BuiDoan's picture

BuiDoan

BuiDoan

·

AI & ML interests

None yet

Recent Activity

new activity 2 days ago

rahtml/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4:vLLM compatible

new activity 17 days ago

cyankiwi/Devstral-Small-2-24B-Instruct-2512-AWQ-4bit:Loading Mistral Models in vLLM

reacted to Kseniase's post with 👀 21 days ago

15 Outstanding Research Papers from NeurIPS 2025 NeurIPS 2025, as a premier annual event in machine learning and computational neuroscience, tackles major topics like the future of AI, current research, and the most difficult challenges. While we’re not attending this year, we’re closely following the updates and today we pull together a quick, easy-to-digest roundup of a few standout papers so you can jump in without getting overwhelmed. Here is a list of 15 papers from NeurIPS 2025, including 8 top research papers that received awards, along with 7 others that caught our attention: 1. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks → https://neurips.cc/virtual/2025/loc/san-diego/test-of-time/128328 Test of Time Award winner. Introduces the RPN, a small convnet that predicts objectness and boxes on shared features, enabling Faster R-CNN to share computation and run around 5 fps on a GPU 2. Artificial Hivemind: The Open-Ended Homogeneity of LMs (and Beyond) → https://neurips.cc/virtual/2025/loc/san-diego/poster/121421 Releases a huge open-ended prompt dataset, showing that LLMs often fall into an “artificial hivemind” – generate surprisingly similar answers – and measuring diversity collapse 3. Optimal Mistake Bounds for Transductive Online Learning → https://neurips.cc/virtual/2025/loc/san-diego/poster/119098 Settles a 30-year-old question by showing how much unlabeled data helps in online learning – it gives a precise quadratic advantage with tight matching bounds 4. Gated Attention for LLMs: Non-linearity, Sparsity, and Attention-Sink-Free → https://neurips.cc/virtual/2025/loc/san-diego/poster/120216 Demonstrates how gating actually affects attention: a simple sigmoid gate after Scaled Dot-Product Attention (SDPA) boosts performance, stability, and long-context behavior by adding useful nonlinearity and sparse modulation Read further below ⬇️ Also, subscribe to the Turing Post: https://www.turingpost.com/subscribe

View all activity

Organizations

liked a model 25 days ago

apple/CLaRa-7B-Instruct

Updated 16 days ago • 165

liked 2 models 26 days ago

mistralai/Ministral-3-14B-Base-2512

14B • Updated 7 days ago • 45.7k • 48

cyankiwi/Qwen3-Coder-30B-A3B-Instruct-AWQ-4bit

Text Generation • 5B • Updated 26 days ago • 197k • 30

liked 5 models about 1 month ago

nvidia/NVIDIA-Nemotron-Parse-v1.1

Image-Text-to-Text • Updated 12 days ago • 22.3k • 118

tencent/HunyuanOCR

Image-Text-to-Text • 1.0B • Updated 4 days ago • 897k • 690

eigen-ai-labs/eigen-banana-qwen-image-edit

Text-to-Image • Updated Nov 16 • 96 • 250

facebook/sam3

Mask Generation • 0.9B • Updated Nov 20 • 1.09M • 1.19k

baidu/ERNIE-4.5-VL-28B-A3B-Thinking

Image-Text-to-Text • 30B • Updated 4 days ago • 3.45k • 512

liked 6 models about 2 months ago

google/gemma-3-1b-it-qat-int4-unquantized

Text Generation • 1.0B • Updated Apr 15 • 1.23k • 12

moonshotai/Kimi-K2-Thinking

Text Generation • Updated Nov 8 • 396k • • 1.57k

BAAI/Emu3.5

Any-to-Any • 34B • Updated 3 days ago • 200 • 163

nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16

Image-Text-to-Text • 13B • Updated 25 days ago • 94.2k • 68

cyankiwi/Kimi-Linear-48B-A3B-Instruct-AWQ-4bit

9B • Updated about 1 month ago • 2.35k • 15

moonshotai/Kimi-Linear-48B-A3B-Instruct

Text Generation • 49B • Updated 12 days ago • 135k • 511

liked a Space about 2 months ago

The Smol Training Playbook

The secrets to building world-class LLMs

liked 5 models 2 months ago

allenai/olmOCR-2-7B-1025

Image-to-Text • 8B • Updated Oct 22 • 57.1k • 111

AITeamVN/Vietnamese_Embedding_v2

Sentence Similarity • 0.6B • Updated Jun 11 • 6.43k • • 9

nanonets/Nanonets-OCR2-3B

Image-Text-to-Text • 4B • Updated Oct 16 • 97.4k • 466

PaddlePaddle/PaddleOCR-VL

Image-Text-to-Text • 1.0B • Updated 17 days ago • 17.5k • 1.43k

deepseek-ai/DeepSeek-OCR

Image-Text-to-Text • 3B • Updated Nov 4 • 4.26M • 3k