Heng Ji

papers

1,893

total citations

papers (19)

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

ICLR 2025arXiv

387

citations

Executable Code Actions Elicit Better LLM Agents

ICML 2024arXiv

344

citations

Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-constraint

ICML 2024arXiv

312

citations

Language Models with Image Descriptors are Strong Few-Shot Video-Language Learners

NEURIPS 2022arXiv

164

citations

Training Software Engineering Agents and Verifiers with SWE-Gym

ICML 2025arXiv

156

citations

CLIP-Event: Connecting Text and Images With Event Structures

CVPR 2022arXiv

145

citations

Revisiting Out-of-distribution Robustness in NLP: Benchmarks, Analysis, and LLMs Evaluations

NEURIPS 2023arXiv

134

citations

DRESS: Instructing Large Vision-Language Models to Align and Interact with Humans via Natural Language Feedback

CVPR 2024arXiv

103

citations

Paxion: Patching Action Knowledge in Video-Language Foundation Models

NEURIPS 2023arXiv

citations

Separating Skills and Concepts for Novel Visual Question Answering

CVPR 2021arXiv

citations

Towards Fast Adaptation of Pretrained Contrastive Models for Multi-Channel Video-Language Retrieval

CVPR 2023arXiv

citations

CHEMREASONER: Heuristic Search over a Large Language Model’s Knowledge Space using Quantum-Chemical Feedback

ICML 2024arXiv

citations

Fragment and Geometry Aware Tokenization of Molecules for Structure-Based Drug Design Using Language Models

ICLR 2025arXiv

citations

Learning to Learn Words from Visual Scenes

ECCV 2020arXiv

citations

Search and Detect: Training-Free Long Tail Object Detection via Web-Image Retrieval

CVPR 2025arXiv

citations

Heng Ji

papers (19)

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

Executable Code Actions Elicit Better LLM Agents

Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-constraint

Language Models with Image Descriptors are Strong Few-Shot Video-Language Learners

Training Software Engineering Agents and Verifiers with SWE-Gym

CLIP-Event: Connecting Text and Images With Event Structures

Revisiting Out-of-distribution Robustness in NLP: Benchmarks, Analysis, and LLMs Evaluations

DRESS: Instructing Large Vision-Language Models to Align and Interact with Humans via Natural Language Feedback

Paxion: Patching Action Knowledge in Video-Language Foundation Models

Separating Skills and Concepts for Novel Visual Question Answering

Towards Fast Adaptation of Pretrained Contrastive Models for Multi-Channel Video-Language Retrieval

CHEMREASONER: Heuristic Search over a Large Language Model’s Knowledge Space using Quantum-Chemical Feedback

Fragment and Geometry Aware Tokenization of Molecules for Structure-Based Drug Design Using Language Models

Learning to Learn Words from Visual Scenes

Search and Detect: Training-Free Long Tail Object Detection via Web-Image Retrieval

Enabling Lanuguage Models to Implicitly Learn Self-Improvement

Verbalized Representation Learning for Interpretable Few-Shot Generalization

Skyformer: Remodel Self-Attention with Gaussian Kernel and Nystr\"om Method

Position: TrustLLM: Trustworthiness in Large Language Models

papers (19)

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

Executable Code Actions Elicit Better LLM Agents

Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-constraint

Language Models with Image Descriptors are Strong Few-Shot Video-Language Learners

Training Software Engineering Agents and Verifiers with SWE-Gym

CLIP-Event: Connecting Text and Images With Event Structures

Revisiting Out-of-distribution Robustness in NLP: Benchmarks, Analysis, and LLMs Evaluations

DRESS: Instructing Large Vision-Language Models to Align and Interact with Humans via Natural Language Feedback

Paxion: Patching Action Knowledge in Video-Language Foundation Models

Separating Skills and Concepts for Novel Visual Question Answering

Towards Fast Adaptation of Pretrained Contrastive Models for Multi-Channel Video-Language Retrieval

CHEMREASONER: Heuristic Search over a Large Language Model’s Knowledge Space using Quantum-Chemical Feedback

Fragment and Geometry Aware Tokenization of Molecules for Structure-Based Drug Design Using Language Models

Learning to Learn Words from Visual Scenes

Search and Detect: Training-Free Long Tail Object Detection via Web-Image Retrieval

Enabling Lanuguage Models to Implicitly Learn Self-Improvement

Verbalized Representation Learning for Interpretable Few-Shot Generalization

Skyformer: Remodel Self-Attention with Gaussian Kernel and Nystr\"om Method

Position: TrustLLM: Trustworthiness in Large Language Models