Good Papers

Showing Continual learning Show all papers

67%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026School of Vehicle and Mobility, TsinghuaDidi International Business GrouDIDI GlobalU Science and Technology BeijingContinual learning

Past, Future, All at Once: Breaking Stability-Plasticity Dilemma via Post-hoc JANUS Rectification

Zhilong Zheng, Letian Tao, Yang Guan, Yujie Yang and 6 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
2/20 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: 2 of 20 reviewers recommend it
lenient 1/5
medium 1/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026MITMassachusetts Institute of TechnContinual learning

When to Adopt Model Updates

Aspen Hopkins, Isabella Struckman, Hedi Driss, Aleksander Madry

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
80%Must read
?Must readVote to see the score
NeurIPS 2026Nanyang TechnologicalTulaneContinual learning

EVA-0: Test-Time Model Evolution with Only Two Forward Passes per Sample

EVA-0 achieves test-time adaptation with only two forward passes per sample by using scale-invariant loss, anchor-guided optimization, and symmetric perturbation to avoid backpropagation. It outperforms BP-based DeYO and BP-free FOA on ImageNet-C with ViT-Base while running 14x faster than FOA.

Guohao Chen, Shuaicheng Niu, Geng Li, Yunbei Zhang and 3 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · 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