Search Results for author:
Found 17 papers, 8 papers with code
Dual-Space Knowledge Distillation for Large Language Models
Furthermore, this discrepancy also hinders the KD process between models with different vocabularies, which is common for current LLMs.
Multilingual Knowledge Editing with Language-Agnostic Factual Neurons
To address this issue, we first investigate how LLMs process multilingual factual knowledge and discover that the same factual knowledge in different languages generally activates a shared set of neurons, which we call language-agnostic factual neurons (LAFNs).
Rethinking Early-Fusion Strategies for Improved Multispectral Object Detection
In this paper, we address this issue by improving the performance of efficient single-branch structures.
From Fourier to Neural ODEs: Flow Matching for Modeling Complex Systems
We then incorporate the estimated spatial gradients as additional inputs to a neural network.
Benchmarks and Challenges in Pose Estimation for Egocentric Hand Interactions with Objects
A holistic 3Dunderstanding of such interactions from egocentric views is important for tasks in robotics, AR/VR, action recognition and motion generation.
TransportationGames: Benchmarking Transportation Knowledge of (Multimodal) Large Language Models
Large language models (LLMs) and multimodal large language models (MLLMs) have shown excellent general capabilities, even exhibiting adaptability in many professional domains such as law, economics, transportation, and medicine.
A Quality-based Syntactic Template Retriever for Syntactically-controlled Paraphrase Generation
Furthermore, for situations requiring multiple paraphrases for each source sentence, we design a Diverse Templates Search (DTS) algorithm, which can enhance the diversity between paraphrases without sacrificing quality.
TFDet: Target-Aware Fusion for RGB-T Pedestrian Detection
Different from them, we comprehensively analyze the impacts of false positives on the detection performance and find that enhancing feature contrast can significantly reduce these false positives.
Manifold Graph Signal Restoration using Gradient Graph Laplacian Regularizer
In this paper, focusing on manifold graphs -- collections of uniform discrete samples on low-dimensional continuous manifolds -- we generalize GLR to gradient graph Laplacian regularizer (GGLR) that promotes planar / piecewise planar (PWP) signal reconstruction.
Generating Authentic Adversarial Examples beyond Meaning-preserving with Doubly Round-trip Translation
Generating adversarial examples for Neural Machine Translation (NMT) with single Round-Trip Translation (RTT) has achieved promising results by releasing the meaning-preserving restriction.
Fast Computation of Generalized Eigenvectors for Manifold Graph Embedding
Experiments show that our embedding is among the fastest in the literature, while producing the best clustering performance for manifold graphs.
Graph-Based Depth Denoising & Dequantization for Point Cloud Enhancement
Specifically, we model depth formation as a combined process of signal-dependent noise addition and non-uniform log-based quantization.
FocusNet: Classifying Better by Focusing on Confusing Classes
We also introduce a novel focus-picking loss function to improve classification accuracy by encouraging FocusNet to focus on the most confusing classes.
Battery characterization via eddy-current imaging with nitrogen-vacancy centers in diamond
Sensitive and accurate diagnostic technologies with magnetic sensors are of great importance for identifying and localizing defects of rechargeable solid batteries in a noninvasive detection.
Applied Physics
Fast & Robust Image Interpolation using Gradient Graph Laplacian Regularizer
In the graph signal processing (GSP) literature, it has been shown that signal-dependent graph Laplacian regularizer (GLR) can efficiently promote piecewise constant (PWC) signal reconstruction for various image restoration tasks.
DeepHE: Accurately Predicting Human Essential Genes based on Deep Learning
Results: We proposed a deep learning based method, DeepHE, to predict human essential genes by integrating features derived from sequence data and protein-protein interaction (PPI) network.
How to Train Triplet Networks with 100K Identities?
However, as the number of identities becomes extremely large, the training will suffer from bad local minima because effective hard triplets are difficult to be found.
