Dingwei Zhu, Shihan Dou, Zhiheng Xi, Senjie Jin, Guoqiang Zhang, Jiazheng Zhang, Junjie Ye, Mingxu Chai, Enyu Zhou, Ming Zhang, Yuhui Wang, Caishuang Huang, Chenhao Huang, Yunke Zhang, Yuran Wang, Tao Gui, Qi Zhang, Xipeng Qiu, Xuanjing Huang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Radiation therapyis one of the primary treatment modalities for head and neck (H&N) cancer in clinical practice, aiming to deliver sufficient dose to Planning Target Volume (PTV) while protecting surrounding Organs at Risk (OAR) from or minimizing exposure to radiation. Quantitative dose prediction of various tissues and organs is a prerequisite for implementing intelligent precision radiotherapy. In order to improve dose prediction accuracy, we propose a generative adversarial network CPFTransGAN based on Cross Perception Fusion Transformer (CPF Transformer). Specifically, we design a CPF Transformer module through deeply integrating CNN and Transformer. Using the CPF Transformer as basic unit, we constructed a generator with four-stage encoding-decoding structure called CPFTransGenerator. An adaptive weight loss is used to train the discriminator to alleviate the issues of imbalance training in adversarial learning. To further improve the prediction accuracy, a multiscale cross-window encoding network is designed, which can constrain the differences between predicted dose and the reference one at different granularity levels by calculating feature losses between them at different scales. The proposed method is evaluated on two public head and neck cancer datasets and a local clinical dataset. Extensive experiments demonstrate the superior performance of our method compared with the state-of-the-art ones.

The capability of the reward model (RM) is crucial for the success of Reinforcement Learning from Human Feedback (RLHF) in aligning with human preferences. However, as training progresses, the output space distribution of the policy model shifts. The RM, initially trained on responses sampled from the output distribution of the early policy model, gradually loses its ability to distinguish between responses from the newly shifted distribution. This issue is further compounded when the RM, trained on a specific data distribution, struggles to generalize to examples outside of that distribution. These two issues can be united as a challenge posed by the shifted distribution of the environment. To surmount this challenge, we introduce MetaRM, a novel method leveraging meta-learning to adapt the RM to the shifted environment distribution. MetaRM optimizes the RM in an alternating way, by preserving both the preferences of the original preference pairs, as well as maximizing discrimination power over new examples of the shifted distribution. Extensive experiments demonstrate that MetaRM can iteratively enhance the performance of human preference alignment by improving the RM's capacity to identify subtle differences in samples of shifted distributions.

Reward models (RMs) guide the alignment of large language models (LLMs), steering them toward behaviors preferred by humans. Evaluating RMs is the key to better aligning LLMs. However, the current evaluation of RMs may not directly correspond to their alignment performance due to the limited distribution of evaluation data and evaluation methods that are not closely related to alignment objectives. To address these limitations, we propose RMB, a comprehensive RM benchmark that covers over 49 real-world scenarios and includes both pairwise and Best-of-N (BoN) evaluations to better reflect the effectiveness of RMs in guiding alignment optimization. We demonstrate a positive correlation between our benchmark and the downstream alignment task performance. Based on our benchmark, we conduct extensive analysis on the state-of-the-art RMs, revealing their generalization defects that were not discovered by previous benchmarks, and highlighting the potential of generative RMs. Furthermore, we delve into open questions in reward models, specifically examining the effectiveness of majority voting for the evaluation of reward models and analyzing the impact factors of generative RMs, including the influence of evaluation criteria and instructing methods. We will release our evaluation code and datasets upon publication.

We offer a novel perspective on reward modeling by formulating it as a policy discriminator, which quantifies the difference between two policies to generate a reward signal, guiding the training policy towards a target policy with desired behaviors. Based on this conceptual insight, we propose a scalable pre-training method named POLicy DiscriminAtive LeaRning (POLAR), which trains a reward model (RM) to discern identical policies and discriminate different ones. Unlike traditional reward modeling methods relying on absolute preferences, POLAR captures the relative difference between one policy and an arbitrary target policy, which is a scalable, high-level optimization objective suitable for modeling generic ranking relationships. Leveraging the POLAR pre-training paradigm, we present a series of RMs with parameter scales from 1.8B to 7B. Empirical results show that POLAR substantially outperforms traditional non-pre-trained methods, significantly enhancing RM performance. For instance, POLAR-7B could improve preference accuracy from 54.8% to 81.0% on STEM tasks and from 57.9% to 85.5% on creative writing tasks compared to SOTA baselines. POLAR also shows robust generalization capabilities in RLHF using Reinforcement Fine-tuning (RFT), providing reliable reward signals and markedly enhancing policy performance—improving LLaMa3.1-8B from an average of 47.36% to 56.33% and Qwen2.5-32B from 64.49% to 70.47% on 20 benchmarks. Moreover, scaling experiments reveal a clear power-law relationship between computation and performance, supported by linear correlation coefficients approaching 0.99. The impressive performance, strong generalization, and scaling properties suggest that POLAR is a promising direction for developing general and strong reward models.

Shihan Dou, Yan Liu, Haoxiang Jia, Enyu Zhou, Limao Xiong, Junjie Shan, Caishuang Huang, Xiao Wang, Xiaoran Fan, Zhiheng Xi, Yuhao Zhou, Tao Ji, Rui Zheng, Qi Zhang, Tao Gui, Xuanjing Huang. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

Shihan Dou, Enyu Zhou, Yan Liu, Songyang Gao, Wei Shen, Limao Xiong, Yuhao Zhou, Xiao Wang, Zhiheng Xi, Xiaoran Fan, Shiliang Pu, Jiang Zhu, Rui Zheng, Tao Gui, Qi Zhang, Xuanjing Huang. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

The Janus Problem is a common issue in SDS-based text-to-3D methods. Due to view encoding approach and 2D diffusion prior guidance, the 3D representation model tends to learn content with higher certainty from each perspective, leading to view inconsistency. In this work, we first model and analyze the problem, visualizing the specific causes of the Janus Problem, which are associated with discrete view encoding and shared priors in 2D lifting. Based on this, we further propose the LCGen method, which guides text-to-3D to obtain different priors with different certainty from various viewpoints, aiding in view-consistent generation. Experiments have proven that our LCGen method can be directly applied to different SDS-based text-to-3D methods, alleviating the Janus Problem without introducing additional information, increasing excessive training burden, or compromising the generation effect.

Optical flow estimation is a fundamental task in computer vision. Recent direct-regression methods using deep neural networks achieve remarkable performance improvement. However, they do not explicitly capture long-term motion correspondences and thus cannot handle large motions effectively. In this paper, inspired by the traditional matching-optimization methods where matching is introduced to handle large displacements before energy-based optimizations, we introduce a simple but effective global matching step before the direct regression and develop a learning-based matching-optimization framework, namely GMFlowNet. In GMFlowNet, global matching is efficiently calculated by applying argmax on 4D cost volumes. Additionally, to improve the matching quality, we propose patch-based overlapping attention to extract large context features. Extensive experiments demonstrate that GM-FlowNet outperforms RAFT, the most popular optimization-only method, by a large margin and achieves state-of-the-art performance on standard benchmarks. Thanks to the matching and overlapping attention, GMFlowNet obtains major improvements on the predictions for textureless regions and large motions. Our code is made publicly available at https://github.com/xiaofeng94/GMFlowNet.