We propose a two-stage 'Mine and Refine' contrastive training framework for semantic text embeddings to enhance multi-category e-commerce search retrieval. Larg...
As humans increasingly rely on multiround conversational AI for high stakes decisions, principled frameworks are needed to ensure such interactions reliably imp...
Black-box adversarial attacks on Large Vision-Language Models (LVLMs) are challenging due to missing gradients and complex multimodal boundaries. While prior st...
Traditional electronic recycling processes suffer from significant resource loss due to inadequate material separation and identification capabilities, limiting...
Feature engineering remains a critical yet challenging bottleneck in machine learning, particularly for tabular data, as identifying optimal features from an ex...
Learning time series foundation models has been shown to be a promising approach for zero-shot time series forecasting across diverse time series domains. Insof...
Reasoning with LLMs increasingly unfolds inside a broader verification loop. Internally, systems use cheap checks, such as self-consistency or proxy rewards, wh...
Modern offline Reinforcement Learning (RL) methods find performant actor-critics, however, fine-tuning these actor-critics online with value-based RL algorithms...
Modern big-data systems generate massive, heterogeneous, and geographically dispersed streams that are large-scale and privacy-sensitive, making centralization ...
Reinforcement learning (RL) is widely used to improve large language models on reasoning tasks, and asynchronous RL training is attractive because it increases ...
Big data scenarios, where massive, heterogeneous datasets are distributed across clients, demand scalable, privacy-preserving learning methods. Federated learni...
The proliferation of Large Language Models (LLMs) necessitates efficient mechanisms to distinguish machine-generated content from human text. While statistical ...
