Copertina

MARS: Margin and Semantic-Aware Data Augmentation for Reward Modeling

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Bhattacharjee, Payel, Simeone, Osvaldo, Tandon, Ravi
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Artificial Intelligence Information Theory
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Conformal Sparsification for Bandwidth-Efficient Edge-Cloud Speculative Decoding
di: Bhattacharjee, Payel, et al.
Pubblicazione: (2025)

CURATE: Scaling-up Differentially Private Causal Graph Discovery
di: Bhattacharjee, Payel, et al.
Pubblicazione: (2024)

PROPS: Progressively Private Self-alignment of Large Language Models
di: Teku, Noel, et al.
Pubblicazione: (2025)

Uncertainty Quantification and Data Efficiency in AI: An Information-Theoretic Perspective
di: Simeone, Osvaldo, et al.
Pubblicazione: (2025)

Localized Adaptive Risk Control
di: Zecchin, Matteo, et al.
Pubblicazione: (2024)

Intrinsic Fairness-Accuracy Tradeoffs under Equalized Odds
di: Zhong, Meiyu, et al.
Pubblicazione: (2024)

In-Context Learning for MIMO Equalization Using Transformer-Based Sequence Models
di: Zecchin, Matteo, et al.
Pubblicazione: (2023)

Trustworthy Actionable Perturbations
di: Friedbaum, Jesse, et al.
Pubblicazione: (2024)

Adaptive Learn-then-Test: Statistically Valid and Efficient Hyperparameter Selection
di: Zecchin, Matteo, et al.
Pubblicazione: (2024)

Generalization and Informativeness of Conformal Prediction
di: Zecchin, Matteo, et al.
Pubblicazione: (2024)

Generalization and Informativeness of Weighted Conformal Risk Control Under Covariate Shift
di: Zecchin, Matteo, et al.
Pubblicazione: (2025)

STAMP: Selective Task-Aware Mechanism for Text Privacy
di: Tian, Fengwei, et al.
Pubblicazione: (2026)

Context-Aware Online Conformal Anomaly Detection with Prediction-Powered Data Acquisition
di: Farzaneh, Amirmohammad, et al.
Pubblicazione: (2025)

Post-Selection Distributional Model Evaluation
di: Farzaneh, Amirmohammad, et al.
Pubblicazione: (2026)

Improving Epidemic Analyses with Privacy-Preserving Integration of Sensitive Data
di: Guan, Zihan, et al.
Pubblicazione: (2025)

Beyond Fixed False Discovery Rates: Post-Hoc Conformal Selection with E-Variables
di: Zhu, Meiyi, et al.
Pubblicazione: (2026)

Multi-Objective Hyperparameter Selection via Hypothesis Testing on Reliability Graphs
di: Farzaneh, Amirmohammad, et al.
Pubblicazione: (2025)

Statistically Valid Information Bottleneck via Multiple Hypothesis Testing
di: Farzaneh, Amirmohammad, et al.
Pubblicazione: (2024)

Ensuring Reliability via Hyperparameter Selection: Review and Advances
di: Farzaneh, Amirmohammad, et al.
Pubblicazione: (2025)

Hierarchical Over-the-Air Federated Learning with Awareness of Interference and Data Heterogeneity
di: Azimi-Abarghouyi, Seyed Mohammad, et al.
Pubblicazione: (2024)

SPLITZ: Certifiable Robustness via Split Lipschitz Randomized Smoothing
di: Zhong, Meiyu, et al.
Pubblicazione: (2024)

Modern Neuromorphic AI: From Intra-Token to Inter-Token Processing
di: Simeone, Osvaldo
Pubblicazione: (2026)

Data Augmentation in Graph Neural Networks: The Role of Generated Synthetic Graphs
di: Bas, Sumeyye, et al.
Pubblicazione: (2024)

Semantic Text Transmission via Prediction with Small Language Models: Cost-Similarity Trade-off
di: Madhabhavi, Bhavani A, et al.
Pubblicazione: (2024)

IBB Traffic Graph Data: Benchmarking and Road Traffic Prediction Model
di: Olug, Eren, et al.
Pubblicazione: (2024)

Knowledge Graph-Based Explainable and Generalized Zero-Shot Semantic Communications
di: Zhang, Zhaoyu, et al.
Pubblicazione: (2025)

Synthetic Counterfactual Labels for Efficient Conformal Counterfactual Inference
di: Farzaneh, Amirmohammad, et al.
Pubblicazione: (2025)

Quantile Learn-Then-Test: Quantile-Based Risk Control for Hyperparameter Optimization
di: Farzaneh, Amirmohammad, et al.
Pubblicazione: (2024)

Conditional Denoising Diffusion Probabilistic Models for Data Reconstruction Enhancement in Wireless Communications
di: Letafati, Mehdi, et al.
Pubblicazione: (2023)

Learning Unknown Intervention Targets in Structural Causal Models from Heterogeneous Data
di: Yang, Yuqin, et al.
Pubblicazione: (2023)

Diffusion Model-Based Data Synthesis Aided Federated Semi-Supervised Learning
di: Wang, Zhongwei, et al.
Pubblicazione: (2025)

Semantic Rate Distortion and Posterior Design: Compute Constraints, Multimodality, and Strategic Inference
di: Akyol, Emrah
Pubblicazione: (2026)

Prompt Fairness: Sub-group Disparities in LLMs
di: Zhong, Meiyu, et al.
Pubblicazione: (2025)

Speeding up Speculative Decoding via Sequential Approximate Verification
di: Zhong, Meiyu, et al.
Pubblicazione: (2025)

Environment-Aware Transfer Reinforcement Learning for Sustainable Beam Selection
di: Salami, Dariush, et al.
Pubblicazione: (2025)

Inference Privacy: Properties and Mechanisms
di: Tian, Fengwei, et al.
Pubblicazione: (2024)

Two Birds with One Stone: Multi-Task Semantic Communications Systems over Relay Channel
di: Cao, Yujie, et al.
Pubblicazione: (2024)

Intent-Aware DRL-Based NOMA Uplink Dynamic Scheduler for IIoT
di: Mostafa, Salwa, et al.
Pubblicazione: (2024)

GeoIB: Geometry-Aware Information Bottleneck via Statistical-Manifold Compression
di: Wang, Weiqi, et al.
Pubblicazione: (2026)

Fine-Grained Uncertainty Quantification via Collisions
di: Friedbaum, Jesse, et al.
Pubblicazione: (2024)