Search papers, labs, and topics across Lattice.
Westlake University
4
0
8
Trustworthy medical agents could evolve autonomously through interactive learning, rather than relying solely on parameter scaling.
KAT-Coder-V2.5 outperforms existing models in agentic tool-use, showcasing a new paradigm for autonomous coding agents within executable environments.
LLM-generated test suites are shockingly bad at catching even simple code mutations, with even the best models failing to detect over 60% of them.
Attention Sink, where Transformers fixate on seemingly irrelevant tokens, is more than just a quirk – it's a fundamental challenge impacting training, inference, and even causing hallucinations, demanding a systematic approach to understanding and mitigating its effects.
