相关论文: Nonlinear VRFT with LASSO

Trinity-RFT is a general-purpose, unified and easy-to-use framework designed for reinforcement fine-tuning (RFT) of large language models. It is built with a modular and decoupled design, consisting of (1) an RFT-core that unifies and…

This paper investigates the role of explicit thinking process in rule-based reinforcement fine-tuning (RFT) for MLLMs. We first propose CLS-RL for MLLM image classification, using verifiable rewards for fine-tuning. Experiments show CLS-RL…

Continual post-training (CPT) is a popular and effective technique for adapting foundation models like multimodal large language models to specific and ever-evolving downstream tasks. While existing research has primarily concentrated on…

Offline reinforcement learning (RL) is a variant of RL where the policy is learned from a previously collected dataset of trajectories and rewards. In our work, we propose a practical approach to offline RL with large language models…

We propose in this contribution a method for l one regularization in prototype based relevance learning vector quantization (LVQ) for sparse relevance profiles. Sparse relevance profiles in hyperspectral data analysis fade down those…

Post-training methods, especially Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL), play an important role in improving large language models' (LLMs) complex reasoning abilities. However, the dominant two-stage pipeline (SFT…

This paper presents an approach to target tracking that is based on a variable-gain integrator and the Newton-Raphson method for finding zeros of a function. Its underscoring idea is the determination of the feedback law by measurements of…

Reinforcement Learning with Verifiable Rewards ( RLVR ) has emerged as a transformative paradigm for enhancing the reasoning capabilities of Large Language Models ( LLMs), yet its potential in 3D scene understanding remains under-explored.…

Vector Pseudo Relevance Feedback (VPRF) has shown promising results in improving BERT-based dense retrieval systems through iterative refinement of query representations. This paper investigates the generalizability of VPRF to Large…

Probabilistic Virtual Fixtures (VFs) enable the adaptive selection of the most suitable haptic feedback for each phase of a task, based on learned or perceived uncertainty. While keeping the human in the loop remains essential, for…

The Linear Parameter-Varying (LPV) framework has been introduced with the intention to provide stability and performance guarantees for analysis and controller synthesis for Nonlinear (NL) systems via convex methods. By extending results of…

High-dimensional predictive models, those with more measurements than observations, require regularization to be well defined, perform well empirically, and possess theoretical guarantees. The amount of regularization, often determined by…

Instruction tuning is a crucial supervised training phase in Large Language Models (LLMs), aiming to enhance the LLM's ability to generalize instruction execution and adapt to user preferences. With the increasing integration of multi-modal…

Designing a static state-feedback controller subject to structural constraint achieving asymptotic stability is a relevant problem with many applications, including network decentralized control, coordinated control, and sparse feedback…

Reinforcement fine-tuning with verifiable rewards (RLVR) has emerged as a powerful paradigm for equipping large vision-language models (LVLMs) with agentic capabilities such as tool use and multi-step reasoning. Despite striking empirical…

Enabling large language models with external tools has become a pivotal strategy for extending their functionality beyond text space. To enhance LLMs' tool-calling abilities, previous approaches primarily rely on supervised fine-tuning…

Multimodal RLHF usually happens after supervised finetuning (SFT) stage to continually improve vision-language models' (VLMs) comprehension. Conventional wisdom holds its superiority over continual SFT during this preference alignment…

The integration of LLMs into vulnerability detection (VD) has shifted the field toward more interpretable and context-aware analysis. While post-training techniques have shown promise in general coding tasks, their systematic application to…

Conversational Recommender Systems (CRSs) leverage natural language interactions for personalized recommendation, yet information-scarce dialogue histories and single-turn recommendation paradigms may severely hinder accurate modeling of…

Large Vision-Language Models (LVLMs) have recently shown great promise in advancing robotics by combining embodied reasoning with robot control. A common approach involves training on embodied reasoning tasks related to robot control using…