Tagged articles
domain adaptation
45 articles · Page 1 of 1
JD Retail and Nanjing University propose Road MOPD, a multi-teacher online policy distillation method that uses cross-teacher feedback on the same student response to strengthen consensus signals, weaken divergent signals, and project away conflicting gradient components, enabling simultaneous improvement across high-conflict domain pairs like math+medical and code+medical on Qwen3 models.
Qwen3cross-teacher feedbackdomain adaptation
0 likes · 15 min read

Domain-Adaptive Diffusion Policy (DADP) decouples representation learning and injects domain information into the diffusion process, enabling robots to adapt across varying friction, mass, and dynamics, achieving strong zero-shot performance on MuJoCo and Adroit benchmarks, especially in out-of-distribution scenarios.
AdroitCross-Domain ControlMuJoCo
0 likes · 11 min read

An empirical benchmark of 8,408 runs across 84 tasks shows that manually designed Agent Skills improve performance by up to 16.2 percentage points, while AI‑generated skills can hurt results, and distills six actionable conclusions for crafting useful, focused, and test‑validated skills.
AI agentsSkill designagent skills
0 likes · 7 min read

The article explains how the DOMINO method lets large language models learn a domain from just dozens of real examples instead of hand‑written prompts, describes its trainable "domain switch" architecture, and shows experimental gains on time‑varying code tasks, highlighting more robust and diverse data synthesis.
Data SynthesisDominoKDD2026
0 likes · 8 min read

This presentation explores how large language models can transcend their general knowledge limits by developing domain‑specific deep thinking abilities, addressing challenges such as complex instruction execution, expert reasoning gaps, and tool integration, and proposes reinforcement‑learning‑driven frameworks, structured thinking pipelines, and tool‑calling mechanisms to achieve rational intelligence.
deep reasoningdomain adaptationreinforcement learning
0 likes · 27 min read

This week’s AI paper roundup highlights five recent studies: a construction‑site vision‑language dataset and safety inspection tasks, a deep CORAL method for unsupervised domain adaptation, the discovery of a new family of unstable singularities in nonlinear PDEs, a reinforcement‑learning approach that boosts reasoning in large language models, and the PANORAMA architecture for omnidirectional vision in embodied AI.
Construction SafetyOmnidirectional VisionPDE Research
0 likes · 6 min read


AIWalkerSep 17, 2025 · Artificial Intelligence
This article surveys 183 recent attention‑mechanism papers, classifies them into four innovation categories, and highlights representative works such as MILA, ARFFT, CNN‑Transformer for speech emotion, and LSTM‑attention epidemic forecasting, providing concrete methods, code links, and performance insights.
2025Attention MechanismSurvey
0 likes · 7 min read

The article analyzes major limitations of large language models—hallucination, outdated knowledge, and insufficient domain expertise—and explains how Retrieval‑Augmented Generation and various fine‑tuning strategies can address these issues while outlining practical cost considerations.
RAGdomain adaptationfine-tuning
0 likes · 4 min read

Continuing pretraining (CP) bridges pretraining and SFT to inject domain knowledge, but faces catastrophic forgetting; this article explores leveraging importance sampling to balance common and domain data, discusses data selection, annealing strategies, and practical tips for mitigating forgetting while enhancing specialized capabilities.
Catastrophic ForgettingContinue PretrainingImportance Sampling
0 likes · 8 min read

This article presents the Fudan University Knowledge Workshop Lab's comprehensive research on domain large models, covering background, domain adaptation, capability enhancement, collaborative workflows, challenges such as inference cost and alignment, and proposed solutions including source‑enhanced training, self‑correction mechanisms, and hybrid retrieval‑augmented generation.
AI researchSelf-Correctiondomain adaptation
0 likes · 16 min read

ADSNet introduces an adaptive Siamese network for cross‑domain lifetime value (LTV) prediction in advertising, leveraging external channel data to mitigate sample sparsity, employing gain‑based sample selection, domain adaptation, and ordinal classification to improve pLTV accuracy and address negative transfer.
AdvertisingCross-Domain TransferLTV prediction
0 likes · 12 min read

This article presents an overview of graph knowledge transfer, discussing the data‑hungry problem, distribution shift in graph data, the Knowledge Bridge Learning (KBL) paradigm, the Bridged‑GNN implementation, experimental results across multiple scenarios, and future research directions.
bridged-GNNdomain adaptationgraph representation learning
0 likes · 19 min read

This article presents a comprehensive guide to data engineering for research‑focused large language models, covering domain‑adaptive pre‑training, supervised fine‑tuning, retrieval‑augmented generation, dataset construction, data cleaning pipelines, token‑izer adaptation, and prompt engineering best practices to boost model performance in specialized tasks.
Data EngineeringFine‑TuningLLM
0 likes · 20 min read


NewBeeNLPJun 24, 2024 · Artificial Intelligence
This article reviews Fudan University's Knowledge Factory Lab research on domain large models, covering background, three major deployment challenges, data‑selection strategies, ability‑enhancement techniques, collaborative workflows, and retrieval‑augmented generation methods that aim to make large models practical for real‑world tasks.
Knowledge Extractiondomain adaptationlarge language models
0 likes · 18 min read

This article presents Fudan University's Knowledge Factory Lab research on domain large models, covering background, challenges, data selection, source‑enhanced tagging, capability improvements, self‑correction, collaborative workflows, and retrieval‑augmented generation for practical AI deployment.
AI researchSelf-Correctiondomain adaptation
0 likes · 16 min read

This article presents a comprehensive overview of graph knowledge transfer, covering its definition, the data‑hungry problem, distribution shift challenges, the Knowledge Bridge Learning (KBL) framework, the Bridged‑GNN model, extensive experiments on real‑world scenarios, and a concluding Q&A session.
Graph Neural Networksdomain adaptationgraph learning
0 likes · 22 min read

This article introduces causal learning, explains its distinction from traditional correlation‑based machine learning, outlines its three main parts, discusses the two primary paradigms—learning with known causal graphs and learning via causal discovery—and highlights their advantages, challenges, and recent research directions.
Causal Inferencecausal discoverycausal learning
0 likes · 11 min read

This article presents a comprehensive overview of how knowledge graphs are leveraged in e‑commerce AIGC pipelines, detailing domain‑specific and general graph‑based text generation, model architecture, controllable generation techniques, experimental results, and future directions for large language model integration.
AIGCdomain adaptatione-commerce
0 likes · 22 min read

This article introduces the KANGAROO model, which injects hierarchical semantic information via hyperbolic space and leverages contrastive learning on dense subgraph structures to overcome global sparsity in vertical‑domain knowledge‑enhanced pre‑trained language models, and evaluates its performance on finance and medical tasks.
Contrastive LearningNLPdomain adaptation
0 likes · 10 min read

This article reviews the growing interest in causal learning within machine learning, explaining what causal learning is, its advantages over purely correlational methods, and detailing two main paradigms—learning with known causal structures and learning via causal discovery—along with examples, challenges, and future directions.
Causal Inferencecausal discoverycausal learning
0 likes · 12 min read

This article presents the development and evaluation of EcomGPT, a domain‑specific large language model for e‑commerce, detailing dataset construction, instruction‑tuning methods, experimental results, and the impact of atomic tasks on model performance.
EcomGPTdomain adaptatione-commerce NLP
0 likes · 9 min read

This article reviews eight CVPR 2023 papers selected by Meituan’s technology team, covering self‑supervised learning, domain adaptation, federated learning, object detection, 3D reconstruction, GAN‑based pre‑training, RGB‑T tracking, vision‑language navigation, and visual‑textual layout generation, highlighting each work’s methodology, experiments, and reported performance gains.
3D Object DetectionCVPR 2023Computer Vision
0 likes · 15 min read

This presentation introduces a decoupled domain‑adaptation network that separates popularity and attribute representations to mitigate popularity bias in recommender systems, describing the problem, existing IPS and causal‑inference solutions, the CD2AN architecture, experimental results, and practical Q&A.
AIdomain adaptationmachine learning
0 likes · 13 min read

This article reviews recent advances in graph transfer learning, introduces the novel VS-Graph scenario for knowledge transfer between dominant and silent nodes, and details the Knowledge Transferable Graph Neural Network (KTGNN) framework with domain‑adaptive feature completion, message passing, and transferable classifier modules, highlighting experimental results and future research directions.
AIGraph Neural NetworksVS-Graph
0 likes · 27 min read

This article reviews recent developments in causal representation learning, explaining why causal reasoning is essential, describing methods for i.i.d. data, time‑series, and multi‑distribution scenarios, and illustrating applications such as domain adaptation, video analysis, and financial data with numerous examples and visualizations.
Causal InferenceRepresentation Learningcausal discovery
0 likes · 22 min read

The Adaptive Domain Interest Network (ADIN) introduces a shared backbone with scenario‑specific subnetworks, domain‑specific batch normalization and SE‑Block attention to capture both commonalities and divergences across recommendation scenarios, and, combined with self‑supervised training, consistently outperforms baselines, delivering a 1.8% revenue lift in Alibaba’s display‑ad platform and now runs in production.
Self-Supervised Learningdeep learningdomain adaptation
0 likes · 12 min read

This article presents a comprehensive overview of lightweight adaptation methods—including language, domain, and optimization‑goal adapters and structured prompts—to overcome language mismatch, low domain fit, and objective differences when deploying open‑source multimodal large models in real‑world AI applications.
AIAdapterMultimodal Models
0 likes · 14 min read

The paper proposes CDAN, a dual‑tower retrieval model that separates item attribute and popularity representations via a Feature Decoupling Module with orthogonal embeddings, aligns head‑tail attribute distributions using MMD and contrastive learning, and jointly trains biased and unbiased towers, achieving higher tail recall, lower exposure concentration, and measurable online click‑through improvements.
Contrastive Learningdomain adaptationdual-tower model
0 likes · 13 min read

The paper introduces UKD, an uncertainty‑regularized knowledge‑distillation framework that uses a click‑adaptive teacher to generate pseudo‑conversion labels for unclicked impressions and trains a student model with uncertainty‑weighted loss, thereby mitigating sample‑selection bias and achieving up to 3.4% CVR improvement and 4.3% CPA reduction on large‑scale advertising datasets.
CVR debiasingadvertising algorithmsconversion rate estimation
0 likes · 20 min read


Code DAOApr 24, 2022 · Artificial Intelligence
The article explains how transfer learning reduces data and time requirements in deep learning by reusing pretrained models for vision, natural language processing, and reinforcement learning, while discussing challenges such as overfitting, the need for progressive networks, entropy regularization, domain adaptation, multi‑task learning, and model distillation.
deep learningdomain adaptationmodel distillation
0 likes · 10 min read

This talk presents a comprehensive overview of music-domain Named Entity Recognition, covering its definition, unique challenges, candidate generation, training data construction, offline and online system architecture, successive model improvements (V1‑V3), knowledge‑fusion techniques, and future research directions.
Knowledge FusionMusicNER
0 likes · 25 min read

This article introduces the fundamentals of transfer learning, formalizes its theoretical foundations, and demonstrates how multi‑task learning and domain adaptation techniques can be applied to financial risk control to overcome label scarcity, distribution shift, and improve model performance.
artificial intelligencedomain adaptationfinancial risk control
0 likes · 17 min read

By constructing virtual mirror samples that occupy identical positions across source and target domains, the authors eliminate covariate shift while preserving distribution structure, enabling superior unsupervised domain adaptation that achieves state‑of‑the‑art performance on Office and VisDA benchmarks and improves real‑world lighting and gender‑recognition tasks.
AI researchSOTAcovariate shift
0 likes · 3 min read

This article introduces the fundamentals of transfer learning, explains its theoretical foundations and formulas, and demonstrates how multi‑task learning and domain‑adaptation techniques are applied to financial risk‑control scenarios to overcome label scarcity, distribution shift, and model complexity challenges, presenting detailed experimental results and analysis.
Model Evaluationdeep learningdomain adaptation
0 likes · 17 min read

Kuaishou secured 14 accepted papers at CVPR 2021, spanning 3D hand mesh recovery, unsupervised keypoint detection, point cloud completion, modular interactive video segmentation, deep video matting, co‑salient object detection, occlusion‑aware instance segmentation, semantic image matting, and face forgery detection, showcasing the maturity of its research collaborations.
CVPRFace Forgery Detectiondomain adaptation
0 likes · 14 min read

This article reviews the CVPR2021 paper on Regressive Domain Adaptation (RegDA) for unsupervised keypoint detection, explaining its motivation, novel adversarial regression framework, sparse output-space modeling, min‑min training strategy, extensive experiments, and the resulting performance gains across multiple datasets.
Computer VisionUnsupervised Learningdomain adaptation
0 likes · 13 min read

At a CVPR 2021 pre‑lecture, Meituan’s Visual Intelligence Center showcased five cutting‑edge papers—VisTR transformer‑based video instance segmentation, a feature‑decomposition facial expression recognizer, an accelerated BiSeNet for real‑time semantic segmentation, an embedded discriminative attention mechanism for weakly supervised segmentation, and a partial‑feature selection framework for multi‑source domain adaptation—highlighting the company’s large AI R&D team, university collaborations, real‑world deployment across its services, and ongoing recruitment.
AICVPR2021Facial Expression Recognition
0 likes · 10 min read

AAAI 2021, the premier AI conference with a 21.4% acceptance rate, accepted four papers from Alibaba Entertainment covering non‑stationary stochastic bandits with graph feedback, spatial‑temporal causal inference for image‑to‑video adaptation, a unified MRC framework for aspect‑based sentiment analysis, and amodal segmentation using shape priors.
AAAI 2021Alibaba ResearchAmodal Segmentation
0 likes · 5 min read

FinBERT 1.0 is an open‑source Chinese BERT model pre‑trained on large‑scale financial corpora that achieves 2‑5 % F1 improvements across multiple downstream fintech tasks without additional tuning, demonstrating the value of domain‑specific pre‑training for natural language processing.
BERTChineseFinBERT
0 likes · 14 min read

The paper presents iCartoonFace, the largest manually annotated cartoon‑face dataset with 5,013 identities and 389,678 images, and a multi‑task learning framework that jointly trains on cartoon and real faces using classification, unknown‑identity rejection, and domain‑adaptation losses, achieving state‑of‑the‑art recognition despite pose, occlusion, and illumination challenges.
domain adaptationface recognitionmulti-task learning
0 likes · 10 min read

This article introduces the fundamentals of transfer learning and federated transfer learning, explains domain adaptation for sentiment analysis, presents two illustrative examples—mid-level image feature transfer and text-to-image transfer—and outlines the model architecture and loss functions of federated transfer learning frameworks.
domain adaptationmodel architectureprivacy
0 likes · 14 min read

This article explains two model‑independent learning paradigms—multi‑task learning and transfer learning—detailing their motivations, sharing mechanisms, training procedures, theoretical formulations, and practical benefits such as improved generalization, data efficiency, and domain‑invariant representations.
deep learningdomain adaptationmachine learning
0 likes · 21 min read

This article describes the development of MT‑BERT, a BERT‑based language model pre‑trained on Meituan‑Dianping business data, its distributed mixed‑precision training pipeline, domain adaptation, knowledge‑graph integration, model compression techniques, and the wide range of downstream NLP applications achieved in the platform.
BERTMeituanNLP
0 likes · 31 min read


Didi TechJul 13, 2019 · Artificial Intelligence
The Didi Computer Vision in Transportation workshop teaches fundamentals, advanced domain‑adaptation and lightweight model techniques, and real‑world applications such as driver identification and driving‑scenario analysis, delivered by Didi AI Labs experts, emphasizing practical use cases and cutting‑edge research.
AIDriver Identificationdomain adaptation
0 likes · 6 min read


AntTechMay 25, 2018 · Artificial Intelligence
The article provides a comprehensive overview of the AAAI 2018 conference, including submission statistics, country rankings, popular research tracks, award-winning papers, detailed summaries of notable AI papers such as GraphGAN, HARP, PrivSR, and domain adaptation, as well as Ant Financial's own contributions like cw2vec and privacy‑preserving recommendation systems.
AAAI 2018Privacy-Preserving Recommendationartificial intelligence
0 likes · 15 min read
