Hangyu Li

Hangyu Li, Yihan Xu, Jiangchao Yao et al.

Existing facial expression recognition (FER) methods typically fine-tune a pre-trained visual encoder using discrete labels. However, this form of supervision limits to specify the emotional concept of different facial expressions. In this paper, we observe that the rich knowledge in text embeddings, generated by vision-language models, is a promising alternative for learning discriminative facial expression representations. Inspired by this, we propose a novel knowledge-enhanced FER method with an emotional-to-neutral transformation. Specifically, we formulate the FER problem as a process to match the similarity between a facial expression representation and text embeddings. Then, we transform the facial expression representation to a neutral representation by simulating the difference in text embeddings from textual facial expression to textual neutral. Finally, a self-contrast objective is introduced to pull the facial expression representation closer to the textual facial expression, while pushing it farther from the neutral representation. We conduct evaluation with diverse pre-trained visual encoders including ResNet-18 and Swin-T on four challenging facial expression datasets. Extensive experiments demonstrate that our method significantly outperforms state-of-the-art FER methods. The code will be publicly available.

Dingyuan Shi, Yong Wang, Hangyu Li et al.

Diffusion models have shown remarkable success in text-to-image generation, making preference alignment for these models increasingly important. The preference labels are typically available only at the terminal of denoising trajectories, which poses challenges in optimizing the intermediate denoising steps. In this paper, we propose to conduct Denoised Distribution Estimation (DDE) that explicitly connects intermediate steps to the terminal denoised distribution. Therefore, preference labels can be used for the entire trajectory optimization. To this end, we design two estimation strategies for our DDE. The first is stepwise estimation, which utilizes the conditional denoised distribution to estimate the model denoised distribution. The second is single-shot estimation, which converts the model output into the terminal denoised distribution via DDIM modeling. Analytically and empirically, we reveal that DDE equipped with two estimation strategies naturally derives a novel credit assignment scheme that prioritizes optimizing the middle part of the denoising trajectory. Extensive experiments demonstrate that our approach achieves superior performance, both quantitatively and qualitatively.

Xiang Huang, Ting-En Lin, Feiteng Fang et al.

Instruction following (IF) is a critical capability for large language models (LLMs). However, handling complex instructions with multiple constraints remains challenging. Previous methods typically select preference pairs based on the number of constraints they satisfy, introducing noise where chosen examples may fail to follow some constraints and rejected examples may excel in certain respects over the chosen ones. To address the challenge of aligning with multiple preferences, we propose a simple yet effective method called Reverse Preference Optimization (RPO). It mitigates noise in preference pairs by dynamically reversing the constraints within the instruction to ensure the chosen response is perfect, alleviating the burden of extensive sampling and filtering to collect perfect responses. Besides, reversal also enlarges the gap between chosen and rejected responses, thereby clarifying the optimization direction and making it more robust to noise. We evaluate RPO on two multi-turn IF benchmarks, Sysbench and Multi-IF, demonstrating average improvements over the DPO baseline of 4.6 and 2.5 points (on Llama-3.1 8B), respectively. Moreover, RPO scales effectively across model sizes (8B to 70B parameters), with the 70B RPO model surpassing GPT-4o.