Search papers, labs, and topics across Lattice.
3
0
3
0
Extensive offline evaluation, human calibration, and online A/B tests show that SARA-7B generates more specific, polarity-consistent, and grounded rationales than strong MLLM baselines, while SARA-Ranker improves engagement and reduces negative feedback in production.
Non-monotonic performance in experimental trajectories reveals that later rounds can sometimes undermine earlier successes, challenging conventional assumptions in industrial ML research.
Behavior-derived rewards enable MLLMs to generate effective recommendations without user-specific data at inference, outperforming traditional methods.
