arXiv:2605. 07724v2 Announce Type: replace-cross Abstract: Recursive retraining of generative models poses a critical representation challenge: when synthetic outputs are curated based on a fixed reward signal, the model tends to collapse onto a narrow set of outputs that over-optimize that objective.
arXiv:2607. 02291v1 Announce Type: new Abstract: Conventional reinforcement learning strategies for visual generation typically employ sample-wise reward functions, yet this practice frequently results in reward hacking that degrades image diversity and introduces visual anomalies.
arXiv:2606. 03962v1 Announce Type: cross Abstract: Classical reinforcement learning (RL) typically seeks a deterministic policy that maximizes the expected sum of a scalar reward.
arXiv:2606. 00291v1 Announce Type: cross Abstract: In RLHF, each training example contains a prompt $x$ and two candidate responses $y,y'$, and annotators provide pairwise preferences between these responses.
arXiv:2607. 00691v1 Announce Type: new Abstract: Black-box optimization is a fundamental science and engineering tool that makes it possible to optimize objectives without gradient information.
Classical reinforcement learning (RL) typically seeks a deterministic policy that maximizes the expected sum of a scalar reward. Yet, modern applications such as language model fine-tuning or scientific discovery demand diversity.
arXiv:2601. 12401v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has emerged as a powerful paradigm for fine-tuning large-scale generative models, such as diffusion and flow models, to align with complex human preferences and user-specified tasks.
arXiv:2409. 11535v3 Announce Type: replace Abstract: Many decision-support systems recommend actions by optimizing measurable objectives, even when a human decision-maker retains final authority and considers additional criteria that are difficult to specify in advance.
arXiv:2608. 01556v1 Announce Type: new Abstract: Large language models are increasingly aligned to human preferences via reward modeling, but user preference data are sensitive and often cannot be centralized.
arXiv:2505. 09655v5 Announce Type: replace-cross Abstract: Post-training LLMs with Reinforcement Learning, specifically Group Relative Policy Optimization (GRPO), has emerged as a paradigm for enhancing mathematical reasoning.
arXiv:2506. 13702v4 Announce Type: replace-cross Abstract: Single-trajectory preference optimization methods learn from datasets of ((prompt, response, reward)) tuples, offering a practical alternative to pairwise preference learning by directly leveraging scalar feedback.
arXiv:2604. 18239v4 Announce Type: replace-cross Abstract: Preference optimization is widely used to align large language models (LLMs) with human preferences.
arXiv:2602. 02572v2 Announce Type: replace-cross Abstract: Existing alignment methods directly use the reward model learned from user preference data to optimize an LLM policy, subject to KL regularization with respect to the base policy.