-
SyncDreamer: Generating Multiview-consistent Images from a Single-view Image
Paper • 2309.03453 • Published • 12 -
TeCH: Text-guided Reconstruction of Lifelike Clothed Humans
Paper • 2308.08545 • Published • 33 -
Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Model
Paper • 2311.06214 • Published • 29
sambit sekhar
sam2ai
AI & ML interests
Recsys, text2image, audio2image, transformer, ddpm, LLM
Organizations
Collections
22
-
Large Language Models as Optimizers
Paper • 2309.03409 • Published • 75 -
One Wide Feedforward is All You Need
Paper • 2309.01826 • Published • 31 -
Self-Alignment with Instruction Backtranslation
Paper • 2308.06259 • Published • 41 -
Shepherd: A Critic for Language Model Generation
Paper • 2308.04592 • Published • 30
Papers
1
spaces
13
models
66
sam2ai/odia_token_test
Updated
sam2ai/odia-paligemma-2b-9900-v1.1
Updated
•
1
sam2ai/odia-paligemma-2b-5000-v1.0
Updated
•
8
sam2ai/paligeema_hindi_vgqa_v1.1
Updated
•
3
sam2ai/paligeema_hindi_vgqa_v1.0
Updated
•
3
sam2ai/llama_wat_2024_hindi
Updated
•
3
sam2ai/paligemma_3b_vg_hindi_v0.1
Updated
•
1
sam2ai/paligemma_hindi_vg_3b
Updated
•
3
sam2ai/llama3.1_odia_8b_lora_sft_v1.2
Updated
•
1
sam2ai/llama3.1_odia_8b_gpu_sft_v1.2
Text Generation
•
Updated
•
7
datasets
21
sam2ai/hindi_vgqa_v1.0
Viewer
•
Updated
•
28k
•
39
sam2ai/hindi_translation_wat2024
Viewer
•
Updated
•
116k
•
34
sam2ai/hindi_vg_wat
Viewer
•
Updated
•
995
•
38
sam2ai/test_image
Viewer
•
Updated
•
998
•
16
sam2ai/MLLM_odia_llava_500
Viewer
•
Updated
•
500
•
32
sam2ai/MLLM_odia_llava_100
Viewer
•
Updated
•
100
•
35
sam2ai/MLLM_hindi_llava_50
Viewer
•
Updated
•
50
•
32
sam2ai/MLLM_hindi_50
Updated
•
5
sam2ai/openwebtext-10k
Viewer
•
Updated
•
10k
•
49
sam2ai/hindi_hellaswag_mini
Viewer
•
Updated
•
50
•
37