Picture for Heng Tao Shen

Heng Tao Shen

Syzygy of Thoughts: Improving LLM CoT with the Minimal Free Resolution

Add code
Apr 16, 2025
Viaarxiv icon

Exploring Kernel Transformations for Implicit Neural Representations

Add code
Apr 07, 2025
Viaarxiv icon

Attention Hijackers: Detect and Disentangle Attention Hijacking in LVLMs for Hallucination Mitigation

Add code
Mar 11, 2025
Viaarxiv icon

New Dataset and Methods for Fine-Grained Compositional Referring Expression Comprehension via Specialist-MLLM Collaboration

Add code
Feb 28, 2025
Viaarxiv icon

PSCon: Toward Conversational Product Search

Add code
Feb 19, 2025
Viaarxiv icon

Skip Tuning: Pre-trained Vision-Language Models are Effective and Efficient Adapters Themselves

Add code
Dec 16, 2024
Viaarxiv icon

GT23D-Bench: A Comprehensive General Text-to-3D Generation Benchmark

Add code
Dec 13, 2024
Viaarxiv icon

SeMv-3D: Towards Semantic and Mutil-view Consistency simultaneously for General Text-to-3D Generation with Triplane Priors

Add code
Oct 10, 2024
Viaarxiv icon

On Efficient Variants of Segment Anything Model: A Survey

Add code
Oct 07, 2024
Figure 1 for On Efficient Variants of Segment Anything Model: A Survey
Figure 2 for On Efficient Variants of Segment Anything Model: A Survey
Figure 3 for On Efficient Variants of Segment Anything Model: A Survey
Figure 4 for On Efficient Variants of Segment Anything Model: A Survey
Viaarxiv icon

MMEvol: Empowering Multimodal Large Language Models with Evol-Instruct

Add code
Sep 09, 2024
Figure 1 for MMEvol: Empowering Multimodal Large Language Models with Evol-Instruct
Figure 2 for MMEvol: Empowering Multimodal Large Language Models with Evol-Instruct
Figure 3 for MMEvol: Empowering Multimodal Large Language Models with Evol-Instruct
Figure 4 for MMEvol: Empowering Multimodal Large Language Models with Evol-Instruct
Viaarxiv icon