0

Heng Ji

Professor at UIUC; one of the most prolific NLP researchers; works on information extraction, multimodal LLMs, and scientific reasoning.

Role
professor
GitHub
Unknown
Papers
71

Cite

Notes

Only stored in your browser.

71papers

Authored papers

71

Foundation Protocol: A Coordination Layer for Agentic Society

arXiv 2026

2026

CreativityBench: Evaluating Agent Creative Reasoning via Affordance-Based Tool Repurposing

arXiv 2026

2026

Tool-R0: Self-Evolving LLM Agents for Tool-Learning from Zero Data

arXiv 2026

2026

Toward Cognitive Supersensing in Multimodal Large Language Model

arXiv 2026

2026

Agentic Reasoning for Large Language Models

arXiv 2026

2026

ReIn: Conversational Error Recovery with Reasoning Inception

arXiv 2026

2026

Adaptation of Agentic AI

arXiv 2025

2025

EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents

arXiv 2025

2025

ToolRL: Reward is All Tool Learning Needs

arXiv 2025

2025

Seed1.5-VL Technical Report

arXiv 2025

2025

RM-R1: Reward Modeling as Reasoning

arXiv 2025

2025

Large Language Models Post-training: Surveying Techniques from Alignment to Reasoning

arXiv 2025

2025

On the Trustworthiness of Generative Foundation Models: Guideline, Assessment, and Perspective

arXiv 2025

2025

Internal Activation as the Polar Star for Steering Unsafe LLM Behavior

arXiv 2025

2025

Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers

arXiv 2025

2025

The Landscape of Agentic Reinforcement Learning for LLMs: A Survey

arXiv 2025

2025

From Word to World: Can Large Language Models be Implicit Text-based World Models?

arXiv 2025

2025

Energy-Based Transformers are Scalable Learners and Thinkers

arXiv 2025

2025

Perception-Aware Policy Optimization for Multimodal Reasoning

arXiv 2025

2025

UserRL: Training Interactive User-Centric Agent via Reinforcement Learning

arXiv 2025

2025

oMeBench: Towards Robust Benchmarking of LLMs in Organic Mechanism Elucidation and Reasoning

arXiv 2025

2025

Prioritizing Image-Related Tokens Enhances Vision-Language Pre-Training

arXiv 2025

2025

Context Engineering for Trustworthiness: Rescorla Wagner Steering Under Mixed and Inappropriate Contexts

arXiv 2025

2025

CALM: Unleashing the Cross-Lingual Self-Aligning Ability of Language Model Question Answering

arXiv 2025

2025

A Survey of Self-Evolving Agents: On Path to Artificial Super Intelligence

arXiv 2025

2025

Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum

arXiv 2025

2025

UserBench: An Interactive Gym Environment for User-Centric Agents

arXiv 2025

2025

SMART: Self-Aware Agent for Tool Overuse Mitigation

arXiv 2025

2025

MultiAgentBench: Evaluating the Collaboration and Competition of LLM agents

arXiv 2025

2025

Beyond Sample-Level Feedback: Using Reference-Level Feedback to Guide Data Synthesis

arXiv 2025

2025

SWE-Gym: An Open Environment for Training Software Engineering Agents and Verifiers

preprint

2024

OpenHands: An Open Platform for AI Software Developers as Generalist Agents

arXiv 2024

2024

TrustLLM: Trustworthiness in Large Language Models

arXiv 2024

2024

From Pixels to Insights: A Survey on Automatic Chart Understanding in the Era of Large Foundation Models

arXiv 2024

2024

Infogent: An Agent-Based Framework for Web Information Aggregation

arXiv 2024

2024

CoRNStack: High-Quality Contrastive Data for Better Code Retrieval and Reranking

arXiv 2024

2024

Weak-to-Strong Extrapolation Expedites Alignment

arXiv 2024

2024

MentalArena: Self-play Training of Language Models for Diagnosis and Treatment of Mental Health Disorders

arXiv 2024

2024

Chem-FINESE: Validating Fine-Grained Few-shot Entity Extraction through Text Reconstruction

chem-finese-validating-fine-grained-few-shot

2024

SOLO: A Single Transformer for Scalable Vision-Language Modeling

arXiv 2024

2024

L+M-24: Building a Dataset for Language + Molecules @ ACL 2024

arXiv 2024

2024

FIRST: Faster Improved Listwise Reranking with Single Token Decoding

arXiv 2024

2024

Visually Descriptive Language Model for Vector Graphics Reasoning

arXiv 2024

2024

Eliminating Position Bias of Language Models: A Mechanistic Approach

arXiv 2024

2024

Named Entity Recognition Under Domain Shift via Metric Learning for Life Sciences

arXiv 2024

2024

Self-Correction is More than Refinement: A Learning Framework for Visual and Language Reasoning Tasks

arXiv 2024

2024

SciMON: Scientific Inspiration Machines Optimized for Novelty

arXiv 2023

2023

Tool Learning with Foundation Models

arXiv 2023

2023

Large Language Models on Graphs: A Comprehensive Survey

arXiv 2023

2023

Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration

arXiv 2023

2023

Word Embeddings Are Steers for Language Models

arXiv 2023

2023

R-Tuning: Instructing Large Language Models to Say `I Don't Know'

arXiv 2023

2023

Instruct and Extract: Instruction Tuning for On-Demand Information Extraction

arXiv 2023

2023

Do LVLMs Understand Charts? Analyzing and Correcting Factual Errors in Chart Captioning

arXiv 2023

2023

Mitigating the Alignment Tax of RLHF

arXiv 2023

2023

LM-Infinite: Zero-Shot Extreme Length Generalization for Large Language Models

arXiv 2023

2023

CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets

arXiv 2023

2023

CREATOR: Tool Creation for Disentangling Abstract and Concrete Reasoning of Large Language Models

arXiv 2023

2023

The Shifted and The Overlooked: A Task-oriented Investigation of User-GPT Interactions

arXiv 2023

2023

Non-Sequential Graph Script Induction via Multimedia Grounding

arXiv 2023

2023

Towards a Unified Multi-Dimensional Evaluator for Text Generation

arXiv 2022

2022

Open-Vocabulary Argument Role Prediction for Event Extraction

arXiv 2022

2022

Multimedia Generative Script Learning for Task Planning

arXiv 2022

2022

Stage-wise Fine-tuning for Graph-to-Text Generation

ACL 2021 5

2021

A Context-Dependent Gated Module for Incorporating Symbolic Semantics into Event Coreference Resolution

NAACL 2021 4

2021

Efficient Attentions for Long Document Summarization

NAACL 2021 4

2021

A Survey of Knowledge-Enhanced Text Generation

arXiv 2020

2020

ReviewRobot: Explainable Paper Review Generation based on Knowledge Synthesis

INLG (ACL) 2020 12

2020

PaperRobot: Incremental Draft Generation of Scientific Ideas

paperrobot-incremental-draft-generation-of-1

2019

Describing a Knowledge Base

describing-a-knowledge-base-1

2018

Paper Abstract Writing through Editing Mechanism

paper-abstract-writing-through-editing-1

2018

Affiliations

Frequent co-authors

10

from 71 papers