Search papers, labs, and topics across Lattice.
3
0
9
0
By prioritizing gradient direction in token optimization and using a two-stage loss, TAO-Attack achieves near-perfect jailbreak success rates against multiple LLMs, exposing critical vulnerabilities in current safety alignments.
Clinical question answering gets a boost: TARSE aligns language model reasoning with clinically valid logic by retrieving and adapting to relevant skills and prior reasoning experiences at test time.
Overcome underwater visibility challenges and improve fish detection accuracy by explicitly modeling and compensating for frequency-specific information loss due to wavelength-dependent absorption and turbidity.
