Picture for Jinjun Xiong

Jinjun Xiong

Combating Partial Perception Deficit in Autonomous Driving with Multimodal LLM Commonsense

Add code
Mar 10, 2025
Viaarxiv icon

Towards Understanding Multi-Round Large Language Model Reasoning: Approximability, Learnability and Generalizability

Add code
Mar 05, 2025
Viaarxiv icon

Recognize Any Surgical Object: Unleashing the Power of Weakly-Supervised Data

Add code
Jan 25, 2025
Figure 1 for Recognize Any Surgical Object: Unleashing the Power of Weakly-Supervised Data
Figure 2 for Recognize Any Surgical Object: Unleashing the Power of Weakly-Supervised Data
Figure 3 for Recognize Any Surgical Object: Unleashing the Power of Weakly-Supervised Data
Figure 4 for Recognize Any Surgical Object: Unleashing the Power of Weakly-Supervised Data
Viaarxiv icon

Tiny-Align: Bridging Automatic Speech Recognition and Large Language Model on the Edge

Add code
Nov 21, 2024
Figure 1 for Tiny-Align: Bridging Automatic Speech Recognition and Large Language Model on the Edge
Figure 2 for Tiny-Align: Bridging Automatic Speech Recognition and Large Language Model on the Edge
Figure 3 for Tiny-Align: Bridging Automatic Speech Recognition and Large Language Model on the Edge
Figure 4 for Tiny-Align: Bridging Automatic Speech Recognition and Large Language Model on the Edge
Viaarxiv icon

NVCiM-PT: An NVCiM-assisted Prompt Tuning Framework for Edge LLMs

Add code
Nov 12, 2024
Figure 1 for NVCiM-PT: An NVCiM-assisted Prompt Tuning Framework for Edge LLMs
Figure 2 for NVCiM-PT: An NVCiM-assisted Prompt Tuning Framework for Edge LLMs
Figure 3 for NVCiM-PT: An NVCiM-assisted Prompt Tuning Framework for Edge LLMs
Figure 4 for NVCiM-PT: An NVCiM-assisted Prompt Tuning Framework for Edge LLMs
Viaarxiv icon

Automatic Screening for Children with Speech Disorder using Automatic Speech Recognition: Opportunities and Challenges

Add code
Oct 07, 2024
Figure 1 for Automatic Screening for Children with Speech Disorder using Automatic Speech Recognition: Opportunities and Challenges
Figure 2 for Automatic Screening for Children with Speech Disorder using Automatic Speech Recognition: Opportunities and Challenges
Figure 3 for Automatic Screening for Children with Speech Disorder using Automatic Speech Recognition: Opportunities and Challenges
Figure 4 for Automatic Screening for Children with Speech Disorder using Automatic Speech Recognition: Opportunities and Challenges
Viaarxiv icon

Towards Precision Characterization of Communication Disorders using Models of Perceived Pragmatic Similarity

Add code
Sep 13, 2024
Figure 1 for Towards Precision Characterization of Communication Disorders using Models of Perceived Pragmatic Similarity
Figure 2 for Towards Precision Characterization of Communication Disorders using Models of Perceived Pragmatic Similarity
Figure 3 for Towards Precision Characterization of Communication Disorders using Models of Perceived Pragmatic Similarity
Figure 4 for Towards Precision Characterization of Communication Disorders using Models of Perceived Pragmatic Similarity
Viaarxiv icon

LLaVA-Surg: Towards Multimodal Surgical Assistant via Structured Surgical Video Learning

Add code
Aug 15, 2024
Figure 1 for LLaVA-Surg: Towards Multimodal Surgical Assistant via Structured Surgical Video Learning
Figure 2 for LLaVA-Surg: Towards Multimodal Surgical Assistant via Structured Surgical Video Learning
Figure 3 for LLaVA-Surg: Towards Multimodal Surgical Assistant via Structured Surgical Video Learning
Figure 4 for LLaVA-Surg: Towards Multimodal Surgical Assistant via Structured Surgical Video Learning
Viaarxiv icon

FASA: a Flexible and Automatic Speech Aligner for Extracting High-quality Aligned Children Speech Data

Add code
Jun 25, 2024
Figure 1 for FASA: a Flexible and Automatic Speech Aligner for Extracting High-quality Aligned Children Speech Data
Figure 2 for FASA: a Flexible and Automatic Speech Aligner for Extracting High-quality Aligned Children Speech Data
Viaarxiv icon

Large Language Models have Intrinsic Self-Correction Ability

Add code
Jun 21, 2024
Viaarxiv icon