List your company
ResearchFormerly WizWand

Multiple Choice VideoQA on IntentQA

68AccuracyKTV-34B-dense
58.43260.91663.465.884Jul 22, 2024Oct 23, 2024Jan 25, 2025Apr 28, 2025Jul 31, 2025Nov 1, 2025Feb 3, 2026
Updated 8mo ago

Evaluation results

MethodLinks
KTV-34B-denseLLM Size=34B, Vis Encoder=CLIP-L, Training Regime=Training-Free, Variant=dense2026.0268
TS-LLaVALLM Size=34B, Vision Encoder=CLIP-L, Training Strategy=Training-free2024.1167.9
TS-LLaVALLM Size=34B, Vision Encoder=CLIP-L, Training Strategy=Training-free2024.1167.9
TS-LLaVALLM Size=34B, Vision Encoder=CLIP-L, Training Strategy=Training-free2024.1167.9
VideoTreeLLM Size=GPT-4, Vision Encoder=Unknown, Training Protocol=Training-free2024.0766.9
VideoTreeLLM Size=GPT-4, Vision Encoder=Unknown, Training Strategy=Training-free2024.1166.9
VideoTreeLLM Size=GPT-4, Vision Encoder=Unknown, Training Strategy=Training-free2024.1166.9
VideoTreeLLM Size=GPT-4, Vision Encoder=Unknown, Training Strategy=Training-free2024.1166.9
KTV-34B-normalLLM Size=34B, Vis Encoder=CLIP-L, Training Regime=Training-Free, Variant=normal2026.0266.6
SF-LLaVA-34BLLM Size=34B, Vision Encoder=CLIP-L, Training Protocol=Training-free2024.0766.5
SF-LLAVALLM Size=34B, Vision Encoder=CLIP-L, Training Strategy=Training-free2024.1166.5
SF-LLAVALLM Size=34B, Vision Encoder=CLIP-L, Training Strategy=Training-free2024.1166.5
SF-LLAVALLM Size=34B, Vision Encoder=CLIP-L, Training Strategy=Training-free2024.1166.5
DYTOLLM Size=34B, Vis Encoder=CLIP-L, Training Regime=Training-Free2026.0266.4
SF-LLaVA-7BLLM Size=34B, Vis Encoder=CLIP-L, Training Regime=Training-Free2026.0266.1
KTV-34B-sparseLLM Size=34B, Vis Encoder=CLIP-L, Training Regime=Training-Free, Variant=sparse2026.0265.9
IG-VLM (LLaVA-v1.6)LLM Size=34B, Vision Encoder=CLIP-L, Training Protocol=Training-free2024.0765.3
IG-VLMLLM Size=34B, Vision Encoder=CLIP-L, Training Strategy=Training-free2024.1165.3
IG-VLMLLM Size=34B, Vision Encoder=CLIP-L, Training Strategy=Training-free2024.1165.3
IG-VLMLLM Size=34B, Vision Encoder=CLIP-L, Training Strategy=Training-free2024.1165.3
IG-VLMLLM Size=34B, Vis Encoder=CLIP-L, Training Regime=Training-Free2026.0264.5
LLoViLLM Size=GPT-3.5, Vision Encoder=Unknown, Training Protocol=Training-free2024.0764
LLoViLLM Size=GPT-3.5, Vision Encoder=Unknown, Training Strategy=Training-free2024.1164
LLoViLLM Size=GPT-3.5, Vision Encoder=Unknown, Training Strategy=Training-free2024.1164
LLoViLLM Size=GPT-3.5, Vision Encoder=Unknown, Training Strategy=Training-free2024.1164
KTV-7B-denseLLM Size=7B, Vis Encoder=CLIP-L, Training Regime=Training-Free, Variant=dense2026.0262
TS-LLaVALLM Size=7B, Vision Encoder=CLIP-L, Training Strategy=Training-free2024.1161.7
TS-LLaVALLM Size=7B, Vision Encoder=CLIP-L, Training Strategy=Training-free2024.1161.7
DYTOLLM Size=7B, Vis Encoder=CLIP-L, Training Regime=Training-Free2026.0261.6
KTV-7B-normalLLM Size=7B, Vis Encoder=CLIP-L, Training Regime=Training-Free, Variant=normal2026.0261.3
KTV-7B-sparseLLM Size=7B, Vis Encoder=CLIP-L, Training Regime=Training-Free, Variant=sparse2026.0261.2
SF-LLaVA-7BLLM Size=7B, Vis Encoder=CLIP-L, Training Regime=Training-Free2026.0260.5
IG-VLM (LLaVA-v1.6)LLM Size=7B, Vision Encoder=CLIP-L, Training Protocol=Training-free2024.0760.3
IG-VLMLLM Size=7B, Vision Encoder=CLIP-L, Training Strategy=Training-free2024.1160.3
IG-VLMLLM Size=7B, Vision Encoder=CLIP-L, Training Strategy=Training-free2024.1160.3
IG-VLMLLM Size=7B, Vis Encoder=CLIP-L, Training Regime=Training-Free2026.0260.3
SF-LLaVA-7BLLM Size=7B, Vision Encoder=CLIP-L, Training Protocol=Training-free2024.0760.1
SF-LLaVALLM Size=7B, Vision Encoder=CLIP-L, Training Strategy=Training-free2024.1160.1
SF-LLaVALLM Size=7B, Vision Encoder=CLIP-L, Training Strategy=Training-free2024.1160.1
M3LLM Size=7B, Vision Encoder=CLIP-L, Training Strategy=Video-trained2024.1158.8
M3LLM Size=7B, Vision Encoder=CLIP-L, Training Strategy=Video-trained2024.1158.8