Jingting Ding

Siyang Li, Yifan Xu, Huanyu Wu et al.

Facial affect analysis remains a challenging task with its setting transitioned from lab-controlled to in-the-wild situations. In this paper, we present novel frameworks to handle the two challenges in the 4th Affective Behavior Analysis In-The-Wild (ABAW) competition: i) Multi-Task-Learning (MTL) Challenge and ii) Learning from Synthetic Data (LSD) Challenge. For MTL challenge, we adopt the SMM-EmotionNet with a better ensemble strategy of feature vectors. For LSD challenge, we propose respective methods to combat the problems of single labels, imbalanced distribution, fine-tuning limitations, and choice of model architectures. Experimental results on the official validation sets from the competition demonstrated that our proposed approaches outperformed baselines by a large margin. The code is available at https://github.com/sylyoung/ABAW4-HUST-ANT.

Yufan Liu, Jiajiong Cao, Bing Li et al.

Transformer attracts much attention because of its ability to learn global relations and superior performance. In order to achieve higher performance, it is natural to distill complementary knowledge from Transformer to convolutional neural network (CNN). However, most existing knowledge distillation methods only consider homologous-architecture distillation, such as distilling knowledge from CNN to CNN. They may not be suitable when applying to cross-architecture scenarios, such as from Transformer to CNN. To deal with this problem, a novel cross-architecture knowledge distillation method is proposed. Specifically, instead of directly mimicking output/intermediate features of the teacher, partially cross attention projector and group-wise linear projector are introduced to align the student features with the teacher's in two projected feature spaces. And a multi-view robust training scheme is further presented to improve the robustness and stability of the framework. Extensive experiments show that the proposed method outperforms 14 state-of-the-arts on both small-scale and large-scale datasets.

Zhaokang Liao, Yingguo Gao, Yi Yang et al.

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a promising approach to improve the reasoning abilities of Large Language Models (LLMs). Among RLVR algorithms, Group Relative Policy Optimization (GRPO) and its variants have demonstrated strong performance and high training efficiency. However, GRPO-style objectives exhibit two issues on high accuracy prompts including mastered prompts (rollout accuracy =1) and majority-correct prompts (rollout accuracy in (0.5,1)). For mastered prompts, group-relative advantages vanish, yielding no training signal and unconstrained policy drift that can cause forgetting. For majority-correct prompts, the induced query weight shrinks as accuracy increases, weakening consolidation from partial correctness to mastery. To alleviate this, we propose Mastery-Consolidated Policy Optimization (MCPO), which introduces (i) a hinge-KL regularizer applied exclusively to mastered prompts to bound harmful policy drift between successive gradient steps, and (ii) a weighting mechanism that prioritizes majority-correct prompts to better allocate optimization effort. Extensive experiments across three mathematical benchmarks demonstrate that MCPO consistently improves pass@1 performance. Counter-intuitively, rather than restricting exploration, MCPO boosts pass@k metrics, indicating that mastery consolidation further catalyzes solution diversity.