相关论文: Data-Juicer Sandbox: A Feedback-Driven Suite for M…

As more and more internet users post images online to express their daily emotions, image sentiment analysis has attracted increasing attention. Recently, researchers generally tend to design different neural networks to extract visual…

Real-world problems are often dependent on multiple data modalities, making multimodal fusion essential for leveraging diverse information sources. In high-stakes domains, such as in healthcare, understanding how each modality contributes…

We introduce Vocal Sandbox, a framework for enabling seamless human-robot collaboration in situated environments. Systems in our framework are characterized by their ability to adapt and continually learn at multiple levels of abstraction…

Research in the field of automated vehicles, or more generally cognitive cyber-physical systems that operate in the real world, is leading to increasingly complex systems. Among other things, artificial intelligence enables an…

As industrial recommender systems enter a scaling-driven regime, Transformer architectures have become increasingly attractive for scaling models towards larger capacity and longer sequence. However, existing Transformer-based…

Learning multimodal representations involves integrating information from multiple heterogeneous sources of data. In order to accelerate progress towards understudied modalities and tasks while ensuring real-world robustness, we release…

Current status quo in machine learning is to use static datasets of real images for training, which often come from long-tailed distributions. With the recent advances in generative models, researchers have started augmenting these static…

Crowd movement simulation is crucial for pedestrian safety management and facility design. Data-driven models offer the potential to improve realism and predictive accuracy, but most are developed for a single scenario, limiting their…

Active learning as a paradigm in deep learning is especially important in applications involving intricate perception tasks such as object detection where labels are difficult and expensive to acquire. Development of active learning methods…

Effective tool use is essential for large language models (LLMs) to interact with their environment. However, progress is limited by the lack of efficient reinforcement learning (RL) frameworks specifically designed for tool use, due to…

Currently, it is urgent to ensure QoS in distributed computing systems. This became especially important to the development and spread of cloud services. Big data structures become heavily distributed. Necessary to consider the…

In the era of flourishing large-scale models, the challenge of selecting and optimizing datasets from the vast and complex sea of data, to enhance the performance of large language models within the constraints of limited computational…

Learning from human feedback has become a pivot technique in aligning large language models (LLMs) with human preferences. However, acquiring vast and premium human feedback is bottlenecked by time, labor, and human capability, resulting in…

Recent advancements in parallel simulation and successful robotic applications are spurring a resurgence in sampling-based model predictive control. To build on this progress, however, the robotics community needs common tooling for…

As large language models (LLMs) continue to advance, the need for up-to-date and well-organized benchmarks becomes increasingly critical. However, many existing datasets are scattered, difficult to manage, and make it challenging to perform…

The integration of AI assistants into software development workflows is rapidly evolving, shifting from automation-assisted tasks to collaborative interactions between developers and AI. Large Language Models (LLMs) have demonstrated their…

As large language model agents advance beyond software engineering (SWE) tasks toward machine learning engineering (MLE), verifying agent behavior becomes orders of magnitude more expensive: while SWE tasks can be verified via…

Large Language Models (LLMs) are increasingly embedded in applications, and people can shape model behavior by editing prompt instructions. Yet encoding subtle, domain-specific policies into prompts is challenging. Although this process…

Combining the results of different search engines in order to improve upon their performance has been the subject of many research papers. This has become known as the "Data Fusion" task, and has great promise in dealing with the vast…

Evaluating human-robot social interactions in a rigorous manner is notoriously difficult: studies are either conducted in labs with constrained protocols to allow for robust measurements and a degree of replicability, but at the cost of…