Good Papers: read the good ones

Showing Feature attribution Show all papers

76%Highly rated

?Highly ratedVote to see the score

TMLR 2026Feature attribution

MCIR: A Feature Dependence-Aware Explainability Method with Reliability Guarantees

MCIR-M quantifies unique predictive information beyond dependent neighbors via a normalized conditional ratio in [0,1], yielding stable dependence-aware global rankings under multicollinearity and near-duplicates.

Poushali Sengupta, Sabita Maharjan, Frank Eliassen, Shashi Raj Pandey and 1 more

Published Oct 1, 2026 · 0 citations

– ReadersNo votes yet

10/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 10 of 20 reviewers recommend it

lenient 4/5

medium 5/10

strict 1/5

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026Korea Advanced Institute of Scie KAIST Feature attribution

TreePII: Efficient Computation of Higher-Order Probabilistic Interaction Indices in Tree Ensembles

Junho Choi, Jaesik Choi

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it

lenient 0/5

medium 0/10

strict 0/5

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026International Monetary Fund kudan suuriken Fukuoka Waseda Feature attribution

ESENSC: A Polynomial-Time Axiomatic Alternative to SHAP

Kazuhiro Hiraki, Shinichi Ishihara, Takumi Kongo, Junnosuke Shino

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it

lenient 0/5

medium 0/10

strict 0/5

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026Freie Universität Berlin Nanjing Feature attribution

Explaining Cross-Modal Model Behavior with Gradient-Estimation-Based Feature Interaction

Yi Cai, Xinpeng Li, Gerhard Wunder

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it

lenient 0/5

medium 0/10

strict 0/5

57%Worth a look

?Worth a lookVote to see the score

NeurIPS 2026SpotlightGerman Research Center for Artif German Research Center for AI Feature attribution

Weakly Supervised Concept Learning for Interpreting and Attributing LVLM Predictions

Md Abdul Kadir, Omair Shahzad Bhatti, Daniel Sonntag

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it

lenient 1/5

medium 0/10

strict 0/5

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026KTH Royal Institute of Technolog KTH Royal Institute of Technolog Feature attribution

Exact power indices for plurality-voting ensembles

Ilie Sarpe, Theofanis Georgakopoulos, Aristides Gionis

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it

lenient 0/5

medium 0/10

strict 0/5

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026U Pennsylvania U Pennsylvania, University of Pe Feature attribution

Position-aware eXplanation: A Model-Agnostic Framework for Positional Attributions

Chaehyeon Kim, Gary Weissman, Eric Wong

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it

lenient 0/5

medium 0/10

strict 0/5

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026ETHZ - ETH Zurich UT Austin U Texas at Austin EPFL - EPF Lausanne ETH Zurich Feature attribution

Parasite Features: Causal Abstraction Through Spurious Pathways

Denis Sutter, Qing Yao, Sasha Boguraev, Julian Minder and 4 more

Paris Poster Session 3, Thu, Dec 10, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it

lenient 0/5

medium 0/10

strict 0/5

57%Worth a look

?Worth a lookVote to see the score

NeurIPS 2026Seoul National Feature attribution

Decomposing Conformal Uncertainty: Calibration- and Instance-Driven Feature Attribution

Sangyeon Cho, Minyoung Cho, Jungsoo Kim, Sujeong Oh and 1 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it

lenient 1/5

medium 0/10

strict 0/5

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026U British Columbia The University of British Columb Feature attribution

Causal Gradient Steering: Exposing Shortcut Gradients by Destroying Causal Signal

Ahmed Radwan, Ahmad Abdel-Qader, Mahmoud Soliman, Omar Abdelaziz and 3 more

Paris Poster Session 1, Wed, Dec 9, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it

lenient 0/5

medium 0/10

strict 0/5

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026Northeastern Emory Feature attribution

Designing Kernel Surrogate Models for Multimodal Attribution

Ziniu Zhang, Zhenshuo Zhang, Jianglin Lu, Ruoxuan Xiong and 2 more

Atlanta Poster Session 6, Fri, Dec 11, 4:30 PM–7:30 PM, Hall C1 · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it

lenient 0/5

medium 0/10

strict 0/5

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026Cornell Imperial College London Goodfire AI Feature attribution

Jacobian Scopes: A Unified Geometric Framework for Token-Level LLM Attributions

Toni Liu, Baran Zadeoğlu, Nicolas Boulle, Raphaël Sarfati and 2 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it

lenient 0/5

medium 0/10

strict 0/5

45%Niche pick

?Niche pickVote to see the score

NeurIPS 2026U Southampton Feature attribution

In search of a definition of importance: Do attributions capture it?

Antonia Marcu, Jonathon Hare, Annika Catulli, Srinandan Dasmahapatra and 1 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it

lenient 0/5

medium 0/10

strict 0/5

83%Must read

?Must readVote to see the score

NeurIPS 2026The Ohio State Carnegie Mellon Ohio State University, Columbus Feature attribution

Generalized Priority-Aware Shapley Value

GPASV extends priority-aware Shapley values to cyclic weighted priority graphs via penalized violations, yielding differing LLM ensemble valuations.

Kiljae Lee, Ziqi Liu, Weijing Tang, Yuan Zhang

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

13/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 13 of 20 reviewers recommend it

lenient 5/5

medium 7/10

strict 1/5

74%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026U Vienna Feature attribution

FRInGe: Distribution-Space Integrated Gradients with Fisher–Rao Geometry

FRInGe defines Integrated Gradients via Fisher-Rao geodesics in predictive distribution space, improving calibration-oriented attribution metrics across ImageNet models.

Gabriele Martino, Sebastian Tschiatschek

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

9/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 9 of 20 reviewers recommend it

lenient 2/5

medium 6/10

strict 1/5

76%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026U Bari Aldo Moro Eindhoven University of Technolo Feature attribution

Matching-Based Few-Shot Semantic Segmentation Models Are Interpretable by Design

Affinity Explainer leverages matching-based FSS architectures to extract support-pixel attribution maps outperforming standard attribution methods and enabling model diagnosis.

Pasquale De Marinis, Uzay Kaymak, Rogier Brussee, Gennaro Vessio and 1 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · Code

– ReadersNo votes yet

10/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 10 of 20 reviewers recommend it

lenient 4/5

medium 6/10

strict 0/5

80%Must read

?Must readVote to see the score

NeurIPS 2026Institute of Mathematics of Toul Centre National de Recherches Mé CERFACS CNRS - Institut de Mathématiques Feature attribution

Explanation of Dynamic Physical Field Predictions using WassersteinGrad: Application to Autoregressive Weather Forecasting

WassersteinGrad replaces pointwise averaging with an entropic Wasserstein barycenter to align geometrically displaced attributions in dynamic physical field predictions, improving explainability for autoregressive weather forecasts.

Younes Essafouri, Laure Raynaud, Luciano DROZDA, Laurent Risser

Paris Poster Session 2, Wed, Dec 9, 5:00 PM–7:00 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet

12/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 12 of 20 reviewers recommend it

lenient 5/5

medium 6/10

strict 1/5

80%Must read

?Must readVote to see the score

NeurIPS 2026Leiden University Medical Center Nanyang Technological CISPA Helmholtz Center for Infor Feature attribution

Amortized Linear-time Exact Shapley Value for Product-Kernel Methods

PKeX-Shapley computes exact Shapley values for product-kernel methods via a distribution-free removal operator, achieving amortized linear-time per feature without sampling or density estimation and extending to MMD and HSIC.

Majid Mohammadi, Siu Lun (Alan) Chau, Krikamol Muandet

Paris Poster Session 1, Wed, Dec 9, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet

12/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 12 of 20 reviewers recommend it

lenient 5/5

medium 6/10

strict 1/5

89%Must read

?Must readVote to see the score

NeurIPS 2026U Virginia National Institutes of Health U Virginia, Charlottesville Feature attribution

Rethinking Visual Attribution for Chest X-ray Reasoning in Large Vision Language Models

A causal framework reveals standard visual attribution methods poorly explain chest X-ray reasoning in vision-language models, and MedFocus improves evidence localization via concept-based optimal transport.

Guangzhi Xiong, Qiao Jin, Sanchit Sinha, Zhiyong Lu and 1 more

Atlanta Poster Session 6, Fri, Dec 11, 4:30 PM–7:30 PM, Hall C1 · Published 2026 · ▲ 1 on Hugging Face · Code ★ 6

– ReadersNo votes yet

16/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 16 of 20 reviewers recommend it

lenient 5/5

medium 8/10

strict 3/5

78%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026Computer Engineering, Sharif Uni Sharif University of Technology,Sharif University of Technology Feature attribution

Causal Attribution via Activation Patching

CAAP estimates vision transformer patch contributions by directly intervening on internal activations, yielding more faithful and localized attributions than existing methods.

Amirmohammad Izadi, Mohammadali Banayeeanzade, Alireza Mirrokni, Hosein Hasani and 3 more

Paris Poster Session 4, Thu, Dec 10, 5:30 PM–7:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet

11/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 11 of 20 reviewers recommend it

lenient 4/5

medium 7/10

strict 0/5

76%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026The Chinese University of Hong K Aalto Taobao (China) Software Co., Ltd Technical University of Denmark Feature attribution

From Baselines to Transport Geodesics: Axiomatic Attribution via Optimal Generative Flows

Fixed-path attribution uniquely requires Aumann-Shapley line integrals, while transport-geodesic paths via minimized kinetic action yield more stable, structured explanations.

Cenwei Zhang, Lin Zhu, Manxi Lin, Lei You

Paris Poster Session 2, Wed, Dec 9, 5:00 PM–7:00 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet

10/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 10 of 20 reviewers recommend it

lenient 2/5

medium 6/10

strict 2/5

89%Must read

?Must readVote to see the score

NeurIPS 2026UC Santa Barbara U California, Santa Barbara UCSB Feature attribution

Revealing the Gap in Human and VLM Scene Perception through Counterfactual Semantic Saliency

Counterfactual Semantic Saliency reveals VLMs diverge from human scene perception via size, center, and saliency biases while underweighting people.

Ziqi Wen, Parsa Madinei, Miguel Eckstein

Atlanta Poster Session 2, Wed, Dec 9, 4:30 PM–7:30 PM, Hall C1 · Published 2026

– ReadersNo votes yet

16/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 16 of 20 reviewers recommend it

lenient 4/5

medium 9/10

strict 3/5

74%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026Columbia U Michigan - Ann Arbor Feature attribution

Model-Agnostic FDR Control via Group Gaussian Mirror and Permutation SHAP

A model-agnostic framework controls FDR for grouped features via block-level mirror statistics and permutation SHAP, ensuring reliable selection across linear and neural sequential models.

Jiaan Han, Junxiao Chen, Yanzhe Fu

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

9/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 9 of 20 reviewers recommend it

lenient 2/5

medium 6/10

strict 1/5

78%Highly rated

?Highly ratedVote to see the score

NeurIPS 2026LMU Munich Institute of Computer Science, L Marburguniversity Feature attribution

OperatorSHAP: Fast and Accurate Shapley Value Estimation for Neural Operators

OperatorSHAP trains grid-agnostic amortized Shapley explainers for neural operators, yielding resolution-consistent attributions that transfer across grids without retraining.

Joshua Stiller, Santo Thies, Felix Czaja, Eyke Hüllermeier

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

11/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 11 of 20 reviewers recommend it

lenient 5/5

medium 6/10

strict 0/5

91%Must read

?Must readVote to see the score

NeurIPS 2026New York NYU KAIST Feature attribution

Explanation Multiplicity in SHAP: Characterization and Assessment

SHAP produces multiple valid yet different explanations for identical predictions due to intrinsic stochasticity, and magnitude-based stability metrics mask substantial rank instability across datasets and models.

Hyunseung Hwang, Seungeun Lee, Lucas Rosenblatt, Steven Whang and 1 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet

17/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 17 of 20 reviewers recommend it

lenient 5/5

medium 8/10

strict 4/5

71%Highly rated

?Highly ratedVote to see the score