Models trained for LLM to VLM workshop : https://logeshumapathi.com/VLM_workshop/
Logesh Kumar umapathi PRO
infinitylogesh
AI & ML interests
NLP - Healthcare , Information retrieval , Open domain question answering.
Recent Activity
authored a paper about 2 hours ago
Ambient @ EgoProactive 2026 : Proactive Egocentric Assistance with Visually Grounded Supervision authored a paper about 2 hours ago
Ambient @ EgoLongQA 2026: Distilling Long-Video perception into a Sub-2B Model submitted a paper about 3 hours ago
Ambient @ EgoProactive 2026 : Proactive Egocentric Assistance with Visually Grounded SupervisionOrganizations
models 32
infinitylogesh/watercolour-painting-grpo-v1
Updated • 7 • 1
infinitylogesh/qwen35-4b-videomme-grpo
Updated
infinitylogesh/vlm-workshop-qwen3.5-4b-sft
Text Generation • Updated • 8
infinitylogesh/vlm-workshop-qwen3.5-0.8b-sdft-1k
Text Generation • Updated • 6
infinitylogesh/vlm-workshop-qwen3.5-0.8b-sdft
Text Generation • Updated • 4
infinitylogesh/vlm-workshop-qwen3.5-0.8b-distilled-nowarmup
Text Generation • Updated • 5
infinitylogesh/vlm-workshop-qwen3.5-0.8b-distilled
Text Generation • Updated • 6
infinitylogesh/vlm-workshop-gemma4-e2b-grpo-think
Text Generation • Updated • 5
infinitylogesh/nanovlm-speedrun-checkpoints
Updated
infinitylogesh/nanoVLM
Image-Text-to-Text • 0.2B • Updated • 7
datasets 11
infinitylogesh/Video-MME-xLong
Viewer • Updated • 51 • 4
infinitylogesh/svg-rl-dataset
Viewer • Updated • 2.53k • 37
infinitylogesh/math_12k_gt
Viewer • Updated • 12.5k • 17
infinitylogesh/math_12k
Viewer • Updated • 12.5k • 22
infinitylogesh/yupp-svg-20251204_rendered
Viewer • Updated • 3.53k • 5
infinitylogesh/book_dataset_no_mem_token_gte_largev1_5_M512_C1024_1B
Viewer • Updated • 606k • 44
infinitylogesh/math_12k_srt_single_stage
Viewer • Updated • 12.5k • 14
infinitylogesh/math_12k_srt_splits
Viewer • Updated • 13.5k • 33
infinitylogesh/eval_grab_toy_car_smolvla
Viewer • Updated • 3.23k • 21
infinitylogesh/eval_grab_toy_car_act
Viewer • Updated • 1.2k • 37