Good Papers

Showing papers from MTS AI Show all papers

72%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026MTS AIMWS AIITMOPruning & sparsity

ROCKET: Rapid Optimization via Calibration-guided Knapsack-Enhanced Truncation for Efficient Model Compression

ROCKET is a training-free compression method using knapsack-based layer allocation and calibration-guided sparse factorization to cut model sizes 20-50% with minimal accuracy loss.

Ammar Ali, Baher Mohammad, Denis Makhov, Dmitriy Shopkhoev and 2 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 18 on Hugging Face · Code ★ 25

– ReadersNo votes yet
8/20 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: 8 of 20 reviewers recommend it
lenient 4/5
medium 4/10
strict 0/5
74%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026MWS AIMTS AIITMOEfficient inference & serving

COMPOT: Calibration-Optimized Matrix Procrustes Orthogonalization for Transformers Compression

COMPOT proposes training-free transformer compression via orthogonal dictionaries and closed-form sparse factorization with dynamic layer-wise budget allocation. It achieves superior quality-compression trade-offs versus low-rank and sparse baselines and integrates with quantization.

Denis Makhov, Dmitriy Shopkhoev, Magauiya Zhussip, Ammar Ali and 2 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 9 on Hugging Face

– ReadersNo votes yet
9/20 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: 9 of 20 reviewers recommend it
lenient 5/5
medium 4/10
strict 0/5
71%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026MWS AIMTS AIPruning & sparsity

GeoPair: Geometry-Preserving Cross-Layer Factorization for Training-Free Transformer Compression

GeoPair sequentially optimizes cross-layer weight pairings and shared-dictionary factorizations to preserve layer-specific activation geometry for training-free transformer compression, achieving state-of-the-art results.

Baher Mohammad, Ammar Ali, Stamatios Lefkimmiatis

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 17 on Hugging Face

– ReadersNo votes yet
7/20 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: 7 of 20 reviewers recommend it
lenient 2/5
medium 5/10
strict 0/5