Search Results for author:
Found 19 papers, 3 papers with code
LIAM: Multimodal Transformer for Language Instructions, Images, Actions and Semantic Maps
The availability of large language models and open-vocabulary object perception methods enables more flexibility for domestic service robots.
A Stronger Mixture of Low-Rank Experts for Fine-Tuning Foundation Models
In order to streamline the fine-tuning of foundation models, Low-Rank Adapters (LoRAs) have been substantially adopted across various fields, including instruction tuning and domain adaptation.
Toward Copyright Integrity and Verifiability via Multi-Bit Watermarking for Intelligent Transportation Systems
Furthermore, ITSmark can also customize the watermark embedding position and proportion according to user needs, making embedding more flexible.
U-GIFT: Uncertainty-Guided Firewall for Toxic Speech in Few-Shot Scenario
While manual content moderation is still prevalent, the overwhelming volume of content and the psychological strain on human moderators underscore the need for automated toxic speech detection.
DeSplat: Decomposed Gaussian Splatting for Distractor-Free Rendering
Gaussian splatting enables fast novel view synthesis in static 3D environments.
LLM4PR: Improving Post-Ranking in Search Engine with Large Language Models
In this study, we introduce a novel paradigm named Large Language Models for Post-Ranking in search engine (LLM4PR), which leverages the capabilities of LLMs to accomplish the post-ranking task in SE.
State-of-the-art Advances of Deep-learning Linguistic Steganalysis Research
With the evolution of generative linguistic steganography techniques, conventional steganalysis falls short in robustly quantifying the alterations induced by steganography, thereby complicating detection.
Squid: Long Context as a New Modality for Energy-Efficient On-Device Language Models
Our work contributes to the development of more sustainable and scalable language models for on-device applications, addressing the critical need for energy-efficient and responsive AI technologies in resource-constrained environments while maintaining the accuracy to understand long contexts.
Official-NV: An LLM-Generated News Video Dataset for Multimodal Fake News Detection
To address this issue, we construct a dataset named Official-NV, comprising officially published news videos.
MODRL-TA:A Multi-Objective Deep Reinforcement Learning Framework for Traffic Allocation in E-Commerce Search
Existing methods based on learning to rank neglect the long-term value of traffic allocation, whereas approaches of reinforcement learning suffer from balancing multiple objectives and the difficulties of cold starts within realworld data environments.
Linguistic Steganalysis via LLMs: Two Modes for Efficient Detection of Strongly Concealed Stego
In this mode, LSGC deleted the LS-task "description" and used the "causalLM" LLMs to extract steganographic features.
DAIRstega: Dynamically Allocated Interval-Based Generative Linguistic Steganography with Roulette Wheel
Based on the invisible characteristics of LS, we give three constraints that need to be met to design the function.
UP4LS: User Profile Constructed by Multiple Attributes for Enhancing Linguistic Steganalysis
The extracted features are mapped to high-dimensional user features via the deep-learning model of the method to be improved.
Propagate And Calibrate: Real-time Passive Non-line-of-sight Tracking
In contrast, we propose a purely passive method to track a person walking in an invisible room by only observing a relay wall, which is more in line with real application scenarios, e. g., security.
Exploring the Impact of Negative Samples of Contrastive Learning: A Case Study of Sentence Embedding
We define a maximum traceable distance metric, through which we learn to what extent the text contrastive learning benefits from the historical information of negative samples.
ESOD:Edge-based Task Scheduling for Object Detection
In detail, we train a DNN model (termed as pre-model) to predict which object detection model to use for the coming task and offloads to which edge servers by physical characteristics of the image task (e. g., brightness, saturation).
Improving Adversarial Robustness for Free with Snapshot Ensemble
Based on the snapshot ensemble, we present a new method that is easier to implement: unlike original snapshot ensemble that seeks for local minima, our snapshot ensemble focuses on the last few iterations of a training and stores the sets of parameters from them.
I-Nema: A Biological Image Dataset for Nematode Recognition
In this paper, we identify two main bottlenecks: (1) the lack of a publicly available imaging dataset for diverse species of nematodes (especially the species only found in natural environment) which requires considerable human resources in field work and experts in taxonomy, and (2) the lack of a standard benchmark of state-of-the-art deep learning techniques on this dataset which demands the discipline background in computer science.
Imaging disorder-induced scattering centers in quantum Hall incompressible strip
While the disorder-induced quantum Hall (QH) effect has been studied previously, the effect ofdisorder potential on microscopic features of the integer QH effect remains unclear, particularly forthe incompressible (IC) strip.
Mesoscale and Nanoscale Physics
