Search papers, labs, and topics across Lattice.
University of Wisconsin-Madison
3
0
9
LVLMs can now better judge their own vision-based answers, thanks to a new method that focuses on how much they actually "see" in the image.
Forget tweaking prompts – understanding how retrieved context warps an LLM's hidden states is the key to unlocking better RAG performance.
Ditch reward maximization: a new RL objective learns the *distribution* of reasoning advantages, boosting LLM accuracy and diversity without extra training costs.
