Related papers: Toward Causal-Visual Programming: Enhancing Agenti…
Large language models excel at generating fluent text but frequently struggle with structured reasoning involving temporal constraints, causal relationships, and probabilistic reasoning. To address these limitations, we propose Temporal…
As large language models engage in extended reasoning tasks, they accumulate significant state -- architectural mappings, trade-off decisions, codebase conventions -- within the context window. This understanding is lost when sessions reach…
Agentic visual analytics (VA) represents an emerging class of systems in which large language model (LLM)-driven agents autonomously plan, execute, evaluate, and iterate across the full visual analytics pipeline. By shifting users from…
Causal Representation Learning (CRL) aims to uncover the data-generating process and identify the underlying causal variables and relations, whose evaluation remains inherently challenging due to the requirement of known ground-truth causal…
Causal induction, i.e., identifying unobservable mechanisms that lead to the observable relations among variables, has played a pivotal role in modern scientific discovery, especially in scenarios with only sparse and limited data. Humans,…
Generalization in Visual Question Answering (VQA) requires models to answer questions about images with contexts beyond the training distribution. Existing attempts primarily refine unimodal aspects, overlooking enhancements in multimodal…
Autonomous driving requires generating safe and reliable trajectories from complex multimodal inputs. Traditional modular pipelines separate perception, prediction, and planning, while recent end-to-end (E2E) systems learn them jointly.…
Modern processor architectures, in addition to having still more cores, also require still more consideration to memory-layout in order to run at full capacity. The usefulness of most languages is deprecating as their abstractions,…
Personalized AI assistants often struggle to incorporate complex personal data and causal knowledge, leading to generic advice that lacks explanatory power. We propose REMI, a Causal Schema Memory architecture for a multimodal lifestyle…
Disentangled representation learning aims to learn low-dimensional representations where each dimension corresponds to an underlying generative factor. While the Variational Auto-Encoder (VAE) is widely used for this purpose, most existing…
In the fundamental statistics course, students are taught to remember the well-known saying: "Correlation is not Causation". Till now, statistics (i.e., correlation) have developed various successful frameworks, such as Transformer and…
Visual reasoning -- the ability to interpret the visual world -- is crucial for embodied agents that operate within three-dimensional scenes. Progress in AI has led to vision and language models capable of answering questions from images.…
Causal reasoning is viewed as crucial for achieving human-level machine intelligence. Recent advances in language models have expanded the horizons of artificial intelligence across various domains, sparking inquiries into their potential…
Large Language Models (LLMs) have demonstrated strong performance across a wide range of tasks, yet they still struggle with complex mathematical reasoning, a challenge fundamentally rooted in deep structural dependencies. To address this…
Artificial Intelligence has achieved remarkable advancements in recent years, yet much of its progress relies on identifying increasingly complex correlations. Enabling causality awareness in AI has the potential to enhance its performance…
On-the-fly reasoning often requires adaptation to novel problems under limited data and distribution shift. This work introduces CausalARC: an experimental testbed for AI reasoning in low-data and out-of-distribution regimes, modeled after…
Recent advances in Large Language Models (LLMs) and Vision Language Models (VLMs) have shown significant progress in mathematical reasoning, yet they still face a critical bottleneck with problems requiring visual assistance, such as…
LLMs suffer from critical reasoning issues such as unfaithfulness, bias, and inconsistency, since they lack robust causal underpinnings and may rely on superficial correlations rather than genuine understanding. Successive LRMs have emerged…
Leveraging large-scale Text-to-Image (TTI) models have become a common technique for generating exemplar or training dataset in the fields of image synthesis, video editing, 3D reconstruction. However, semantic structural visual…
Visual representation learning has been a cornerstone in computer vision, involving typical forms such as visual embeddings, structural symbols, and text-based representations. Despite the success of CLIP-type visual embeddings, they often…