No article text was recorded for this version.
reward hacking (reward hacking in generative models)
Version 2 of 2158 papers180 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Follow-Your-Preference: Towards Preference-Aligned Image Inpainting
- Blog: Training Diffusion Models with Reinforcement Learning
- Blog: TASR: Timestep-Aware Diffusion Model for Image Super-Resolution
- Blog: Pareto-Guided Optimal Transport for Multi-Reward Alignment
- Blog: Learning an Image Editing Model without Image Editing Pairs
- Blog: Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning
- Blog: Reward Guided Latent Consistency Distillation
- Blog: Automated patent extraction powers generative modeling in focused chemical spaces
- Blog: Deep Reward Supervisions for Tuning Text-to-Image Diffusion Models
- Blog: ROCM: RLHF on consistency models
- Blog: Reward Guided Latent Consistency Distillation
- Blog: TAGRPO: Boosting GRPO on Image-to-Video Generation with Direct Trajectory Alignment
- Blog: Carve3D: Improving Multi-view Reconstruction Consistency for Diffusion Models with RL Finetuning
- Blog: Object Hallucination in Image Captioning
- Blog: ConsistentRFT: Reducing Visual Hallucinations in Flow-based Reinforcement Fine-Tuning
- Blog: AdaGen: Learning Adaptive Policy for Image Synthesis
- Blog: Large-Scale Reinforcement Learning for Diffusion Models
- Blog: TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching and Clap-Ranked Preference Optimization
- Blog: Unified Control for Inference-Time Guidance of Denoising Diffusion Models
- Blog: Improving Video Generation with Human Feedback
- Blog: Learning from Few Samples: A Novel Approach for High-Quality Malcode Generation
- Blog: Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models
- Blog: Diffusion Tree Sampling: Scalable inference‑time alignment of diffusion models
- Blog: Aligning Text-to-Image Models using Human Feedback
- Blog: Generating Creative Chess Puzzles
- Blog: Training-Free Reward-Guided Image Editing via Trajectory Optimal Control
- Blog: DenseDPO: Fine-Grained Temporal Preference Optimization for Video Diffusion Models
- Blog: Objective-Reinforced Generative Adversarial Networks (ORGAN) for Sequence Generation Models
- Blog: Bridging Model-Based Optimization and Generative Modeling via Conservative Fine-Tuning of Diffusion Models
- Blog: Guidance Matters: Rethinking the Evaluation Pitfall for Text-to-Image Generation
- Blog: PIRF: Physics-Informed Reward Fine-Tuning for Diffusion Models
- Blog: Efficient symmetry-aware materials generation <i>via</i> hierarchical generative flow networks
- Blog: Fine-tuning of diffusion models via stochastic control: entropy regularization and beyond
- Blog: Improving Video Generation with Human Feedback
- Blog: The Image as Its Own Reward: Reinforcement Learning with Adversarial Reward for Image Generation
- Blog: CMI-RewardBench: Evaluating Music Reward Models with Compositional Multimodal Instruction
- Blog: Diffusion Fine-Tuning via Reparameterized Policy Gradient of the Soft Q-Function
- Blog: InstructVideo: Instructing Video Diffusion Models with Human Feedback
- Blog: EvolGAN: Evolutionary Generative Adversarial Networks
- Blog: IQA-Adapter: Exploring Knowledge Transfer from Image Quality Assessment to Diffusion-based Generative Models
- Blog: Composition and Alignment of Diffusion Models using Constrained Learning
- Blog: AdaNAT: Exploring Adaptive Policy for Token-Based Image Generation
- Blog: Scalable Ranked Preference Optimization for Text-to-Image Generation
- Blog: Alignment of Diffusion Models: Fundamentals, Challenges, and Future
- Blog: Generating Creative Chess Puzzles
- Blog: Beyond VLM-Based Rewards: Diffusion-Native Latent Reward Modeling
- Blog: Enhancing Diffusion-based Unrestricted Adversarial Attacks via Adversary Preferences Alignment
- Blog: Deep Noise Suppression with Non-Intrusive PESQNet Supervision Enabling the Use of Real Training Data
- Blog: T2V-Turbo-v2: Enhancing Video Model Post-Training through Data, Reward, and Conditional Guidance Design
- Blog: You Only Look One Step: Accelerating Backpropagation in Diffusion Sampling with Gradient Shortcuts
- Blog: Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps
- Blog: Tilt Matching for Scalable Sampling and Fine-Tuning
- Blog: Towards Knowledge‑and‑Data‑Driven Organic Reaction Prediction: RAG‑Enhanced and Reasoning‑Powered Hybrid System with LLMs
- Blog: T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT
- Blog: Exploring Question-Specific Rewards for Generating Deep Questions
- Blog: Scaling Inference Time Compute for Diffusion Models
- Blog: DiffusionReward: Enhancing Blind Face Restoration through Reward Feedback Learning
- Blog: Follow-Your-Preference: Towards Preference-Aligned Image Inpainting
- Blog: Directly Fine-Tuning Diffusion Models on Differentiable Rewards
- Blog: Inference-time scaling of diffusion models through classical search
Showing 60 of 158 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_reward_hacking_reward_hacking_in_generat_5f57000b,
title = {reward hacking (reward hacking in generative models)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/reward-hacking-reward-hacking-in-generative-models/rdr_5f57000b55e8486c8dbc505ea7649706},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-21},
}This exact version (version 2, frozen text):
@misc{lacuna_reward_hacking_reward_hacking_in_generat_5f57000b_v2,
title = {reward hacking (reward hacking in generative models)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/reward-hacking-reward-hacking-in-generative-models/rdr_5f57000b55e8486c8dbc505ea7649706/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-21},
}