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 TDPM, a time-aware diffusion model for generative recommendation, which significantly improves recommendation accuracy by explicitly modeling the non-stationary, time-evolving natur…

This paper analyzes Best-of-$N$ preference data, deriving explicit reward targets for independent-reference variants and establishing design principles for choosing $N$ and the base distribution to op…

ShaplEIG introduces a Bayesian experimental design framework to efficiently and adaptively estimate Shapley values by minimizing the number of required costly function evaluations.

This paper proposes a new framework called STRIDE for training data attribution in Large Language Models.

OmniOPD introduces a logit-free, chunk-level distillation framework that improves on standard On-Policy Distillation by using semantic similarity and peak-entropy scheduling, achieving state-of-the-ar…

DASH introduces a dual-branch distillation framework to effectively compress class-conditional diffusion models by independently supervising both score branches, significantly preserving guidance fide…

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 COPF, an online framework that ensures deployment-stable counterfactual fairness in link recommendation systems operating on evolving graphs by monitoring and controlling group di…

The paper introduces Entropy-Cut Metropolis-Hastings, an efficient sampling method that uses next-token entropy to identify and resample from critical decision points in a reasoning trace, significant…

The paper proposes S2L-PO, a framework that uses smaller, naturally diverse models as structured explorers to enhance the policy-level diversity and performance of larger language models during traini…

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 introduces NumLeak, a framework demonstrating that top-tier LLMs often exhibit high fidelity recall of specific public numeric benchmarks (like financial factors) due to memorization, which…

The paper introduces NumLeak, a framework demonstrating that top-tier LLMs often exhibit high fidelity recall of specific public numeric benchmarks, suggesting that their apparent skill may be due to…

PReMISE introduces a framework to audit and improve the quality of rubrics used to guide LLM judges, demonstrating that it can significantly increase judge accuracy and reduce the exploitability of re…

The paper introduces ARCA, a novel credit assignment method that measures token salience directly from the adapter's residual hidden state, addressing the degeneracy of standard intrinsic signals when…

The paper introduces a comprehensive framework, Realtime Risk Studio, that operationalizes qualitative risk models (Bowtie diagrams) into formal, probabilistic, and intervention-ready runtime models u…

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 introduces Canonical-Context On-Policy Distillation (CCOPD) to improve multi-turn language model performance by mitigating 'self-anchored drift,' ensuring consistent answers regardless of wh…

The paper introduces Chunk-Level Guided Generation, a training-free method that uses an off-the-shelf large language model (LLM) as a process scorer to guide small model generation, achieving performa…