Related papers: STAR: Mitigating Cascading Errors in Spatial Reaso…
Modeling ultra-long user behavior sequences is pivotal for capturing evolving and lifelong interests in modern recommendation systems. However, deploying such models in real-time industrial environments faces a strict "Latency Wall",…
General-purpose large language models (LLMs), despite their broad capabilities, often struggle with specialized domain knowledge. This gap hinders their deployment as reliable research agents in demanding fields such as astronomy. Building…
We propose a variant of the Rapidly Exploring Random Tree Star (RRT$^{\star}$) algorithm to synthesize trajectories satisfying a given spatio-temporal specification expressed in a fragment of Signal Temporal Logic (STL) for linear systems.…
End-to-end spoken language understanding (SLU) predicts intent directly from audio using a single model. It promises to improve the performance of assistant systems by leveraging acoustic information lost in the intermediate textual…
Learning control policies for complex, long-horizon tasks is a central challenge in robotics and autonomous systems. Signal Temporal Logic (STL) offers a powerful and expressive language for specifying such tasks, but its non-Markovian…
A pointing accuracy better than 1"(3sigma) star tracker plays a significant role for the advanced scientific missions. This thesis makes a series of studies on the typical error sources associated with the positioning and calibration…
Self-evolving trainin--where models iteratively learn from their own outputs--has emerged as a key approach for complex reasoning tasks, addressing the scarcity of high-quality chain-of-thought data. However, its effectiveness in multimodal…
While Multimodal Large Language Models (MLLMs) excel in semantic tasks, they frequently lack the "spatial sense" essential for sophisticated geometric reasoning. Current models typically suffer from exorbitant modality-alignment costs and…
Diffusion Language Models (DLMs) enable parallel decoding via iterative denoising, where remasking strategies play a critical role in balancing inference speed and output quality. Existing methods predominantly rely on static confidence…
The STAR architecture was designed to test the value of the full Selective Tuning model of visual attention for complex real-world visuospatial tasks and behaviors. However, knowledge of how humans solve such tasks in 3D as active observers…
We investigate star-galaxy classification for astronomical surveys in the context of four methods enabling the interpretation of black-box machine learning systems. The first is outputting and exploring the decision boundaries as given by…
Clinical 12-lead ECG classification remains difficult because of diverse recording conditions, overlapping pathologies, and pronounced label imbalance hinder generalization, while unconstrained augmentations risk distorting diagnostically…
Deep neural networks, especially transformer-based architectures, have achieved remarkable success in semantic segmentation for environmental perception. However, existing models process video frames independently, thus failing to leverage…
We present rStar-Math to demonstrate that small language models (SLMs) can rival or even surpass the math reasoning capability of OpenAI o1, without distillation from superior models. rStar-Math achieves this by exercising "deep thinking"…
While large vision-language models (VLMs) show promise for object goal navigation, current methods still struggle with low success rates and inefficient localization of unseen objects--failures primarily attributed to weak temporal-spatial…
Large language models (LLMs) deployed in real-world agentic applications must be capable of replanning and adapting when mid-task disruptions invalidate their prior decisions. Existing dynamic benchmarks primarily measure whether LLMs can…
We introduce STAR (Stream Transduction with Anchor Representations), a novel Transformer-based model designed for efficient sequence-to-sequence transduction over streams. STAR dynamically segments input streams to create compressed anchor…
With the current surge in spatial reasoning explorations, researchers have made significant progress in understanding indoor scenes, but still struggle with diverse applications such as robotics and autonomous driving. This paper aims to…
Tabular reasoning involves interpreting natural language queries about tabular data, which presents a unique challenge of combining language understanding with structured data analysis. Existing methods employ either textual reasoning,…
Multimodal large language models (MLLMs) have shown promising reasoning abilities, yet evaluating their performance in specialized domains remains challenging. STEM reasoning is a particularly valuable testbed because it provides highly…