Related papers: Right Looks, Wrong Reasons: Compositional Fidelity…
Large Language Models, despite their power, have a fundamental architectural vulnerability stemming from their causal transformer design -- order sensitivity. This architectural constraint may distorts classification outcomes when prompt…
Continual learning -- the ability to acquire knowledge incrementally without forgetting previous skills -- is fundamental to natural intelligence. While the human brain excels at this, artificial neural networks struggle with "catastrophic…
Systematic generalization refers to the capacity to understand and generate novel combinations from known components. Despite recent progress by large language models (LLMs) across various domains, these models often fail to extend their…
Recent advancements in text-to-image models, particularly diffusion models, have shown significant promise. However, compositional text-to-image models frequently encounter difficulties in generating high-quality images that accurately…
Recent breakthroughs in diffusion models, multimodal pretraining, and efficient finetuning have led to an explosion of text-to-image generative models. Given human evaluation is expensive and difficult to scale, automated methods are…
Large text-to-image models have achieved astonishing performance in synthesizing diverse and high-quality images guided by texts. With detail-oriented conditioning control, even finer-grained spatial control can be achieved. However, some…
The burgeoning field of generative artificial intelligence has fundamentally reshaped our approach to content creation, with Large Vision-Language Models (LVLMs) standing at its forefront. While current LVLMs have demonstrated impressive…
Large language models are few-shot learners that can solve diverse tasks from a handful of demonstrations. This implicit understanding of tasks suggests that the attention mechanisms over word tokens may play a role in analogical reasoning.…
Text-to-image (T2I) models have achieved remarkable progress, yet they continue to struggle with complex prompts that require simultaneously handling multiple objects, relations, and attributes. Existing inference-time strategies, such as…
Understanding spatial relations is a crucial cognitive ability for both humans and AI. While current research has predominantly focused on the benchmarking of text-to-image (T2I) models, we propose a more comprehensive evaluation that…
In language reasoning, longer chains of thought consistently yield better performance, which naturally suggests that visual latent reasoning may likewise benefit from longer latent sequences. However, we discover a counterintuitive…
An image related question defines a specific visual task that is required in order to produce an appropriate answer. The answer may depend on a minor detail in the image and require complex reasoning and use of prior knowledge. When humans…
Text-to-image generative models are a new and powerful way to generate visual artwork. However, the open-ended nature of text as interaction is double-edged; while users can input anything and have access to an infinite range of…
Training models on uncurated Text Embeddings (TEs) derived from raw tabular data can lead to a severe failure mode known as model collapse, where predictions converge to a single class regardless of input. By comparing models trained with…
We argue that generative text-to-image models often struggle with prompt adherence due to the noisy and unstructured nature of large-scale datasets like LAION-5B. This forces users to rely heavily on prompt engineering to elicit desirable…
As large language models are deployed as autonomous agents with tool execution privileges, a critical assumption underpins their security architecture: that model errors are detectable at runtime. We present empirical evidence that this…
LLM-based formal proof assistants (e.g., in Lean) hold great promise for automating mathematical discovery. But beyond syntactic correctness, do these systems truly understand mathematical structure as humans do? We investigate this…
Recent advancements in diffusion models have significantly impacted the trajectory of generative machine learning research, with many adopting the strategy of fine-tuning pre-trained models using domain-specific text-to-image datasets.…
Text-to-video diffusion models generate realistic videos, but often fail on prompts requiring fine-grained compositional understanding, such as relations between entities, attributes, actions, and motion directions. We hypothesize that…
Natural language is characterized by compositionality: the meaning of a complex expression is constructed from the meanings of its constituent parts. To facilitate the evaluation of the compositional abilities of language processing…