Search Results for author:
Found 26 papers, 7 papers with code
iMD4GC: Incomplete Multimodal Data Integration to Advance Precise Treatment Response Prediction and Survival Analysis for Gastric Cancer
The limited availability of modalities for each patient would cause information loss, adversely affecting predictive accuracy.
Multitask Multilingual Model Adaptation with Featurized Low-Rank Mixtures
By composing feature-specific parameters for each dataset, FLix can accommodate diverse dataset mixtures and generalize better to unseen datasets.
Corrective Retrieval Augmented Generation
Experiments on four datasets covering short- and long-form generation tasks show that CRAG can significantly improve the performance of RAG-based approaches.
Efficient Tuning and Inference for Large Language Models on Textual Graphs
In this paper, we propose ENGINE, a parameter- and memory-efficient fine-tuning method for textual graphs with an LLM encoder.
Beyond Sparse Rewards: Enhancing Reinforcement Learning with Language Model Critique in Text Generation
We investigate this approach under two different settings: one where the policy model is smaller and is paired with a more powerful critic model, and another where a single language model fulfills both roles.
SPGroup3D: Superpoint Grouping Network for Indoor 3D Object Detection
To this end, we propose a novel superpoint grouping network for indoor anchor-free one-stage 3D object detection.
Ranked #4 on
3D Object Detection
on S3DIS
SiRA: Sparse Mixture of Low Rank Adaptation
Parameter Efficient Tuning has been an prominent approach to adapt the Large Language Model to downstream tasks.
Fusion-Eval: Integrating Evaluators with LLMs
Evaluating natural language systems poses significant challenges, particularly in the realms of natural language understanding and high-level reasoning.
RedCoast: A Lightweight Tool to Automate Distributed Training of LLMs on Any GPU/TPUs
In this work, we present RedCoast(Redco), a lightweight and user-friendly tool crafted to automate distributed training and inference for LLMs, as well as to simplify ML pipeline development.
GraphControl: Adding Conditional Control to Universal Graph Pre-trained Models for Graph Domain Transfer Learning
These pre-trained models can be applied to various downstream Web applications, saving training time and improving downstream (target) performance.
Critique Ability of Large Language Models
In the era of large language models (LLMs), this study explores the ability of LLMs to deliver accurate critiques across various tasks.
Cluster Language Model for Improved E-Commerce Retrieval and Ranking: Leveraging Query Similarity and Fine-Tuning for Personalized Results
This paper proposes a novel method to improve the accuracy of product search in e-commerce by utilizing a cluster language model.
Towards an On-device Agent for Text Rewriting
Large Language Models (LLMs) have demonstrated impressive capabilities for text rewriting.
MARIO: Model Agnostic Recipe for Improving OOD Generalization of Graph Contrastive Learning
In this work, we investigate the problem of out-of-distribution (OOD) generalization for unsupervised learning methods on graph data.
Analysis and tuning of a three-term DMC
Most MPC (Model Predictive Control) algorithms used in industries and studied in the control academia use a two-term QP (quadratic programming), where the first term is the weighted norm of the output errors, and the second term is that of the input increments.
RewriteLM: An Instruction-Tuned Large Language Model for Text Rewriting
In this work, we develop new strategies for instruction tuning and reinforcement learning to better align LLMs for cross-sentence rewriting tasks using diverse wording and structures expressed through natural languages including 1) generating rewriting instruction data from Wiki edits and public corpus through instruction generation and chain-of-thought prompting; 2) collecting comparison data for reward model training through a new ranking function.
SmartBERT: A Promotion of Dynamic Early Exiting Mechanism for Accelerating BERT Inference
In this paper, we propose a novel dynamic early exiting combined with layer skipping for BERT inference named SmartBERT, which adds a skipping gate and an exiting operator into each layer of BERT.
Structure-Aware Group Discrimination with Adaptive-View Graph Encoder: A Fast Graph Contrastive Learning Framework
Albeit having gained significant progress lately, large-scale graph representation learning remains expensive to train and deploy for two main reasons: (i) the repetitive computation of multi-hop message passing and non-linearity in graph neural networks (GNNs); (ii) the computational cost of complex pairwise contrastive learning loss.
SGL-PT: A Strong Graph Learner with Graph Prompt Tuning
And aiming for graph classification task, we unify pre-training and fine-tuning by designing a novel verbalizer-free prompting function, which reformulates the downstream task in a similar format as pretext task.
RoSA: A Robust Self-Aligned Framework for Node-Node Graph Contrastive Learning
To the best of our awareness, RoSA is the first work focuses on the non-aligned node-node graph contrastive learning problem.
Fostering the Robustness of White-Box Deep Neural Network Watermarks by Neuron Alignment
The wide application of deep learning techniques is boosting the regulation of deep learning models, especially deep neural networks (DNN), as commercial products.
Efficient Sensor Management for Multitarget Tracking in Passive Sensor Networks via Cauchy-Schwarz Divergence
To address this problem, we present an efficient information-theoretic approach to manage the sensors for better tracking of the unknown and time-varying number of targets.
Active Learning for Product Type Ontology Enhancement in E-commerce
Entity-based semantic search has been widely adopted in modern search engines to improve search accuracy by understanding users' intent.
Fast Coherent Point Drift
After iteration begins, our method only needs to update a diagonal matrix with linear computational complexity, and perform matrix multiplication operation with time complexity approximately O(M2) in each iteration.
Semantic Similarity Strategies for Job Title Classification
A large-scale job title classification system can power various downstream applications such as semantic search, job recommendations and labor market analytics.
