Publication
Export 47 results:
Filters: Author is Katz, Boris [Clear All Filters]
Incorporating Rich Social Interactions Into MDPs. (2022).
CBMM-Memo-133.pdf (1.68 MB)

Trajectory Prediction with Linguistic Representations. (2022).
CBMM-Memo-132.pdf (1.15 MB)

Compositional Networks Enable Systematic Generalization for Grounded Language Understanding. (2021).
CBMM-Memo-129.pdf (1.2 MB)

Compositional RL Agents That Follow Language Commands in Temporal Logic. Frontiers in Robotics and AI 8, (2021).
frobt-08-689550.pdf (1.57 MB)

Compositional RL Agents That Follow Language Commands in Temporal Logic. (2021).
CBMM-Memo-127.pdf (2.12 MB)

Measuring Social Biases in Grounded Vision and Language Embeddings. NAACL (Annual Conference of the North American Chapter of the Association for Computational Linguistics) (2021).
Measuring Social Biases in Grounded Vision and Language Embeddings. (2021).
CBMM-Memo-126.pdf (1.32 MB)

Multi-resolution modeling of a discrete stochastic process identifies causes of cancer. International Conference on Learning Representations (2021). at <https://openreview.net/forum?id=KtH8W3S_RE>
Neural Regression, Representational Similarity, Model Zoology Neural Taskonomy at Scale in Rodent Visual Cortex. (2021).
CBMM-Memo-131.pdf (9.37 MB)

PHASE: PHysically-grounded Abstract Social Events for Machine Social Perception. (2021).
CBMM-Memo-123.pdf (3.08 MB)

Social Interactions as Recursive MDPs. (2021).
CBMM-Memo-130.pdf (1.52 MB)

Spoken ObjectNet: A Bias-Controlled Spoken Caption Dataset. Interspeech 2021 (2021). doi:10.21437/Interspeech.2021
Spoken ObjectNet: A Bias-Controlled Spoken Caption Dataset. (2021).
CBMM-Memo-128.pdf (2.91 MB)

Deep compositional robotic planners that follow natural language commands. (2020).
CBMM-Memo-124.pdf (1.03 MB)

Deep compositional robotic planners that follow natural language commands . International Conference on Robotics and Automation (ICRA) (2020).
Encoding formulas as deep networks: Reinforcement learning for zero-shot execution of LTL formulas. (2020).
CBMM-Memo-125.pdf (2.12 MB)

Encoding formulas as deep networks: Reinforcement learning for zero-shot execution of LTL formulas. 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (2020). doi:10.1109/IROS45743.2020.9341325
Learning a natural-language to LTL executable semantic parser for grounded robotics. (2020). doi:https://doi.org/10.48550/arXiv.2008.03277
CBMM-Memo-122.pdf (1.03 MB)

Learning a Natural-language to LTL Executable Semantic Parser for Grounded Robotics. (Proceedings of Conference on Robot Learning (CoRL-2020), 2020). at <https://corlconf.github.io/paper_385/>
PHASE: PHysically-grounded Abstract Social Eventsfor Machine Social Perception. Shared Visual Representations in Human and Machine Intelligence (SVRHM) workshop at NeurIPS 2020 (2020). at <https://openreview.net/forum?id=_bokm801zhx>
phase_physically_grounded_abstract_social_events_for_machine_social_perception.pdf (2.49 MB)

Deep Compositional Robotic Planners that Follow Natural Language Commands. Workshop on Visually Grounded Interaction and Language (ViGIL) at the Thirty-third Annual Conference on Neural Information Processing Systems (NeurIPS), (2019). at <https://vigilworkshop.github.io/>
Deep video-to-video transformations for accessibility with an application to photosensitivity. Pattern Recognition Letters (2019). doi:10.1016/j.patrec.2019.01.019
How Does the Brain Represents Language and Answers Questions? Using an AI System to Understand the Underlying Neurobiological Mechanisms. Frontiers in Computational Neuroscience 13, (2019).