Related papers: Reward Incremental Learning in Text-to-Image Gener…

Multi-task learns multiple tasks, while sharing knowledge and computation among them. However, it suffers from catastrophic forgetting of previous knowledge when learned incrementally without access to the old data. Most existing object…

We propose a novel Inverse Reinforcement Learning (IRL) method that mitigates the rigidity of fixed reward structures and the limited flexibility of implicit reward regularization. Building on the Maximum Entropy IRL framework, our approach…

Diffusion Language Models (DLMs) have recently achieved strong results in text generation. However, their multi-step sampling leads to slow inference, limiting practical use. To address this, we extend Inverse Distillation, a technique…

Incremental learning attempts to develop a classifier which learns continuously from a stream of data segregated into different classes. Deep learning approaches suffer from catastrophic forgetting when learning classes incrementally, while…

Continual learning refers to a dynamical framework in which a model receives a stream of non-stationary data over time and must adapt to new data while preserving previously acquired knowledge. Unluckily, neural networks fail to meet these…

Class-Incremental Learning (CIL) struggles with catastrophic forgetting when learning new knowledge, and Data-Free CIL (DFCIL) is even more challenging without access to the training data of previously learned classes. Though recent DFCIL…

The gap in representations between image and video makes Image-to-Video Re-identification (I2V Re-ID) challenging, and recent works formulate this problem as a knowledge distillation (KD) process. In this paper, we propose a mutual…

Optimizing a text-to-image diffusion model with a given reward function is an important but underexplored research area. In this study, we propose Deep Reward Tuning (DRTune), an algorithm that directly supervises the final output image of…

Recursive Self-Improvement (RSI) enables intelligence systems to autonomously refine their capabilities. This paper explores the application of RSI in text-to-image diffusion models, addressing the challenge of training collapse caused by…

Reward Feedback Learning (ReFL) has recently shown great potential in aligning model outputs with human preferences across various generative tasks. In this work, we introduce a ReFL framework, named DiffusionReward, to the Blind Face…

Diffusion models have emerged as the leading approach for text-to-image generation. However, their iterative sampling process, which gradually morphs random noise into coherent images, introduces significant latency that limits their…

Enabling Large Language Models (LLMs) to continuously improve from environmental interactions is a central challenge in post-training. While on-policy self-distillation offers a promising paradigm, existing methods predominantly treat…

Masked auto-regressive diffusion models (MAR) benefit from the expressive modeling ability of diffusion models and the flexibility of masked auto-regressive ordering. However, vanilla MAR suffers from slow inference due to its hierarchical…

Deep learning architectures have shown remarkable results in scene understanding problems, however they exhibit a critical drop of performances when they are required to learn incrementally new tasks without forgetting old ones. This…

Interactive Text-to-image retrieval (I-TIR) is an important enabler for a wide range of state-of-the-art services in domains such as e-commerce and education. However, current methods rely on finetuned Multimodal Large Language Models…

Diffusion models, such as Stable Diffusion, have shown incredible performance on text-to-image generation. Since text-to-image generation often requires models to generate visual concepts with fine-grained details and attributes specified…

In-Context Reinforcement Learning (ICRL) represents a promising paradigm for developing generalist agents that learn at inference time through trial-and-error interactions, analogous to how large language models adapt contextually, but with…

The push to compress and impart the proficiency of Large Language Models (LLMs) into more deployable and efficient Small Language Models (SLMs) has benefited from improvements in knowledge distillation (KD) techniques. These techniques…

Pre-trained text-to-image diffusion models are increasingly applied to real-world image super-resolution (Real-ISR) task. Given the iterative refinement nature of diffusion models, most existing approaches are computationally expensive.…

In class-incremental learning (CIL) scenarios, the phenomenon of catastrophic forgetting caused by the classifier's bias towards the current task has long posed a significant challenge. It is mainly caused by the characteristic of…