Related papers: Beyond Experience Retrieval: Learning to Generate …

Large Language Models (LLMs) are known for their expensive and time-consuming training. Thus, oftentimes, LLMs are fine-tuned to address a specific task, given the pretrained weights of a pre-trained LLM considered a foundation model. In…

Large language models (LLMs) achieve strong performance on plain text tasks but underperform on structured data like tables and databases. Potential challenges arise from their underexposure during pre-training and rigid text-to-structure…

Recently, numerous algorithms have been developed to tackle the problem of vision-language navigation (VLN), i.e., entailing an agent to navigate 3D environments through following linguistic instructions. However, current VLN agents simply…

Designing optimal prompts for Large Language Models (LLMs) is a complicated and resource-intensive task, often requiring substantial human expertise and effort. Existing approaches typically separate the optimization of prompt instructions…

Large Language Models (LLMs) pose a new paradigm of modeling and computation for information tasks. Recommendation systems are a critical application domain poised to benefit significantly from the sequence modeling capabilities and world…

Function calling enables large language models (LLMs) to interact with external systems by leveraging tools and APIs. When faced with multi-step tool usage, LLMs still struggle with tool selection, parameter generation, and tool-chain…

Large Language Models (LLMs) can generate SQL queries from natural language questions but struggle with database-specific schemas and tacit domain knowledge. We introduce a framework for continual learning from human feedback in…

Large Language Models (LLMs) typically rely on Supervised Fine-Tuning (SFT) to specialize in downstream tasks, with the Cross Entropy (CE) loss being the de facto choice. However, CE maximizes the likelihood of observed data without…

Personalization, the ability to tailor a system to individual users, is an essential factor in user experience with natural language processing (NLP) systems. With the emergence of Large Language Models (LLMs), a key question is how to…

Large Language Models (LLMs) are constrained by their inability to process lengthy inputs, resulting in the loss of critical historical information. To address this limitation, in this paper, we propose the Self-Controlled Memory (SCM)…

When SE data is scarce, "active learners" use models learned from tiny samples of the data to find the next most informative example to label. In this way, effective models can be generated using very little data. For multi-objective…

The deployment of large language models (LLMs) is often constrained by their substantial computational and memory demands. While structured pruning presents a viable approach by eliminating entire network components, existing methods suffer…

Although many efforts have been made, it is still a challenge to balance the training budget, downstream performance, and the general capabilities of the LLMs in many applications. Training the whole model for downstream tasks is expensive,…

Large language models(LLMs) have shown its outperforming ability on various tasks and question answering. However, LLMs require substantial memory storage on low-resource devices. More critically, the computational speed on these devices is…

While many text-to-audio systems produce monophonic or fixed-stereo outputs, generating audio with user-defined spatial properties remains a challenge. Existing deep learning-based spatialization methods often rely on latent-space…

Large Language Model (LLM) agents have shown strong results on multi-turn tool-use tasks, yet they operate in isolation during training, failing to leverage experiences accumulated across episodes. Existing experience-augmented methods…

Pre-trained language models (PLMs) show impressive performance in various downstream NLP tasks. However, pre-training large language models demands substantial memory and training compute. Furthermore, due to the substantial resources…

Online Reinforcement Learning (RL) offers a promising paradigm for enhancing GUI agents through direct environment interaction. However, its effectiveness is severely hindered by inefficient credit assignment in long-horizon tasks and…

Language models (LMs) require robust episodic grounding-the capacity to learn from and apply past experiences-to excel at physical planning tasks. Current episodic grounding approaches struggle with scalability and integration, limiting…

Modern generative pre-trained language models excel at open-ended text generation, yet continue to underperform on structure-related tasks such as NER, relation extraction, and semantic role labeling, especially when compared to…