Search Results for author:
Found 46 papers, 11 papers with code
KaLM-Embedding-V2: Superior Training Techniques and Data Inspire A Versatile Embedding Model
In this paper, we propose KaLM-Embedding-V2, a versatile and compact embedding model, which achieves impressive performance in general-purpose text embedding tasks by leveraging superior training techniques and data.
D2R: dual regularization loss with collaborative adversarial generation for model robustness
The adversarial distribution and clean distribution optimizations enhance the target model's robustness by leveraging the strengths of different loss functions obtained via a suitable function space exploration to focus more precisely on the target model's distribution.
VerIPO: Cultivating Long Reasoning in Video-LLMs via Verifier-Gudied Iterative Policy Optimization
Applying Reinforcement Learning (RL) to Video Large Language Models (Video-LLMs) shows significant promise for complex video reasoning.
U2-BENCH: Benchmarking Large Vision-Language Models on Ultrasound Understanding
Ultrasound is a widely-used imaging modality critical to global healthcare, yet its interpretation remains challenging due to its varying image quality on operators, noises, and anatomical structures.
Sparse Attention Remapping with Clustering for Efficient LLM Decoding on PIM
Transformer-based models are the foundation of modern machine learning, but their execution, particularly during autoregressive decoding in large language models (LLMs), places significant pressure on memory systems due to frequent memory accesses and growing key-value (KV) caches.
Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models
Large Multimodal Reasoning Models (LMRMs) have emerged as a promising paradigm, integrating modalities such as text, images, audio, and video to support complex reasoning capabilities and aiming to achieve comprehensive perception, precise understanding, and deep reasoning.
Take Off the Training Wheels Progressive In-Context Learning for Effective Alignment
We find that the transformer embeds the task function learned from demonstrations into the separator token representation, which plays an important role in the generation of prior response tokens.
TAET: Two-Stage Adversarial Equalization Training on Long-Tailed Distributions
This paper provides a comprehensive analysis of adversarial training under long-tailed distributions and identifies limitations in the current state-of-the-art method, AT-BSL, in achieving robust performance under such conditions.
Picking the Cream of the Crop: Visual-Centric Data Selection with Collaborative Agents
Specifically, our approach consists of 1) an image information quantification method via visual agents collaboration to select images with rich visual information, and 2) a visual-centric instruction quality assessment method to select high-quality instruction data related to high-quality images.
Importance-Aware Source-Channel Coding for Multi-Modal Task-Oriented Semantic Communication
This paper explores the concept of information importance in multi-modal task-oriented semantic communication systems, emphasizing the need for high accuracy and efficiency to fulfill task-specific objectives.
Bayesian Beamforming for Integrated Sensing and Communication Systems
The uncertainty of the sensing target brings great challenge to the beamforming design of the integrated sensing and communication (ISAC) system.
A Unified Analysis of Stochastic Gradient Descent with Arbitrary Data Permutations and Beyond
Using the general assumption, we develop a unified framework for permutation-based SGD with arbitrary permutations of examples, incorporating all the aforementioned representative algorithms.
Collaborative Channel Access and Transmission for NR Sidelink and Wi-Fi Coexistence over Unlicensed Spectrum
To address this demand, 5G-Advanced has introduced sidelink communication over the unlicensed spectrum (SL-U) to increase data rates.
Multivariate Wireless Link Quality Prediction Based on Pre-trained Large Language Models
In this paper, we propose GAT-LLM, a novel multivariate wireless link quality prediction model that combines Large Language Models (LLMs) with Graph Attention Networks (GAT) to enable accurate and reliable multivariate LQP of wireless communications.
KaLM-Embedding: Superior Training Data Brings A Stronger Embedding Model
As retrieval-augmented generation prevails in large language models, embedding models are becoming increasingly crucial.
A CSI Feedback Framework based on Transmitting the Important Values and Generating the Others
The application of deep learning (DL)-based channel state information (CSI) feedback frameworks in massive multiple-input multiple-output (MIMO) systems has significantly improved reconstruction accuracy.
Joint Beamforming for Multi-target Detection and Multi-user Communication in ISAC Systems
Sensing and communication suffer from a performance trade-off in ISAC systems.
Guardians of Discourse: Evaluating LLMs on Multilingual Offensive Language Detection
Identifying offensive language is essential for maintaining safety and sustainability in the social media era.
Medico: Towards Hallucination Detection and Correction with Multi-source Evidence Fusion
Therefore, it is necessary to resort to external knowledge to detect and correct the hallucinated content.
Joint Beamforming for Backscatter Integrated Sensing and Communication
Integrated sensing and communication (ISAC) is a key technology of next generation wireless communication.
Rate-Distortion-Perception Controllable Joint Source-Channel Coding for High-Fidelity Generative Communications
Based on this framework, we introduce a distortion-perception controllable transmission (DPCT) model, which addresses the variation in the perception-distortion trade-off.
Dynamic Label Adversarial Training for Deep Learning Robustness Against Adversarial Attacks
Additionally, we found that a budgeted dimension of inner optimization for the target model may contribute to the trade-off between clean accuracy and robust accuracy.
Csi-LLM: A Novel Downlink Channel Prediction Method Aligned with LLM Pre-Training
In this work, we introduce Csi-LLM, a novel LLM-powered downlink channel prediction technique that models variable-step historical sequences.
B-ISAC: Backscatter Integrated Sensing and Communication for IoE Applications
In this paper, we propose a novel cognitive wireless system called backscatter-ISAC (B-ISAC) and develop a joint beamforming framework for different stages (task modes).
In-Context Learning State Vector with Inner and Momentum Optimization
In this paper, we address this gap by presenting a comprehensive analysis of these compressed vectors, drawing parallels to the parameters trained with gradient descent, and introduce the concept of state vector.
Robotics and Computer-Integrated Manufacturing
In real- world experiments on grasping objects in different shapes and trajectories, the average grasping prediction success rate (GPSR) and grasping reaching success rate (GRSR) of MA-TD3H are above 90 percent and 80 percent respectively, and the average GRSR is improved by 20–30 percent compared with the other algorithms.
Improving Attributed Text Generation of Large Language Models via Preference Learning
Large language models have been widely adopted in natural language processing, yet they face the challenge of generating unreliable content.
P2LHAP:Wearable sensor-based human activity recognition, segmentation and forecast through Patch-to-Label Seq2Seq Transformer
Traditional deep learning methods struggle to simultaneously segment, recognize, and forecast human activities from sensor data.
Enhance DNN Adversarial Robustness and Efficiency via Injecting Noise to Non-Essential Neurons
Deep Neural Networks (DNNs) have revolutionized a wide range of industries, from healthcare and finance to automotive, by offering unparalleled capabilities in data analysis and decision-making.
Point Transformer with Federated Learning for Predicting Breast Cancer HER2 Status from Hematoxylin and Eosin-Stained Whole Slide Images
Furthermore, we demonstrate that our model can generalize to two unseen sites with 229 WSIs.
Dig-CSI: A Distributed and Generative Model Assisted CSI Feedback Training Framework
The advent of deep learning (DL)-based models has significantly advanced Channel State Information (CSI) feedback mechanisms in wireless communication systems.
A Survey of Large Language Models Attribution
Open-domain generative systems have gained significant attention in the field of conversational AI (e. g., generative search engines).
Explaining How a Neural Network Play the Go Game and Let People Learn
The AI model has surpassed human players in the game of Go, and it is widely believed that the AI model has encoded new knowledge about the Go game beyond human players.
Separate the Wheat from the Chaff: Model Deficiency Unlearning via Parameter-Efficient Module Operation
To evaluate the effectiveness of our approach in terms of truthfulness and detoxification, we conduct extensive experiments on LLMs, encompassing additional abilities such as language modeling and mathematical reasoning.
HybridCVLNet: A Hybrid CSI Feedback System and its Domain Adaptation
Deep Learning (DL)-based channel state information (CSI) feedback is a promising technique for the transmitter to accurately acquire the CSI of massive multiple-input multiple-output (MIMO) systems.
Task-Balanced Distillation for Object Detection
To alleviate this problem, a novel Task-decoupled Feature Distillation (TFD) is proposed by flexibly balancing the contributions of classification and regression tasks.
Look Before You Leap: Safe Model-Based Reinforcement Learning with Human Intervention
Safety has become one of the main challenges of applying deep reinforcement learning to real world systems.
Multi-Faceted Representation Learning with Hybrid Architecture for Time Series Classification
Time series classification problems exist in many fields and have been explored for a couple of decades.
A Markovian Model-Driven Deep Learning Framework for Massive MIMO CSI Feedback
Forward channel state information (CSI) often plays a vital role in scheduling and capacity-approaching transmission optimization for massive multiple-input multiple-output (MIMO) communication systems.
Text Classification based on Multi-granularity Attention Hybrid Neural Network
Conventionally, there are two mainstream neural architectures for NLP tasks: the recurrent neural network (RNN) and the convolution neural network (ConvNet).
Multichannel CNN with Attention for Text Classification
Alternatively, CNN is able to capture n-gram features of texts by utilizing convolutional filters.
Human Activity Recognition based on Dynamic Spatio-Temporal Relations
In the proposed method, an activity is divided into several successive actions represented by spatio temporal patterns, and the evolution of these actions are captured by a sequential model.
A Novel Decision Tree for Depression Recognition in Speech
Depression is a common mental disorder worldwide which causes a range of serious outcomes.
MODMA dataset: a Multi-modal Open Dataset for Mental-disorder Analysis
The EEG dataset includes not only data collected using traditional 128-electrodes mounted elastic cap, but also a novel wearable 3-electrode EEG collector for pervasive applications.
Computation Error Analysis of Block Floating Point Arithmetic Oriented Convolution Neural Network Accelerator Design
The heavy burdens of computation and off-chip traffic impede deploying the large scale convolution neural network on embedded platforms.
