Good Papers

Showing papers from Hokkaido University Show all papers

70%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026HokkaidoMBZUAI / RIKEN AIPBandits & online learning

An Efficient Algorithm for Thresholding Monte Carlo Tree Search

A Track-and-Stop algorithm solves thresholding Monte Carlo Tree Search with asymptotically optimal sample complexity, and a ratio-based D-Tracking modification improves empirical efficiency and reduces per-round computation to logarithmic time.

Shoma Nameki, Atsuyoshi Nakamura, Junpei Komiyama, Koji Tabata

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · 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 2/5
medium 2/10
strict 0/5
80%Must read
?Must readVote to see the score
NeurIPS 2026WestlakeShandong University of Science aHokkaidoShanghai Jiao TongRIKENImage recognition

OFBD: Object-Focused Background Debiasing for Long-Tailed Learning

OFBD identifies background-biased representations as a cause of long-tailed degradation and proposes foreground-guided CutMix and background-guided feature rectification to improve accuracy and tail-class performance.

Shenghan Chen, Yiming Liu, Zhipeng Deng, Haolin Wang and 5 more

Sydney Poster Session 3, Wed, Dec 9, 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 4/5
medium 7/10
strict 1/5
78%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026Institute of Science TokyoHokkaidoSouthwest JiaotongRIKENThe University of Tokyo, RIKEN AMedical imaging

RAM-H1200: A Unified Evaluation and Dataset on Hand Radiographs for Rheumatoid Arthritis

RAM-H1200 introduces 1,200 annotated hand radiographs supporting unified bone segmentation, pixel-level erosion masks, and joint-level SvdH scoring, showing bone segmentation is mature but quantitative erosion analysis remains a major open challenge.

YANG SONGXIAO, Haolin Wang, Yao Fu, Junmu Peng and 8 more

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

– 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 5/5
medium 5/10
strict 1/5
88%Must read
?Must readVote to see the score
NeurIPS 2026HokkaidoHokkaido University A*STARImage recognition

Closed-Form Linear-Probe Dataset Distillation for Pre-trained Vision Models

CLP-DD distills synthetic datasets for frozen-feature linear probing via a closed-form kernel ridge solver, achieving near-state-of-the-art accuracy with roughly 14x faster training and far lower memory.

Bincheng Peng, Miki Haseyama, Guang Li, Ping Liu and 1 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 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 3/5
medium 9/10
strict 3/5
78%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026HokkaidoHokkaido University Model-based RL

Predictive but Not Plannable: RC-aux for Latent World Models

RC-aux improves latent world model planning by adding multi-horizon prediction and budget-conditioned reachability supervision to align latent spaces with long-horizon search.

Wenyuan Li, Guang Li, Keisuke Maeda, Takahiro Ogawa and 1 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · 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