Heng Ji
Professor at UIUC; one of the most prolific NLP researchers; works on information extraction, multimodal LLMs, and scientific reasoning.
- Role
- professor
- Currently at
- University of Illinois Urbana-Champaign
- twitter.com/hengjinlp
- GitHub
- Unknown
- Scholar
- scholar.google.com/citations
- Papers
- 71
Cite
Notes
Only stored in your browser.
Authored papers
71Foundation Protocol: A Coordination Layer for Agentic Society
arXiv 2026
CreativityBench: Evaluating Agent Creative Reasoning via Affordance-Based Tool Repurposing
arXiv 2026
Tool-R0: Self-Evolving LLM Agents for Tool-Learning from Zero Data
arXiv 2026
Toward Cognitive Supersensing in Multimodal Large Language Model
arXiv 2026
ReIn: Conversational Error Recovery with Reasoning Inception
arXiv 2026
A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents
arXiv 2026
Adaptation of Agentic AI
arXiv 2025
EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents
arXiv 2025
ToolRL: Reward is All Tool Learning Needs
arXiv 2025
Seed1.5-VL Technical Report
arXiv 2025
RM-R1: Reward Modeling as Reasoning
arXiv 2025
Large Language Models Post-training: Surveying Techniques from Alignment to Reasoning
arXiv 2025
On the Trustworthiness of Generative Foundation Models: Guideline, Assessment, and Perspective
arXiv 2025
Internal Activation as the Polar Star for Steering Unsafe LLM Behavior
arXiv 2025
Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers
arXiv 2025
The Landscape of Agentic Reinforcement Learning for LLMs: A Survey
arXiv 2025
From Word to World: Can Large Language Models be Implicit Text-based World Models?
arXiv 2025
A Survey of Self-Evolving Agents: On Path to Artificial Super Intelligence
arXiv 2025
SMART: Self-Aware Agent for Tool Overuse Mitigation
arXiv 2025
MultiAgentBench: Evaluating the Collaboration and Competition of LLM agents
arXiv 2025
Prioritizing Image-Related Tokens Enhances Vision-Language Pre-Training
arXiv 2025
Context Engineering for Trustworthiness: Rescorla Wagner Steering Under Mixed and Inappropriate Contexts
arXiv 2025
CALM: Unleashing the Cross-Lingual Self-Aligning Ability of Language Model Question Answering
arXiv 2025
Beyond Sample-Level Feedback: Using Reference-Level Feedback to Guide Data Synthesis
arXiv 2025
Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum
arXiv 2025
Energy-Based Transformers are Scalable Learners and Thinkers
arXiv 2025
Perception-Aware Policy Optimization for Multimodal Reasoning
arXiv 2025
UserRL: Training Interactive User-Centric Agent via Reinforcement Learning
arXiv 2025
UserBench: An Interactive Gym Environment for User-Centric Agents
arXiv 2025
oMeBench: Towards Robust Benchmarking of LLMs in Organic Mechanism Elucidation and Reasoning
arXiv 2025
SWE-Gym: An Open Environment for Training Software Engineering Agents and Verifiers
preprint
OpenHands: An Open Platform for AI Software Developers as Generalist Agents
arXiv 2024
TrustLLM: Trustworthiness in Large Language Models
arXiv 2024
From Pixels to Insights: A Survey on Automatic Chart Understanding in the Era of Large Foundation Models
arXiv 2024
Infogent: An Agent-Based Framework for Web Information Aggregation
arXiv 2024
CoRNStack: High-Quality Contrastive Data for Better Code Retrieval and Reranking
arXiv 2024
L+M-24: Building a Dataset for Language + Molecules @ ACL 2024
arXiv 2024
FIRST: Faster Improved Listwise Reranking with Single Token Decoding
arXiv 2024
Named Entity Recognition Under Domain Shift via Metric Learning for Life Sciences
arXiv 2024
Chem-FINESE: Validating Fine-Grained Few-shot Entity Extraction through Text Reconstruction
chem-finese-validating-fine-grained-few-shot
Self-Correction is More than Refinement: A Learning Framework for Visual and Language Reasoning Tasks
arXiv 2024
SOLO: A Single Transformer for Scalable Vision-Language Modeling
arXiv 2024
Weak-to-Strong Extrapolation Expedites Alignment
arXiv 2024
Visually Descriptive Language Model for Vector Graphics Reasoning
arXiv 2024
Eliminating Position Bias of Language Models: A Mechanistic Approach
arXiv 2024
MentalArena: Self-play Training of Language Models for Diagnosis and Treatment of Mental Health Disorders
arXiv 2024
SciMON: Scientific Inspiration Machines Optimized for Novelty
arXiv 2023
Tool Learning with Foundation Models
arXiv 2023
R-Tuning: Instructing Large Language Models to Say `I Don't Know'
arXiv 2023
CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets
arXiv 2023
CREATOR: Tool Creation for Disentangling Abstract and Concrete Reasoning of Large Language Models
arXiv 2023
Mitigating the Alignment Tax of RLHF
arXiv 2023
Large Language Models on Graphs: A Comprehensive Survey
arXiv 2023
Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration
arXiv 2023
LM-Infinite: Zero-Shot Extreme Length Generalization for Large Language Models
arXiv 2023
Word Embeddings Are Steers for Language Models
arXiv 2023
Instruct and Extract: Instruction Tuning for On-Demand Information Extraction
arXiv 2023
Do LVLMs Understand Charts? Analyzing and Correcting Factual Errors in Chart Captioning
arXiv 2023
The Shifted and The Overlooked: A Task-oriented Investigation of User-GPT Interactions
arXiv 2023
Non-Sequential Graph Script Induction via Multimedia Grounding
arXiv 2023
Open-Vocabulary Argument Role Prediction for Event Extraction
arXiv 2022
Multimedia Generative Script Learning for Task Planning
arXiv 2022
Towards a Unified Multi-Dimensional Evaluator for Text Generation
arXiv 2022
Efficient Attentions for Long Document Summarization
NAACL 2021 4
Stage-wise Fine-tuning for Graph-to-Text Generation
ACL 2021 5
A Context-Dependent Gated Module for Incorporating Symbolic Semantics into Event Coreference Resolution
NAACL 2021 4
A Survey of Knowledge-Enhanced Text Generation
arXiv 2020
ReviewRobot: Explainable Paper Review Generation based on Knowledge Synthesis
INLG (ACL) 2020 12
PaperRobot: Incremental Draft Generation of Scientific Ideas
paperrobot-incremental-draft-generation-of-1
Describing a Knowledge Base
describing-a-knowledge-base-1
Paper Abstract Writing through Editing Mechanism
paper-abstract-writing-through-editing-1
Affiliations
Frequent co-authors
10from 71 papers