Search Results for author:
Found 53 papers, 22 papers with code
Visual Prompt Tuning for Few-Shot Text Classification
In few-shot text classification, a feasible paradigm for deploying VL-PTMs is to align the input samples and their category names via the text encoders.
Pre-train, Align, and Disentangle: Empowering Sequential Recommendation with Large Language Models
Sequential recommendation (SR) aims to model the sequential dependencies in users' historical interactions to better capture their evolving interests.
HunyuanVideo: A Systematic Framework For Large Video Generative Models
In this report, we introduce HunyuanVideo, an innovative open-source video foundation model that demonstrates performance in video generation comparable to, or even surpassing, that of leading closed-source models.
LEADRE: Multi-Faceted Knowledge Enhanced LLM Empowered Display Advertisement Recommender System
Display advertising provides significant value to advertisers, publishers, and users.
Scaling Mesh Generation via Compressive Tokenization
We propose a compressive yet effective mesh representation, Blocked and Patchified Tokenization (BPT), facilitating the generation of meshes exceeding 8k faces.
Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent
In this paper, we introduce Hunyuan-Large, which is currently the largest open-source Transformer-based mixture of experts model, with a total of 389 billion parameters and 52 billion activation parameters, capable of handling up to 256K tokens.
Tencent Hunyuan3D-1.0: A Unified Framework for Text-to-3D and Image-to-3D Generation
To address this issue, we propose a two-stage approach named Hunyuan3D-1. 0 including a lite version and a standard version, that both support text- and image-conditioned generation.
EEGPT: Unleashing the Potential of EEG Generalist Foundation Model by Autoregressive Pre-training
First, we propose an electrode-wise modeling strategy that treats each electrode as a fundamental unit, enabling the integration of diverse EEG datasets collected from up to 138 electrodes, amassing 37. 5M pre-training samples.
Towards Scalable Semantic Representation for Recommendation
With recent advances in large language models (LLMs), there has been emerging numbers of research in developing Semantic IDs based on LLMs to enhance the performance of recommendation systems.
Long-Sequence Recommendation Models Need Decoupled Embeddings
In this work, we identify and characterize, for the first time, a neglected deficiency in existing long-sequence recommendation models: a single set of embeddings struggles with learning both attention and representation, leading to interference between these two processes.
ADSNet: Cross-Domain LTV Prediction with an Adaptive Siamese Network in Advertising
We introduce a gain evaluation strategy to calculate information gain, aiding the model in learning helpful information for the target domain and providing the ability to reject noisy samples, thus avoiding negative transfer.
Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding
For fine-grained language understanding, we train a Multimodal Large Language Model to refine the captions of the images.
Deep Event-based Object Detection in Autonomous Driving: A Survey
Object detection plays a critical role in autonomous driving, where accurately and efficiently detecting objects in fast-moving scenes is crucial.
Self-Bootstrapped Visual-Language Model for Knowledge Selection and Question Answering
Motivated by the research of retrieval-augmented generation in the field of natural language processing, we use Dense Passage Retrieval (DPR) to retrieve related knowledge to help the model answer questions.
Deep Pattern Network for Click-Through Rate Prediction
These patterns harbor substantial potential to significantly enhance CTR prediction performance.
Understanding the Ranking Loss for Recommendation with Sparse User Feedback
We introduce a novel perspective on the effectiveness of the auxiliary ranking loss in CTR prediction: it generates larger gradients on negative samples, thereby mitigating the optimization difficulties when using the BCE loss only and resulting in improved classification ability.
Towards Training A Chinese Large Language Model for Anesthesiology
3) We introduce a standardized benchmark for evaluating medical LLM in Anesthesiology.
Retrieval-Augmented Generation for AI-Generated Content: A Survey
We first classify RAG foundations according to how the retriever augments the generator, distilling the fundamental abstractions of the augmentation methodologies for various retrievers and generators.
Ads Recommendation in a Collapsed and Entangled World
We present Tencent's ads recommendation system and examine the challenges and practices of learning appropriate recommendation representations.
Emulating Complex Synapses Using Interlinked Proton Conductors
The memory consolidation from coupled storage components is revealed by both numerical simulations and experimental observations.
Deep Neural Network Solutions for Oscillatory Fredholm Integral Equations
We first developed a numerical method for solving the equation with DNNs as an approximate solution by designing a numerical quadrature that tailors to computing oscillatory integrals involving DNNs.
MRFS: Mutually Reinforcing Image Fusion and Segmentation
Then the cascade of IGM-Att and PC-Att couples image fusion and semantic segmentation tasks implicitly bringing vision-related and semantics-related features into closer alignment.
Pareto-based Multi-Objective Recommender System with Forgetting Curve
Considering recency effect in memories, we propose a forgetting model based on Ebbinghaus Forgetting Curve to cope with negative feedback.
LGFCTR: Local and Global Feature Convolutional Transformer for Image Matching
Inspired by the locality and implicit positional encoding of convolutions, a novel convolutional transformer is proposed to capture both local contexts and global structures more sufficiently for detector-free matching.
On the Embedding Collapse when Scaling up Recommendation Models
On the one hand, interacting with collapsed embeddings restricts embedding learning and exacerbates the collapse issue.
Decoupled Training: Return of Frustratingly Easy Multi-Domain Learning
Multi-domain learning (MDL) aims to train a model with minimal average risk across multiple overlapping but non-identical domains.
STEM: Unleashing the Power of Embeddings for Multi-task Recommendation
Surprisingly, negative transfer still occurs in existing MTL methods on samples that receive comparable feedback across tasks.
Temporal Interest Network for User Response Prediction
To fill this gap, we propose a Temporal Interest Network (TIN) to capture the semantic-temporal correlation simultaneously between behaviors and the target.
Global and Local Semantic Completion Learning for Vision-Language Pre-training
MGSC promotes learning more representative global features, which have a great impact on the performance of downstream tasks, while MLTC reconstructs modal-fusion local tokens, further enhancing accurate comprehension of multimodal data.
VLPD: Context-Aware Pedestrian Detection via Vision-Language Semantic Self-Supervision
Firstly, we propose a self-supervised Vision-Language Semantic (VLS) segmentation method, which learns both fully-supervised pedestrian detection and contextual segmentation via self-generated explicit labels of semantic classes by vision-language models.
Ranked #5 on
Pedestrian Detection
on Caltech
ForkMerge: Mitigating Negative Transfer in Auxiliary-Task Learning
Auxiliary-Task Learning (ATL) aims to improve the performance of the target task by leveraging the knowledge obtained from related tasks.
The state-of-the-art 3D anisotropic intracranial hemorrhage segmentation on non-contrast head CT: The INSTANCE challenge
It is intended to resolve the above-mentioned problems and promote the development of both intracranial hemorrhage segmentation and anisotropic data processing.
Tencent AVS: A Holistic Ads Video Dataset for Multi-modal Scene Segmentation
Therefore, TAVS is distinguished from previous temporal segmentation datasets due to its multi-modal information, holistic view of categories, and hierarchical granularities.
AdaTask: A Task-aware Adaptive Learning Rate Approach to Multi-task Learning
In this paper, we propose to measure the task dominance degree of a parameter by the total updates of each task on this parameter.
Seeing What You Miss: Vision-Language Pre-training with Semantic Completion Learning
Cross-modal alignment is essential for vision-language pre-training (VLP) models to learn the correct corresponding information across different modalities.
Ranked #10 on
Zero-Shot Video Retrieval
on LSMDC
AutoAttention: Automatic Field Pair Selection for Attention in User Behavior Modeling
In this paper, we propose a novel model named AutoAttention, which includes all item/user/context side fields as the query, and assigns a learnable weight for each field pair between behavior fields and query fields.
Towards In-distribution Compatibility in Out-of-distribution Detection
Various training criteria for these auxiliary outliers are proposed based on heuristic intuitions.
DPTNet: A Dual-Path Transformer Architecture for Scene Text Detection
We further propose a parallel design that integrates the convolutional network with a powerful self-attention mechanism to provide complementary clues between the attention path and convolutional path.
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations
With multi-level representations for video and text, hierarchical contrastive learning is designed to explore fine-grained cross-modal relationships, i. e., frame-word, clip-phrase, and video-sentence, which enables HCMI to achieve a comprehensive semantic comparison between video and text modalities.
Ranked #1 on
Video Retrieval
on MSR-VTT-1kA
(using extra training data)
Exploiting Spatial-Temporal Semantic Consistency for Video Scene Parsing
Compared with image scene parsing, video scene parsing introduces temporal information, which can effectively improve the consistency and accuracy of prediction.
Pure Characteristics Demand Models and Distributionally Robust Mathematical Programs with Stochastic Complementarity Constraints
We formulate pure characteristics demand models under uncertainties of probability distributions as distributionally robust mathematical programs with stochastic complementarity constraints (DRMP-SCC).
Optimization and Control 90C15, 90C33, 90C26
New gedanken experiment on higher-dimensional asymptotically AdS Reissner-Nordström black hole
Viewing the negative cosmological constant as a dynamical quantity derived from the matter field, we study the weak cosmic censorship conjecture for the higher-dimensional asymptotically AdS Reissner-Nordstr\"om black hole.
General Relativity and Quantum Cosmology High Energy Physics - Theory
Scene Segmentation with Dual Relation-aware Attention Network
We conduct extensive experiments to validate the effectiveness of our network and achieve new state-of-the-art segmentation performance on four challenging scene segmentation data sets, i. e., Cityscapes, ADE20K, PASCAL Context, and COCO Stuff data sets.
Ranked #8 on
Semantic Segmentation
on COCO-Stuff test
The Joint Automated Repository for Various Integrated Simulations (JARVIS) for data-driven materials design
The Joint Automated Repository for Various Integrated Simulations (JARVIS) is an integrated infrastructure to accelerate materials discovery and design using density functional theory (DFT), classical force-fields (FF), and machine learning (ML) techniques.
Materials Science Computational Physics
Non-Autoregressive Image Captioning with Counterfactuals-Critical Multi-Agent Learning
In this paper, we propose a Non-Autoregressive Image Captioning (NAIC) model with a novel training paradigm: Counterfactuals-critical Multi-Agent Learning (CMAL).
KACC: A Multi-task Benchmark for Knowledge Abstraction, Concretization and Completion
Based on the datasets, we propose novel tasks such as multi-hop knowledge abstraction (MKA), multi-hop knowledge concretization (MKC) and then design a comprehensive benchmark.
AHash: A Load-Balanced One Permutation Hash
Unlike the densification to fill the empty bins after they undesirably occur, our design goal is to balance the load so as to reduce the empty bins in advance.
X-Forest: Approximate Random Projection Trees for Similarity Measurement
First, we introduced RP Trees into the tasks of similarity measurement such that accuracy is improved.
Static charged dilaton black hole cannot be overcharged by gedanken experiments
We consider the new version of the gedanken experiments proposed recently by Sorce and Wald to overcharge a static charged dilaton black hole.
High Energy Physics - Theory
Deep Learning Based Energy Disaggregation and On/Off Detection of Household Appliances
On the basis of energy disaggregation, we then investigate the performance of two deep-learning based frameworks for the task of on/off detection which aims at estimating whether an appliance is in operation or not.
DENet: A Universal Network for Counting Crowd with Varying Densities and Scales
Counting people or objects with significantly varying scales and densities has attracted much interest from the research community and yet it remains an open problem.
Accelerated Discovery of Efficient Solar-cell Materials using Quantum and Machine-learning Methods
Solar-energy plays an important role in solving serious environmental problems and meeting high-energy demand.
Materials Science
Machine Translation for Subtitling: A Large-Scale Evaluation
This article describes a large-scale evaluation of the use of Statistical Machine Translation for professional subtitling.
