Related papers: PopAlign: Population-Level Alignment for Fair Text…

The increasing ubiquity of text-to-image (T2I) models as tools for visual content generation raises concerns about their ability to accurately represent diverse cultural contexts -- where missed cues can stereotype communities and undermine…

Text-to-image (T2I) diffusion models generate high-quality images but often fail to capture the spatial relations specified in text prompts. This limitation can be traced to two factors: lack of fine-grained spatial supervision in training…

Text-to-image (T2I) diffusion models, when fine-tuned on a few personal images, can generate visuals with a high degree of consistency. However, such fine-tuned models are not robust; they often fail to compose with concepts of pretrained…

Text-to-image (T2I) diffusion models have made remarkable strides in generating and editing high-fidelity images from text. Yet, these models remain fundamentally generic, failing to adapt to the nuanced aesthetic preferences of individual…

Recent advances in text-to-video (T2V) generative models have shown impressive capabilities. However, these models are still inadequate in aligning synthesized videos with human preferences (e.g., accurately reflecting text descriptions),…

Alignment of large language models (LLMs) via SFT and RLHF/DPO typically ignores the global geometry of the representation space, relying instead on local token likelihoods or scalar scores. We view generation as tracing a semantic…

Text-to-Image (T2I) models have recently achieved remarkable success in generating images from textual descriptions. However, challenges still persist in accurately rendering complex scenes where actions and interactions form the primary…

Text-to-image generation has evolved beyond single monolithic models to complex multi-component pipelines. These combine fine-tuned generators, adapters, upscaling blocks and even editing steps, leading to significant improvements in image…

Large foundation models pretrained on raw web-scale data are not readily deployable without additional step of extensive alignment to human preferences. Such alignment is typically done by collecting large amounts of pairwise comparisons…

Vision-Language Models (VLMs) have demonstrated remarkable progress in single-image understanding, yet effective reasoning across multiple images remains challenging. We identify a critical capability gap in existing multi-image alignment…

Recent text-to-image generative models can generate high-fidelity images from text inputs, but the quality of these generated images cannot be accurately evaluated by existing evaluation metrics. To address this issue, we introduce Human…

Large language models (LLMs) have exhibited impressive reasoning abilities on a wide range of complex tasks. However, enhancing these capabilities through post-training remains resource intensive, particularly in terms of data and…

Direct Preference Optimization (DPO) and its variants have become the de facto standards for aligning large language models (LLMs) with human preferences or specific goals. However, DPO requires high-quality preference data and suffers from…

Large language models (LLMs) are typically aligned with population-level preferences, despite substantial variation across individual users. We introduce POPI, a user-level personalization framework that separates the problem into two…

This paper argues that generating output tokens is more effective than using pooled representations for prediction tasks because token-level generation retains more mutual information. Since LLMs are trained on massive text corpora using…

Text-to-image (T2I) models are increasingly popular, producing a large share of AI-generated images online. To compare model quality, voting-based leaderboards have become the standard, relying on anonymized model outputs for fairness. In…

Aligning text-to-image (T2I) diffusion models with Direct Preference Optimization (DPO) has shown notable improvements in generation quality. However, applying DPO to T2I faces two challenges: the sensitivity of DPO to preference pairs and…

Large Language Models (LLMs) aligned using Reinforcement Learning from Human Feedback (RLHF) have shown remarkable generation abilities in numerous tasks. However, collecting high-quality human preferences creates costly bottlenecks in…

Reinforcement Learning from Human Feedback (RLHF) has become central to aligning large language models with human values, typically by first learning a reward model from preference data which is then used to update the model with…

Recently, large-scale text-to-image (T2I) models have shown impressive performance in generating high-fidelity images, but with limited controllability, e.g., precisely specifying the content in a specific region with a free-form text…