Good Papers

Showing papers from Telecom Paris Show all papers

78%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026Télécom ParisTélecom ParisTelecom ParisFairness & bias

A Comprehensive View of Fairness through Distributional Stability

Reframing fairness as distributional stability under protected-group shifts unifies classical fairness notions via Lipschitz constants and yields a second-order cone program with uniform test-time guarantees.

Gayane Taturyan, Charlotte Laclau, Stephan Clémençon

Paris Poster Session 6, Fri, Dec 11, 2:30 PM–4:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet
11/20 AI panelreviewers recommend it

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.

AI panel: 11 of 20 reviewers recommend it
lenient 4/5
medium 6/10
strict 1/5
70%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026Telecom ParisTélécom ParisTechLearning theory

Beyond Kemeny Medians: Consensus Ranking Distributions. Definition, Properties and Statistical Learning

Consensus ranking distributions approximate ranking distributions via sparse Dirichlet mixtures with optimal Kendall τ distortion expressed through pairwise probabilities, enabling efficient tree-structured statistical learning.

Stephan Clémençon, Ekhine Irurozki

Paris Poster Session 2, Wed, Dec 9, 5:00 PM–7:00 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet
4/20 AI panelreviewers recommend it

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.

AI panel: 4 of 20 reviewers recommend it
lenient 1/5
medium 2/10
strict 1/5
83%Must read
?Must readVote to see the score
NeurIPS 2026Institut Polytechnique de ParisTelecom ParisTokenization

Effective Context in Transformers: An Analysis of Fragmentation and Tokenization

Smaller units can worsen prediction via fragmentation despite larger windows, while greedy tokenization extends effective context via compression, yielding an information-theoretic framework for representation choices.

Amirmehdi Jafari Fesharaki, Mohammadamin Rami, Aslan Tchamkerten

Paris Poster Session 1, Wed, Dec 9, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet
13/20 AI panelreviewers recommend it

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.

AI panel: 13 of 20 reviewers recommend it
lenient 5/5
medium 6/10
strict 2/5
70%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026Télécom ParisTechTélécom ParisTelecom ParisMulti-agent LLM systems

Decentralized Ranking Aggregation via Gossip: Convergence and Robustness

Gossip algorithms enable decentralized ranking aggregation via local peer interactions, yielding global consensus without central authority despite corrupted nodes and distributed preferences.

Kerrian Le Caillec, Anna van Elst, Igor Colin, Stephan Clémençon

Paris Poster Session 4, Thu, Dec 10, 5:30 PM–7:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet
4/20 AI panelreviewers recommend it

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.

AI panel: 4 of 20 reviewers recommend it
lenient 3/5
medium 1/10
strict 0/5