Yong Li

Efficient Reasoning with Balanced Thinking

RL of Thoughts: Navigating LLM Reasoning with Inference-time Reinforcement Learning

FingerTip 20K: A Benchmark for Proactive and Personalized Mobile LLM Agents

LoRAGen: Structure-Aware Weight Space Learning for LoRA Generation

Reinforcement Learning Fine-Tuning Enhances Activation Intensity and Diversity in the Internal Circuitry of LLMs

Dynamics-Informed Weight Diffusion for Generalizable Prediction of  Complex Systems

CityLens: Evaluating Large Vision-Language Models for Urban Socioeconomic Sensing

Probing Neural Topology of Large Language Models

Beyond Model Ranking: Predictability-Aligned Evaluation for Time Series Forecasting

MoWM: Mixture-of-World-Models for Embodied Planning via Latent-to-Pixel Feature Modulation

MorphoGen: Evolving Robot Morphologies with Large Language Models

ChaosNexus: A Foundation Model for Universal Chaotic System Forecasting with Multi-scale Representations

COFormer: Towards a Foundation Model for Solving Combinatorial Optimization Problems

Contrastive Weak-to-Strong Generalization

RoadBench: Benchmarking MLLMs on Fine-Grained Spatial Understanding and Reasoning in Urban Road Scenarios

TravelReasoner: Reasoning-Augmented Travel Survey Simulations with Large Reasoning Models

SciNetBench: A Relation-Aware Benchmark for Scientific Literature Retrieval Agents

Fine-Tuning Flow Matching via Maximum Likelihood Estimation of Reconstructions

KeyWorld: Key Frame Reasoning Enables Effective and Efficient World Models

Unifying Counterfactual Data Augmentation and Architectural Inductive Biases in Offline Reinforcement Learning

Collaborative Deterministic–Probabilistic Forecasting for Diverse Spatiotemporal Systems

Route-and-Reason: Scaling Large Language Model Reasoning with Reinforced Model Router

LLMs Reading the Rhythms of Daily Life: Aligned Understanding for Behavior Prediction and Generation

Fidelity Breeds Complexity: Simulating Stock Markets with Large-Scale Generative Agents

Towards Generalizable LLM Multi-Agent System: Identifying Collective Intelligence Factor in LLM Agent Groups

Coordinated Search for Symbolic Formulas of Complex Network Dynamics

MoveFM-R: Advancing Mobility Foundation Models via Language-driven Semantic Reasoning

MoveGPT: Scaling Mobility Foundation Models with Spatially-Aware Mixture of Experts

Sample-efficient diffusion-based control of complex nonlinear systems

Mamba Integrated with Physics Principles Masters Long-term Chaotic System Forecasting

LongScape: Advancing Long-Horizon Embodied World Models with Context-Aware MoE

Deep Ideation: Designing LLM Agents to Generate Novel Research Ideas on Scientific Concept Network

Beyond Formula Complexity: Effective Information Criterion Improves Performance and Interpretability for Symbolic Regression

Eliciting Human-like Social Reasoning in Large Language Models

The Thinking Spectrum: An Empirical Study of Tunable Reasoning in LLMs Through Model Merging

DroneDreamer: Multi-View Low-Altitude World Model with Adaptive Control

MobiSim-Bench: A Multi-Perspective Benchmark for Evaluating LLM-Agent-Based Human Mobility Simulation

RoboScape: Physics-informed Embodied World Model

Diffusion Transformers as Open-World Spatiotemporal Foundation Models

CityBench: Evaluating the Capabilities of Large Language Models for Urban Tasks

PID-controlled Langevin Dynamics for Faster Sampling on Generative Models

Balanced Token Pruning: Accelerating Vision Language Models Beyond Local Optimization

LLM-Explorer: A Plug-in Reinforcement Learning Policy Exploration Enhancement Driven by Large Language Models

A Large-scale Dataset and Benchmark for Commuting Origin-Destination Flow Generation

Sample-efficient diffusion-based control of complex nonlinear systems

TrajAgent: An LLM-Agent Framework for Trajectory Modeling via Large-and-Small Model Collaboration

Reinforcement Learning with Adaptive Reward Modeling for Expensive-to-Evaluate Systems

Exploring Large Language Model Agents for Piloting Social Experiments

AgentSquare: Automatic LLM Agent Search in Modular Design Space

Sparse Diffusion Autoencoder for Test-time Adapting Prediction of Complex Systems

Predicting the Energy Landscape of Stochastic Dynamical System via Physics-informed Self-supervised Learning

Symbolic regression via MDLformer-guided search: from minimizing prediction error to minimizing description length

Neural Symbolic Regression of Complex Network Dynamics

UrbanMLLM: Joint Learning of Cross-view Imagery for Urban Understanding

Adaptive Source Localization on Complex Networks via Conditional Diffusion Model

A GPU-accelerated Large-scale Simulator for Transportation System Optimization Benchmarking

Solving Diverse Combinatorial Optimization Problems with a Unified Model

Token Signature: Predicting Chain-of-Thought Gains with Token Decoding Feature in Large Language Models

LCSim: A Large-Scale Controllable Traffic Simulator

A Large-scale Dataset with Behavior, Attributes, and Content of Mobile Short-video Platform

UrbanWorld: An Urban World Model for 3D City Generation

GenNet: A Generative AI-Driven Mobile Network Simulator for Multi-Objective Network Optimization

OpenCity: A Scalable Platform to Simulate Urban Activities with Massive LLM Agents

UrbanDiT: A Foundation Model for Open-World Urban Spatio-Temporal Learning

Identify Critical Nodes in Complex Network with Large Language Models

Collaborative Deterministic–Probabilistic Forecasting for Real-World Spatiotemporal Systems

A Diffusion-based Generative Approach for Model-free Finite-time Control of Complex Systems

A Diffusive Data Augmentation Framework for Reconstruction of Complex Network Evolutionary History

LLM-Exp: Exploring the Policy in Reinforcement Learning with Large Language Models

UrbanPlanBench: A Comprehensive Assessment of Urban Planning Abilities in Large Language Models

EmbodiedCity: A Benchmark Platform for Embodied Agent in Real-world City Environment