Related papers: TaylorGAN: Neighbor-Augmented Policy Update for Sa…

Reranking is fundamental to information retrieval and retrieval-augmented generation, with recent Large Language Models (LLMs) significantly advancing reranking quality. Most current works rely on large-scale LLMs (>7B parameters),…

Traditional RLHF optimizes language models with coarse, scalar rewards that mask the fine-grained reasons behind success or failure, leading to slow and opaque learning. Recent work augments RL with textual critiques through prompting or…

Retrieval-augmented generation (RAG) grounds large language models with external evidence, but under a limited context budget, the key challenge is deciding which retrieved passages should be injected. We show that retrieval relevance…

The sequential nature of modern LLMs makes them expensive and slow, and speculative sampling has proven to be an effective solution to this problem. Methods like EAGLE perform autoregression at the feature level, reusing top-layer features…

Large Language Models (LLMs) have achieved impressive results in Machine Translation (MT). However, careful evaluations by human reveal that the translations produced by LLMs still contain multiple errors. Importantly, feeding back such…

Handling imbalanced target distributions in regression poses a persistent challenge, as the underrepresentation of relevant target values can significantly hinder model performance. Existing data-level solutions often adapt…

We show that pre-trained Generative Adversarial Networks (GANs), e.g., StyleGAN, can be used as a latent bank to improve the restoration quality of large-factor image super-resolution (SR). While most existing SR approaches attempt to…

Large-scale generative models have shown impressive image-generation capabilities, propelled by massive data. However, this often inadvertently leads to the generation of harmful or inappropriate content and raises copyright concerns.…

This paper proposes a series of new approaches to improve Generative Adversarial Network (GAN) for conditional image synthesis and we name the proposed model as ArtGAN. One of the key innovation of ArtGAN is that, the gradient of the loss…

Training GANs under limited data often leads to discriminator overfitting and memorization issues, causing divergent training. Existing approaches mitigate the overfitting by employing data augmentations, model regularization, or attention…

Uncertainty estimation (UE) of generative large language models (LLMs) is crucial for evaluating the reliability of generated sequences. A significant subset of UE methods utilize token probabilities to assess uncertainty, aggregating…

The computational cost of training multimodal large language models (MLLMs) grows rapidly with the number of processed tokens. Existing efficiency methods mainly target inference via token reduction or merging, offering limited benefits…

In recent research advancements within the community, large language models (LLMs) have sparked great interest in creating autonomous agents. However, current prompt-based agents often heavily rely on large-scale LLMs. Meanwhile, although…

Retrieval-Augmented Generation (RAG) improves the factual accuracy of large language model (LLM) outputs by grounding generation in external knowledge. Recent agentic RAG systems extend this paradigm with critical agents to evaluate model…

This paper addresses the problem of super-resolution: constructing a highly resolved (HR) image from a low resolved (LR) one. Recent unsupervised approaches search the latent space of a StyleGAN pre-trained on HR images, for the image that…

Automated code review comment generation (RCG) aims to assist developers by automatically producing natural language feedback for code changes. Existing approaches are primarily either generation-based, using pretrained language models, or…

Recent months have seen the emergence of a powerful new trend in which large language models (LLMs) are augmented to become autonomous language agents capable of performing objective oriented multi-step tasks on their own, rather than…

Standard knowledge distillation for autoregressive models often suffers from distribution mismatch. While on-policy methods mitigate this by leveraging student-generated outputs, they rely on computationally expensive Reinforcement Learning…

Current pre-training works in natural language generation pay little attention to the problem of exposure bias on downstream tasks. To address this issue, we propose an enhanced multi-flow sequence to sequence pre-training and fine-tuning…

The emergence of Large Language Models (LLMs) has significantly advanced natural language processing, but these models often generate factually incorrect information, known as "hallucination". Initial retrieval-augmented generation (RAG)…