arXiv subjects

Jacob Anderson

Publications and source records attributed to Jacob Anderson.

8 recordsLinked to original sources

arXiv2026

Spatio-Temporal Grounding of Large Language Models from Perception Streams

Embodied-AI agents must reason about how objects move and interact in 3-D space over time, yet existing smaller frontier Large Language Models (LLMs) still mis-handle fine-grained spatial relations, metric distances, and temporal orderings. We introduce the general framework Formally Explainable Spatio-Temporal Scenes (FESTS) that injects verifiable spatio-temporal supervision into an LLM by compiling natural-language queries into Spatial Regular Expression (SpRE) -- a language combining regular expression syntax with S4u spatial logic and extended here with universal and existential quantification. The pipeline matches each SpRE against any structured video log and exports aligned (query, frames, match, explanation) tuples, enabling unlimited training data without manual labels. Training a 3-billion-parameter model on 27k such tuples boosts frame-level F1 from 48.5% to 87.5%, matching GPT-4.1 on complex spatio-temporal reasoning while remaining two orders of magnitude smaller, and, hence, enabling spatio-temporal intelligence for Video LLM.

cs.RO↗

arXiv2024

Querying Perception Streams with Spatial Regular Expressions

Perception in fields like robotics, manufacturing, and data analysis generates large volumes of temporal and spatial data to effectively capture their environments. However, sorting through this data for specific scenarios is a meticulous and error-prone process, often dependent on the application, and lacks generality and reproducibility. In this work, we introduce SpREs as a novel querying language for pattern matching over perception streams containing spatial and temporal data derived from multi-modal dynamic environments. To highlight the capabilities of SpREs, we developed the STREM tool as both an offline and online pattern matching framework for perception data. We demonstrate the offline capabilities of STREM through a case study on a publicly available AV dataset (Woven Planet Perception) and its online capabilities through a case study integrating STREM in ROS with the CARLA simulator. We also conduct performance benchmark experiments on various SpRE queries. Using our matching framework, we are able to find over 20,000 matches within 296 ms making STREM applicable in runtime monitoring applications.

cs.RO↗

arXiv2022

Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks

How well can NLP models generalize to a variety of unseen tasks when provided with task instructions? To address this question, we first introduce Super-NaturalInstructions, a benchmark of 1,616 diverse NLP tasks and their expert-written instructions. Our collection covers 76 distinct task types, including but not limited to classification, extraction, infilling, sequence tagging, text rewriting, and text composition. This large and diverse collection of tasks enables rigorous benchmarking of cross-task generalization under instructions -- training models to follow instructions on a subset of tasks and evaluating them on the remaining unseen ones. Furthermore, we build Tk-Instruct, a transformer model trained to follow a variety of in-context instructions (plain language task definitions or k-shot examples). Our experiments show that Tk-Instruct outperforms existing instruction-following models such as InstructGPT by over 9% on our benchmark despite being an order of magnitude smaller. We further analyze generalization as a function of various scaling parameters, such as the number of observed tasks, the number of instances per task, and model sizes. We hope our dataset and model facilitate future progress towards more general-purpose NLP models.

cs.CL↗

arXiv2021

PSY-TaLiRo: A Python Toolbox for Search-Based Test Generation for Cyber-Physical Systems

In this paper, we present the Python package PSY-TaLiRo which is a toolbox for temporal logic robustness guided falsification of Cyber-Physical Systems (CPS). PSY-TaLiRo is a completely modular toolbox supporting multiple temporal logic offline monitors as well as optimization engines for test case generation. Among the benefits of PSY-TaLiRo is that it supports search-based test generation for many different types of systems under test. All PSY-TaLiRo modules can be fully modified by the users to support new optimization and robustness computation engines as well as any System under Test (SUT).

cs.SE↗

arXiv2019

Fully Convolutional Networks for Text Classification

In this work I propose a new way of using fully convolutional networks for classification while allowing for input of any size. I additionally propose two modifications on the idea of attention and the benefits and detriments of using the modifications. Finally, I show suboptimal results on the ITAmoji 2018 tweet to emoji task and provide a discussion about why that might be the case as well as a proposed fix to further improve results.

cs.LG↗

arXiv2013

Benefits to the U.S. from Physicists Working at Accelerators Overseas

We illustrate benefits to the U.S. economy and technological infrastructure of U.S. participation in accelerators overseas. We discuss contributions to experimental hardware and analysis and to accelerator technology and components, and benefits stemming from the involvement of U.S. students and postdoctoral fellows in global scientific collaborations. Contributed to the proceedings of the Snowmass 2013 Community Summer Study.

physics.soc-ph↗

arXiv2013

Excited quark production at a 100 TeV VLHC

I look for a dijet resonance produced by an excited quark q* in a simulated sample corresponding to 3 ab^{-1} of pp collisions at $\sqrt{s} = 100$ TeV. Using a cut and count analysis approach I demonstrate the potential to explore q* masses up to 50 TeV, corresponding to a length scale of around 4 am.

hep-ex↗

arXiv2013

Snowmass Energy Frontier Simulations

This document describes the simulation framework used in the Snowmass Energy Frontier studies for future Hadron Colliders. An overview of event generation with {\sc Madgraph}5 along with parton shower and hadronization with {\sc Pythia}6 is followed by a detailed description of pile-up and detector simulation with {\sc Delphes}3. Details of event generation are included in a companion paper cited within this paper. The input parametrization is chosen to reflect the best object performance expected from the future ATLAS and CMS experiments; this is referred to as the "Combined Snowmass Detector". We perform simulations of $pp$ interactions at center-of-mass energies $\sqrt{s}=$ 14, 33, and 100 TeV with 0, 50, and 140 additional $pp$ pile-up interactions. The object performance with multi-TeV $pp$ collisions are studied for the first time using large pile-up interactions.

hep-ex↗