Article
21
Hritik Bansal
hbXNov
AI & ML interests
Multimodal | LLM
Organizations
Articles 2
Article
4
Introducing ConTextual: How well can your Multimodal model jointly reason over text and image in text-rich scenes?
models 53
hbXNov/Qwen3-VL-2B-Instruct-HoneyBee
2B • Updated • 16 • 4
hbXNov/lavida-llada-reason
8B • Updated • 2.37k • 2
hbXNov/hero-reason-ckpt-ep2
8B • Updated • 9
hbXNov/vlrethinker-full-ep5
8B • Updated • 4
hbXNov/vlrethinker-partial-ep5
8B • Updated • 3
hbXNov/llada_sft_rethinker_partial_2048
8B • Updated • 2
hbXNov/llada_sft_openvlthinker2_sft1_2048
8B • Updated • 3
hbXNov/LLaDA-8B-Instruct-mlp2x_gelu-pretrain_blip558k_plain_e3
Updated • 4
hbXNov/LLaDA-8B-Instruct-mlp2x_gelu-pretrain_blip558_v4-cont_200k_openllavanext_allava_gpt4omini
8B • Updated • 3
hbXNov/LLaDA-8B-Instruct-mlp2x_gelu-pretrain_blip558_v4-cont_lr_8e-5
8B • Updated • 3
datasets 79
hbXNov/HoneyBee_Processed
Preview • Updated • 21 • 1
hbXNov/musr_input_target
Viewer • Updated • 756 • 26
hbXNov/dynamath_mini
Viewer • Updated • 1k • 20
hbXNov/MATHVERSE_NUMERIC_OR_CHOICE_ANSWER
Viewer • Updated • 788 • 39
hbXNov/lavida-reason-data
Viewer • Updated • 19.2k • 19 • 3
hbXNov/virl39k_vlrethinker7b
Viewer • Updated • 13.9k • 28
hbXNov/virl39k_reasoning
Viewer • Updated • 1.95k • 228
hbXNov/allava_subset_200k_mini
Viewer • Updated • 39.9k • 16
hbXNov/llava_next_raw_format_processed
Updated • 16
hbXNov/llama_3p3_70b_math_train_gpt4o_verify_all_train
Viewer • Updated • 28.1k • 39