5 papers
Seed2Scale: A Self-Evolving Data Engine for Embodied AI via Small to Large Model Synergy and Multimodal Evaluation
Cong Tai, Zhaoyu Zheng, Haixu Long +12
Existing data generation methods suffer from exploration limits, embodiment gaps, and low signal-to-noise ratios, leading to performance degradation during self-iteration. To addre…
MammothModa2: A Unified AR-Diffusion Framework for Multimodal Understanding and Generation
Tao Shen, Xin Wan, Taicai Chen +10
Unified multimodal models aim to integrate understanding and generation within a single framework, yet bridging the gap between discrete semantic reasoning and high-fidelity visual…
ThinkQE: Query Expansion via an Evolving Thinking Process
Yibin Lei, Tao Shen, Andrew Yates
Effective query expansion for web search benefits from promoting both exploration and result diversity to capture multiple interpretations and facets of a query. While recent LLM-b…
Enhancing Lexicon-Based Text Embeddings with Large Language Models
Yibin Lei, Tao Shen, Yu Cao +1
Recent large language models (LLMs) have demonstrated exceptional performance on general-purpose text embedding tasks. While dense embeddings have dominated related research, we in…
LLMs are Also Effective Embedding Models: An In-depth Overview
Chongyang Tao, Tao Shen, Shen Gao +6
Large language models (LLMs) have revolutionized natural language processing by achieving state-of-the-art performance across various tasks. Recently, their effectiveness as embedd…