Tagged articles
Multi-Objective Optimization
46 articles · Page 1 of 1
HarnessPro introduces a multi-agent recursive self-improvement framework that uses Pareto optimization and AI-generated tests to simultaneously increase task pass rates and reduce execution costs across Heavy, Medium, and Lite tiers, achieving 26% cost reduction with 2% pass-rate improvement over RHO on SWE-Bench Pro.
AI agentsCost-Performance Trade-offHarnessPro
0 likes · 12 min read

This review examines how evolutionary computation supports trustworthy AI across three research lines: evolutionary attacks to find failures, evolutionary defenses to search protective measures, and trustworthy self-evolution to govern which changes persist long-term, highlighting the shift from static robustness to continuous governance of memory, skills, and safeguards.
AI safety benchmarksMulti-Objective OptimizationTrustworthy AI
0 likes · 31 min read

This article details the architecture and optimization of a Prediction Server for fine-ranking in recommender systems, covering model management, batch inference, multi-objective fusion, probability calibration, deployment pipelines, and high-availability patterns to score thousands of candidates within milliseconds.
Batch InferenceHigh AvailabilityModel Serving
0 likes · 46 min read


AIWalkerApr 6, 2026 · Artificial Intelligence
The paper introduces TIR‑Agent, an image‑restoration agent that learns a tool‑calling policy via supervised fine‑tuning and reinforcement learning, addressing exploration stagnation and multi‑objective reward imbalance, and demonstrates over 2.5× faster inference and superior multi‑metric performance on synthetic and real degradation datasets.
Computer VisionMulti-Objective OptimizationReinforcement Learning
0 likes · 18 min read

Tencent's ad tech team redesigned its ad ranking system by adding a parallel user‑experience‑optimized pipeline and evolving from manual CEM tuning to DDPG‑based reinforcement learning, achieving 10‑20% improvements in CTR, repeat‑view rates, and other experience metrics while maintaining overall spend.
AdvertisingMulti-Objective OptimizationRanking
0 likes · 17 min read

This article treats life as an optimization problem and breaks it into three core forces—cognition, choice, and growth—showing how Bayesian inference, multi‑objective optimization, and dynamic system theory can model their interactions, guide decision‑making, and illustrate the feedback loops that drive personal development.
Bayesian inferenceMulti-Objective Optimizationdecision-making
0 likes · 8 min read

This article treats personal life decisions as scheduling problems, presenting time, resource, priority, multi‑objective, stochastic, and robust optimization models—complete with objective functions, constraints, and solution approaches—to demonstrate how mathematical modeling can provide quantitative guidance for balancing work, health, learning, and happiness.
Multi-Objective OptimizationSchedulinglife optimization
0 likes · 10 min read

This tutorial provides a systematic overview of gradient‑based multi‑objective optimization for deep learning, covering core solution strategies, algorithmic details, convergence and generalization analyses, and demonstrates how these methods can be applied to fine‑tune and align large language models.
Gradient MethodsLLM fine-tuningMulti-Objective Optimization
0 likes · 3 min read

This article explores how mathematical models—ranging from matrix representations of formations to error analysis, phase synchronization, timing control, perspective geometry, and multi‑objective optimization—can be applied to design, evaluate, and perfect military parades.
Multi-Objective Optimizationformation optimizationmathematical modeling
0 likes · 6 min read

The paper introduces One4All, a scalable multi‑task generative recommendation framework for CPS advertising that combines few‑shot intent prompting, a Rewards‑in‑Context multi‑objective optimization, and an online model‑selection strategy, delivering 2‑3× offline HitRate/NDCG gains and notable online CTR, CVR, and commission improvements.
AdvertisingLLMMulti-Objective Optimization
0 likes · 14 min read

This article surveys recent advances in generative recommendation for CPS advertising, detailing explicit intent‑aware controllable product recommendation, multi‑objective optimization techniques based on reward‑in‑context and DPO, and the scalable One4All framework that unifies behavior and language modeling across diverse ad scenarios.
CPS advertisingLLMMulti-Objective Optimization
0 likes · 14 min read

Since large language models have excelled in NLP, researchers are now enhancing CPS advertising recommendation systems by integrating generative LLMs for explicit intent perception, multi‑objective optimization, and a unified One4All framework, achieving significant offline and online performance gains across click‑through, conversion, and revenue metrics.
CPS advertisingLLMMulti-Objective Optimization
0 likes · 19 min read

UniCBE introduces a unified multi‑objective optimization framework for contrastive‑based evaluation that mitigates sampling bias, unbalanced uncertainty reduction, and inefficient resource allocation by combining three decoupled probability matrices through a greedy and Hadamard‑product strategy, achieving Pearson correlations above 0.995 with only 83 % of the annotation budget and cutting evaluation costs by more than 50 % across diverse LLM evaluators.
Contrastive EvaluationEfficiencyMulti-Objective Optimization
0 likes · 10 min read

The paper presents a generative recommendation framework for JD Alliance advertising that combines semantic‑ID modeling, large‑model pre‑training and fine‑tuning, and Direct Preference Optimization (including Softmax‑DPO and β‑DPO) to jointly boost click‑through and conversion rates, achieving +0.6% UCTR and +8% UCVR in online tests while outlining future multi‑objective extensions.
AdvertisingDPOMulti-Objective Optimization
0 likes · 12 min read

The article presents a CIKM‑2024 paper that introduces MODRL‑TA, a multi‑objective deep reinforcement learning system combining multi‑objective Q‑learning, a cross‑entropy‑based decision‑fusion algorithm, and a progressive data‑augmentation pipeline to dynamically allocate search traffic on JD.com, with both offline and online experiments showing substantial gains in CTR, CVR, and overall platform performance.
Multi-Objective OptimizationOnline A/B TestingReinforcement Learning
0 likes · 14 min read

This article outlines the current bottlenecks of conventional recommendation pipelines and proposes a comprehensive 2026 research agenda covering retention improvement, user growth, content ecosystem, multi‑objective Pareto optimization, long‑term value modeling, whole‑site optimization, interactive recommendation, personalized modeling, decision‑theoretic formulation, and the OneRec multi‑source fusion framework.
Multi-Objective OptimizationPersonalizationlarge language models
0 likes · 18 min read

This article introduces the fundamentals of multi‑objective optimization, explains the NSGA‑II algorithm’s non‑dominated sorting, crowding distance, and selection mechanisms, and demonstrates its application to a production‑line case study with a complete Python implementation and visualized Pareto front.
Evolutionary AlgorithmsMulti-Objective OptimizationNSGA-II
0 likes · 10 min read

This article introduces a mathematical model for designing compromise solutions in multi‑party decision making, explains the underlying multi‑objective optimization framework, presents a quadratic programming example, and discusses how adjusting indicator ranges can balance differing preferences to achieve mutually acceptable outcomes.
Multi-Objective OptimizationOperations Researchcompromise modeling
0 likes · 6 min read


NewBeeNLPApr 8, 2024 · Artificial Intelligence
This article analyzes the current bottlenecks of conventional recommendation systems and outlines ten forward‑looking research directions for 2026, including retention improvement, user growth, content ecosystem, multi‑objective Pareto optimization, long‑term value estimation, site‑wide optimization, interactive recommendation, personalized modeling, decision‑theoretic framing, and the integration of large language models via the OneRec framework.
Multi-Objective Optimizationinteractive recommendationlarge language models
0 likes · 18 min read

This presentation outlines the current bottlenecks of conventional recommendation pipelines and proposes a 2026 roadmap that includes retention improvement, user‑growth strategies, content‑ecosystem metrics, Pareto‑optimal multi‑objective optimization, long‑term value modeling, site‑wide spatial optimization, interactive recommendation, personalized modeling, and the integration of large‑model fusion through the OneRec framework.
Multi-Objective Optimizationinteractive recommendationlarge language models
0 likes · 18 min read

The paper introduces a real‑time controllable, multi‑objective re‑ranking framework for Taobao’s feed recommendation that combines actor‑critic reinforcement learning with hypernetworks to instantly adjust objective weights, handling diverse media and cold‑start constraints while delivering higher click‑through, diversity, and cold‑start ratios with only 20‑25 ms latency.
AlibabaHypernetworksMulti-Objective Optimization
0 likes · 34 min read

This article presents a comprehensive study of a controllable multi‑objective re‑ranking model for Taobao's information‑flow recommendation, detailing the challenges of complex feed scenarios, three modeling paradigms (V1‑V3), an actor‑critic reinforcement learning framework with hypernet‑generated weights, and extensive online evaluation results.
HypernetworksMulti-Objective OptimizationRe-ranking
0 likes · 31 min read

Pareto optimality, also known as Pareto efficiency, describes a state where improving any individual's outcome inevitably worsens another's, serving as a key criterion in multi‑objective optimization and decision science for evaluating trade‑offs such as maximizing profit while minimizing environmental impact.
Multi-Objective OptimizationOperations ResearchPareto optimality
0 likes · 5 min read


AntTechMar 13, 2023 · Cloud Computing
Cougar is a cloud‑native, multi‑objective optimization framework that unifies metadata and monitoring ingestion to improve resource efficiency and performance for large‑scale AI and big‑data jobs, demonstrating over 50% CPU‑memory savings and stable latency in production experiments.
Multi-Objective Optimizationartificial intelligencecloud computing
0 likes · 10 min read

This report details the multi‑stage architecture of Taobao’s main search, introduces a new global‑transaction hitrate metric, analyzes offline and online evaluation gaps, and presents a series of model, loss‑function, and sampling improvements that together lifted overall conversion by about one percent.
Multi-Objective Optimizationcoarse rankinge-commerce
0 likes · 26 min read

This article explains the architecture of video search engine ranking, covering optimization objectives such as relevance, click‑through rate and watch time, and detailing pointwise, pairwise and listwise learning approaches, model training pipelines, and online serving strategies.
Multi-Objective Optimizationclick-through ratemachine learning
0 likes · 17 min read

Alibaba’s AIDA framework combines a bidding‑agent layer and a novel auction layer—Deep GSP and Neural Auction—to allocate display ads across its ecosystem, achieving incentive‑compatible, multi‑objective optimization, higher ROI, and scalable deployment via TensorFlow‑based platform services.
Multi-Objective Optimizationauctionmechanism design
0 likes · 16 min read

The article presents JD's e‑commerce recommendation system, detailing its four‑stage ranking pipeline, multi‑objective optimization with personalized fusion, transformer‑based user behavior sequence modeling, fine‑grained behavior modeling, and multimodal feature integration, and shares experimental results and engineering optimizations.
Multi-Objective Optimizatione-commercemultimodal features
0 likes · 17 min read

Deep GSP is a multi‑objective, deep‑learning ad auction that jointly learns rank scores while enforcing game‑theoretic constraints—monotonicity, incentive compatibility, and Nash equilibrium—and a smooth‑transition penalty, using DDPG reinforcement learning to outperform traditional GSP across revenue, clicks, conversions, and add‑to‑cart metrics.
Multi-Objective OptimizationReinforcement Learningadvertising auction
0 likes · 18 min read

The article presents JD's end‑to‑end recommendation pipeline, detailing the four‑stage ranking chain, challenges of fine‑ranking, and practical solutions including multi‑objective learning, transformer‑based user behavior sequence modeling, fine‑grained click behavior integration, and multimodal image features, with offline and online performance gains.
Multi-Objective Optimizationfine-grained behaviormultimodal features
0 likes · 18 min read

The paper presents MACG, a multi‑agent cooperative bidding game that integrates a global objective with individual advertiser goals, derives optimal bidding formulas, employs a strategy network and evolutionary search to tune parameters, and demonstrates over‑5% metric gains and stable 15‑day performance in Taobao’s online advertising platform.
Multi-Agent Reinforcement LearningMulti-Objective OptimizationOnline Advertising
0 likes · 18 min read

This article details how 58 Community improved content value share, click‑through, and user retention by designing a generalized multi‑objective recommendation algorithm that leverages cross‑domain embeddings, DeepFM‑DIN models, EGES‑inspired pre‑training, and online CEM‑based parameter optimization.
CEMMulti-Objective Optimizationcross-domain embedding
0 likes · 16 min read

This article presents the end‑to‑end practice of a second‑hand housing recommendation system at 58.com and Anjuke, covering business background, embedding‑based vector recall, multi‑objective ranking methods such as ESMM and MMOE, experimental results, and future development directions.
ESMMEmbeddingFaiss
0 likes · 14 min read

Deep Neural Auction (DNA) integrates deep learning with mechanism design to end-to-end optimize multi-objective e-commerce ad auctions, preserving incentive compatibility and individual rationality, using differentiable sorting and set encoding, achieving superior revenue, CTR, CVR, and conversion metrics versus GSP variants in Alibaba experiments.
Multi-Objective Optimizationdifferentiable sortinge-commerce advertising
0 likes · 17 min read

The paper introduces PAPERec, a personalized multi‑objective recommendation framework that leverages Pareto‑oriented reinforcement learning to generate user‑specific objective weights, enabling the model to approximate Pareto‑optimal solutions and achieve superior click‑through rate and dwell‑time performance in both offline and online experiments.
CTRMulti-Objective OptimizationPareto efficiency
0 likes · 12 min read

This article presents the design and implementation of a multi‑objective optimization framework using Multi‑gate Mixture‑of‑Experts (MMoE) to improve click‑through, conversion, and purchase behaviors in Taobao's "Lying Flat" home‑goods recommendation channel, detailing model variants, feature engineering, loss weighting, and online A/B test results.
CTRCVRMMoE
0 likes · 10 min read

This article details the end‑to‑end technical architecture of WeChat's "Look" personalized recommendation service, covering data collection, recall, multi‑stage ranking, various CTR and multi‑objective models, reinforcement‑learning based mixing, diversity optimization, and the engineering hurdles overcome to deploy these solutions at massive scale.
CTR predictionMulti-Objective OptimizationReinforcement Learning
0 likes · 17 min read

The paper proposes a two‑stage framework that first fits a differential‑equation‑based exposure‑click (P2C) model for each new video and then uses a genetic‑algorithm multi‑objective optimization to allocate scarce scene‑level exposure slots, simultaneously maximizing total views and halving CTR variance while outperforming manual baselines.
KDDMulti-Objective OptimizationODE modeling
0 likes · 8 min read

This article presents a data‑driven approach for allocating limited video exposure resources by building a PV‑click‑CTR (P2C) sensitivity model and a multi‑objective optimization framework that balances overall view volume and fairness across scenes, validated through offline metrics and online bucket tests.
AlgorithmMulti-Objective Optimizationbig data
0 likes · 9 min read

The KDD 2020 paper from Alibaba Entertainment presents a differential‑equation‑based hot‑content exposure sensitivity model and a multi‑objective optimization framework that, under exposure‑resource constraints, guarantees video delivery by accounting for nonlinear content exposure, timing, strategies, and user click habits, now deployed on Youku.
KDD 2020Multi-Objective Optimizationdifferential equations
0 likes · 2 min read

This document presents a multi‑objective optimization project that integrates the Shell Score credit system into exhibition slot allocation using adaptive‑grid based AG‑MOPSO, evaluates several swarm‑intelligence algorithms (ABC, ACO, PSO, MOPSO), and details the algorithm design, implementation steps, and experimental results across multiple cities.
AIMulti-Objective OptimizationParticle Swarm Optimization
0 likes · 12 min read

This article presents a comprehensive overview of short‑video recommendation at UC, covering business background, system architecture, the evolution from LR to Wide & Deep models, multi‑objective loss design with positive‑sample weighting, graph‑embedding fusion, time‑weighted loss, continuity modeling, a Boosting‑based WnD solution, and future research directions.
Multi-Objective OptimizationRecommendation Systemboosting
0 likes · 11 min read

Alibaba's short‑video recommendation team details how they enhance both click‑through rate and viewing duration by applying sample reweighting, weighted logistic regression, and playback‑completion‑rate normalization, achieving over 6% offline AUC gains and more than 10% increase in average user watch time.
Multi-Objective Optimizationclick-through ratemachine learning
0 likes · 10 min read

This article explains how short‑video platforms enhance recommendation quality by combining click‑through‑rate models with multi‑objective optimization of watch time and completion rate, using sample reweighting and weighted logistic regression to balance perceived and real relevance while improving offline AUC and online user engagement.
CTRMulti-Objective Optimizationrecommendation
0 likes · 10 min read


AntTechJun 15, 2018 · Artificial Intelligence
The article explains how Alipay’s AutoPilot module leverages AI, semi‑supervised and evolutionary algorithms to achieve autonomous, personalized risk‑control decisions, optimizing multi‑objective trade‑offs and dramatically improving fraud loss rates during high‑traffic events like the 2017 Double‑11 sale.
AIAlipayAutopilot
0 likes · 7 min read

The article explains how search engine techniques such as large‑scale candidate recall, fine‑grained ranking, user profiling, and multi‑objective optimization are applied to news personalization at Toutiao, highlighting data sampling, machine‑learning pipelines, challenges of news freshness, and architectural evolution.
Multi-Objective Optimizationnews recommendationrecommendation
0 likes · 5 min read
