Related papers: MIRO: MultI-Reward cOnditioned pretraining improve…

Unpaired multimodal image-to-image translation is a task of translating a given image in a source domain into diverse images in the target domain, overcoming the limitation of one-to-one mapping. Existing multimodal translation models are…

The development of large language models leads to the formation of a pre-train-then-align paradigm, in which the model is typically pre-trained on a large text corpus and undergoes a tuning stage to align the model with human preference or…

Recent approaches to question generation have used modifications to a Seq2Seq architecture inspired by advances in machine translation. Models are trained using teacher forcing to optimise only the one-step-ahead prediction. However, at…

Image-based reinforcement learning (RL) faces significant challenges in generalization when the visual environment undergoes substantial changes between training and deployment. Under such circumstances, learned policies may not perform…

Multi-turn human-AI collaboration is fundamental to deploying interactive services such as adaptive tutoring, conversational recommendation, and professional consultation. However, optimizing these interactions via reinforcement learning is…

Despite the rapid progress of text-to-image (T2I) models, generating images that accurately reflect complex compositional prompts (covering attribute bindings, object relationships, counting) still remains challenging. To address this, we…

Large language models are classically trained in stages: pretraining on raw text followed by post-training for instruction following and reasoning. However, this separation creates a fundamental limitation: many desirable behaviors such as…

Prompt design plays a crucial role in text-to-video (T2V) generation, yet user-provided prompts are often short, unstructured, and misaligned with training data, limiting the generative potential of diffusion-based T2V models. We present…

Multi-image reasoning and grounding require understanding complex cross-image relationships at both object levels and image levels. Current Large Visual Language Models (LVLMs) face two critical challenges: the lack of cross-image reasoning…

Recommendation models are predominantly trained using implicit user feedback, since explicit feedback is often costly to obtain. However, implicit feedback, such as clicks, does not always reflect users' real preferences. For example, a…

Text-to-video (T2V) generation aims to synthesize videos with high visual quality and temporal consistency that are semantically aligned with input text. Reward-based post-training has emerged as a promising direction to improve the quality…

Multi-objective reinforcement learning (MORL) is a structured approach for optimizing tasks with multiple objectives. However, it often relies on pre-defined reward functions, which can be hard to design for balancing conflicting goals and…

Open-ended post-training benefits from rewards that make prompt-specific success conditions explicit, rather than relying only on post-hoc scalar scores. In instruction following, writing, and decision-support tasks, response quality…

Personalized diffusion models have shown remarkable success in Text-to-Image (T2I) generation by enabling the injection of user-defined concepts into diverse contexts. However, balancing concept fidelity with contextual alignment remains a…

Preference-based reward learning is a popular technique for teaching robots and autonomous systems how a human user wants them to perform a task. Previous works have shown that actively synthesizing preference queries to maximize…

Faithful text rendering remains a persistent weakness of large text-to-image generative models, as it requires both semantic instruction following and fine-grained glyph-level structure. Prior methods often improve this ability through…

Training robust and generalizable reward models for human visual preferences is essential for aligning text-to-image and text-to-video generative models with human intent. However, current reward models often fail to generalize, and…

We introduce a problem-level prioritization framework for RL post-training of large language models. Building on insights from prioritized replay in deep RL, as well as prior observations that rollouts with intermediate success rates tend…

Human feedback plays a critical role in learning and refining reward models for text-to-image generation, but the optimal form the feedback should take for learning an accurate reward function has not been conclusively established. This…

Pre-trained text-to-image generative models can produce diverse, semantically rich, and realistic images from natural language descriptions. Compared with language, images usually convey information with more details and less ambiguity. In…