Vladimir

vstiff

·

AI & ML interests

None yet

Recent Activity

new activity about 3 hours ago

FINAL-Bench/Darwin-180B-RSI:Does it still hallucinate?

new activity about 4 hours ago

Qwen/Qwen3.8-Flash-Next:Strix Halo teaser: 88 GB Qwen3.8-Flash-Next (512 experts) at 42–44 tok/s on a Radeon 8060S — what we've been cooking in our llama.cpp fork

upvoted a paper 1 day ago

Disaggregated Quantization: Specializing LLM Prefill and Decode

View all activity

Organizations

None yet

upvoted a paper 1 day ago

Disaggregated Quantization: Specializing LLM Prefill and Decode

Paper • 2609.26333 • Published 8 days ago • 65

upvoted 2 papers 21 days ago

Online Draft Co-Training for Speculative Decoding in Large-Scale, Long-Context RL Post-Training

Paper • 2609.07108 • Published 23 days ago • 36

Unlocking Lossless Speedups in LLMs via Discrete Diffusion

Paper • 2609.04010 • Published 27 days ago • 114

upvoted 2 papers about 2 months ago

Addressable Memory for Video World Models

Paper • 2608.07408 • Published Aug 7 • 16

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA

Paper • 2608.09819 • Published Aug 10 • 178

upvoted 3 papers 2 months ago

EvoEmbedding: Evolvable Representations for Long-Context Retrieval and Agentic Memory

Paper • 2606.21649 • Published Jun 19 • 36

Gemma 4 Technical Report

Paper • 2607.02770 • Published Jul 2 • 84

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation

Paper • 2607.21553 • Published Jul 23 • 40