8 accepted papers
Reinforcement Learning (RL) with rubric-based rewards has recently shown remarkable progress in enhancing general reasoning capabilities of Large Language Models (LLMs), yet still suffers from ineffective exploration confined to current policy distribution. In fact, RL optimization can be viewed as …
In this work, we propose ***R**einforced **F**unctional **T**oken **T**uning* (RFTT), a novel reinforced fine-tuning framework that empowers Large Language Models (LLMs) with learn-to-reason capabilities. Unlike prior prompt-driven reasoning efforts, RFTT embeds a rich set of learnable functional to…
Reinforcement Learning (RL) has shown promise for aligning Large Language Models (LLMs) to follow instructions with various constraints. Despite the encouraging results, RL improvement inevitably relies on sampling successful, high-quality responses; however, the initial model often struggles to gen…
Recent advances of Reinforcement Learning (RL) have highlighted its potential in complex reasoning tasks, yet effective training often relies on external supervision, which limits the broader applicability. In this work, we propose a novel self-rewarding reinforcement learning framework to enhance L…
Landing on a vertically oscillating platform poses a significant challenge for multi-rotor unmanned aerial vehicle (UAVs) due to the time-varying ground effect (GE). In this work, we formulated a data-driven GE dynamic model that accurately describes the complex interactions between UAVs and both st…
Structural re-parameterization has drawn increasing attention in various computer vision tasks. It aims at improving the performance of deep models without introducing any inference-time cost. Though efficient during inference, such models rely heavily on the complicated training-time blocks to achi…
This paper tackles the purely unsupervised person re-identification (Re-ID) problem that requires no annotations. Some previous methods adopt clustering techniques to generate pseudo labels and use the produced labels to train Re-ID models progressively. These methods are relatively simple but effec…
In this paper, we propose a novel method to perform weakly-supervised image parsing based on the dictionary learning framework. To deal with the challenges caused by the label ambiguities, we design a saliency guided weight assignment scheme to boost the discriminative dictionary learning. More spec…