Image de couverture de livre

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

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Bhattacharjee, Payel, Simeone, Osvaldo, Tandon, Ravi
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Artificial Intelligence Information Theory
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Conformal Sparsification for Bandwidth-Efficient Edge-Cloud Speculative Decoding
par: Bhattacharjee, Payel, et autres
Publié: (2025)

CURATE: Scaling-up Differentially Private Causal Graph Discovery
par: Bhattacharjee, Payel, et autres
Publié: (2024)

PROPS: Progressively Private Self-alignment of Large Language Models
par: Teku, Noel, et autres
Publié: (2025)

Uncertainty Quantification and Data Efficiency in AI: An Information-Theoretic Perspective
par: Simeone, Osvaldo, et autres
Publié: (2025)

Localized Adaptive Risk Control
par: Zecchin, Matteo, et autres
Publié: (2024)

Intrinsic Fairness-Accuracy Tradeoffs under Equalized Odds
par: Zhong, Meiyu, et autres
Publié: (2024)

In-Context Learning for MIMO Equalization Using Transformer-Based Sequence Models
par: Zecchin, Matteo, et autres
Publié: (2023)

Trustworthy Actionable Perturbations
par: Friedbaum, Jesse, et autres
Publié: (2024)

Adaptive Learn-then-Test: Statistically Valid and Efficient Hyperparameter Selection
par: Zecchin, Matteo, et autres
Publié: (2024)

Generalization and Informativeness of Conformal Prediction
par: Zecchin, Matteo, et autres
Publié: (2024)

Generalization and Informativeness of Weighted Conformal Risk Control Under Covariate Shift
par: Zecchin, Matteo, et autres
Publié: (2025)

STAMP: Selective Task-Aware Mechanism for Text Privacy
par: Tian, Fengwei, et autres
Publié: (2026)

Context-Aware Online Conformal Anomaly Detection with Prediction-Powered Data Acquisition
par: Farzaneh, Amirmohammad, et autres
Publié: (2025)

Post-Selection Distributional Model Evaluation
par: Farzaneh, Amirmohammad, et autres
Publié: (2026)

Improving Epidemic Analyses with Privacy-Preserving Integration of Sensitive Data
par: Guan, Zihan, et autres
Publié: (2025)

Beyond Fixed False Discovery Rates: Post-Hoc Conformal Selection with E-Variables
par: Zhu, Meiyi, et autres
Publié: (2026)

Multi-Objective Hyperparameter Selection via Hypothesis Testing on Reliability Graphs
par: Farzaneh, Amirmohammad, et autres
Publié: (2025)

Statistically Valid Information Bottleneck via Multiple Hypothesis Testing
par: Farzaneh, Amirmohammad, et autres
Publié: (2024)

Ensuring Reliability via Hyperparameter Selection: Review and Advances
par: Farzaneh, Amirmohammad, et autres
Publié: (2025)

Hierarchical Over-the-Air Federated Learning with Awareness of Interference and Data Heterogeneity
par: Azimi-Abarghouyi, Seyed Mohammad, et autres
Publié: (2024)

SPLITZ: Certifiable Robustness via Split Lipschitz Randomized Smoothing
par: Zhong, Meiyu, et autres
Publié: (2024)

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

Data Augmentation in Graph Neural Networks: The Role of Generated Synthetic Graphs
par: Bas, Sumeyye, et autres
Publié: (2024)

Semantic Text Transmission via Prediction with Small Language Models: Cost-Similarity Trade-off
par: Madhabhavi, Bhavani A, et autres
Publié: (2024)

IBB Traffic Graph Data: Benchmarking and Road Traffic Prediction Model
par: Olug, Eren, et autres
Publié: (2024)

Knowledge Graph-Based Explainable and Generalized Zero-Shot Semantic Communications
par: Zhang, Zhaoyu, et autres
Publié: (2025)

Synthetic Counterfactual Labels for Efficient Conformal Counterfactual Inference
par: Farzaneh, Amirmohammad, et autres
Publié: (2025)

Quantile Learn-Then-Test: Quantile-Based Risk Control for Hyperparameter Optimization
par: Farzaneh, Amirmohammad, et autres
Publié: (2024)

Conditional Denoising Diffusion Probabilistic Models for Data Reconstruction Enhancement in Wireless Communications
par: Letafati, Mehdi, et autres
Publié: (2023)

Learning Unknown Intervention Targets in Structural Causal Models from Heterogeneous Data
par: Yang, Yuqin, et autres
Publié: (2023)

Diffusion Model-Based Data Synthesis Aided Federated Semi-Supervised Learning
par: Wang, Zhongwei, et autres
Publié: (2025)

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

Prompt Fairness: Sub-group Disparities in LLMs
par: Zhong, Meiyu, et autres
Publié: (2025)

Speeding up Speculative Decoding via Sequential Approximate Verification
par: Zhong, Meiyu, et autres
Publié: (2025)

Environment-Aware Transfer Reinforcement Learning for Sustainable Beam Selection
par: Salami, Dariush, et autres
Publié: (2025)

Inference Privacy: Properties and Mechanisms
par: Tian, Fengwei, et autres
Publié: (2024)

Two Birds with One Stone: Multi-Task Semantic Communications Systems over Relay Channel
par: Cao, Yujie, et autres
Publié: (2024)

Intent-Aware DRL-Based NOMA Uplink Dynamic Scheduler for IIoT
par: Mostafa, Salwa, et autres
Publié: (2024)

GeoIB: Geometry-Aware Information Bottleneck via Statistical-Manifold Compression
par: Wang, Weiqi, et autres
Publié: (2026)

Fine-Grained Uncertainty Quantification via Collisions
par: Friedbaum, Jesse, et autres
Publié: (2024)