arXiv introduces Visual Token Routing for efficient computer-use agents
VTR matches full-resolution performance on OSWorld and CUA-World using 2.5-5.8x fewer visual tokens, reducing inference cost by up to 3.3x.
Stories per day · 30 days
3 stories, newest first · one card per story
Stories tagged #llm-efficiency
Frontier LLMs maintain accuracy with short contexts only
Compaction shows minimal accuracy loss on long-horizon tasks, suggesting semantic state space models.
A*-Thought-V2: Efficient Latent Reasoning via Geometric Dynamics of LLM
A*-Thought-V2 compresses chain-of-thought into latent tokens using geometric hidden-state dynamics, cutting computation while improving accuracy on Qwen models.