Li, Wei

InfoCom: Kilobyte-Scale Communication-Efficient Collaborative Perception with Information Bottleneck

Precise environmental perception is critical for the reliability of autonomous driving systems. While collaborative perception mitigates the limitations of single-agent perception through...

DynamicMind: A Tri-Mode Thinking System for Large Language Models

Modern large language models (LLMs) often struggle to dynamically adapt their reasoning depth to varying task complexities, leading to suboptimal performance or inefficient resource utilization....

RoCo-ACE: Rollout-Conditioned Online Distillation for Retention-Aware Knowledge Injection

InfoSpec: Information-Guided Anchor Selection for Retrieval-Based Speculative Decoding

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Synergizing-Oriented Multi-Turn Reinforcement Learning

Divide-and-Adapt: Fine-Tuning VLMs via Model Division and Routing

Ask Only When Needed: Proactive Retrieval from Memory and Skills for Experience-Driven Lifelong Agents

SPARK: Skeleton-Guided Reasoning Synthesis from Large-Scale Scientific Literature

JFY-IV machine translation system

A Question Answering System Supported by Information Extraction

Location Normalization for Information Extraction

Extracting Exact Answers to Questions Based on Structural Links

Bootstrapping for Named Entity Tagging Using Concept-based Seeds

An Expert Lexicon Approach to Identifying English Phrasal Verbs

A Bootstrapping Approach to Named Entity Classification Using Successive Learners

InfoXtract location normalization: a hybrid approach to geographic references in information extraction

Early results for Named Entity Recognition with Conditional Random Fields, Feature Induction and Web-Enhanced Lexicons

InfoXtract: A Customizable Intermediate Level Information Extraction Engine