Instant research discovery
Search and browse arXiv CS/AI/ML papers, enriched with AI-generated insights.
Generate novel research ideas grounded in real arXiv papers with Brainstorm.
PreviousNext
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
Search and browse arXiv CS/AI/ML papers, enriched with AI-generated insights.
Generate novel research ideas grounded in real arXiv papers with Brainstorm.
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
Search and browse arXiv CS/AI/ML papers, enriched with AI-generated insights.
Generate novel research ideas grounded in real arXiv papers with Brainstorm.
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
| Retrieval is Enough: Training-Free Interpretability with a Tool-Using Agent Soheil Feizi, Sriram Balasubramanian Published: 2026-07-17Area: cs.LGCitations: - Tags: ai-safety, cslg, interpretability, preprint | 2026-07-17 | cs.LG | ai-safety, cslg, interpretability, preprint | E11 / R9 (90%) | - |
| Interior interpretability with attention rollout: contraction and propagation profiles in Transformers Enrique Zuazua, Qian Huang, Umberto Biccari Published: 2026-07-24Area: cs.LGCitations: - Tags: ai-safety, cslg, interpretability, preprint | 2026-07-24 | cs.LG | ai-safety, cslg, interpretability, preprint | - | - |
| KANEx: Translating Kolmogorov-Arnold Networks' Interpretability to Medical Explainability Aditi Anand, Ananya Lakshmi Ravi, Balaraman Ravindran, Gokul S. Krishnan Published: 2026-07-27Area: cs.CVCitations: - Tags: ai-safety, cscv, interpretability, preprint | 2026-07-27 | cs.CV | ai-safety, cscv, interpretability, preprint | - | - |
| ECG-InterpBench: Benchmarking the Interpretability of ECG Foundation Models with Matched-Scale Sparse Autoencoders Wei Qiu, Yixuan Duan Published: 2026-07-29Area: cs.LGCitations: - Tags: ai-safety, cslg, interpretability, preprint | 2026-07-29 | cs.LG | ai-safety, cslg, interpretability, preprint | E13 / R12 (91%) | - |
| Interpretability-Guided Soft Pruning of Attention Heads in Vision Transformers Jacek Tabor, Kamil Ksi膮偶ek, Micha艂 Jan W艂odarczyk, Piotr Suszy艅ski Published: 2026-07-31Area: cs.CVCitations: 41 Tags: ai-safety, cscv, interpretability, preprint | 2026-07-31 | cs.CV | ai-safety, cscv, interpretability, preprint | E10 / R8 (92%) | 41 |
| MI-MIDI: Mechanistic Interpretability of Text-to-MIDI Generation Models via Probing, Lenses and Steering Jakub Po膰wiardowski, Mateusz Modrzejewski Published: 2026-08-06Area: cs.SDCitations: - Tags: ai-safety, cssd, interpretability, preprint | 2026-08-06 | cs.SD | ai-safety, cssd, interpretability, preprint | E11 / R13 (91%) | - |
| From Interpretability to Control: Insights from Six Years of the TrustNLP Workshop Abhinav Mohanty, Anaelia Ovalle, Anil Ramakrishna, Anubrata Das Published: 2026-08-11Area: cs.CLCitations: - Tags: ai-safety, cscl, interpretability, preprint | 2026-08-11 | cs.CL | ai-safety, cscl, interpretability, preprint | E12 / R9 (91%) | - |
| HyperANFIS: Enhancing Rule Representation and Interpretability in Adaptive Neuro-Fuzzy Systems via Hyperbolic Geometry Binbin Yong, Haoran Li, Haoran Pei, Jun Shen Published: 2026-08-12Area: cs.AICitations: - Tags: ai-safety, csai, interpretability, preprint | 2026-08-12 | cs.AI | ai-safety, csai, interpretability, preprint | - | - |
| Explanation Multiplicity: Circuit-Level Interpretability Evidence Does Not Survive Defensible Analytic Variation Ajay Pravin Mahale Published: 2026-08-13Area: cs.AICitations: - Tags: ai-safety, csai, interpretability, preprint | 2026-08-13 | cs.AI | ai-safety, csai, interpretability, preprint | E10 / R7 (93%) | - |
| Mechanistic Interpretability of Structure-Aware Numerical Reasoning in LLaMA 3.1 8B David Bau, Jiahao Liu, Octavia Camps, Pu Zhao Published: 2026-08-19Area: cs.LGCitations: - Tags: ai-safety, cslg, interpretability, preprint | 2026-08-19 | cs.LG | ai-safety, cslg, interpretability, preprint | E8 / R6 (93%) | - |
| Mechanistic Tomography: Designed Measurement for Control-Oriented Interpretability Vijay Erramilli Published: 2026-08-19Area: cs.LGCitations: - Tags: ai-safety, cslg, interpretability, preprint | 2026-08-19 | cs.LG | ai-safety, cslg, interpretability, preprint | E9 / R7 (94%) | - |
| Beyond Static Interpretability: Anticipating Post-SFT Mechanisms from Pre-SFT Parameters for Better Tuning Hang Chen, Jiaying Zhu, Wenya Wang Published: 2026-08-25Area: cs.LGCitations: - Tags: ai-safety, cslg, interpretability, preprint | 2026-08-25 | cs.LG | ai-safety, cslg, interpretability, preprint | E9 / R9 (94%) | - |
| Efficient Auto-Interpretability of AI Models in Biology Oliver M. Crook, Piotr Jedryszek Published: 2026-08-27Area: q-bio.QMCitations: 13 Tags: ai-safety, interpretability, preprint, q-bioqm | 2026-08-27 | q-bio.QM | ai-safety, interpretability, preprint, q-bioqm | E7 / R5 (93%) | 13 |
| A Unifying Perspective on Language Model Representations: From Filler-Role Structure to Mechanistic Interpretability R. Thomas McCoy, Zhang Enyan Published: 2026-08-29Area: cs.CLCitations: - Tags: ai-safety, cscl, interpretability, preprint | 2026-08-29 | cs.CL | ai-safety, cscl, interpretability, preprint | E12 / R8 (94%) | - |
| Tensor Methods for Language Models: From Token Representation to Training, Adaptation, Inference, Compression, and Interpretability Andre L. F. de Almeida, Andrzej Cichocki, Matvei Tarasov, Salman Ahmadi-Asl Published: 2026-08-31Area: cs.LGCitations: - Tags: ai-safety, cslg, interpretability, preprint | 2026-08-31 | cs.LG | ai-safety, cslg, interpretability, preprint | E12 / R8 (92%) | - |
| SAEScientist-Bench: Can AI Agents Conduct Autonomous SAE Interpretability Research? Jun Zhao, Kang Liu, Shizhu He, Yuqiao Tan Published: 2026-09-08Area: cs.AICitations: - Tags: ai-safety, csai, interpretability, preprint | 2026-09-08 | cs.AI | ai-safety, csai, interpretability, preprint | E11 / R9 (94%) | - |
| Generative Interpretability via Scalable Neuro-Symbolic Models Xiaocong Yang Published: 2026-09-11Area: cs.LGCitations: 52 Tags: ai-safety, cslg, interpretability, preprint | 2026-09-11 | cs.LG | ai-safety, cslg, interpretability, preprint | E9 / R8 (92%) | 52 |
| Bangla Sentence Function Classification: Corpus Development, Model Benchmarking, and Interpretability Abdullah Al Shafi, Abdul Muntakim, Jannatul Ferdousi, M. A. Moyeen Published: 2026-09-12Area: cs.CLCitations: - Tags: ai-safety, cscl, interpretability, preprint | 2026-09-12 | cs.CL | ai-safety, cscl, interpretability, preprint | E13 / R9 (96%) | - |
| Calibrating Interpretability Instruments Before Trusting Their Verdicts Orion Reblitz-Richardson Published: 2026-09-13Area: cs.LGCitations: - Tags: ai-safety, cslg, interpretability, preprint | 2026-09-13 | cs.LG | ai-safety, cslg, interpretability, preprint | - | - |
| The Misery of Mechanistic Interpretability: A Formal Perspective Matthias Althoff, Tobias Ladner Published: 2026-09-14Area: cs.LGCitations: - Tags: ai-safety, cslg, interpretability, preprint | 2026-09-14 | cs.LG | ai-safety, cslg, interpretability, preprint | - | - |
| A unified framework for global and local interpretability using adaptive derivative-ordered random explanation Anran Fanga, Lemen Chao, Ming Lei Published: 2026-09-15Area: cs.LGCitations: - Tags: ai-safety, cslg, interpretability, preprint | 2026-09-15 | cs.LG | ai-safety, cslg, interpretability, preprint | - | - |
| A unified framework for global and local interpretability using adaptive derivative-ordered random explanation Anran Fang, Lemen Chao, Ming Lei Published: 2026-09-15Area: cs.LGCitations: - Tags: ai-safety, cslg, interpretability, preprint | 2026-09-15 | cs.LG | ai-safety, cslg, interpretability, preprint | E10 / R8 (93%) | - |
| Flag Game: A Toy Model for Mechanistic Swarm Interpretability Elizabeth Pavlova, Hidenori Tanaka Published: 2026-09-16Area: cs.AICitations: - Tags: ai-safety, csai, interpretability, preprint | 2026-09-16 | cs.AI | ai-safety, csai, interpretability, preprint | E11 / R9 (91%) | - |
| Xeno-Interpretability: Investigating the Alien Minds of LLMs F. Giarrusso, F. Pierucci, M. Bracale Syrnikov, M. Galisai Published: 2026-09-17Area: cs.CLCitations: - Tags: ai-safety, cscl, interpretability, preprint | 2026-09-17 | cs.CL | ai-safety, cscl, interpretability, preprint | E10 / R6 (90%) | - |
| Xeno-Interpretability: Investigating the Alien Minds of LLMs F. Giarrusso, F. Pierucci, M. Bracale Syrnikov, M. Galisai Published: 2026-09-17Area: cs.CLCitations: - Tags: ai-safety, cscl, interpretability, preprint | 2026-09-17 | cs.CL | ai-safety, cscl, interpretability, preprint | E10 / R6 (91%) | - |
| Triggers and Diagnostics for LLM-Based Interpretability Failures in Active Inference Agents Archana Vaidheeswaran, Param Raval, Rohit Shenoy Published: 2026-09-19Area: cs.LGCitations: - Tags: ai-safety, cslg, interpretability, preprint | 2026-09-19 | cs.LG | ai-safety, cslg, interpretability, preprint | E8 / R7 (94%) | - |
| Watching Quantum Models Think: Hilbert-Space Interpretability in Quantum Transformer Blocks Andrea Gasparini, Diego Iacopetta Published: 2026-09-19Area: quant-phCitations: 26 Tags: ai-safety, interpretability, preprint, quant-ph | 2026-09-19 | quant-ph | ai-safety, interpretability, preprint, quant-ph | E13 / R9 (95%) | 26 |
| Augmenting Visual Anomaly Detection with Automated Interpretability Antonio De Santis, Arsenio Leo, Marco Brambilla Published: 2026-09-27Area: cs.CVCitations: - Tags: ai-safety, cscv, interpretability, preprint | 2026-09-27 | cs.CV | ai-safety, cscv, interpretability, preprint | - | - |
| Dynamical Parameters: An Interpretability Framework for Time-Series Foundation Models Gaofeng Dong, Kang Yang, Liying Han, Mani Srivastava Published: 2026-09-28Area: cs.AICitations: - Tags: ai-safety, csai, interpretability, preprint | 2026-09-28 | cs.AI | ai-safety, csai, interpretability, preprint | - | - |
| Less Sycophancy, Stronger Refusal? Lessons for AI Safety from Mechanistic Interpretability Difan Zou, Xuansheng Wu, Xu Wang Published: 2026-09-28Area: cs.CLCitations: - Tags: ai-safety, cscl, interpretability, preprint | 2026-09-28 | cs.CL | ai-safety, cscl, interpretability, preprint | - | - |