Imagen de Portada

MIRA: Towards Mitigating Reward Hacking in Inference-Time Alignment of T2I Diffusion Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhai, Kevin, Singh, Utsav, Thatipelli, Anirudh, Chakraborty, Souradip, Sahu, Anit Kumar, Huang, Furong, Bedi, Amrit Singh, Shah, Mubarak
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

LIAR: Leveraging Inference Time Alignment (Best-of-N) to Jailbreak LLMs in Seconds
por: Beetham, James, et al.
Publicado: (2024)

RL with Learnable Textual Feedback: A Bilevel Approach
por: Singh, Utsav, et al.
Publicado: (2026)

Towards Realistic Mechanisms That Incentivize Federated Participation and Contribution
por: Bornstein, Marco, et al.
Publicado: (2023)

Direct Preference Optimization for Primitive-Enabled Hierarchical RL: A Bilevel Approach
por: Singh, Utsav, et al.
Publicado: (2024)

Test-Time Scaling in Diffusion LLMs via Hidden Semi-Autoregressive Experts
por: Lee, Jihoon, et al.
Publicado: (2025)

Uncertainty-Aware Answer Selection for Improved Reasoning in Multi-LLM Systems
por: Agrawal, Aakriti, et al.
Publicado: (2025)

PARL: A Unified Framework for Policy Alignment in Reinforcement Learning from Human Feedback
por: Chakraborty, Souradip, et al.
Publicado: (2023)

REBEL: Reward Regularization-Based Approach for Robotic Reinforcement Learning from Human Feedback
por: Chakraborty, Souradip, et al.
Publicado: (2023)

Safety Recovery in Reasoning Models Is Only a Few Early Steering Steps Away
por: Ghosal, Soumya Suvra, et al.
Publicado: (2026)

Transfer Q Star: Principled Decoding for LLM Alignment
por: Chakraborty, Souradip, et al.
Publicado: (2024)

Why Pass@k Optimization Can Degrade Pass@1: Prompt Interference in LLM Post-training
por: Barakat, Anas, et al.
Publicado: (2026)

Bounded Rationality for LLMs: Satisficing Alignment at Inference-Time
por: Chehade, Mohamad, et al.
Publicado: (2025)

MaxMin-RLHF: Alignment with Diverse Human Preferences
por: Chakraborty, Souradip, et al.
Publicado: (2024)

Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment
por: Ghosal, Soumya Suvra, et al.
Publicado: (2024)

DIPPER: Direct Preference Optimization to Accelerate Primitive-Enabled Hierarchical Reinforcement Learning
por: Singh, Utsav, et al.
Publicado: (2024)

BalancedDPO: Adaptive Multi-Metric Alignment
por: Tamboli, Dipesh, et al.
Publicado: (2025)

SafeR-CLIP: Mitigating NSFW Content in Vision-Language Models While Preserving Pre-Trained Knowledge
por: Yousaf, Adeel, et al.
Publicado: (2025)

Leveraging Pre-Trained Visual Models for AI-Generated Video Detection
por: Veeramachaneni, Keerthi, et al.
Publicado: (2025)

Align-Pro: A Principled Approach to Prompt Optimization for LLM Alignment
por: Trivedi, Prashant, et al.
Publicado: (2025)

On the Global Optimality of Policy Gradient Methods in General Utility Reinforcement Learning
por: Barakat, Anas, et al.
Publicado: (2024)

Beyond Text: Utilizing Vocal Cues to Improve Decision Making in LLMs for Robot Navigation Tasks
por: Sun, Xingpeng, et al.
Publicado: (2024)

Code Comprehension then Auditing for Unsupervised LLM Evaluation
por: Patel, Bhrij, et al.
Publicado: (2024)

SAIL: Self-Improving Efficient Online Alignment of Large Language Models
por: Ding, Mucong, et al.
Publicado: (2024)

On The Sample Complexity Bounds In Bilevel Reinforcement Learning
por: Gaur, Mudit, et al.
Publicado: (2025)

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

FACT or Fiction: Can Truthful Mechanisms Eliminate Federated Free Riding?
por: Bornstein, Marco, et al.
Publicado: (2024)

VARP: Reinforcement Learning from Vision-Language Model Feedback with Agent Regularized Preferences
por: Singh, Anukriti, et al.
Publicado: (2025)

Does Thinking More always Help? Mirage of Test-Time Scaling in Reasoning Models
por: Ghosal, Soumya Suvra, et al.
Publicado: (2025)

AI Cap-and-Trade: Efficiency Incentives for Accessibility and Sustainability
por: Bornstein, Marco, et al.
Publicado: (2026)

A lift for input-convex neural network training
por: Siahkoohi, Ali, et al.
Publicado: (2026)

Hypernetwork-based approach for grid-independent functional data clustering
por: Thatipelli, Anirudh, et al.
Publicado: (2026)

PIPER: Primitive-Informed Preference-based Hierarchical Reinforcement Learning via Hindsight Relabeling
por: Singh, Utsav, et al.
Publicado: (2024)

Temper and Tilt Lead to SLOP: Reward Hacking Mitigation with Inference-Time Alignment
por: Wang, Ye, et al.
Publicado: (2026)

Dystruct: Dynamically Structured Diffusion Language Model Decoding via Bayesian Inference
por: Sun, Bian, et al.
Publicado: (2026)

On the Role of Feedback in Test-Time Scaling of Agentic AI Workflows
por: Chakraborty, Souradip, et al.
Publicado: (2025)

Achieving Zero Constraint Violation for Constrained Reinforcement Learning via Conservative Natural Policy Gradient Primal-Dual Algorithm
por: Bai, Qinbo, et al.
Publicado: (2022)

Auction-Based Regulation for Artificial Intelligence
por: Bornstein, Marco, et al.
Publicado: (2024)

Directional Alignment Mitigates Reward Hacking in Reinforcement Learning for Language Models
por: Deng, Wenlong, et al.
Publicado: (2026)

Reward Shaping to Mitigate Reward Hacking in RLHF
por: Fu, Jiayi, et al.
Publicado: (2025)

On the Vulnerability of LLM/VLM-Controlled Robotics
por: Wu, Xiyang, et al.
Publicado: (2024)