Loading...

학술행사

Korean AI Association

학술행사

  >   학술행사   >   국내학술대회

국내학술대회

NeurIPS Preview Paper

2025  NeurIPS Preview Session 1 (TBA)

 

1. Visual Diversity and Region-aware Prompt Learning for Zero-shot HOI detection
2. VideoTitans: Scalable Video Prediction with Integrated Short- and Long-term Memory
3. Blockwise Flow Matching: Improving Flow Matching Models For Efficient High-Quality Generation
4. PRESTO: Preimage-Informed Instruction Optimization for Prompting Black-Box LLMs 
5. CLAWS:Creativity detection for LLM-generated solutions using Attention Window of Sections
6. Towards Reliable Code-as-Policies: A Neuro-Symbolic Framework for Embodied Task Planning
7. Layer-Wise Modality Decomposition for Interpretable Multimodal Sensor Fusion
8. Automated Model Discovery via Multi-modal & Multi-step Pipeline
9. MMPB: It’s Time for Multi-Modal Personalization
10. Exploring and Leveraging Class Vectors for Classifier Editing
11. Exploration via Feature Perturbation in Contextual Bandits
12 Preference-based Reinforcement Learning beyond Pairwise Comparisons: Benefits of Multiple Options
13. Revisiting Follow-the-Perturbed-Leader with Unbounded Perturbations in Bandit Problems
14. Cooperative Retrieval-Augmented Generation for Question Answering: Mutual Information Exchange and Ranking by Contrasting Layers
15. Mitigating Instability in High Residual Adaptive Sampling for PINNs via Langevin Dynamics
16. Influence Functions for Edge Edits in Non-Convex Graph Neural Networks
17. Prior Forgetting and In-Context Overfitting
18. Metropolis-Hastings Sampling for 3D Gaussian Reconstruction
19. Tree-Guided Diffusion Planner
20. Partial Correlation Network Estimation by Semismooth Newton Methods
21. Perturb a Model, Not an Image: Towards Robust Privacy Protection via Anti-Personalized Diffusion Models
22. Holistic Order Prediction in Natural Scenes
23. Single-Teacher View Augmentation: Boosting Knowledge Distillation via Angular Diversity
24. The Cost of Robustness: Tighter Bounds on Parameter Complexity for Robust Memorization in ReLU Nets
25. An Analysis of Concept Bottleneck Models: Measuring, Understanding, and Mitigating the Impact of Noisy Annotations
26. Composed Program Induction with Latent Program Lattice
27. KSP: Kolmogorov-Smirnov metric-based Post-Hoc Calibration for Survival Analysis
28. Diffusion-Driven Two-Stage Active Learning for Low-Budget Semantic Segmentation
29. Position: AI Should Sense Better, Not Just Scale Bigger: Adaptive Sensing as a Paradigm Shift
30. Periodic Skill Discovery
31. SpecEdge: Scalable Edge-Assisted Serving Framework for Interactive LLMs

 

2025  NeurIPS Preview Session 2 (TBA)

 

1. Knowledge Distillation of Uncertainty using Deep Latent Factor Model
2. Towards Generalizable 3D Human Pose Estimation via Ensembles on Flat Loss Landscapes
3. On Epistemic Uncertainty of Visual Tokens for Object Hallucinations in Large Vision-Language Models
4. Structural Causal Bandits under Markov Equivalence
5. DeepVideo-R1: Video Reinforcement Fine-Tuning via Difficulty-aware Regressive GRPO
6. Non-Stationary Structural Causal Bandits
7. Backpropagation-Free Test-Time Adaptation via Probabilistic Gaussian Alignment
8. RePIC: Reinforced Post-Training for Personalizing Multi-Modal Language Models
9. ScaleDiff: Higher-Resolution Image Synthesis via Efficient and Model-Agnostic Diffusion
10. Topology-aware Graph Diffusion Model with Persistent Homology
11. Don’t Let It Fade: Preserving Edits in Diffusion Language Models via Token Timestep Allocation
12. Tractable Multinomial Logit Contextual Bandits with Non-Linear Utilities
13. Seg4Diff: Unveiling Open-Vocabulary Segmentation in Text-to-Image Diffusion Transformers
14. Enhancing 3D Reconstruction for Dynamic Scenes
15. Emergent Temporal Correspondences from Video Diffusion Transformers
16. Where and How to Perturb: On the Design of Perturbation Guidance in Diffusion and Flow Models
17. Dataset Distillation of 3D Point Clouds via Distribution Matching
18. Active Test-time Vision-Language Navigation
19. ConceptScope: Characterizing Dataset Bias via Disentangled Visual Concepts
20. Thompson Sampling for Multi-Objective Linear Contextual Bandit
21. EUGens: Efficient, Unified, and General Dense Layers
22. From Linear to Nonlinear: Provable Weak-to-Strong Generalization through Feature Learning
23. NeSyPr: Neurosymbolic Proceduralization For Efficient Embodied Reasoning
24. True Impact of Cascade Length in Contextual Cascading Bandits 25. OpenBox: Annotate Any Bounding Boxes in 3D
26. Infrequent Exploration in Linear Bandits
27. Through the River: Understanding the Benefit of Schedule-Free Methods for Language Model Training
28. Layer-wise Update Aggregation with Recycling for Communication-Efficient Federated Learning
29. Efficient Multi-bit Quantization Network Training via Weight Bias Correction and Bit-wise Coreset Sampling
30. AliO: Output Alignment Matters in Long-Term Time Series Forecasting