conftrace_

Adam Block

18 papers · 2021–2025 · 5 conferences · across top CS/AI conferences

Achievements

Jump to papers ↓
+7 more ↓ πŸŒ‰ Interdisciplinary Bridge πŸ—ΊοΈ Taxonomy Completionist (27) 🌍 Conference Polyglot (5) 🌈 Renaissance Researcher (6) 🧭 Keyword Pioneer
🧭 Keyword Pioneer πŸ† Keyword Champion (5) ❓ The Questioner (2) ⚑ Prolific Year (5) πŸ’Ž Century Club (18) πŸ—ƒοΈ Keyword Collector (56) πŸ”₯ Unstoppable (5)

Conferences

COLT (7) NIPS (6) ICLR (2) ICML (2) JMLR (1)

Papers

Self-Improvement in Language Models: The Sharpening Mechanism ICLR 2025 Is Best-of-N the Best of Them? Coverage, Scaling, and Optimality in Inference-Time Alignment ICML 2025 A Theory of Learning with Autoregressive Chain of Thought COLT 2025 Computational-Statistical Tradeoffs at the Next-Token Prediction Barrier: Autoregressive and Imitation Learning under Misspecification (extended abstract) COLT 2025 GaussMark: A Practical Approach for Structural Watermarking of Language Models ICML 2025 Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression ICLR 2024 Oracle-Efficient Differentially Private Learning with Public Data NIPS 2024 Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning NIPS 2024 On the Performance of Empirical Risk Minimization with Smoothed Data COLT 2024 Oracle-Efficient Smoothed Online Learning for Piecewise Continuous Decision Making COLT 2023 Provable Guarantees for Generative Behavior Cloning: Bridging Low-Level Stability and High-Level Behavior NIPS 2023 Smoothed Online Learning for Prediction in Piecewise Affine Systems NIPS 2023 Efficient Model-Free Exploration in Low-Rank MDPs NIPS 2023 The Sample Complexity of Approximate Rejection Sampling With Applications to Smoothed Online Learning COLT 2023 Intrinsic Dimension Estimation Using Wasserstein Distance JMLR 2022 Smoothed Online Learning is as Easy as Statistical Learning COLT 2022 Efficient and Near-Optimal Smoothed Online Learning for Generalized Linear Functions NIPS 2022 Majorizing Measures, Sequential Complexities, and Online Learning COLT 2021