shared amongst groups, and hence groups can borrow information from each other.
Smoothed Hierarchical Dirichlet Process: A Non-Parametric Approach to Constraint Measures
The key novelty of this model is that we place a temporal constraint amongst the nearby discrete measures $\{G_j\}$ in the form of symmetric Kullback-Leibler (KL) Divergence with a fixed bound $B$.
