paper-with-me

홈 › Papers

Exploring the Role of the Bottleneck in Slot-Based Models Through Covariance Regularization

2023-06-05 · Andrew Stange, Robert Lo, Abishek Sridhar, Kousik Rajesh

In this project we attempt to make slot-based models with an image reconstruction objective competitive with those that use a feature reconstruction objective on real world datasets. We propose a loss-based approach to constricting the bottleneck of slot-based models, allowing larger-capacity encoder networks to be used with Slot Attention without producing degenerate stripe-shaped masks. We find that our proposed method offers an improvement over the baseline Slot Attention model but does not reach the performance of \dinosaur on the COCO2017 dataset. Throughout this project, we confirm the superiority of a feature reconstruction objective over an image reconstruction objective and explore the role of the architectural bottleneck in slot-based models.

📄 PDF Abstract BibTeX arXiv:2306.02577

Code (1)

robert1003/slot-attention-disentanglement 공식 구현 pytorch

Tasks

Image Reconstruction

Similar Papers 제목 키워드 기반

Exploring Named Entity Recognition As an Auxiliary Task for Slot Filling in Conversational Language Understanding

2018-10-01 · WS 2018 10 · Samuel Louvan, Bernardo Magnini

Slot filling is a crucial task in the Natural Language Understanding (NLU) component of a dialogue system. Most approaches for this task rely solely on the domain-specific datasets for training. We propose a joint model …

Domain AdaptationMulti-Task Learningnamed-entity-recognitionNamed Entity Recognition+6

Automatic Intent-Slot Induction for Dialogue Systems

2021-03-16 · Zengfeng Zeng, Dan Ma, Haiqin Yang, Zhen Gou 외

Automatically and accurately identifying user intents and filling the associated slots from their spoken language are critical to the success of dialogue systems. Traditional methods require manually defining the DOMAIN-…

Intent Detectionslot-fillingSlot Filling

Reusable Slotwise Mechanisms

2023-02-21 · NeurIPS 2023 11

Agents with the ability to comprehend and reason about the dynamics of objects would be expected to exhibit improved robustness and generalization in novel scenarios. However, achieving this capability necessitates not o…

Future predictionObjectOut-of-Distribution GeneralizationQuestion Answering+1

On Connecting Deep Trigonometric Networks with Deep Gaussian Processes: Covariance, Expressivity, and Neural Tangent Kernel

2022-03-14 · Chi-Ken Lu, Patrick Shafto

Deep Gaussian Process (DGP) as a model prior in Bayesian learning intuitively exploits the expressive power in function composition. DGPs also offer diverse modeling capabilities, but inference is challenging because mar…

Gaussian Processes

Chronicals: A High-Performance Framework for LLM Fine-Tuning with 3.51x Speedup over Unsloth

2026-01-06 · Arjun S. Nair arxiv

Large language model fine-tuning is bottlenecked by memory: a 7B parameter model requires 84GB--14GB for weights, 14GB for gradients, and 56GB for FP32 optimizer states--exceeding even A100-40GB capacity. We present Chro…