相关论文: Relations, Negations, and Numbers: Looking for Log…

State-of-the-art T2I models are capable of generating high-resolution images given textual prompts. However, they still struggle with accurately depicting compositional scenes that specify multiple objects, attributes, and spatial…

Text-guided diffusion models (TDMs) are widely applied but can fail unexpectedly. Common failures include: (i) natural-looking text prompts generating images with the wrong content, or (ii) different random samples of the latent variables…

The growing number of generative AI-based dialogue systems has made their evaluation a crucial challenge. This paper presents our contribution to this important problem through the Dialogue System Technology Challenge (DSTC-12, Track 1),…

Large reasoning models with reasoning capabilities achieve state-of-the-art performance on complex tasks, but their robustness under multi-turn adversarial pressure remains underexplored. We evaluate nine frontier reasoning models under…

We investigate bias trends in text-to-image generative models over time, focusing on the increasing availability of models through open platforms like Hugging Face. While these platforms democratize AI, they also facilitate the spread of…

Traditional static analysis methods struggle to detect semantic design flaws, such as violations of the SOLID principles, which require a strong understanding of object-oriented design patterns and principles. Existing solutions typically…

Effectiveness and interpretability are two essential properties for trustworthy AI systems. Most recent studies in visual reasoning are dedicated to improving the accuracy of predicted answers, and less attention is paid to explaining the…

The quality of the prompts provided to text-to-image diffusion models determines how faithful the generated content is to the user's intent, often requiring `prompt engineering'. To harness visual concepts from target images without prompt…

Large Language Models (LLMs) have achieved remarkable success in tasks requiring complex reasoning, such as code generation, mathematical problem solving, and algorithmic synthesis -- especially when aided by reasoning tokens and…

Diffusion models have recently achieved remarkable advancements in terms of image quality and fidelity to textual prompts. Concurrently, the safety of such generative models has become an area of growing concern. This work introduces a…

Text-To-Image (TTI) Diffusion Models such as DALL-E and Stable Diffusion are capable of generating images from text prompts. However, they have been shown to perpetuate gender stereotypes. These models process data internally in multiple…

Current vision-language detection and grounding models predominantly focus on prompts with positive semantics and often struggle to accurately interpret and ground complex expressions containing negative semantics. A key reason for this…

Text-to-image (T2I) generation has achieved remarkable progress, yet existing methods often lack the ability to dynamically reason and refine during generation--a hallmark of human creativity. Current reasoning-augmented paradigms most rely…

Deep generative models have shown impressive results in text-to-image synthesis. However, current text-to-image models often generate images that are inadequately aligned with text prompts. We propose a fine-tuning method for aligning such…

Extracting abstract causal structures and applying them to novel situations is a hallmark of human intelligence. While Large Language Models (LLMs) and Vision Language Models (VLMs) have shown strong performance on a wide range of reasoning…

Text-to-image generative AI systems exhibit significant limitations when engaging with under-represented domains, including non-Western art forms, often perpetuating biases and misrepresentations. We present a focused case study on the…

Large language models (LLMs) are increasingly embedded in AI-based tutoring systems. Can they faithfully model novice reasoning and metacognitive judgments? Existing evaluations emphasize problem-solving accuracy, overlooking the fragmented…

The field of text-conditioned image generation has made unparalleled progress with the recent advent of latent diffusion models. While remarkable, as the complexity of given text input increases, the state-of-the-art diffusion models may…

Due to their architecture and vast pre-training data, large language models (LLMs) demonstrate strong text classification performance. However, LLM output - here, the category assigned to a text - depends heavily on the wording of the…

Does prompting a large language model (LLM) like GPT-3 with explanations improve in-context learning? We study this question on two NLP tasks that involve reasoning over text, namely question answering and natural language inference. We…