Search papers, labs, and topics across Lattice.
7
0
10
5
FaithEyes reveals that self-judging mechanisms in VLMs can drastically improve tool use fidelity, leading to more reliable multimodal reasoning.
Tailoring feedback to individual student abilities could revolutionize how automated essay scoring systems support personalized learning.
All tested coding agents fail within 5-6 turns, but providing feedback can boost their performance by up to 12x, revealing critical insights into agent design.
A new dataset of 1,111 transvaginal ultrasound images with detailed annotations finally enables AI-powered diagnosis of Cesarean Scar Defects, a condition frequently missed by sonographers.
Multi-agent collaboration and retrieval augmentation can overcome the limitations of static parametric memory in LLMs, enabling more nuanced and accurate multimodal emotion recognition.
LLMs working as specialized teams dramatically outperform solo LLMs on complex, multi-step reasoning tasks, suggesting a new paradigm for LLM collaboration.
You can get surprisingly reliable multi-turn LLM agents by having a small, open-source critic supervise a powerful, fixed LLM actor *during* the conversation.
