相关论文: For-Value: Efficient Forward-Only Data Valuation f…
The autonomous decision-making process, which is increasingly applied to computer systems, requires that the choices made by these systems align with human values. In this context, systems must assess how well their decisions reflect human…
Predictive modeling on tabular data is the cornerstone of many real-world applications. Although gradient boosting machines and some recent deep models achieve strong performance on tabular data, they often lack interpretability. On the…
Many NLP classification tasks, such as sexism/racism detection or toxicity detection, are based on human values. Yet, human values can vary under diverse cultural conditions. Therefore, we introduce a framework for value-aligned…
This paper focuses on extending the success of large language models (LLMs) to sequential decision making. Existing efforts either (i) re-train or finetune LLMs for decision making, or (ii) design prompts for pretrained LLMs. The former…
Visual-Language Models (VLMs) have become a powerful tool for bridging the gap between visual and linguistic understanding. However, the conventional learning approaches for VLMs often suffer from limitations, such as the high resource…
Any entity in the visual world can be hierarchically grouped based on shared characteristics and mapped to fine-grained sub-categories. While Multi-modal Large Language Models (MLLMs) achieve strong performance on coarse-grained visual…
While guided decoding, especially value-guided methods, has emerged as a cost-effective alternative for controlling language model outputs without re-training models, its effectiveness is limited by the accuracy of the value function. We…
The rapid progress of large language models (LLMs) is fueled by the growing reliance on datasets that blend real and synthetic data. While synthetic data offers scalability and cost-efficiency, it often introduces systematic distributional…
Data-centric learning emphasizes curating high-quality training samples to boost performance rather than designing new architectures. A central problem is to estimate the influence of training sample efficiently. Prior studies largely focus…
Vision Language Models (VLMs) are becoming increasingly integral to multimedia understanding; however, they often struggle with domain-specific video classification tasks, particularly in cases with limited data. This stems from a critical…
As Large Language Models (LLMs) achieve remarkable breakthroughs, aligning their values with humans has become imperative for their responsible development and customized applications. However, there still lack evaluations of LLMs values…
Large language models (LLMs) inevitably make mistakes when performing step-by-step mathematical reasoning. Process Reward Models (PRMs) have emerged as a promising solution by evaluating each reasoning step. However, existing PRMs typically…
Large Vision Language Models (LVLMs) have demonstrated remarkable reasoning capabilities over textual and visual inputs. However, these models remain prone to generating misinformation. Identifying and mitigating ungrounded responses is…
Multi-Task Learning (MTL) models have shown their robustness, effectiveness, and efficiency for transferring learned knowledge across tasks. In real industrial applications such as web content classification, multiple classification tasks…
Large Multimodal Models (LMMs) have achieved remarkable success in vision-language tasks, yet their vast parameter counts are often underutilized during both training and inference. In this work, we embrace the idea of looping back to move…
Data valuation has found various applications in machine learning, such as data filtering, efficient learning and incentives for data sharing. The most popular current approach to data valuation is the Shapley value. While popular for its…
Recent years have witnessed remarkable progress in the development of large vision-language models (LVLMs). Benefiting from the strong language backbones and efficient cross-modal alignment strategies, LVLMs exhibit surprising capabilities…
Large vision-language models (LVLMs) have shown premise in a broad range of vision-language tasks with their strong reasoning and generalization capabilities. However, they require considerable computational resources for training and…
Aligning large language models (LLMs) to value systems has emerged as a significant area of research within the fields of AI and NLP. Currently, this alignment process relies on the availability of high-quality supervised and preference…
Large vision-language models (VLMs) typically process hundreds or thousands of visual tokens per image or video frame, incurring quadratic attention cost and substantial redundancy. Existing token reduction methods often ignore the textual…