Vlad Kostoglodov

vkost's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 21 days ago

Error-Free Linear Attention is a Free Lunch: Exact Solution from Continuous-Time Dynamics

Paper • 2512.12602 • Published 23 days ago • 41

upvoted a paper about 2 months ago

TiDAR: Think in Diffusion, Talk in Autoregression

Paper • 2511.08923 • Published Nov 12, 2025 • 119

upvoted 2 papers 4 months ago

Set Block Decoding is a Language Model Inference Accelerator

Paper • 2509.04185 • Published Sep 4, 2025 • 53

UltraMemV2: Memory Networks Scaling to 120B Parameters with Superior Long-Context Learning

Paper • 2508.18756 • Published Aug 26, 2025 • 36

upvoted a paper 8 months ago

Grokking in the Wild: Data Augmentation for Real-World Multi-Hop Reasoning with Transformers

Paper • 2504.20752 • Published Apr 29, 2025 • 92

upvoted 2 papers 10 months ago

Forgetting Transformer: Softmax Attention with a Forget Gate

Paper • 2503.02130 • Published Mar 3, 2025 • 32

SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution

Paper • 2502.18449 • Published Feb 25, 2025 • 75

upvoted 2 papers about 1 year ago

Training Large Language Models to Reason in a Continuous Latent Space

Paper • 2412.06769 • Published Dec 9, 2024 • 92

Breaking the Memory Barrier: Near Infinite Batch Size Scaling for Contrastive Loss

Paper • 2410.17243 • Published Oct 22, 2024 • 92

upvoted a collection over 1 year ago

Llama 3.2

Collection

This collection hosts the transformers and original repos of the Llama 3.2 and Llama Guard 3 • 15 items • Updated Dec 6, 2024 • 649

upvoted an article over 1 year ago

view article

Article

The LASER technique: Evaluating SVD compression

• 

Apr 4, 2024

•

8

upvoted a paper over 1 year ago

nabla^2DFT: A Universal Quantum Chemistry Dataset of Drug-Like Molecules and a Benchmark for Neural Network Potentials

Paper • 2406.14347 • Published Jun 20, 2024 • 102