Circuits

Follow this topic Ask about this topic

Momentum

25 papers in the last four weeks, up 213% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 140

All topics

Are We Recovering Mechanisms? Objective-Level Recovery Gaps in Mechanistic Interpretability
Oct 1, 2026Chuqin Geng, Li Zhang, Haolin Ye +3Mechanistic Interpretability Model Discovery
University of Toronto · McGill University
PCB-MC: Missing Component Analysis in Printed Circuit Boards
Sep 30, 2026Betsy Villa Brochero, Ian Gibson, Estefania TalaveraPrinted Circuit Board Defect Detection
EEMCS-CS-DMB University of Twente Enschede, The Netherlands · ET-DPM-AMSPES University of Twente Enschede, The Netherlands
A Biophysically Detailed C. elegans Circuit as a Task-Agnostic Dynamical Core for Visually Robust Robot Manipulation
Sep 30, 2026Linrui Qian, Jiajia Zhang, Gan He +7Visuomotor Policy Sensorimotor Experience
CogLeap.AI Space Intelligence (Wuxi) Technology Co., Ltd., Beijing 100080, China · School of Mathematics and Computational Science, Xiangtan University, Xiangtan 411105, China · Institute for Brain and Intelligence, Fudan University, Shanghai 200433, China. +1
Rethinking Circuit Evaluation: Do Circuits Explain Model Errors?
Sep 28, 2026Li Zhang, Chuqin Geng, Mark Zhang +4Mechanistic Interpretability Circuits
University of Toronto · McGill University · Tsinghua University
PROACT-Agent: Progressive Runtime Oversight and Active Circuit-breaking for Real-Time Safety
Sep 28, 2026Ding Jia, Wei Liu, Xianglong Du +5Large Language Model Safety Safety-Critical Scenarios
State Key Laboratory of Intelligent Vehicle Safety Technology, Changan Automobile · Independent Researcher
Where Hallucinations Live: A Cross-Architecture Circuit in VQ-Tokenized Vision-Language Models
Sep 24, 2026Shamanthak Hegde, Xiangrui Liu, Maitreya Patel +1Recent Vision-Language Models Object Hallucination
Arizona State University · Adobe
Bridge of $Ψ$ 's: Quantum Circuit Optimization with Schrödinger Bridges
Sep 22, 2026Lino S. Hofstetter, Lia Yeh, Prakash MuraliQuantum Circuits Schrödinger Bridges
ETH Zürich Zürich, Switzerland · University of Cambridge Cambridge, United Kingdom
Weakly Supervised Quantum Error Mitigation
Sep 22, 2026Seyed Mohamad Ali Tousi, G. N. DeSouzaQuantum Error Correction Quantum Circuits
Vision-Guided and Intelligent Robotics Lab (ViGIR) University of Missouri Columbia, US
Attention as a Routing Graph: Live Circuit Extraction from a Single Forward Pass
Sep 21, 2026Ash Manvi, Samreena TajreenCircuits Ablation
Aquin Labs
Circuit Hypernetworks for Quantum-Augmented Diffusion Language Models
Sep 21, 2026Xiaoqiang Wang, Mengyang Xiong, Jun Dai +1Large Language Model Quantization Diffusion Language Models
D´epartement d´informatique et de recherche op´erationnelle, Universit´e de Montr´eal, Montr´eal, QC, Canada. · Mila, Quebec AI Institute, Montr´eal, QC, Canada. · McGill University, Montr´eal, QC, Canada.
Circuit-Diff: Factual Edit-based Intervention Method for Localizing Knowledge in Attribution Graphs
Sep 20, 2026Edward G. Friedman, Xiangchen SongCircuits Mechanistic Interpretability
School of Computer Science Machine Learning Department Carnegie Mellon University Pittsburgh, PA 15213
Weighted Quantum Signal Processing: Low-Depth Polynomial Approximation with Applications to Kolmogorov-Arnold Networks
Sep 18, 2026Rohit Sarma Sarkar, Rupayan Bhattacharjee, Elias F. Combarro +5Quantum Learning Kolmogorov-Arnold Networks
Universitat Polit`ecnica de Catalunya, Barcelona, Spain · Universidad de Oviedo, Spain · Quantum Computing Infrastructures and Algorithms Competence Centre, European Organization for Nuclear Research (CERN), Geneva 1211, Switzerland +2
State-Space-Based FIR Filtering on a Quantum Computer
Sep 17, 2026Roope Salmi, Davide Rocchesso, Vesa VälimäkiImpulse Response Circuits
Acoustics Lab, Dept. of Information and Communications Eng., Aalto University, Espoo, Finland · Universit`a degli studi di Milano Statale, Milan, Italy
ReDIL-GNN: Resynthesis Domain Incremental Learning for Circuit Graph Neural Networks
Sep 16, 2026Rupesh Raj Karn, Johann Knechtel, Ozgur SinanogluDifferentiable Logic Gate Networks Gnn-Based Detectors
Center for Cyber Security, New York University, Abu Dhabi, UAE.
QEMScore: How Much Does the Measurement Add to Learned Quantum Error Mitigation?
Sep 15, 2026Yue Zhao, Huayue Gu, Yushun Dong +1Quantum Error Correction Equal Error Rate
University of Southern California · Kennesaw State University · Florida State University +1
Decoy Direction Optimization: A Post-Hoc Defense Against LLM Abliteration
Sep 14, 2026Aashiq Muhamed, Mona T. Diab, Virginia SmithLLM Defense Mechanisms White-Box Spectral-Subspace-Guided Attack
Carnegie Mellon University
Circuit-MLLM: Topological Logic-Guided Latent-Space Visual Reasoning for Circuit Schematic Understanding
Sep 14, 2026Jinyuan Deng, Yuqi Jiang, Wenjing Huang +3Circuits Multimodal Reasoning
Zhejiang University, Hangzhou, China
Fractional-order hardware for neuromorphic computing: Is the order really the problem?
Sep 11, 2026Christof TeuscherNeuromorphic Computing Order
Department of Electrical and Computer Engineering, Portland State University, Portland, Oregon, United States of America
Sparse Weight and Edge Circuit Discovery in Transformer-based Acoustic Models
Sep 11, 2026Jiankun Wei, Ewan Dunbar, Gerald PennTransformer Encoder Neural Audio
Department of Computer Science University of Toronto Toronto, Canada
Quantum Feature Engineering for Credit Default Prediction: When and Why IQP Circuits Help Linear Classifiers
Sep 9, 2026Menachem Finkelstein, Diana Legziel Levy, Zohar Yakhini +1Credit Risk Prediction Circuits
Reichman University, Israel
Training Trajectories Determine Circuit Removability in Annealable Soft-Prior Transformers
Sep 9, 2026Zonglin Yang, Ziming Zhao, Wei Tang +5Circuits
Criminal Science and Technology, Guangdong Police College, China · Cybersecurity and Law Enforcement, Guangdong Police College, China · Traffic Management Engineering, Guangdong Police College, China
Fidelity-Aware Scheduling of Quantum Circuits on Multi-QPU Systems
Sep 9, 2026Innocenzo Fulginiti, Antonio Tudisco, Salvatore Zammuto +7Quantum Circuits Schedulers
Technical University of Munich, Munich, Germany · Department of Electronics and Telecommunications, Politecnico di Torino, Turin, Italy · MQSC, Garching near Munich, Germany +1
"World Knowledge" in the Weights: Reading Concept Circuits of Vision Transformers
Sep 8, 2026Yanlin Chen, Tang Li, Xi PengVision Transformer Circuits
Department of Computer & Information Sciences, University of Delaware, USA · Department of Computer Science, University of Virginia, USA
CircuTutor: Transforming Static Circuit Problems into Intelligent and Dynamic Tutoring
Sep 8, 2026Ziyu Luo, Xiaorui Ma, Lin Chen +1Circuits Tutors
Beijing Technology and Business University Beijing, China
CircuitLens: Reasoning Circuits as Data Selection Signals for Reinforcement Learning with Verifiable Rewards
Sep 7, 2026Zhuofan Chen, Ziqian Jiao, Yikai Cui +3Reinforcement Learning With Verifiable Reward Verifiable Rewards
School of Computer Science and Engineering, Beihang University, Beijing, China · Beijing Institute for General Artificial Intelligence, China
A Circuit for Plural Reference: How LLMs Represent and Retrieve Singular and Plural Entities
Sep 3, 2026Anh Danh, Rick Nouwen, Massimo PoesioCoreference Resolution Entities
Utrecht University · Queen Mary University of London
Analog-DB: An Agent-First Analog Integrated Circuit Database, From Blocks to Systems
Sep 1, 2026Danial Noori Zadeh, Mohamed B. ElamienAnalog Design Analog
The authors are with the Department of Electrical and Computer Engineering, McMaster University, Hamilton, ON, Canada
S^3martCirc: Self-supervised Smart Circuit Discovery
Sep 1, 2026Wendy Zheng, Yinhan He, Liang Wu +1Mechanistic Interpretability Circuits
University of Virginia · Nokia
On the Complexity of the Compatibility Problem for Succinctly Encoded Conditional Distributions
Aug 31, 2026Guy EmersonConditional Distribution Probabilistic Model
AaLLM: An End-to-End Analog Circuit Design Framework from Topology Generation to Sizing Using Large Language Models
Aug 13, 2026Mohammed Ayman Habib, Rylan Hart, Morteza FayaziAnalog Design Circuits
University of Utah, Salt Lake City, Utah, USA
Finding the Needle in a Haystack: Test-Time Analog Circuit Representation Adaptation for Bayesian Optimization
Aug 13, 2026Fin Amin, Sounak Dutta, Paul D. FranzonBayesian Optimization Analog Design
Department of Electrical and Computer Engineering, North Carolina State University, Raleigh, NC, USA
A 12-CNOT Double Qubit Excitation Gate
Aug 12, 2026Irfansha ShaikCircuits
Kvantify Aps, Copenhagen, Denmark
CircuitReason-1k: Benchmarking Long-Horizon Visual-to-Symbolic Reasoning inElectrical Circuits
Aug 10, 2026Xinqi Yang, Kang An, Tengyue Wang +8Circuits Visual Reasoning
Shanghai Jiao Tong University · South China University of Technology · ModelBest +6
Can Graph Learning Learn Circuits?
Aug 9, 2026Chester Tan, Moritz Lampert, Courtney Maynard +3Graph Representation Learning Graph Neural Networks
Chair of Machine Learning for Complex Networks Center for AI and Data Science (CAIDAS) Julius-Maximilians-Universität Würzburg · Khoury College of Computer Sciences Northeastern University · Network Science Institute Northeastern University
Circuit Fine-Tuning for Compute-Efficient Transformer Adaptation
Aug 8, 2026Uri Z. Kialy, Gil Ben-ArtziParameter-Efficient Fine-Tuning Methods Self-Supervised Vision Transformers
School of Computer Science, Ariel University, Israel
Decided Upstream, Written Late: Locating and Pricing the Cross-Lingual Refusal Circuit of a Multilingual MoE
Aug 8, 2026Ramakrishna P. Kompella, Aadit MahajanMultilingual Safety Refusals
Gödel Machines · IIT Madras
Learning to Rank Tensor Network Contraction Plans for GPU-Accelerated Quantum Circuit Simulation
Aug 6, 2026Alfred M. Pastor, Maribel Castillo, Jose M. BadiaTensor Networks Quantum Circuits
Department of Computer Science, Universitat de València, 46100 Burjassot, Spain · Department of Computer Science and Engineering, Universitat Jaume I, 12071 Castelló de la Plana, Spain
Separating quantum circuits from classical LLMs
Aug 4, 2026Srinivasan Arunachalam, Arkopal Dutt, Hari Krovi +1Quantum Circuits Large Language Model Quantization
IBM Research
Sparse Weight Decomposition for Efficient Circuit Extraction
Aug 4, 2026Chuanhao Yan, Xuhan Huang, Yawen Duan +4Transformer Architectures Model Weights
IQuest Research · Safe AI Forum · University of Oxford +2
VeriTrace: Human-Like Temporal Exploration Completes Agentic Action Space
Aug 3, 2026Yu-Tung Liu, Cunxi YuHigh-Level Synthesis Traces
University of Maryland, College Park College Park, USA
Transpiler Autotuning with Predictive Models for Quantum Circuit Optimization
Jul 31, 2026Piotr Malkowski, Domenik Eichhorn, Joshua Ammermann +4Quantum Circuits Qubit
Karlsruhe Institute of Technology, Germany · Technical University of Munich, Germany
InferQ: A Database-Oriented Benchmark for Quantum Circuits Simulation
Jul 31, 2026Andrei Ilinescu, Aadi Patwardhan, Rihan HaiQuantum Circuits Text-To-Sql
Delft University of Technology, Delft, The Netherlands
Wiring diagram extraction and gluing: a case study in classifying figure skating jumps using 3D dataset
Jul 30, 2026Jason Lo, Mohammadnima JafariClustering Unsupervised
The Kinetics of Training: A Driven-Nucleation Rate Law for Emergence, Plasticity Loss, and Circuit Control in Language Models
Jul 29, 2026Lei DongPlasticity Circuits
Independent Researcher
OmniQEC: discovering practical quantum error-correcting codes by an AI scientist
Jul 28, 2026Ge Yan, Shanchuan Li, Pengyue Ma +5Quantum Error Correction Post-Quantum Cryptography
College of Computing and Data Science, Nanyang Technological University, Singapore · Department of Electrical Engineering and Computer Science, Tokyo University of Agriculture and Technology, Koganei, Tokyo, Japan · 3Zhejiang University of Technology, China +3
Neural Circuit Function Inference with LLMs
Jul 27, 2026Yijie Yin, Albert CardonaNeural Circuits Connectome
Department of Physiology, Development and Neuroscience, University of Cambridge, Cambridge, UK · MRC Laboratory of Molecular Biology, Cambridge, UK
ADVERSARIAL: And-Inverter Graph-Assisted Hardware Trojan Detection At Scale
Jul 26, 2026Yaroslav Popryho, Debjit Pal, Inna Partin-VaisbandMalware Circuits
Department of Electrical and Computer Engineering, University of Illinois Chicago, Chicago, IL 60607 USA
ParasGB: A Graph Benchmark Suite for Parasitic Estimation on AMS Circuits
Jul 25, 2026Jiajun Zou, Jiawei Liu, Ao Liu +8Printed Circuit Board Circuits
1Nanjing University of Science and Technology, Nanjing, China · 2The Chinese University of Hong Kong, Hong Kong SAR, China · 3Dept. Computer Science & Tech., BNRist, Tsinghua University, Beijing, China +3
What, Where, and How: Disentangling the Roles of Task, Language, and Model in Code Model Representations
Jul 23, 2026Piotr WilamLanguage Modeling Circuits
University College London
Cautious optimism for deep parameterized quantum circuits
Jul 23, 2026Marie Kempkes, Elies Gil-Fuster, Carlos Bravo-Prieto +5Quantum Machine Learning Quantum Circuits
Leiden University, Niels Bohrweg 1, 2333 CA Leiden, Netherlands · Volkswagen Group Innovation, Berliner Ring 2, 38440 Wolfsburg, Germany · Dahlem Center for Complex Quantum Systems, Freie Universität Berlin, 14195 Berlin, Germany +4
Approximate Quantum State Preparation Through Proximal Policy Optimization
Jul 23, 2026Marco Mordacci, Michele AmorettiQubit Proximal Policy Optimization
Quantum Software Laboratory, University of Parma, Parco Area delle Scienze, 181/A, Parma, 43124, Italy.
Where Animacy Lives in Large Language Models: Tracing the Circuits of the Animacy Concept
Jul 23, 2026Samuele Punzo, Giovanni Cinà, Sandro PezzelleLarge Language Model Annotations Contextual Cues
Graduate School of Informatics, University of Amsterdam · Department of Medical Informatics, Amsterdam University Medical Center · ILLC, University of Amsterdam
CircuitKIT : Circuit Discovery, Evaluation, and Application Toolkit for Mechanistic Interpretability
Jul 21, 2026Pratinav Seth, Hem Gosalia, Aditya Kasliwal +1Circuits Model Discovery
Lexsi Labs
Circuit Claims Depend on What Is Extracted and How It Is Compared
Jul 21, 2026Yang Sheng, Jie FuCircuits Ablation
1Fudan University · 2Shanghai Innovation Institute · 3IQuest Research
Entanglement geometry separates circuit cutting, classical hardness, and trainability
Jul 20, 2026Maria Gragera Garces, Sabina Drăgoi, Lirandë PiraQuantum Circuits Variational Quantum Algorithms
Quantum Software Lab University of Edinburgh, UK · ETH ZÜrich, ZÜrich, Switzerland IBM Research, RÜschlikon, Switzerland · Centre for Quantum Technologies, National University of Singapore, Singapore
Are Arithmetic Heuristic Neurons Form-Invariant? A Mechanistic Analysis of Symbols, Text, and Code in LLMs
Jul 18, 2026Sharath Naganna, Tanvir Ahmed Sijan, Uddipta KalitaLarge Language Models Fail Mechanistic Interpretability
Indian Institute of Technology Bombay, Mumbai, India · Jahangirnagar University, Dhaka, Bangladesh · National Institute of Technology, Silchar, India
CLDRoute: Conditional Latent Diffusion for Routability Map Generation in Physical Design
Jul 18, 2026Kiran Thorat, Nicole Meng, Caiwen Ding +2Road Networks Identity-Conditioned Latent Diffusion Models
University of Connecticut · Tufts University · University of Minnesota Twin Cities
A Shared Subcircuit Lets LLMs Count Down Across Tasks
Jul 14, 2026Jacob Dunefsky, Wes Gurnee, Emmanuel AmeisenCircuits
Yale University · Anthropic
Invariant Learning Dynamics of Transformers in Inductive Reasoning Tasks
Jul 13, 2026Tiberiu Musat, Tiago Pimentel, Nicolas Zucchet +1Transformer Architectures Induction
ETH Zurich · Stanford University
Tropical Circuits with Scalar Multiplication Gates
Jul 13, 2026Christoph Hertrich, Moritz StargallaTensor Networks Exponents
University of Technology Nuremberg

Oct 1, 2026, cs.LGJ/K move · Enter open · S save

Are We Recovering Mechanisms? Objective-Level Recovery Gaps in Mechanistic Interpretability

Chuqin Geng, Li Zhang, Haolin Ye, Mark Zhang+2

University of Toronto · McGill University

Mechanistic Interpretability Model Discovery Circuits

Open paper AskPDF arXiv

Mechanistic interpretability aims to recover the internal computations responsible for model behavior. Progress in automated circuit discovery is often framed as a search problem: better attribution or optimization should identify better mechanisms. This assumes that the evaluation objective can recognize a better circuit once it is found. We show that intervention-defined faithfulness can instead prefer an equally sized circuit that reproduces the model's behavior less well, creating an objective-level recovery gap. Across four human-reference tasks and InterpBench, we compare validation faithfulness with behavior on held-out prompts under fixed ordinary resampling. The behavioral criterion is agreement with the intact model, including its mistakes, except on Greater-Than, where we use semantic accuracy. Controlled reference edits reveal misranking without any discovery algorithm, and outputs of EAP, EAP-IG, ACDC, and Edge-SP exhibit the same failure. Under resampling, KL misranks 9.4%-41.2% of candidate pairs across these methods on the human-reference tasks. We investigate context distortion as an explanation: replacing excluded signals changes the inputs on which retained components operate. Restoring selected signals from the recipient's intact-model execution repairs 96 of 100 persistent KL misrankings from the discovery pool on both validation and held-out prompts. The circuits and their original behavioral scores remain unchanged. These findings show why better discovery alone is insufficient when its objective rewards the wrong candidate.

Momentum

Related topics

Latest papers 140