This paper characterizes proper binary classification from positive-only samples, revealing a rich landscape that differs from standard PAC learning.

The paper systematically evaluates concept-based explainability in MLLMs, finding that forcing models to generate formal explanations degrades predictive accuracy, suggesting that explaining is genuin…

This paper unifies the fragmented field of Tree-of-Thoughts (ToT) reasoning by mapping LLM-based search processes onto a formal taxonomy derived from classical heuristic search theory.

This paper introduces the Data-Model Compatibility (DMC) metric to quantify how suitable a dataset is for reasoning distillation, showing that optimizing data selection using DMC significantly improve…

CB-SLICE is a novel concept-based method for discovering model error slices that leverages Concept Bottleneck Models (CBMs) to provide fine-grained, faithful explanations directly linked to the root c…

The paper introduces PRAXIS, a novel algorithm that efficiently approximates the computation of 'Rashomon sets' for decision trees, significantly reducing memory and runtime complexity.

The paper introduces CodeGolf Bench, a novel multi-language benchmark using code golf to measure LLMs' ability to generate highly concise and efficient code, showing that reasoning models significantl…

This paper proposes a model for few-shot class-incremental audio classification, which consists of a pseudo-incrementally trained embedding learner and a continually updated stochastic classifier.

The paper introduces SPAWN, a training-free method that allows users to inject specified visual concepts into existing autoregressive world models, enabling controllable scene composition beyond the i…

This paper explores using Knowledge Components (KCs) as interpretable signals to understand assignment difficulty and student struggle in intro programming courses.

This paper explores the effectiveness of diverse LLM-generated explanations versus generic explanations in computer science education, finding that diverse explanations led to higher open-ended respon…

EvoGens is an evolution-inspired framework that treats scientific idea generation as an evolutionary search, significantly boosting the novelty and diversity of generated research ideas compared to ex…

This paper synthesizes over 150 scattered studies and reports to provide the first comprehensive primer on post-training reasoning data, organizing the field around data objects, utility, construction…

This paper compares different approaches for embedding source code in machine learning models for learning analytics in programming education, specifically for the visual block-based programming langu…

The authors conducted a user study to assess the effectiveness of their interactive visual query tracer and builder tools for Nemo, a Datalog reasoner, in helping students learn Datalog.

This paper introduces a new way to represent finite posets as subwords of finite words in categories, and characterizes the monic categories that admit this representation.

The paper proposes Neighbor-Aware Localized Concept Erasure (NLCE), a training-free framework that effectively removes specific concepts from text-to-image models while minimizing the unintended degra…