Saumitra Mishra
12 papers · 2022–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
π Cross-Pollinator (7) π Interdisciplinary Bridge π§ Keyword Pioneer πΊοΈ Taxonomy Completionist (23) π Renaissance Researcher (5)
π
Conference Polyglot
(4)
π
Grand Slam
β
The Questioner
π
Century Club
(12)
Conferences
ICML (7)
NIPS (3)
AAAI (1)
ICLR (1)
Top co-authors
Keywords
counterfactual explanation
(4)
model interpretability
(2)
pose estimation
(1)
model robustness
(1)
interpretable machine learning
(1)
video understanding
(1)
symbolic regression
(1)
multi-modal alignment
(1)
covariate shift
(1)
gradient descent
(1)
label shift
(1)
object segmentation
(1)
tree-based ensemble
(1)
variational autoencoder
(1)
feature importance
(1)
scene understanding
(1)
3d reconstruction
(1)
3d grounding
(1)
assembly instruction
(1)
causal inference
(1)
Papers
Interpreting Language Reward Models via Contrastive Explanations
ICLR 2025
To Steer or Not to Steer? Mechanistic Error Reduction with Abstention for Language Models
ICML 2025
Quantifying Prediction Consistency Under Fine-tuning Multiplicity in Tabular LLMs
ICML 2025
Sequential Harmful Shift Detection Without Labels
NIPS 2024
IKEA Manuals at Work: 4D Grounding of Assembly Instructions on Internet Videos
NIPS 2024
Counterfactual Metarules for Local and Global Recourse
ICML 2024
Progressive Inference: Explaining Decoder-Only Sequence Classification Models Using Intermediate Predictions
ICML 2024
Robust Counterfactual Explanations for Neural Networks With Probabilistic Guarantees
ICML 2023
Symbolic Metamodels for Interpreting Black-Boxes Using Primitive Functions
AAAI 2023
GLOBE-CE: A Translation Based Approach for Global Counterfactual Explanations
ICML 2023
CLEAR: Generative Counterfactual Explanations on Graphs
NIPS 2022
Robust Counterfactual Explanations for Tree-Based Ensembles
ICML 2022