Heng Ji

19

Papers

496

Total Citations

Papers (19)

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

Training Software Engineering Agents and Verifiers with SWE-Gym

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

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

CLIP-Event: Connecting Text and Images With Event Structures

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

Learning to Learn Words from Visual Scenes

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

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

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

Executable Code Actions Elicit Better LLM Agents

Position: TrustLLM: Trustworthiness in Large Language Models

Separating Skills and Concepts for Novel Visual Question Answering

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

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

Paxion: Patching Action Knowledge in Video-Language Foundation Models

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