Hybrid Token-Efficient Routing Agent
How I built TOKENMAN for AMD Developer Hackathon ACT II: a deterministic, local-model, and Fireworks routing agent that climbed from 6,101 counted tokens to zero.
July 22, 2026
Autoresearch
Showing 3 of 15 posts tagged Autoresearch
All15AlignmentAutoresearchICMLImage GenerationMechanistic InterpretabilityMulti-Agent SystemsPre-TrainingRLSFTSparse AutoencodersTrustworthy AI
[ICML ’26 Effort] Efficient Qwen: Making Qwen3.5-4B Faster on a Single A10G
My ICML 2026 AdaptFM effort to optimize Qwen3.5-4B for low-latency inference on a single NVIDIA A10G through 100+ runtime, compiler, and quantization experiments.
June 30, 2026
Parameter Golf: My OpenAI Model Craft Experiment
I didn't come close to the Parameter Golf leaderboard, but I still had a lot of fun running scattered H100 experiments on Modal, hunting tiny BPB improvements while watching ideas collapse against artifact size limits, and figuring out the hard way why squeezing a capable model into 16 MB is trickier than it sounds.
May 4, 2026
July 22, 2026reads
Hybrid Token-Efficient Routing Agent
June 30, 2026reads
[ICML ’26 Effort] Efficient Qwen: Making Qwen3.5-4B Faster on a Single A10G
May 4, 2026reads