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…

The paper proposes Test-Time Collective Action (TTCA), a framework allowing groups of users to correct algorithmic biases in black-box systems by applying pooled, proxy-based perturbations at inferenc…

BiasEdit introduces a training-free framework that automatically detects and edits unknown social biases in web-sourced image datasets to construct a debiased dataset for fair visual classification.

COFT is a training-free decoding method that significantly reduces societal biases in large language model chain-of-thought reasoning by applying token-level fairness control at decode time.

The paper proposes ProRL, an effective Reinforcement Learning framework that rectifies gradient estimation deficiencies to optimize proactive recommendation paths, significantly outperforming existing…

The paper proposes a proactive client selection framework that optimizes the selection of client subsets to ensure high data utility and fairness before federated learning begins, leading to faster an…

The paper proposes a dual-regime architecture combining Bernoulli CUSUM and asymmetric scoring to significantly improve trust fraud detection in sparse rating networks, achieving superior performance…

This paper studies a dynamic assortment problem on a two-sided service platform with incomplete information and heterogeneous customers, and develops a data-driven algorithm to learn parameters and op…

This paper studies a dynamic assortment problem on a two-sided service platform with incomplete information and heterogeneous customers, and develops a data-driven algorithm to learn parameters and op…

This paper investigates how individual agent biases amplify system-wide unfairness in multi-agent systems, demonstrating that uniform exposure to bias can elevate overall bias beyond the sum of indivi…

The paper introduces 'reward bias substitution,' demonstrating that single-axis mitigations of reward model biases merely shift optimization pressure to correlated proxies, and proposes augmenting eva…

The paper introduces Nested Contextual Causal Bandits (NCCBs) to model multi-timescale sequential decisions and proposes a certified policy optimization method, NCTS, that provides quantifiable risk b…

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…

This paper addresses the challenge of achieving optimal fairness and accuracy simultaneously in multi-class classification by proposing novel in-processing and post-processing algorithms that converge…

This paper analyzes multi-model self-consuming training, showing that while human curation helps individual models, cross-model interactions can degrade long-term alignment by dampening or inverting t…

The paper introduces HF-KCU, an efficient and robust method for performing causal unlearning in federated learning by approximating influence reversal, achieving significant speedups while maintaining…

CHRONOS is a novel three-layer architecture designed to address coupled failures in temporal data marketplaces by integrating temporal decay, changepoint-aware pricing, and differential privacy for ro…

The paper introduces WebKnoGraph, an open-source framework for systematically evaluating internal linking strategies on websites by modeling the site as a graph and assessing trade-offs between author…