Search Results for author:
Found 23 papers, 9 papers with code
FunReason: Enhancing Large Language Models' Function Calling via Self-Refinement Multiscale Loss and Automated Data Refinement
FunReason provides a comprehensive solution for enhancing LLMs' function calling capabilities by introducing a balanced training methodology and a data refinement pipeline.
PiCo: Enhancing Text-Image Alignment with Improved Noise Selection and Precise Mask Control in Diffusion Models
In this work, we highlight two factors that affect this alignment: the quality of the randomly initialized noise and the reliability of the generated controlling mask.
Uni4D: A Unified Self-Supervised Learning Framework for Point Cloud Videos
Self-supervised representation learning for point cloud videos remains a challenging problem with two key limitations: (1) existing methods rely on explicit knowledge to learn motion, resulting in suboptimal representations; (2) prior Masked AutoEncoder (MAE) frameworks struggle to bridge the gap between low-level geometry and high-level dynamics in 4D data.
SQLCritic: Correcting Text-to-SQL Generation via Clause-wise Critic
Existing refinement methods in LLM-based Text-to-SQL systems exhibit limited effectiveness.
CSR:Achieving 1 Bit Key-Value Cache via Sparse Representation
The emergence of long-context text applications utilizing large language models (LLMs) has presented significant scalability challenges, particularly in memory footprint.
Explainable Behavior Cloning: Teaching Large Language Model Agents through Learning by Demonstration
In this paper, we propose an Explainable Behavior Cloning LLM Agent (EBC-LLMAgent), a novel approach that combines large language models (LLMs) with behavior cloning by learning demonstrations to create intelligent and explainable agents for autonomous mobile app interaction.
DiffuseST: Unleashing the Capability of the Diffusion Model for Style Transfer
Style transfer aims to fuse the artistic representation of a style image with the structural information of a content image.
Magnet: We Never Know How Text-to-Image Diffusion Models Work, Until We Learn How Vision-Language Models Function
In this work, we critically examine the limitations of the CLIP text encoder in understanding attributes and investigate how this affects diffusion models.
Mitigate Position Bias with Coupled Ranking Bias on CTR Prediction
Using both synthetic and industrial datasets, we first show how this widely coexisted ranking bias deteriorates the performance of the existing position bias estimation methods.
CDFormer:When Degradation Prediction Embraces Diffusion Model for Blind Image Super-Resolution
Existing Blind image Super-Resolution (BSR) methods focus on estimating either kernel or degradation information, but have long overlooked the essential content details.
Exploring Heterogeneity and Uncertainty for Graph-based Cognitive Diagnosis Models in Intelligent Education
Specifically, to explore heterogeneity, we propose a semantic-aware graph neural networks based CD model.
DNS-Rec: Data-aware Neural Architecture Search for Recommender Systems
Our principal contribution is the development of a Data-aware Neural Architecture Search for Recommender System (DNS-Rec).
MoDE: A Mixture-of-Experts Model with Mutual Distillation among the Experts
However, the gate's routing mechanism also gives rise to narrow vision: the individual MoE's expert fails to use more samples in learning the allocated sub-task, which in turn limits the MoE to further improve its generalization ability.
CharPoet: A Chinese Classical Poetry Generation System Based on Token-free LLM
A video demonstration of CharPoet is available at https://youtu. be/voZ25qEp3Dc.
CDFormer: When Degradation Prediction Embraces Diffusion Model for Blind Image Super-Resolution
Existing Blind image Super-Resolution (BSR) methods focus on estimating either kernel or degradation information but have long overlooked the essential content details.
Lookahead: An Inference Acceleration Framework for Large Language Model with Lossless Generation Accuracy
Instead of generating a single token at a time, we propose a Trie-based retrieval and verification mechanism to be able to accept several tokens at a forward step.
GreenFlow: A Computation Allocation Framework for Building Environmentally Sound Recommendation System
of a cascade RS, when a user triggers a request, we define two actions that determine the computation: (1) the trained instances of models with different computational complexity; and (2) the number of items to be inferred in the stage.
Large Multimodal Model Compression via Efficient Pruning and Distillation at AntGroup
In our research, we constructed a dataset, the Multimodal Advertisement Audition Dataset (MAAD), from real-world scenarios within Alipay, and conducted experiments to validate the reliability of our proposed strategy.
Intelligent Virtual Assistants with LLM-based Process Automation
This paper proposes a novel LLM-based virtual assistant that can automatically perform multi-step operations within mobile apps based on high-level user requests.
Fast Chain-of-Thought: A Glance of Future from Parallel Decoding Leads to Answers Faster
In this work, we propose FastCoT, a model-agnostic framework based on parallel decoding without any further training of an auxiliary model or modification to the LLM itself.
Tensorized Hypergraph Neural Networks
THNN is a faithful hypergraph modeling framework through high-order outer product feature message passing and is a natural tensor extension of the adjacency-matrix-based graph neural networks.
hpGAT: High-order Proximity Informed Graph Attention Network
Graph neural networks (GNNs) have recently made remarkable breakthroughs in the paradigm of learning with graph-structured data.
Ranked #37 on
Node Classification
on Citeseer
