Education
Stochastic contextual bandits with graph feedback: from independence number to MAS number Y uxiao Wen Y anjun Han
The framework of formulating the feedback structure as feedback graphs in bandits has a long history (Mannor and Shamir, 2011; Alon et al., 2015, 2017; Lykouris et al.,
Alignment for Honesty Y uqing Y ang
However, a pivotal aspect of alignment for honesty involves discerning an LLM's
Provably Transformers Harness Multi-Concept Word Semantics for Efficient In-Context Learning
Transformer-based large language models (LLMs) have displayed remarkable creative prowess and emergence capabilities. Existing empirical studies have revealed a strong connection between these LLMs' impressive emergence abilities and their
Task-recency bias strikes back: Adapting covariances in Exemplar-Free Class Incremental Learning
Exemplar-Free Class Incremental Learning (EFCIL) tackles the problem of training a model on a sequence of tasks without access to past data.
Mitigating Partial Observability in Sequential Decision Processes via the Lambda Discrepancy Cameron Allen UC Berkeley Aaron Kirtland Brown University Ruo Y u Tao
These authors contributed equally and are ordered alphabetically.
SelfCodeAlign: Self-Alignment for Code Generation Y uxiang Wei
SelfCodeAlign employs the same base model for inference throughout the data generation process. It first extracts diverse coding concepts from high-quality seed snippets to generate new tasks.