Search Results for author:
Found 40 papers, 15 papers with code
Hybrid Cost Volume for Memory-Efficient Optical Flow
Compared to the recurrent flow methods based the all-pairs cost volumes, our HCVFlow significantly reduces memory consumption while ensuring high accuracy.
Random Time-hopping Secure Ranging Strategy Against Distance-Reduction Attacks in UWB
In order to mitigate the distance reduction attack in Ultra-Wide Band (UWB) ranging, this paper proposes a secure ranging scheme based on a random time-hopping mechanism without redundant signaling overhead.
Learning from Students: Applying t-Distributions to Explore Accurate and Efficient Formats for LLMs
Using this format as a high-accuracy reference, we then propose augmenting E2M1 with two variants of supernormal support for higher model accuracy.
Hybrid Bit and Semantic Communications
Semantic communication technology is regarded as a method surpassing the Shannon limit of bit transmission, capable of effectively enhancing transmission efficiency.
The Third Monocular Depth Estimation Challenge
This paper discusses the results of the third edition of the Monocular Depth Estimation Challenge (MDEC).
Exploiting Self-Supervised Constraints in Image Super-Resolution
Recent advances in self-supervised learning, predominantly studied in high-level visual tasks, have been explored in low-level image processing.
Transforming Image Super-Resolution: A ConvFormer-based Efficient Approach
Recent progress in single-image super-resolution (SISR) has achieved remarkable performance, yet the computational costs of these methods remain a challenge for deployment on resource-constrained devices.
Ranked #32 on
Image Super-Resolution
on Manga109 - 4x upscaling
VaQuitA: Enhancing Alignment in LLM-Assisted Video Understanding
Recent advancements in language-model-based video understanding have been progressing at a remarkable pace, spurred by the introduction of Large Language Models (LLMs).
Token-Level Adversarial Prompt Detection Based on Perplexity Measures and Contextual Information
Our work aims to address this concern by introducing a novel approach to detecting adversarial prompts at a token level, leveraging the LLM's capability to predict the next token's probability.
AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language Models
Safety alignment of Large Language Models (LLMs) can be compromised with manual jailbreak attacks and (automatic) adversarial attacks.
Learning from History: Task-agnostic Model Contrastive Learning for Image Restoration
Our approach, named Model Contrastive Learning for Image Restoration (MCLIR), rejuvenates latency models as negative models, making it compatible with diverse image restoration tasks.
Ranked #13 on
Image Super-Resolution
on Manga109 - 4x upscaling
FLIQS: One-Shot Mixed-Precision Floating-Point and Integer Quantization Search
With integer models, we increase the accuracy of ResNet-18 on ImageNet by 1. 31% and ResNet-50 by 0. 90% with equivalent model cost over previous methods.
Fully $1\times1$ Convolutional Network for Lightweight Image Super-Resolution
By incorporating a parameter-free spatial-shift operation, it equips the fully $1\times1$ convolutional network with powerful representation capability while impressive computational efficiency.
The RoboDepth Challenge: Methods and Advancements Towards Robust Depth Estimation
In this paper, we summarize the winning solutions from the RoboDepth Challenge -- an academic competition designed to facilitate and advance robust OoD depth estimation.
A Restarted Large-Scale Spectral Clustering with Self-Guiding and Block Diagonal Representation
Specifically, our framework has a potential boost for clustering algorithms and works well even using an initial guess chosen randomly.
Two-Way Semantic Transmission of Images without Feedback
As a competitive technology for 6G, semantic communications can significantly improve transmission efficiency.
Syntax-aware Hybrid prompt model for Few-shot multi-modal sentiment analysis
Multimodal Sentiment Analysis (MSA) has been a popular topic in natural language processing nowadays, at both sentence and aspect level.
Dual-Granularity Contrastive Learning for Session-based Recommendation
At factor-level, we employ Disentangled Representation Learning to obtain finer-grained data(e. g. factor-level embeddings), with which we can construct factor-level convolution channels.
Discreetly Exploiting Inter-session Information for Session-based Recommendation
First, inter-session dependencies are not differentiated at the factor-level.
Incorporating Transformer Designs into Convolutions for Lightweight Image Super-Resolution
Building upon the NA module, we propose a lightweight single image super-resolution (SISR) network named TCSR.
Distributed Two-tier DRL Framework for Cell-Free Network: Association, Beamforming and Power Allocation
Intelligent wireless networks have long been expected to have self-configuration and self-optimization capabilities to adapt to various environments and demands.
TripLe: Revisiting Pretrained Model Reuse and Progressive Learning for Efficient Vision Transformer Scaling and Searching
One promising way to accelerate transformer training is to reuse small pretrained models to initialize the transformer, as their existing representation power facilitates faster model convergence.
LayoutDETR: Detection Transformer Is a Good Multimodal Layout Designer
Graphic layout designs play an essential role in visual communication.
ESIE-BERT: Enriching Sub-words Information Explicitly with BERT for Joint Intent Classification and SlotFilling
We address the problem by introducing a novel joint method on top of BERT which explicitly models the multiple sub-tokens features after wordpiece tokenization, thereby contributing to the two tasks.
BotSIM: An End-to-End Bot Simulation Framework for Commercial Task-Oriented Dialog Systems
We have open-sourced the toolkit at https://github. com/salesforce/botsim
Channel Estimation for RIS-Aided Multi-User mmWave Systems with Uniform Planar Arrays
Specifically, in Stage I, the channel state information (CSI) of a typical user is estimated.
Show Me What I Like: Detecting User-Specific Video Highlights Using Content-Based Multi-Head Attention
We propose a method to detect individualized highlights for users on given target videos based on their preferred highlight clips marked on previous videos they have watched.
GLaMa: Joint Spatial and Frequency Loss for General Image Inpainting
Our proposed GLaMa can better capture different types of missing information by using more types of masks.
Effectively Using Long and Short Sessions for Multi-Session-based Recommendations
The RNN often used in previous work is not suitable to process short sessions, because RNN only focuses on the sequential relationship, which we find is not the only relationship between items in short sessions.
Converse: A Tree-Based Modular Task-Oriented Dialogue System
At the core of the struggle is the need to script every single turn of interactions between the bot and the human user.
Online MAP Inference and Learning for Nonsymmetric Determinantal Point Processes
In this paper, we introduce the online and streaming MAP inference and learning problems for Non-symmetric Determinantal Point Processes (NDPPs) where data points arrive in an arbitrary order and the algorithms are constrained to use a single-pass over the data as well as sub-linear memory.
A Practical Contrastive Learning Framework for Single-Image Super-Resolution
Contrastive learning has achieved remarkable success on various high-level tasks, but there are fewer contrastive learning-based methods proposed for low-level tasks.
HighlightMe: Detecting Highlights from Human-Centric Videos
We train our network to map the activity- and interaction-based latent structural representations of the different modalities to per-frame highlight scores based on the representativeness of the frames.
Stability of singular solutions to the Navier-Stokes system
We present results on asymptotic properties of such solutions either for large values of the space variables (so called the far-field asymptotics) or for large values of time.
Analysis of PDEs 35A21, 35B40, 35C06, 35Q30, 76D05
Structured Policy Iteration for Linear Quadratic Regulator
In this paper, we introduce the \textit{Structured Policy Iteration} (S-PI) for LQR, a method capable of deriving a structured linear policy.
Scalable Bid Landscape Forecasting in Real-time Bidding
The highest bidding advertiser wins but pays only the second-highest bid (known as the winning price).
Deep Relational Factorization Machines
Factorization Machines (FMs) is an important supervised learning approach due to its unique ability to capture feature interactions when dealing with high-dimensional sparse data.
Higher-Order Ranking and Link Prediction: From Closing Triangles to Closing Higher-Order Motifs
In this work, we investigate higher-order network motifs and develop techniques based on the notion of closing higher-order motifs that move beyond closing simple triangles.
A theoretical contribution to the fast implementation of null linear discriminant analysis method using random matrix multiplication with scatter matrices
The null linear discriminant analysis method is a competitive approach for dimensionality reduction.
EXTRA: An Exact First-Order Algorithm for Decentralized Consensus Optimization
In this paper, we develop a decentralized algorithm for the consensus optimization problem $$\min\limits_{x\in\mathbb{R}^p}~\bar{f}(x)=\frac{1}{n}\sum\limits_{i=1}^n f_i(x),$$ which is defined over a connected network of $n$ agents, where each function $f_i$ is held privately by agent $i$ and encodes the agent's data and objective.
Optimization and Control
