Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
Affiliation:
3
0
5
4
LLM routing models can achieve higher task success and drastically cut costs by learning from realized responses, even when routing decisions are made before the response is known.
A simple training framework boosts pixel-level tampering detection performance in VLMs by over 26%, showcasing the power of balanced sampling and late-injection strategies.
Language agents can achieve more diverse and effective self-reflection by encoding cross-sample reflection patterns directly into model parameters, leading to significant performance gains in reasoning tasks.