← Authors

Victor Veitch

24 papers · 2019–2025 · 7 conferences · across top CS/AI conferences

Achievements

🐝 Cross-Pollinator (13) πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🌍 Conference Polyglot (7) πŸƒ Academic Marathon (6) πŸ—ΊοΈ Taxonomy Completionist (29) 🌈 Renaissance Researcher (5) πŸ‘₯ Mega-Team (40) πŸ”¬ Deep Specialist (10) πŸ† Keyword Champion (2) πŸ”₯ Unstoppable (7) πŸ’Ž Century Club (24) ⚑ Prolific Year (5) πŸ—ƒοΈ Keyword Collector (72)

Conferences

NIPS (10) ICML (5) ICLR (4) UAI (2) AISTATS (1) JMLR (1) NAACL (1)

Top co-authors

Yibo Jiang (4) Dhanya Sridhar (3) David Blei (3) Jacob Eisenstein (3) Lin Gui (3) Bryon Aragam (2) Morgane Austern (2) Peter Orbanz (2) Alexander D'Amour (2) Claudia Shi (2)

Keywords

causal inference (10) representation learning (4) observational datum (3) domain generalization (3) text classification (2) embedding learning (2) network embedding (2) unobserved confounding (2) policy optimization (1) reward modeling (1) sentiment analysis (1) domain adaptation (1) knowledge distillation (1) language model alignment (1) stochastic gradient descent (1) graph embedding (1) model alignment (1) empirical risk minimization (1) sensitivity analysis (1) reinforcement learning from human feedback (1)

Papers

RATE: Causal Explainability of Reward Models with Imperfect Counterfactuals ICML 2025
The Geometry of Categorical and Hierarchical Concepts in Large Language Models ICLR 2025
On the Origins of Linear Representations in Large Language Models ICML 2024
BoNBoN Alignment for Large Language Models and the Sweetness of Best-of-n Sampling NIPS 2024
The Linear Representation Hypothesis and the Geometry of Large Language Models ICML 2024
Transforming and Combining Rewards for Aligning Large Language Models ICML 2024
Efficient Conditionally Invariant Representation Learning ICLR 2023
Uncovering Meanings of Embeddings via Partial Orthogonality NIPS 2023
Causal Context Connects Counterfactual Fairness to Robust Prediction and Group Fairness NIPS 2023
Concept Algebra for (Score-Based) Text-Controlled Generative Models NIPS 2023
Causal Estimation for Text Data with (Apparent) Overlap Violations ICLR 2023
Using Embeddings for Causal Estimation of Peer Influence in Social Networks NIPS 2022
Underspecification Presents Challenges for Credibility in Modern Machine Learning JMLR 2022
Invariant and Transportable Representations for Anti-Causal Domain Shifts NIPS 2022
Invariant representation learning for treatment effect estimation UAI 2021
Counterfactual Invariance to Spurious Correlations in Text Classification NIPS 2021
Valid Causal Inference with (Some) Invalid Instruments ICML 2021
Causal Effects of Linguistic Properties NAACL 2021
Sense and Sensitivity Analysis: Simple Post-Hoc Analysis of Bias Due to Unobserved Confounding NIPS 2020
Adapting Text Embeddings for Causal Inference UAI 2020
Empirical Risk Minimization and Stochastic Gradient Descent for Relational Data AISTATS 2019
Using Embeddings to Correct for Unobserved Confounding in Networks NIPS 2019
Adapting Neural Networks for the Estimation of Treatment Effects NIPS 2019
Non-vacuous Generalization Bounds at the ImageNet Scale: a PAC-Bayesian Compression Approach ICLR 2019