Good Papers

Showing papers from McGill University / Mila Show all papers

45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026McGill University/MilaMcGill University, Mila, Paris-SMcGill University & Quebec AILLS and MILA | CNRS Paris-SaclMila / McGillLLM pretraining & scaling laws

From Infrastructure to Interface, the AI Value Chain Drives LLM Homogenization

Khaoula Chehbouni, Cléa Chataigner, Prakhar Ganesh, Pablo Piantanida and 2 more

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

– ReadersNo votes yet
0/20 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: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026McGill University, Mila, Paris-SILLS and MILA | CNRS Paris-SaclMcGill University / MilaLLM evaluation & benchmarks

Auditing is not Evaluating: LLM Audit Requires Dynamic, Contextual, Budget-aware and Reliable Evidence

Cléa Chataigner, Pablo Piantanida, Golnoosh Farnadi

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

– ReadersNo votes yet
1/20 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: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026SpotlightMILA / McGillEPFLETHZ - ETH ZurichApertus ETH Zürich McGill University / MilaVision-language models

Scaling Laws for Multimodal Data Mixtures

Aditi Khandelwal, Ayush Kumar Tarun, Yixuan Xu, Imanol Schlag and 4 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 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: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
88%Must read
?Must readVote to see the score
NeurIPS 2026Mila and McGillMcGill University / MilaMila / McGillElement AI, a ServiceNow companyLLM evaluation & benchmarks

Forecasting Downstream Performance of LLMs With Proxy Metrics

Aggregating token-level statistics over expert solutions yields proxy metrics that outperform loss-based baselines for model selection, data selection, and training-time forecasting.

Arkil Patel, Siva Reddy, Marius Mosbach, Dzmitry Bahdanau

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 12 on Hugging Face · Code ★ 11

– 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 5/5
medium 8/10
strict 2/5
76%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026McGill University / MILAGoogle DeepmindConcordiaÉcole de technologie supérieure,McGill University / MilaLLM evaluation & benchmarks

IDEAFix: Evaluation Framework for Creative Defixation Prompting in LLMs

IDEAFix evaluates LLM divergent thinking via controlled design scenarios and defixation prompts, showing task formulation and simple prompting boost originality but homogenization persists.

Florian Carichon, Soumya Sharma, Meaghan J. Girard, Romain Rampa and 1 more

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

– ReadersNo votes yet
10/20 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: 10 of 20 reviewers recommend it
lenient 4/5
medium 6/10
strict 0/5