Good Papers

Showing papers from Academia Sinica Show all papers

45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026U Illinois at ChicagoU Tennessee, KnoxvilleGeorge MasonAcademia SinicaSun Yat-senData curation

Subdata Selection: A Unified Framework for Optimal Selection and Statistical Efficiency Assessment

Min Yang, Wei Zheng, John Stufken, Ming-Chung Chang 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
69%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026Academia SinicaWatermarking & AI-text detection

Face Deepfake-aware Recovery via Semantic-driven Facial Representation-based Watermarking

Yuan-Chih Chen, Chun-Shien Lu

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

– ReadersNo votes yet
3/20 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: 3 of 20 reviewers recommend it
lenient 2/5
medium 1/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026Academia SinicaDeep learning theory

Compositional Generalization Certificates via the Van Kampen Theorem

Karen Sargsyan

Sydney Poster Session 4, Wed, Dec 9, 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 2026National Cheng KungAcademia SinicaRepresentation & contrastive learning

Distance-Dependent Connectivity Shapes Continual Learning by Synaptic-Resource-Delimited Separation of Neural Dynamics

CHIU-CHANG CHENG, Ching-Lung Hsu, Ya-Ning Chang, Chao-Hung Wang

Sydney Poster Session 6, Thu, Dec 10, 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 2026NVIDIANational TaiwanYuan ZeAltai StateAcademia SinicaSpeech enhancement

Rethinking Training Targets, Architectures and Data Quality for Universal Speech Enhancement

Time-shifted anechoic targets, a two-stage distortion-perception framework, and curated data improve universal speech enhancement and achieve state-of-the-art results.

Szu-Wei Fu, Rong Chao, Xuesong Yang, Sung-Feng Huang and 5 more

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

– 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 9/10
strict 1/5
88%Must read
?Must readVote to see the score
NeurIPS 2026National TaiwanInternational Business MachinesIBM ResearchAcademia SinicaInstruction tuning

Learning Rate Matters: Vanilla LoRA May Suffice for LLM Fine-tuning

Vanilla LoRA matches variant performance within 1-2% when learning rates are tuned, and differing optimal rates stem from Hessian eigenvalue variations.

Yu-Ang Lee, Ching-Yun Ko, Pin-Yu Chen, Mi-Yen Yeh

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 7 on Hugging Face · Code ★ 13

– 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 9/10
strict 2/5
74%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026ETH ZürichAcademia SinicaETH ZurichLLM pretraining & scaling laws

Support Before Frequency in Discrete Diffusion

Discrete diffusion models learn data support before frequencies because reverse edits scale by validity first and coefficients second; absorbing diffusion prioritizes validity-improving moves over uniform diffusion's trichotomy.

Adrian Müller, Antoine Gonon, Zebang Shen, Ya-Ping Hsieh and 1 more

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

– 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 2/5
medium 5/10
strict 2/5