Search papers, labs, and topics across Lattice.
Affiliation:
4
0
7
5
Current LLMs falter in complex rule-centered reasoning, with top models only reaching half of the potential performance on a new benchmark.
Real-time emotion predictions can be made more reliable by selectively invoking multimodal reasoning only when necessary, improving accuracy without sacrificing speed.
LLMs can now dynamically re-attend to procedural rules, boosting their reasoning accuracy by up to 19 points in complex scenarios.
Bridging the gap between proprietary and open-source models, MAPD achieves up to 44.4% success in QA tasks by transforming sparse RL signals into dense distillation guidance.
