When Agents Slow Down: Understanding LLM Agents' Test-Time Strategies via Elo-per-token Analysis Paper • 2609.15309 • Published 4 days ago • 12
FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution Paper • 2608.16157 • Published Aug 17 • 109
FrontierSmith: Synthesizing Open-Ended Coding Problems at Scale Paper • 2605.14445 • Published May 14 • 22
Combee: Scaling Prompt Learning for Self-Improving Language Model Agents Paper • 2604.04247 • Published Apr 5 • 32
SVG-EAR: Parameter-Free Linear Compensation for Sparse Video Generation via Error-aware Routing Paper • 2603.08982 • Published Mar 9 • 16
Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization Paper • 2602.02958 • Published Feb 3 • 35