togethercomputer/Aurora-Spec-Qwen3-Coder-Next-FP8
Text Generation • 0.5B • Updated • 122 • 20
Jisen Li
mtilyjason
·
AI & ML interests
Finetuning, multimodal, quantization, agents
Recent Activity
submitted a paper 12 days ago
Multi-Turn Agentic Scientific Literature Search via Workflow Induction authored a paper 13 days ago
When RL Meets Adaptive Speculative Training: A Unified Training-Serving System authored a paper 13 days ago
SAW-INT4: System-Aware 4-Bit KV-Cache Quantization for Real-World LLM ServingOrganizations
liked a
model 5 months ago