Search papers, labs, and topics across Lattice.
5
0
10
Low-probability tokens can be the key to distinguishing AI-generated text from human writing, revealing hidden distributional discrepancies that traditional methods overlook.
Forget monolithic models: a lightweight RL policy can dynamically orchestrate ensembles of frozen experts to outperform GPT-5 and Gemini-2.5-Pro on multimodal tasks, even generalizing to unseen models and skills.
Current omnimodal models may excel in perceptual tasks but fundamentally misunderstand music theory, exposing critical reasoning flaws.
Current multimodal LLMs struggle with guideline-constrained clinical reasoning, but a simple multi-agent framework can significantly boost their performance on real-world lung cancer diagnosis and treatment.
By injecting symbolic reasoning into vision-language-action models, NS-VLA achieves remarkable gains in data efficiency and generalization for robotic manipulation.
