Good Papers

Showing papers from KAIST AI Show all papers

45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026KAISTKorea Advanced Institute of ScieMila - Quebec Artificial IntelliU EdinburghUniversité de Montréal & MilDiffusion models

Aligning Few-Step Generative Model via Amortizing Sample-Based Variational Inference

Jaewoo Lee, Hyeongyu Kang, Dohyun Kim, Kyuil Sim and 8 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 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
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026Korea Advanced Institute of ScieKAIST AIVideo generation

MotionCFG: Boosting Motion Dynamics via Semantic Motion Sharpening

Byungjun Kim, Soobin Um, Jong Chul Ye

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 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 2026Korea Advanced Institute of ScieKAIST AIKorea Advanced Institute of ScieKAISTLLM agents & planning

DoG: Sniffing Out Overconfidence in LLM Agents via Post-hoc Trajectory Restructuring

Hyunjun Jeon, Dongha Lim, Kunwoong Kim, Daewon Choi and 1 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
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026KAIST AIGeorgia Institute of TechnologyKorea Advanced Institute of ScieYonseiSamsung3D vision & reconstruction

Geometry-Aware Representation Denoising for Multi-view Image Restoration and 3D Reconstruction

Jin Hyeon Kim, Jaeeun Lee, Claire Kim, Kyoungjin Oh and 8 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
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026KAIST AIKAISTDiffusion models

Temporal Alignment Guidance: On-manifold Sampling in Diffusion Models

Youngrok Park, Hojung Jung, Sangmin Bae, Se-Young Yun

Sydney Poster Session 2, Tue, Dec 8, 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 2026KAISTKAIST AIKorea Advanced Institute of ScieDiffusion models

DualDrift: Combining Forward and Reverse Drifts for One-Step Generative Modeling

Hojung Jung, Juhyeong Kim, Jaehyun Kwak, Boryeong Cho and 4 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 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
80%Must read
?Must readVote to see the score
NeurIPS 2026SpotlightKAIST AIUNISTEwha WomansLearning theory

Deep Barycentric Regression for Optimal Transport Map Estimation and its Statistical Optimality

BROT estimates optimal transport maps via barycentric regression with deep networks, achieving minimax optimal convergence rates under Lipschitz conditions with stable training.

Kunwoong Kim, Insung Kong, Yongdai Kim

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 5/5
medium 5/10
strict 2/5
83%Must read
?Must readVote to see the score
NeurIPS 2026U MichiganU California, DavisKAIST AILLM pretraining & scaling laws

Data-Constrained Language Model Pretraining: Improved Regularization and Scaling Laws

Masked-input regularization improves autoregressive pretraining over weight decay alone, and SoftQ scaling laws better capture data-constrained training than Chinchilla.

Zhiwei Xu, Shihao Wu, Hanseul Cho, Wei Hu and 1 more

Atlanta Poster Session 1, Wed, Dec 9, 10:00 AM–1:00 PM, Hall C1 · Published 2026

– ReadersNo votes yet
13/20 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: 13 of 20 reviewers recommend it
lenient 4/5
medium 9/10
strict 0/5
86%Must read
?Must readVote to see the score
NeurIPS 2026KAISTKAIST AIImperial College LondonKTHLLM evaluation & benchmarks

Instance-Optimal Estimation with Multiple LLM Judges on a Budget

EST-IVWE adaptively allocates a budget across judges and instances via biased variance estimates to achieve instance-optimal score estimation, with matching local minimax lower bounds.

Junghyun Lee, Sanghwa Kim, Yassir Jedra, Alexandre Proutiere and 1 more

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

– ReadersNo votes yet
14/20 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: 14 of 20 reviewers recommend it
lenient 5/5
medium 7/10
strict 2/5
76%Highly rated
?Highly ratedVote to see the score
ECCV 2026WorkshopKAISTKorea Advanced Institute of ScieKAIST AIVideo generation

CRePE: Curved Ray Expectation Positional Encoding for Unified-Camera-Controlled Video Generation

CRePE encodes tokens as depth-aware distributions along curved unified-camera rays to unify camera control, lens geometry, and external geometry guidance in video generation.

Seonghyun Jin, youngmin Kim, Sunwoo Park, Jong Chul Ye

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · 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 3/5
medium 6/10
strict 1/5
80%Must read
?Must readVote to see the score
NeurIPS 2026KAISTLG AI ResearchKAIST AISeoul NationalGraph generation

MolHIT: Advancing Molecular-Graph Generation with Hierarchical Discrete Diffusion Models

MolHIT uses hierarchical discrete diffusion and decoupled atom encoding to generate molecular graphs with near-perfect validity, surpassing 1D baselines on MOSES.

Hojung Jung, Rodrigo Hormazabal, Jaehyeong Jo, Youngrok Park and 4 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 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 6/10
strict 1/5
72%Highly rated
?Highly ratedVote to see the score
ICML 2026WorkshopKorea Advanced Institute of ScieKAISTKAIST AIDiffusion models

Reward Score Matching: Unifying Reward-based Fine-tuning for Flow and Diffusion Models

Reward Score Matching unifies reward-based diffusion and flow fine-tuning via value-guided score matching, clarifying tradeoffs and yielding simpler, more efficient designs.

Jeongjae Lee, Jinho Chang, Jeongsol Kim, Jong Chul Ye

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

– 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
76%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026KAISTKaist AIKoreaKAIST AIImage restoration

Accelerating Video Inverse Problem Solvers with Autoregressive Diffusion Models

AVIS uses autoregressive diffusion for streaming video inverse problems, cutting latency from 114s to 4s and boosting throughput to 1.18 FPS with better quality, while AVIS Flash reaches 5.91 FPS.

Taesung Kwon, Jonghyun Park, Hyungjin Chung, Jong Chul Ye

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · 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 5/5
medium 5/10
strict 0/5
80%Must read
?Must readVote to see the score
NeurIPS 2026KAIST AIKorea Advanced Institute of ScieKAISTEfficient inference & serving

BASTION: Budget-Aware Speculative Decoding with Tree-structured Block Diffusion Drafting

BASTION uses budget-aware tree-structured block diffusion drafting and adaptive expansion to achieve up to 6.61x speedup over autoregressive decoding, outperforming baselines by 39%.

Soowon Oh, Nam Cao, Yujin Kim, Hojung Jung 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 2/5
medium 9/10
strict 1/5