Showing papers from Uppsala University Show all papers
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.
Paris Poster Session 1, Wed, Dec 9, 12:30 PM–2:30 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.
Self-rewarding sequential Monte Carlo improves masked diffusion language model sampling via trajectory-level confidence weights across parallel particles, boosting quality without training.
Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 5 on Hugging Face · Code ★ 16
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.
MARS fine-tunes autoregressive models to predict multiple tokens per forward pass without architectural changes, matching baseline accuracy while achieving 1.5-1.7x throughput and adjustable real-time speed via confidence thresholds.
Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 36 on Hugging Face · Code ★ 30
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.
Noiseless inverse optimization achieves tight O(d/T) generalization and regret bounds, with parameter-free algorithms matching adversarial lower bounds.
Paris Poster Session 1, Wed, Dec 9, 12:30 PM–2:30 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.
Anytime-valid conformal risk control extends error guarantees to grow with calibration data at arbitrary times, remains tight under distribution shift, and works in practice.
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.
Multi-block DC programming defines a broader structured nonconvex class with polynomial decompositions and constructive formulations for deep networks, plus convergent batch and stochastic algorithms.
Paris Poster Session 3, Thu, Dec 10, 12:30 PM–2:30 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.