Related papers: MARS: Harmonizing Multimodal Convergence via Adapt…

We study unconstrained smooth convex optimization under stochastic first- and zeroth-order oracles subject only to finite-moment bounds, naturally admitting persistent bias and heavy-tailed noise. In this hostile environment, integrating…

Despite remarkable progress, existing multimodal large language models (MLLMs) are still inferior in granular visual recognition. Contrary to previous works, we study this problem from the perspective of image resolution, and reveal that a…

Combinatorial Optimization underpins many real-world applications and yet, designing performant algorithms to solve these complex, typically NP-hard, problems remains a significant research challenge. Reinforcement Learning (RL) provides a…

Multi-Objective Reinforcement Learning (MORL) presents significant challenges and opportunities for optimizing multiple objectives in Large Language Models (LLMs). We introduce a MORL taxonomy and examine the advantages and limitations of…

Low-rank and sparse composite approximation is a natural idea to compress Large Language Models (LLMs). However, such an idea faces two primary challenges that adversely affect the performance of existing methods. The first challenge…

Large Multimodal Models (LMMs) excel at comprehending human instructions and demonstrate remarkable results across a broad spectrum of tasks. Reinforcement Learning from Human Feedback (RLHF) and AI Feedback (RLAIF) further refine LLMs by…

Instruction Tuning has the potential to stimulate or enhance specific capabilities of large language models (LLMs). However, achieving the right balance of data is crucial to prevent catastrophic forgetting and interference between tasks.…

Recent advances in multimodal large language models (MLLMs) have substantially expanded the capabilities of multimodal retrieval, enabling systems to align and retrieve information across visual and textual modalities. Yet, existing…

Recent studies emphasize that manually ensuring a consistent response style and maintaining high data quality in training sets can significantly improve the performance of fine-tuned Large Language Models (LLMs) while reducing the number of…

Learning-to-Rank (LTR) is a supervised machine learning approach that constructs models specifically designed to order a set of items or documents based on their relevance or importance to a given query or context. Despite significant…

Recent advances in pre-trained language models (PLMs) have demonstrated their capabilities in capturing universal knowledge, making them promising for radar signal processing applications. Nevertheless, directly fine-tuning PLMs on radar…

Many recently proposed methods for Neural Architecture Search (NAS) can be formulated as bilevel optimization. For efficient implementation, its solution requires approximations of second-order methods. In this paper, we demonstrate that…

Differentiable neural architecture search (DARTS) is a popular method for neural architecture search (NAS), which performs cell-search and utilizes continuous relaxation to improve the search efficiency via gradient-based optimization. The…

Deep reinforcement learning has achieved impressive success in control tasks. However, its policies, represented as opaque neural networks, are often difficult for humans to understand, verify, and debug, which undermines trust and hinders…

Large Language Models (LLMs) are highly resource-intensive to fine-tune due to their enormous size. While low-rank adaptation is a prominent parameter-efficient fine-tuning approach, it suffers from sensitivity to hyperparameter choices,…

Cascading multiple pre-trained models is an effective way to compose an end-to-end system. However, fine-tuning the full cascaded model is parameter and memory inefficient and our observations reveal that only applying adapter modules on…

Although the advancements of pre-trained Large Language Models have significantly accelerated recent progress in NLP, their ever-increasing size poses significant challenges for conventional fine-tuning, especially in memory-intensive…

The effectiveness of multi-stage text retrieval has been solidly demonstrated since before the era of pre-trained language models. However, most existing studies utilize models that predate recent advances in large language models (LLMs).…

Robust deployment of large multimodal models (LMMs) in real-world scenarios requires access to external knowledge sources, given the complexity and dynamic nature of real-world information. Existing approaches such as retrieval-augmented…

With the rapid development of natural language processing technology, large-scale language models (LLM) have achieved remarkable results in a variety of tasks. However, how to effectively train these huge models and improve their…