大学 × Machine Learning
東北大学
Machine Learning / 2022–2026 LIVE
掲載論文 28 本
論文一覧
28 本
このEditionのランキングに掲載している論文です。同じ大学の複数著者による共著は1本にまとめています。
ランキングの対象論文 28 本と一致しています。
2026年
- Do We Really Need Permutations? Impact of Model Width on Linear Mode Connectivity
掲載ID:
iclr:2026:5eceaacf571380e70c1052ef6bd58cb3 - Frequency Bands in RoPE: Base Frequency and Context Length Shape the Interpolation–Extrapolation Trade-off
掲載ID:
iclr:2026:993dbaec0418a6449090f1debbcb8844 - Learning Semi-Structured Sparsity for LLMs via Shared and Context-Aware Hypernetwork
掲載ID:
iclr:2026:c615f9e5ad3b90ad58af2cc529bc1528 - Neuron-Level Analysis of Cultural Understanding in Large Language Models
掲載ID:
iclr:2026:d50110d749bb4b1a92baec3481655512 - Optimal Sparsity of Mixture-of-Experts Language Models for Reasoning Tasks
掲載ID:
iclr:2026:ab5492f57995409351cbf1a1cdf5f1a4 - Pre-training LLM without Learning Rate Decay Enhances Supervised Fine-Tuning
掲載ID:
iclr:2026:6f9f3e0b4d292310d3e5eeec312d3b98 - Asymmetric Perturbation in Solving Bilinear Saddle-Point Optimization
掲載ID:
openreview:fyae4jq9lw - Last-Iterate Convergence of Regularized Gradient Methods for Stochastic Monotone Variational Inequalities
掲載ID:
openreview:eirv1oeo7f - Revisiting Photometric Ambiguity for Accurate Gaussian-Splatting Surface Reconstruction
掲載ID:
openreview:2znijsn2jc
2025年
- BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions
掲載ID:
iclr:2025:a6a90bcc2aa470c3871b2d39a67d26e8 - Bridging the Data Provenance Gap Across Text, Speech, and Video
掲載ID:
iclr:2025:97b983c974551153d20ddfabb62a5203 - Drop-Upcycling: Training Sparse Mixture of Experts with Partial Re-initialization
掲載ID:
iclr:2025:d24b7366d714b09a977946ef0d9bf3ad - GPS: A Probabilistic Distributional Similarity with Gumbel Priors for Set-to-Set Matching
掲載ID:
iclr:2025:637a456d89289769ac1ab29617ef7213 - MMSearch: Unveiling the Potential of Large Models as Multi-modal Search Engines
掲載ID:
iclr:2025:04e6525463afaa460b5a2e6868b18f18 - Sketch2Diagram: Generating Vector Diagrams from Hand-Drawn Sketches
掲載ID:
iclr:2025:2567c95fd41459a98a73ba893775d22a - SoftMatcha: A Soft and Fast Pattern Matcher for Billion-Scale Corpus Searches
掲載ID:
iclr:2025:159511050630689045bf5593e74b13cc - UniDetox: Universal Detoxification of Large Language Models via Dataset Distillation
掲載ID:
iclr:2025:c4800e97411c7f199b2895425f2933a5 - What's New in My Data? Novelty Exploration via Contrastive Generation
掲載ID:
iclr:2025:e2c39f96da9ec114e0b5fbd639139035 - Self-Supervised Learning of Intertwined Content and Positional Features for Object Detection
掲載ID:
pmlr:v267:liu25bo - You Always Recognize Me (YARM): Robust Texture Synthesis Against Multi-View Corruption
掲載ID:
pmlr:v267:ran25a - Probing Neural Combinatorial Optimization Models
掲載ID:
neurips:2025:becf96dcee66f9df08169e4c96bbbd8c - Transformer Key-Value Memories Are Nearly as Interpretable as Sparse Autoencoders
掲載ID:
neurips:2025:fae3fd16e764af14e23b53fdd7632457
2024年
- Analyzing Feed-Forward Blocks in Transformers through the Lens of Attention Maps
掲載ID:
iclr:2024:61a18c8a7a1ea7445375dd7255905bc3 - Crystalformer: Infinitely Connected Attention for Periodic Structure Encoding
掲載ID:
iclr:2024:c428adf74782c2092d254329b6b02482 - PlaSma: Procedural Knowledge Models for Language-based Planning and Re-Planning
掲載ID:
iclr:2024:16bce4070c4e23434451b180348e3814 - Zipfian Whitening
掲載ID:
neurips:2024:dd1fef536655685898a6602bfbf16857
2023年
- InfoCD: A Contrastive Chamfer Distance Loss for Point Cloud Completion
掲載ID:
neurips:2023:f2ea1943896474b7cd9796b93e526f6f
2022年
- Bridging the Gap from Asymmetry Tricks to Decorrelation Principles in Non-contrastive Self-supervised Learning
掲載ID:
neurips:2022:7d535a224c8ae54ba75bac0457b6b279
掲載対象外の論文や未反映の論文は、この一覧には含まれません。