Picture for Mingda Li

Mingda Li

Quantum Measurement Group, Massachusetts Institute of Technology, Cambridge, MA, USA, Department of Nuclear Science and Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA

ReVision: A Dataset and Baseline VLM for Privacy-Preserving Task-Oriented Visual Instruction Rewriting

Add code
Feb 20, 2025
Viaarxiv icon

AI-driven materials design: a mini-review

Add code
Feb 05, 2025
Viaarxiv icon

Unstructured Text Enhanced Open-domain Dialogue System: A Systematic Survey

Add code
Nov 14, 2024
Figure 1 for Unstructured Text Enhanced Open-domain Dialogue System: A Systematic Survey
Figure 2 for Unstructured Text Enhanced Open-domain Dialogue System: A Systematic Survey
Figure 3 for Unstructured Text Enhanced Open-domain Dialogue System: A Systematic Survey
Figure 4 for Unstructured Text Enhanced Open-domain Dialogue System: A Systematic Survey
Viaarxiv icon

Large Language Model-Guided Prediction Toward Quantum Materials Synthesis

Add code
Oct 28, 2024
Figure 1 for Large Language Model-Guided Prediction Toward Quantum Materials Synthesis
Figure 2 for Large Language Model-Guided Prediction Toward Quantum Materials Synthesis
Figure 3 for Large Language Model-Guided Prediction Toward Quantum Materials Synthesis
Figure 4 for Large Language Model-Guided Prediction Toward Quantum Materials Synthesis
Viaarxiv icon

Policy-driven Knowledge Selection and Response Generation for Document-grounded Dialogue

Add code
Oct 21, 2024
Figure 1 for Policy-driven Knowledge Selection and Response Generation for Document-grounded Dialogue
Figure 2 for Policy-driven Knowledge Selection and Response Generation for Document-grounded Dialogue
Figure 3 for Policy-driven Knowledge Selection and Response Generation for Document-grounded Dialogue
Figure 4 for Policy-driven Knowledge Selection and Response Generation for Document-grounded Dialogue
Viaarxiv icon

TRACE: Temporal Grounding Video LLM via Causal Event Modeling

Add code
Oct 08, 2024
Figure 1 for TRACE: Temporal Grounding Video LLM via Causal Event Modeling
Figure 2 for TRACE: Temporal Grounding Video LLM via Causal Event Modeling
Figure 3 for TRACE: Temporal Grounding Video LLM via Causal Event Modeling
Figure 4 for TRACE: Temporal Grounding Video LLM via Causal Event Modeling
Viaarxiv icon

Enhancing Long Video Understanding via Hierarchical Event-Based Memory

Add code
Sep 10, 2024
Figure 1 for Enhancing Long Video Understanding via Hierarchical Event-Based Memory
Figure 2 for Enhancing Long Video Understanding via Hierarchical Event-Based Memory
Figure 3 for Enhancing Long Video Understanding via Hierarchical Event-Based Memory
Figure 4 for Enhancing Long Video Understanding via Hierarchical Event-Based Memory
Viaarxiv icon

TC-LLaVA: Rethinking the Transfer from Image to Video Understanding with Temporal Considerations

Add code
Sep 05, 2024
Viaarxiv icon

Bridging the Language Gap: Enhancing Multilingual Prompt-Based Code Generation in LLMs via Zero-Shot Cross-Lingual Transfer

Add code
Aug 19, 2024
Viaarxiv icon

Structural Constraint Integration in Generative Model for Discovery of Quantum Material Candidates

Add code
Jul 05, 2024
Viaarxiv icon