English
Related papers

Related papers: POCA: Pareto-Optimal Curriculum Alignment for Visu…

200 papers

A pervasive challenge in Reinforcement Learning (RL) is the "curse of dimensionality" which is the exponential growth in the state-action space when optimizing a high-dimensional target task. The framework of curriculum learning trains the…

Machine Learning · Computer Science 2025-03-24 Mingxuan Li , Junzhe Zhang , Elias Bareinboim

In this paper, we introduce a novel approach to novel object captioning which employs relative contrastive learning to learn visual and semantic alignment. Our approach maximizes compatibility between regions and object tags in a…

Computer Vision and Pattern Recognition · Computer Science 2023-12-12 Jiashuo Fan , Yaoyuan Liang , Leyao Liu , Shaolun Huang , Lei Zhang

Large language models (LLMs) are shifting from answer providers to intelligent tutors in educational settings, yet current supervised fine-tuning methods only learn surface teaching patterns without dynamic adaptation capabilities. Recent…

Artificial Intelligence · Computer Science 2026-01-06 Shouang Wei , Min Zhang , Xin Lin , Bo Jiang , Kun Kuang , Zhongxiang Dai

The evolution of Large Language Models (LLMs) is shifting the focus from single, verifiable tasks toward complex, open-ended real-world scenarios, imposing significant challenges on the post-training phase. In these settings, the scale and…

Artificial Intelligence · Computer Science 2026-04-10 Xuyang Zhi , Peilun zhou , Chengqiang Lu , Hang Lv , Yiwei Liang , Rongyang Zhang , Yan Gao , YI WU , Yao Hu , Hongchao Gu , Defu Lian , Hao Wang , Enhong Chen

Aligning large language models (LLMs) with human values and safety constraints is challenging, especially when objectives like helpfulness, truthfulness, and avoidance of harm conflict. Reinforcement Learning from Human Feedback (RLHF) has…

Computation and Language · Computer Science 2025-03-31 Xuying Li , Zhuo Li , Yuji Kosuga , Victor Bian

Reinforcement learning (RL) is pivotal for enabling large language models (LLMs) to generate long chains of thought (CoT) for complex tasks like math and reasoning. However, Proximal Policy Optimization (PPO), effective in many RL…

Machine Learning · Computer Science 2025-03-04 Yufeng Yuan , Yu Yue , Ruofei Zhu , Tiantian Fan , Lin Yan

Pretrained large-scale vision-language models such as CLIP have demonstrated excellent generalizability over a series of downstream tasks. However, they are sensitive to the variation of input text prompts and need a selection of prompt…

Computer Vision and Pattern Recognition · Computer Science 2024-01-02 Lianyu Hu , Liqing Gao , Zekang Liu , Chi-Man Pun , Wei Feng

Many real-world applications involve black-box optimization of multiple objectives using continuous function approximations that trade-off accuracy and resource cost of evaluation. For example, in rocket launching research, we need to find…

Machine Learning · Statistics 2020-11-24 Syrine Belakaria , Aryan Deshwal , Janardhan Rao Doppa

The fairness-accuracy trade-off is a key challenge in NLP tasks. Current work focuses on finding a single "optimal" solution to balance the two objectives, which is limited considering the diverse solutions on the Pareto front. This work…

Machine Learning · Computer Science 2025-09-18 Yongkang Du , Jieyu Zhao , Yijun Yang , Tianyi Zhou

Multi-objective preference alignment in language models often encounters a challenging trade-off: optimizing for one human preference (e.g., helpfulness) frequently compromises others (e.g., harmlessness) due to the inherent conflicts…

Computation and Language · Computer Science 2025-04-16 Zhihao Xu , Yongqi Tong , Xin Zhang , Jun Zhou , Xiting Wang

Generative recommendation has recently emerged as a promising paradigm for sequential recommendation. It formulates the task as an autoregressive generation process, predicting tokens of the next item conditioned on user interaction…

Information Retrieval · Computer Science 2026-05-29 Yuanqing Yu , Yifan Wang , Weizhi Ma , Zhiqiang Guo , Min Zhang

Multiobjective combinatorial optimization (MOCO) problems can be found in many real-world applications. However, exactly solving these problems would be very challenging, particularly when they are NP-hard. Many handcrafted heuristic…

Machine Learning · Computer Science 2022-05-10 Xi Lin , Zhiyuan Yang , Qingfu Zhang

We present a proximal policy optimization (PPO) agent trained through curriculum learning (CL) principles and meticulous reward engineering to optimize a real-world high-throughput waste sorting facility. Our work addresses the challenge of…

Machine Learning · Computer Science 2024-07-24 Abhijeet Pendyala , Asma Atamna , Tobias Glasmachers

RL-based techniques can be employed to search for prompts that, when fed into a target language model, maximize a set of user-specified reward functions. However, in many target applications, the natural reward functions are in tension with…

Computation and Language · Computer Science 2025-06-10 Yasaman Jafari , Dheeraj Mekala , Rose Yu , Taylor Berg-Kirkpatrick

Prompt design plays a crucial role in text-to-video (T2V) generation, yet user-provided prompts are often short, unstructured, and misaligned with training data, limiting the generative potential of diffusion-based T2V models. We present…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Bingjie Gao , Qianli Ma , Xiaoxue Wu , Shuai Yang , Guanzhou Lan , Haonan Zhao , Jiaxuan Chen , Qingyang Liu , Yu Qiao , Xinyuan Chen , Yaohui Wang , Li Niu

Group Relative Policy Optimization (GRPO), which is widely adopted by R1-like reasoning models, has advanced mathematical reasoning. Nevertheless, GRPO faces challenges in reward sparsity, verbosity, and inadequate focus on problem…

Computation and Language · Computer Science 2025-09-23 Jixiao Zhang , Chunsheng Zuo

While originally developed for continuous control problems, Proximal Policy Optimization (PPO) has emerged as the work-horse of a variety of reinforcement learning (RL) applications, including the fine-tuning of generative models.…

Group Relative Policy Optimization (GRPO) has recently shown strong performance in post-training large language models and vision-language models. It raises a question of whether the GRPO also significantly promotes the test-time adaptation…

Computer Vision and Pattern Recognition · Computer Science 2026-05-06 Yujun Li , Hongyuan Zhang , Yuan Yuan

Reward models are pivotal for aligning Large Language Models (LLMs) with human preferences. Existing approaches face two key limitations: Discriminative reward models require large-scale annotated data, as they cannot exploit the preference…

Computation and Language · Computer Science 2026-02-03 Yongfu Xue

Vision-Language-Action systems follow instructions to execute multi-step tasks in multimodal environments. Recent VLA approaches typically rely on post-hoc correction mechanisms or operate under fixed task decompositions and alignment…

Artificial Intelligence · Computer Science 2026-05-12 Xiyin Zeng , Yuyu Sun , Haoyang Li , Shouqiang Liu , Hao Wang