Multi-Objective Optimization

Follow this topic Ask about this topic

Momentum

21 papers in the last four weeks, up 320% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 171

All topics

How to train your model organism
Oct 7, 2026Xilin Wang, David Bau, Byron C. WallaceMechanistic Interpretability Explainability Evaluation
Northeastern University Boston, MA 02115, USA
A Unified Information-Theoretic Approach to Constrained Multi-Fidelity Multi-Objective Bayesian Optimization
Oct 7, 2026Rikuto Matsumoto, Masanori Ishikura, Masayuki KarasuyamaBayesian Optimization Multi-Objective Optimization
Nagoya Institute of Technology
Counterfactual Route Optimization for Gaussian Head Avatar Modeling
Oct 7, 2026Shikun Zhang, Yong Li, Yiqun Wang +23D Avatar Generation Multi-Objective Optimization
Department of Data Science and AI, Monash University, Australia · College of Computer Science, Chongqing University, China
Pareto-optimal quantum kernel selection for unsupervised anomaly detection on real malware beaconing data
Oct 7, 2026Boaz Micah, Nadia Milazzo, Maissa Beji +8Quantum Kernel Methods Unsupervised Anomaly Detection
Multiverse Computing, Parque Científico y Tecnológico de Gipuzkoa, Paseo de Miramón 170, Planta 2, 20014 Donostia / San Sebastián, Spain · IQM Quantum Computers, 4 rue Royale, 75008 Paris, France · Multiverse Computing, 7 rue de la Croix Martre, 91120 Palaiseau, Paris, France +3
Agentic AutoRAG: RAG Pipeline Optimization through Reasoning-Driven Agents
Oct 6, 2026Lasse B. Strand, Robert Jakob, Kevin O'Sullivan +1Retrieval-Augmented Generation Large Language Model-Guided Optimization
ETH Zurich
Simplified Swarm Optimization for Surrogate-Assisted Reliability Design of Insulated-Gate Bipolar Transistor Power Modules Using an Open-Source Process Finite-Element Model
Oct 5, 2026Wei-Chang YehSurrogate-Assisted Optimization Semiconductor Manufacturing
Department of Industrial Engineering and Engineering Management, National Tsing Hua University, Hsinchu 300044, Taiwan
Learning Pareto Stationary Fronts via Single-Pass Backpropagation
Oct 5, 2026Elina Rojin Celik, Marcos Medeiros Raimundo, Isabel ValeraDeep Learning Optimization Multi-Objective Optimization
Department of Computer Science Saarland University, Germany · Instituto de Computação Universidade Estadual de Campinas, Brazil
Bridging the Evidence-to-Execution Gap:A Reflective Agent for Multi-Objective Peptide Design
Oct 5, 2026Haosen Zhang, Yang YangAI Agents for Scientific Discovery Large Language Model-Guided Optimization
School of Agriculture and Biology, Shanghai Jiao Tong University · School of Computer Science, Shanghai Jiao Tong University
Collaborative Personalized Preference Alignment for LLMs under Data Deficiency
Oct 5, 2026Liyan Yang, Yige Yuan, Zhiqin YangPersonalized Language Models Personalized Language Model Alignment
City University of Hong Kong · University of Washington · The Hong Kong University of Science and Technology
DiMOS: Doob-Guided Inference-Time Multi-Objective Search for Scientific Design
Oct 5, 2026Ziqing Wang, Qijie Zhu, Weimin Wu +4Masked Diffusion Models Inference-Time Search
Northwestern University
pCoMole: Pareto-Constrained Molecule Editing with Discrete Flows
Oct 1, 2026Tong Chen, Maximilian Holsman, Lin Zhao +1Constrained Generative Modeling Protein Design
Department of Computer and Information Science, University of Pennsylvania · Department of Computer Science, Duke University · Department of Bioengineering, University of Pennsylvania
Calibrating Prediction Timeliness Through Multi-Objective Hyperparameter Optimization for Remaining Useful Life Prediction
Oct 1, 2026Tugrul Cabir Hakyemez, Ener Uras GokhanRUL Estimation Multi-Objective Evolutionary Optimization
Department of Management Information Systems Istanbul Bilgi University Istanbul, Turkey · Beştepe Koleji Ankara, Turkey
Cross-entropy optimization with prioritized constraints
Oct 1, 2026Francisco Roldan Sanchez, Pau de las Heras Molins, David Fridovich-Keil +1Constrained Motion Planning Black-Box Optimization
LTCI, Télécom Paris, Institut Polytechnique de Paris · The University of Texas at Austin
ConflictGuide: AutoResearch Improves When Competing Behaviors Are Made Visible
Sep 30, 2026Binqian Xu, Qiran Zou, Xiangbo Shu +1Large Language Model-Guided Optimization Self-Improving Agents
National University of Singapore · Nanjing University of Science and Technology
Learning Where to Steer: Noise-Space Geometry for Efficient Offline Multi-Objective Optimization with Generative Models
Sep 30, 2026Yuan Lu, Esha Singh, Yi-An Ma +1Diffusion Model Guidance Multi-Objective Optimization
Halıcıoğlu Data Science Institute, UC San Diego · Department of Computer Science & Engineering, UC San Diego
MoFlow: Multi-Objective Agentic Workflow Generation
Sep 29, 2026Yining Lu, Aurelie Lozano, Xi Yang +3Multi-Objective Reinforcement Learning Agentic Workflows
University of Notre Dame · IBM
OPDiv: Optimal Selection of Top-K High-Scoring, Diverse Compounds
Sep 23, 2026Miroslav LžičařData Selection Virtual Screening
Deep MedChem
An Unbounded Archive-based Transfer Strategy for Dynamic Multi-Objective Optimization with a Changing Number of Objectives
Sep 23, 2026Zhiyun Xiao, Ke Shang, Yajun Liu +3Evolutionary Optimization Multi-Objective Evolutionary Optimization
School of Artificial Intelligence, Shenzhen University, Shenzhen 518060, China · National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen 518060, China · Shenzhen ZTE Software Co., Ltd.
JAREX: An Acquisition Function for Multi-Objective Algorithmic Process Characterization
Sep 21, 2026Xinyang Li, Kevin Stone, Ajit VikramBayesian Optimization Bayesian Experimental Design
Pharmaceutical Analysis & Digital Technologies, Merck & Co., Inc., Rahway, New Jersey, 07065, United States
CrystalMO-TuRBO: Multi-Objective Trust-Region Bayesian Optimization for High-precision Joint Crystal Structure Refinement
Sep 17, 2026Joseph Agada, Yishu Wang, Arpan BiswasBayesian Optimization Trust-Region Optimization
University of Tennessee - Oak Ridge Innovation Institute University of Tennessee Knoxville, TN 37996 · Department of Materials Science and Engineering University of Tennessee Knoxville, TN 37996
Customizable and Jointly Optimized Route Planning: A Deep Architecture Enabling Differentiable Shortest-Path Search
Sep 17, 2026Rui Zhao, Chao Chen, Longfei Xu +4Graph-Based Planning Differentiable Optimization
Alibaba Group Beijing, China · Alibaba Group Hangzhou, China
Expected Hypervolume Maximization for Multiobjective Optimization under Uncertainties
Sep 17, 2026Victor TrapplerSurrogate-Assisted Optimization Bayesian Optimization
Mines Saint-Étienne MSE, LIMOS, FAYOL-ENSMSE, FAYOL-ENSMSE · Departement GMI Institut Henri Fayol, Mines Saint-Etienne, Univ Clermont Auvergne, CNRS, UMR 6158 LIMOS F - 42023 Saint-Etienne France
The Operable Pareto Front: Distilling Offline Search into Run-Time Control for Multi-Objective UAV Edge-Computing Scheduling
Sep 16, 2026Qiao Liao, Zhiyong Feng, Bin Wu +1Trajectory Optimization Edge Computing
School of Computer Science and Technology, Tianjin University, Tianjin, China · School of Computer Software, Tianjin University, Tianjin, China · School of Information Science and Engineering, Shandong Agriculture and Engineering University, Shandong, China
Steering Generative Robot Policies with Lexicographic Preferences
Sep 14, 2026Yixuan Jia, Jonathan P. HowDiffusion Policy Robotic Manipulation
Department of Aeronautics and Astronautics, Massachusetts Institute of Technology, Cambridge, MA 02319 USA
Fed-Equilibrium Framework for Topological Pareto Control in Robust and Fair Clinical Federated Learning
Sep 14, 2026Ting Xu, Henry LeungFederated Learning Aggregation Byzantine-Robust Federated Learning
Department of Biomedical Engineering University of Calgary Calgary, Canada
Multi-Objective Agent-Based Model Predictive Controller for Plug-and-Play Vehicle Control
Sep 14, 2026Jiaming Zhong, Ladan Khoshnevisan, Shucheng Huang +3Multi-Agent Control Model Predictive Control
Department of Mechanical and Mechatronics Engineering, University of Waterloo, 200 University Ave West, Waterloo ON, N2L3G1 Canada · Department of Mechanical Engineering, University of Ottawa, 75 Laurier Ave East, Ottawa, ON, K1N 6N5 Canada · Department of Electrical and Computer Engineering, University of Waterloo, 200 University Ave West, Waterloo ON, N2L3G1 Canada
SIMS: Scale-Invariant Merit-Function-Based Scalarization for Multi-Task Learning
Sep 14, 2026Zebin Chen, Fei Xing, Yang Chen +4Multi-Task Learning Multi-Task Optimization
Southern University of Science and Technology Shenzhen, China · City University of Hong Kong Hong Kong SAR, China · Shanxi University Taiyuan, China
Solving Few-Shot Multiobjective Multitask Optimization via Iterative Sequential Transfer
Sep 12, 2026Tingyang Wei, Haofeng Wu, Ananda Phan Iman +3Multi-Task Optimization Multi-Objective Optimization
College of Computing and Data Science Nanyang Technological University Singapore · Department of AI Convergence Gwangju Inst. of Sci. & Tech. (GIST) South Korea · Centre for Frontier AI Research (CFAR) A*STAR Singapore
Risk-Averse Decision Making with Multi-Level Reliability Guarantees
Sep 10, 2026Amirmohammad Farzaneh, Osvaldo SimeoneStochastic Optimization Chance-Constrained Optimization
Institute for Intelligent Networked Systems (INSI), Northeastern University London, London, UK
A Better Spur Should Start From Each Objective
Sep 8, 2026Shanwen Mao, Hao Zhang, Guangtao nie +4Multi-Objective Reinforcement Learning Gradient Interference
Harbin Institute of Technology, Harbin, China · JD.com Inc., Beijing, China

Oct 7, 2026, cs.LGJ/K move · Enter open · S save

How to train your model organism

Xilin Wang, David Bau, Byron C. Wallace

Northeastern University Boston, MA 02115, USA

Mechanistic Interpretability Explainability Evaluation Multi-Objective Optimization

Open paper AskPDF arXiv

Model organisms of alignment-relevant behaviors (e.g., backdoors, sycophancy, spurious correlations) have emerged as a key tool for evaluating whitebox interpretability techniques. We argue that the prevailing practice of training model organisms to a single objective of installing the target behavior is insufficient and propose validating model organisms with respect to three objectives with associated metrics: target-behavior installation, general-capability preservation (i.e., parametric knowledge, chat quality), and output naturalness (i.e., CoT and activations). We re-visit two publicly released organism suites using this validation framework and show that (1) chat quality and CoT naturalness degrade substantially across training recipes, and (2) validation metrics predict how well interpretability methods recover the installed behavior, e.g., a logit lens readout covaries with an organism's general capabilities. We introduce a multi-objective training approach based on model merging to train more realistic model organisms. Finally, on a new suite of model organisms targeting demographic biases in clinical reasoning, we compare training recipes and find that DPO training stays closer to the base model than supervised finetuning, and the proposed model optimization approach better preserves capabilities and naturalness. Auditing this suite with an investigator agent, we again observe validation metrics tracking bias recovery. In sum, training methods shape the interpretability conclusions an organism supports, and we argue that one should consider multiple objectives to draw generalizable conclusions about interpretability methods using (realistic) model organisms.

Momentum

Related topics

Latest papers 171