Showing papers from The University of Warwick Show all papers
Paris Poster Session 2, Wed, Dec 9, 5:00 PM–7:00 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.
Policy-gradient dynamics with partner selection are solved analytically, proving population variance is necessary for cooperation and deriving conditions for a stationary cooperative distribution.
Sydney Poster Session 1, Tue, Dec 8, 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.
SCDBench benchmarks LLM smart-contract decompilers on 600 real contracts via semantic replay, finding even top models perfectly recover only 42 and same-model repair substantially helps.
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.
SKMD introduces symmetry-aware interacting-particle dynamics for active MLIP learning that preserves Boltzmann sampling, yielding faster convergence with fewer training iterations.
Atlanta Poster Session 1, Wed, Dec 9, 10:00 AM–1:00 PM, Hall C1 · 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.
The Nanotechnology Molecular Optimization benchmark replaces proxy drug metrics with quantum simulations for nanomaterials, showing simple methods outperform advanced ones and revealing new structural motifs.
Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 5 on Hugging Face · Code ★ 2
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.
EoupCT estimates unknown pre-training gradients via learnable pseudo-data prompts and orthogonalizes updates to preserve general knowledge during continual LLM fine-tuning.
Sydney Poster Session 2, Tue, Dec 8, 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.
Multivariate Kernel Score yields geometry-adapted conformal regions via anisotropic MMD, guaranteeing finite-sample coverage with dimension-free rates and smaller volumes than ellipsoidal baselines.
Sydney Poster Session 2, Tue, Dec 8, 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.