Search Results for author:
Found 46 papers, 14 papers with code
HAMburger: Accelerating LLM Inference via Token Smashing
The growing demand for efficient Large Language Model (LLM) inference requires a holistic optimization on algorithms, systems, and hardware.
Minimax Rate-Optimal Algorithms for High-Dimensional Stochastic Linear Bandits
We study the stochastic linear bandit problem with multiple arms over $T$ rounds, where the covariate dimension $d$ may exceed $T$, but each arm-specific parameter vector is $s$-sparse.
GSFF-SLAM: 3D Semantic Gaussian Splatting SLAM via Feature Field
Semantic-aware 3D scene reconstruction is essential for autonomous robots to perform complex interactions.
PGAD: Prototype-Guided Adaptive Distillation for Multi-Modal Learning in AD Diagnosis
To address this, we propose a Prototype-Guided Adaptive Distillation (PGAD) framework that directly incorporates incomplete multi-modal data into training.
Efficient Sampling and Sensitivity Analysis of Rare Transient Instability Events via Subset Simulation
Assessing the risk of low-probability high-impact transient instability (TI) events is crucial for ensuring robust and stable power system operation under high uncertainty.
Optimizing Multi-Hop Document Retrieval Through Intermediate Representations
This observation suggests that the representations in intermediate layers contain richer information compared to those in other layers.
Speculative Prefill: Turbocharging TTFT with Lightweight and Training-Free Token Importance Estimation
In this work, we present SpecPrefill, a training free framework that accelerates the inference TTFT for both long and medium context queries based on the following insight: LLMs are generalized enough to preserve the quality given only a carefully chosen subset of prompt tokens.
Self-Clustering Graph Transformer Approach to Model Resting-State Functional Brain Activity
Resting-state functional magnetic resonance imaging (rs-fMRI) offers valuable insights into the human brain's functional organization and is a powerful tool for investigating the relationship between brain function and cognitive processes, as it allows for the functional organization of the brain to be captured without relying on a specific task or stimuli.
Correlation of Correlation Networks: High-Order Interactions in the Topology of Brain Networks
Moreover, after applying topological network analysis to the correlation of correlation networks, we observed that some high-order interaction hubs predominantly occurred in primary and high-level cognitive areas, such as the visual and fronto-parietal regions.
ECGN: A Cluster-Aware Approach to Graph Neural Networks for Imbalanced Classification
We propose the Enhanced Cluster-aware Graph Network (ECGN), a novel method that addresses these issues by integrating cluster-specific training with synthetic node generation.
EITNet: An IoT-Enhanced Framework for Real-Time Basketball Action Recognition
To overcome these challenges, we propose the EITNet model, a deep learning framework that combines EfficientDet for object detection, I3D for spatiotemporal feature extraction, and TimeSformer for temporal analysis, all integrated with IoT technology for seamless real-time data collection and processing.
TRACE: Temporal Grounding Video LLM via Causal Event Modeling
To effectively handle various tasks simultaneously and enable zero-shot prediction, there is a growing trend in employing video LLMs for VTG tasks.
PalmBench: A Comprehensive Benchmark of Compressed Large Language Models on Mobile Platforms
Deploying large language models (LLMs) locally on mobile devices is advantageous in scenarios where transmitting data to remote cloud servers is either undesirable due to privacy concerns or impractical due to network connection.
How Much Can RAG Help the Reasoning of LLM?
In this paper, we investigate this issue in depth and find that while RAG can assist with reasoning, the help is limited.
Enhancing Long Video Understanding via Hierarchical Event-Based Memory
While this method excels in short video understanding, it may result in a blend of multiple event information in long videos due to coarse compression, which causes information redundancy.
TC-LLaVA: Rethinking the Transfer from Image to Video Understanding with Temporal Considerations
Multimodal Large Language Models (MLLMs) have significantly improved performance across various image-language applications.
Comparative Analysis of Learning-Based Methods for Transient Stability Assessment
Transient stability and critical clearing time (CCT) are important concepts in power system protection and control.
D&M: Enriching E-commerce Videos with Sound Effects by Key Moment Detection and SFX Matching
Previous studies about adding SFX to videos perform video to SFX matching at a holistic level, lacking the ability of adding SFX to a specific moment.
Dynamic and Compressive Adaptation of Transformers From Images to Videos
On Kinetics-400, InTI reaches a top-1 accuracy of 87. 1 with a remarkable 37. 5% reduction in GFLOPs compared to naive adaptation.
VTG-LLM: Integrating Timestamp Knowledge into Video LLMs for Enhanced Video Temporal Grounding
Video Temporal Grounding (VTG) strives to accurately pinpoint event timestamps in a specific video using linguistic queries, significantly impacting downstream tasks like video browsing and editing.
DSAM: A Deep Learning Framework for Analyzing Temporal and Spatial Dynamics in Brain Networks
Resting-state functional magnetic resonance imaging (rs-fMRI) is a noninvasive technique pivotal for understanding human neural mechanisms of intricate cognitive processes.
How Far Are We From AGI: Are LLMs All We Need?
The evolution of artificial intelligence (AI) has profoundly impacted human society, driving significant advancements in multiple sectors.
Unmasking Efficiency: Learning Salient Sparse Models in Non-IID Federated Learning
In this work, we propose Salient Sparse Federated Learning (SSFL), a streamlined approach for sparse federated learning with efficient communication.
A Survey of Neural Network Robustness Assessment in Image Recognition
We investigate the perturbation metrics and range representations used to measure the degree of perturbations on images, as well as the robustness metrics specifically for the robustness conditions of classification models.
Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning
This paper introduces Scene-LLM, a 3D-visual-language model that enhances embodied agents' abilities in interactive 3D indoor environments by integrating the reasoning strengths of Large Language Models (LLMs).
Efficient Probabilistic Optimal Power Flow Assessment Using an Adaptive Stochastic Spectral Embedding Surrogate Model
This paper presents an adaptive stochastic spectral embedding (ASSE) method to solve the probabilistic AC optimal power flow (AC-OPF), a critical aspect of power system operation.
Brain Networks and Intelligence: A Graph Neural Network Based Approach to Resting State fMRI Data
Resting-state functional magnetic resonance imaging (rsfMRI) is a powerful tool for investigating the relationship between brain function and cognitive processes as it allows for the functional organization of the brain to be captured without relying on a specific task or stimuli.
Graph Ranking Contrastive Learning: A Extremely Simple yet Efficient Method
Thus, we propose GraphRank, a simple yet efficient graph contrastive learning method that addresses the problem of false negative samples by redefining the concept of negative samples to a certain extent, thereby avoiding the issue of false negative samples.
Perfect Alignment May be Poisonous to Graph Contrastive Learning
Graph Contrastive Learning (GCL) aims to learn node representations by aligning positive pairs and separating negative ones.
Effective Long-Context Scaling of Foundation Models
We also examine the impact of various design choices in the pretraining process, including the data mix and the training curriculum of sequence lengths -- our ablation experiments suggest that having abundant long texts in the pretrain dataset is not the key to achieving strong performance, and we empirically verify that long context continual pretraining is more efficient and similarly effective compared to pretraining from scratch with long sequences.
Code Llama: Open Foundation Models for Code
We release Code Llama, a family of large language models for code based on Llama 2 providing state-of-the-art performance among open models, infilling capabilities, support for large input contexts, and zero-shot instruction following ability for programming tasks.
Ranked #38 on
Code Generation
on MBPP
(using extra training data)
Text-guided 3D Human Generation from 2D Collections
To address this \texttt{T3H} task, we propose Compositional Cross-modal Human (CCH).
Ranked #1 on
Text-to-3D-Human Generation
on SHHQ
SalientGrads: Sparse Models for Communication Efficient and Data Aware Distributed Federated Training
Federated learning (FL) enables the training of a model leveraging decentralized data in client sites while preserving privacy by not collecting data.
CLIP-Layout: Style-Consistent Indoor Scene Synthesis with Semantic Furniture Embedding
Whether heuristic or learned, these methods ignore instance-level visual attributes of objects, and as a result may produce visually less coherent scenes.
Prediction of Gender from Longitudinal MRI data via Deep Learning on Adolescent Data Reveals Unique Patterns Associated with Brain Structure and Change over a Two-year Period
Prior work has demonstrated that deep learning models that take advantage of the data's 3D structure can outperform standard machine learning on several learning tasks.
A Sparse Polynomial Chaos Expansion-Based Method for Probabilistic Transient Stability Assessment and Enhancement
This paper proposes an adaptive sparse polynomial chaos expansion(PCE)-based method to quantify the impacts of uncertainties on critical clearing time (CCT) that is an important index in transient stability analysis.
CLIP2TV: Align, Match and Distill for Video-Text Retrieval
Modern video-text retrieval frameworks basically consist of three parts: video encoder, text encoder and the similarity head.
Ranked #13 on
Video Retrieval
on MSR-VTT-1kA
(using extra training data)
Coarse to Fine: Video Retrieval before Moment Localization
The current state-of-the-art methods for video corpus moment retrieval (VCMR) often use similarity-based feature alignment approach for the sake of convenience and speed.
EDFace-Celeb-1M: Benchmarking Face Hallucination with a Million-scale Dataset
It is thus unclear how these algorithms perform on public face hallucination datasets.
Ranked #1 on
Image Super-Resolution
on WLFW
A Structure-Aware Relation Network for Thoracic Diseases Detection and Segmentation
Leveraging on constant structure and disease relations extracted from domain knowledge, we propose a structure-aware relation network (SAR-Net) extending Mask R-CNN.
The Detection of Thoracic Abnormalities ChestX-Det10 Challenge Results
The detection of thoracic abnormalities challenge is organized by the Deepwise AI Lab.
ChestX-Det10: Chest X-ray Dataset on Detection of Thoracic Abnormalities
Instance level detection of thoracic diseases or abnormalities are crucial for automatic diagnosis in chest X-ray images.
Meta-modal Information Flow: A Method for Capturing Multimodal Modular Disconnectivity in Schizophrenia
Through simulation and real data, we show our approach reveals important information about disease-related network disruptions that are missed with a focus on a single modality.
Align, Attend and Locate: Chest X-Ray Diagnosis via Contrast Induced Attention Network With Limited Supervision
We show that the use of contrastive attention and alignment module allows the model to learn rich identification and localization information using only a small amount of location annotations, resulting in state-of-the-art performance in NIH chest X-ray dataset.
Verification Code Recognition Based on Active and Deep Learning
However, the advantages of convolutional neural networks depend on the data used by the training classifier, particularly the size of the training set.
Referring Expression Generation and Comprehension via Attributes
In this paper, we explore the role of attributes by incorporating them into both referring expression generation and comprehension.
