Related papers: EMO: Earth Mover Distance Optimization for Auto-Re…
Model usage is the central challenge of model-based reinforcement learning. Although dynamics model based on deep neural networks provide good generalization for single step prediction, such ability is over exploited when it is used to…
Large Language Models (LLMs) have been found to memorize and recite some of the textual sequences from their training set verbatim, raising broad concerns about privacy and copyright issues when using LLMs. This Textual Sequence…
Research on large language models (LLMs) has shown remarkable performance in domains such as mathematics, programming, and literary creation. However, most studies have focused on semantic memory-based question answering, neglecting LLMs'…
Existing Vision-Language models (VLMs) estimate either long-term trajectory waypoints or a set of control actions as a reactive solution for closed-loop planning based on their rich scene comprehension. However, these estimations are coarse…
Aligning Large Language Models (LLMs) with human preferences is crucial, but standard methods like Reinforcement Learning from Human Feedback (RLHF) are often complex and unstable. In this work, we propose a new, simpler approach that…
The Extreme Learning Machine (ELM) is a growing statistical technique widely applied to regression problems. In essence, ELMs are single-layer neural networks where the hidden layer weights are randomly sampled from a specific distribution,…
Empathetic response generation is a desirable aspect of conversational agents, crucial for facilitating engaging and emotionally intelligent multi-turn conversations between humans and machines. Leveraging large language models for this…
Reinforcement Learning (RL) has proven highly effective for autoregressive language models, but adapting these methods to diffusion large language models (dLLMs) presents fundamental challenges. The core difficulty lies in likelihood…
Scaling neural network training increasingly depends on synchronous data-parallelism, yet full-precision gradient all-reduce imposes a severe communication bottleneck. We propose Decoupled Momentum Optimization (DeMo), a drop-in replacement…
Despite the remarkable advances in language modeling, current mainstream decoding methods still struggle to generate texts that align with human texts across different aspects. In particular, sampling-based methods produce less-repetitive…
We propose a method to optimize language model pre-training data mixtures through efficient approximation of the cross-entropy loss corresponding to each candidate mixture via a Mixture of Data Experts (MDE). We use this approximation as a…
Recently, substantial research efforts in Deep Metric Learning (DML) focused on designing complex pairwise-distance losses, which require convoluted schemes to ease optimization, such as sample mining or pair weighting. The standard…
Non-autoregressive machine translation models significantly speed up decoding by allowing for parallel prediction of the entire target sequence. However, modeling word order is more challenging due to the lack of autoregressive factors in…
Language models (LMs) are trained on billions of tokens in an attempt to recover the true language distribution. Still, vanilla random sampling from LMs yields low quality generations. Decoding algorithms attempt to restrict the LM…
Large Language Models (LLMs) have so far impressed the world, with unprecedented capabilities that emerge in models at large scales. On the vision side, transformer models (i.e., ViT) are following the same trend, achieving the best…
Number prediction stands as a fundamental capability of large language models (LLMs) in mathematical problem-solving and code generation. The widely adopted maximum likelihood estimation (MLE) for LLM training is not tailored to number…
While state-of-the-art models that rely upon massively multilingual pretrained encoders achieve sample efficiency in downstream applications, they still require abundant amounts of unlabelled text. Nevertheless, most of the world's…
Characteristics of an evolutionary multi-objective optimization (EMO) algorithm can be explained using its best solution set. For example, the best solution set for SMS-EMOA is the same as the optimal distribution of solutions for…
Large language models (LLMs) have become increasingly central to AI applications worldwide, necessitating robust multilingual safety alignment to ensure secure deployment across diverse linguistic contexts. Existing preference learning…
Multi-Agent Proximal Policy Optimization (MAPPO) is a variant of the Proximal Policy Optimization (PPO) algorithm, specifically tailored for multi-agent reinforcement learning (MARL). MAPPO optimizes cooperative multi-agent settings by…