Cold decoding: Energy-based constrained text generation with langevin dynamics
Many applications of text generation require incorporating different constraints to control the
semantics or style of generated text. These constraints can be hard (eg, ensuring certain …
semantics or style of generated text. These constraints can be hard (eg, ensuring certain …
Latent space energy-based model for fine-grained open set recognition
Fine-grained open-set recognition (FineOSR) aims to recognize images belonging to
classes with subtle appearance differences while rejecting images of unknown classes. A …
classes with subtle appearance differences while rejecting images of unknown classes. A …
Gedi: Generative and discriminative training for self-supervised learning
Self-supervised learning is a popular and powerful method for utilizing large amounts of
unlabeled data, for which a wide variety of training objectives have been proposed in the …
unlabeled data, for which a wide variety of training objectives have been proposed in the …
Learning symbolic representations through joint generative and discriminative training
We introduce GEDI, a Bayesian framework that combines existing self-supervised learning
objectives with likelihood-based generative models. This framework leverages the benefits …
objectives with likelihood-based generative models. This framework leverages the benefits …
Lazy Layers to Make Fine-Tuned Diffusion Models More Traceable
Foundational generative models should be traceable to protect their owners and facilitate
safety regulation. To achieve this, traditional approaches embed identifiers based on …
safety regulation. To achieve this, traditional approaches embed identifiers based on …
Maximum entropy exploration in contextual bandits with neural networks and energy based models
Contextual bandits can solve a huge range of real-world problems. However, current
popular algorithms to solve them either rely on linear models or unreliable uncertainty …
popular algorithms to solve them either rely on linear models or unreliable uncertainty …
A Bayesian Unification of Self-Supervised Clustering and Energy-Based Models
Self-supervised learning is a popular and powerful method for utilizing large amounts of
unlabeled data, for which a wide variety of training objectives have been proposed in the …
unlabeled data, for which a wide variety of training objectives have been proposed in the …
The Triad of Failure Modes and a Possible Way Out
E Sansone - arxiv preprint arxiv:2309.15420, 2023 - arxiv.org
We present a novel objective function for cluster-based self-supervised learning (SSL) that is
designed to circumvent the triad of failure modes, namely representation collapse, cluster …
designed to circumvent the triad of failure modes, namely representation collapse, cluster …
Triple-Hybrid Energy-based Model Makes Better Calibrated Natural Language Understanding Models
Though pre-trained language models achieve notable success in many applications, it's
usually controversial for over-confident predictions. Specifically, the in-distribution (ID) …
usually controversial for over-confident predictions. Specifically, the in-distribution (ID) …
[PDF][PDF] Unifying Self-Supervised Clustering and Energy-Based Models
Self-supervised learning excels at learning representations from large amounts of data. At
the same time, generative models offer the complementary property of learning information …
the same time, generative models offer the complementary property of learning information …