Athrael Soju PRO
athrael-soju
AI & ML interests
Yes
Recent Activity
liked a model 2 days ago
Alibaba-NLP/gte-multilingual-base updated a model 2 days ago
athrael-soju/VultronRetrieverPrime-Qwen3.5-8B updated a collection 3 days ago
Live ModelsOrganizations
None yet
Visual document retrieval models on Qwen3.5 backbone. ViDoRe v3 leaderboard competitors, 128-dim multi-vector.
-
Spatially-Grounded Document Retrieval via Patch-to-Region Relevance Propagation
Paper • 2512.02660 • Published -
Architecture-Aware LLM Inference Optimization on AMD Instinct GPUs: A Comprehensive Benchmark and Deployment Study
Paper • 2603.10031 • Published -
Hydra: Unifying Document Retrieval and Generation in a Single Vision-Language Model
Paper • 2603.28554 • Published
Dual-head VLM: ColBERT retrieval + autoregressive generation by toggling one LoRA. Canonical 4B + 0.8B, omni proof-of-concept, baselines.
Visual document retrieval models on Qwen3.5 backbone. ViDoRe v3 leaderboard competitors, 128-dim multi-vector.
ColBERT-style late-interaction visual document retrieval adapters built on Google Gemma-4 (E2B and E4B variants).
-
Spatially-Grounded Document Retrieval via Patch-to-Region Relevance Propagation
Paper • 2512.02660 • Published -
Architecture-Aware LLM Inference Optimization on AMD Instinct GPUs: A Comprehensive Benchmark and Deployment Study
Paper • 2603.10031 • Published -
Hydra: Unifying Document Retrieval and Generation in a Single Vision-Language Model
Paper • 2603.28554 • Published