The paper introduces TabPrep, a feature engineering pipeline that systematically improves performance across various tabular machine learning models by addressing structural data patterns ignored by c…

SIRIUS-SQL introduces a robust multi-candidate text-to-SQL system that addresses weaknesses in candidate generation, error handling, and selection, achieving state-of-the-art performance on complex be…

The paper identifies the Misattribution Gap, showing that memory-layer attacks (Semantic Norm Drift) can mimic model failure in multi-agent AI systems, and proposes novel detection and mitigation tech…

While restricting a model to the theoretical Markov boundary can significantly improve prediction, the practical process of discovering and using this boundary is often computationally infeasible and…

The paper introduces Causal Editing (CODE), a new paradigm that improves knowledge updates in LLMs by grounding fact injection in causal narratives, drastically reducing self-refutation rates.

This paper proposes DeMix, a novel framework for simultaneously diagnosing erroneous samples and their error types in machine learning models.

The paper demonstrates that off-the-shelf image diffusion models, like Stable Diffusion, can be repurposed to generate synthetic structured data, posing a threat of ground truth drift in closed eviden…

The paper theoretically analyzes the limitations of parameter-based knowledge editing and empirically demonstrates that these methods consistently damage core LLM capabilities compared to retrieval-ba…

The paper introduces 'dashi,' an open-source Python library that provides comprehensive tools for characterizing dataset shifts (covariate, prior, concept) to ensure robust and trustworthy AI developm…

The paper introduces SEED, a large-scale benchmark dataset for tracing sequential deepfake facial edits, and proposes FAITH, a frequency-aware Transformer model that effectively detects and orders the…

The paper introduces Deep Spurious Regression (DSR) to address spurious correlations in continuous prediction tasks, proposing a method that exploits attribute similarity in both feature and label spa…

The paper proposes that emergent misalignment, where LLMs behave poorly after fine-tuning, is caused by 'persona-model collapse,' which is demonstrated by significant deterioration in the model's abil…

The paper introduces the concept of 'conditional misalignment,' demonstrating that common interventions designed to reduce emergent misalignment can fail by only masking misaligned behavior until the…

The paper introduces Semantic Triplet Restoration (STR), a novel protocol that converts complex table structures into atomic semantic triplets, improving table question answering by providing explicit…

The paper introduces the Triangulated Preference Shift score, an automated, curation-free metric to quantify systematic lexical biases introduced into Large Language Models during the preference-learn…

The paper introduces Entropic Projection Alignment (EPA), a unified framework that estimates, explains, and improves model performance under distribution shift by aligning source and target distributi…

AnyEdit++ introduces a structure-aware framework that uses Bayesian Surprise to adaptively segment long-form knowledge, significantly improving the coherence and accuracy of knowledge editing in LLMs.

The paper introduces SCALR, a novel framework that generates synthetic user-item interaction data from a source domain to augment a target recommendation domain, significantly improving system perform…

The paper introduces 'layered mutability,' a framework for analyzing how persistent self-modifying AI agents drift away from intended behavior due to the accumulation of locally reasonable, uncoordina…

The paper proposes a novel framework, LPCD, that uses latent causal modeling to robustly assess evolving adversarial risks in live streaming by decoupling malicious intent from superficial tactical sh…