Showing papers from University of Roma "La Sapienza" Show all papers
Paris Poster Session 4, Thu, Dec 10, 5:30 PM–7:30 PM, Paris Poster Hall · Published 2026
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
Paris Poster Session 5, Fri, Dec 11, 11:30 AM–1:30 PM, Paris Poster Hall · Published 2026
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
Poetic jailbreaks bypass LLM safety not via specific devices or format confusion, but through accumulated stylistic irregularities altering processing independently of harm detection, requiring style-aware defenses.
Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
HOPSE replaces higher-order message passing with Hasse-graph encodings to scale linearly on combinatorial domains while matching or exceeding state-of-the-art performance.
Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
DashAttention uses adaptive α-entmax to select variable key-value blocks per query, enabling fully differentiable hierarchical sparse attention that matches full-attention accuracy at 75% sparsity with faster inference than FlashAttention-3.
Paris Poster Session 6, Fri, Dec 11, 2:30 PM–4:30 PM, Paris Poster Hall · Published 2026
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.