Good Papers

Showing papers from INRIA - Ecole Normale Superieure Show all papers

80%Must read
?Must readVote to see the score
NeurIPS 2026Paris Dauphine - PSLCentrale SupélecINRIA - Ecole Normale SuperieureEPFLUniversité Paris DauphineAdversarial robustness

Frame the adversary: a structure-aware attack methodology

A structure-aware optimization framework crafts frequency adversarial attacks via weighted projections onto structured non-orthogonal transform constraints, yielding effective cross-architecture vulnerabilities.

Vicky Kouni, Stelios Perrakis, Francis Bach, Pascal Frossard and 1 more

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

– ReadersNo votes yet
12/20 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: 12 of 20 reviewers recommend it
lenient 5/5
medium 7/10
strict 0/5
70%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026INRIA - Ecole Normale SuperieureBayesian & probabilistic methods

A Spectral Framework for Closed-Form Relative Density Estimation

A spectral framework estimates relative log-densities via closed-form chi-squared least-squares, yielding explicit divergence and potential estimators with convergence guarantees.

Francis Bach

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 1/5
medium 3/10
strict 0/5
88%Must read
?Must readVote to see the score
NeurIPS 2026Meta / Ecole Normale SupérieureU California, San DiegoINRIA - Ecole Normale SuperieureFacebook AI ResearchMeta / FAIRRL for LLMs

Don’t Let Gains FADE: Breaking Down Policy Gradient Weights in RL

A framework decomposes RL advantage functions into gradient mass axes, showing trade-offs shift during training and motivating FADE, which adapts weights dynamically to accelerate convergence and improve accuracy-diversity trade-offs.

Juliette Decugis, Sean O'Brien, Francis Bach, Gabriel Synnaeve and 1 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
15/20 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: 15 of 20 reviewers recommend it
lenient 4/5
medium 10/10
strict 1/5
70%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026Inria - ENSU California, BerkeleyINRIA - Ecole Normale SuperieureOptimization

Super-Level-Set Regression: Conditional Quantiles via Volume Minimization

Super-level-set regression directly optimizes minimum-volume prediction regions via geometric optimization, bypassing full conditional density estimation to capture complex multimodal conditional structures.

Sacha Braun, Michael Jordan, Francis Bach

Paris Poster Session 5, Fri, Dec 11, 11:30 AM–1:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet
5/20 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: 5 of 20 reviewers recommend it
lenient 2/5
medium 3/10
strict 0/5
91%Must read
?Must readVote to see the score
NeurIPS 2026Inria - École Normale SupérieureNVIDIAINRIA - Ecole Normale SuperieureU California, BerkeleyUncertainty & calibration

CalArena: A Large Scale Post-Hoc Calibration Benchmark

CalArena benchmarks nearly 2000 post-hoc calibration experiments, finding smooth methods outperform binning and multiclass-specific designs are essential.

Eugène Berta, David Holzmüller, Francis Bach, Michael Jordan

Paris Poster Session 3, Thu, Dec 10, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet
17/20 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: 17 of 20 reviewers recommend it
lenient 5/5
medium 9/10
strict 3/5
86%Must read
?Must readVote to see the score
NeurIPS 2026INRIAINRIA - Ecole Normale SuperieureU California, BerkeleyRL for LLMs

Explaining and Preventing Alignment Collapse in Iterative RLHF

Iterative RLHF ignores policy influence on reward-model updates, causing alignment collapse via exploited blind spots; foresighted optimization restores this term to prevent collapse.

Etienne Gauthier, Francis Bach, Michael Jordan

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
14/20 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: 14 of 20 reviewers recommend it
lenient 5/5
medium 7/10
strict 2/5