大学 × Machine Learning
東京科学大学
Machine Learning / 2022–2026 LIVE
掲載論文 110 本
論文一覧
110 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 110 本と一致しています。
2026年
- AdaBlock-dLLM: Semantic-Aware Diffusion LLM Inference via Adaptive Block Size
掲載ID:
iclr:2026:e2eeb89acc98e8e506d719e330cbc43a - Best-of-Infinity: Asymptotic Performance of Test-Time LLM Ensembling
掲載ID:
iclr:2026:6023833bb511bbf248c83243f5d10395 - Beyond Match Maximization and Fairness: Retention-Optimized Two-Sided Matching
掲載ID:
iclr:2026:825150adf7ecf1969eabf68afab6f9d3 - DisTaC: Conditioning Task Vectors via Distillation for Robust Model Merging
掲載ID:
iclr:2026:c056d6cf7b7108418f2b8c307dfaab02 - Disrupting Hierarchical Reasoning: Adversarial Protection for Geographic Privacy in Multimodal Reasoning Models
掲載ID:
iclr:2026:6f244818d72b2a4be9b1225d1344e950 - EDINET-Bench: Evaluating LLMs on Complex Financial Tasks using Japanese Financial Statements
掲載ID:
iclr:2026:0e22eef358cd1d2bdb227e6b832cc775 - ELLMob: Event-Driven Human Mobility Generation with Self-Aligned LLM Framework
掲載ID:
iclr:2026:829300b183943850930c3ce36fe04268 - ExpVid: A Benchmark for Experiment Video Understanding & Reasoning
掲載ID:
iclr:2026:86833e97827ff52d297a9fbde5842a81 - Explaining Grokking and Information Bottleneck through Neural Collapse Emergence
掲載ID:
iclr:2026:af5509c72a244497c999ac39ba068ff4 - Learning Semi-Structured Sparsity for LLMs via Shared and Context-Aware Hypernetwork
掲載ID:
iclr:2026:c615f9e5ad3b90ad58af2cc529bc1528 - Light of Normals: Unified Feature Representation for Universal Photometric Stereo
掲載ID:
iclr:2026:8b8ff3f012d423c77dc4503d57f84e88 - On Fairness of Task Arithmetic: The Role of Task Vectors
掲載ID:
iclr:2026:186c95238d737f419846b244e6bd2f28 - Optimal Sparsity of Mixture-of-Experts Language Models for Reasoning Tasks
掲載ID:
iclr:2026:ab5492f57995409351cbf1a1cdf5f1a4 - Rewriting Pre-Training Data Boosts LLM Performance in Math and Code
掲載ID:
iclr:2026:8cc2387522e4473b6de7d0667a5be3ab - Robust Deep Reinforcement Learning against Adversarial Behavior Manipulation
掲載ID:
iclr:2026:15b780350b302a1bf9a3bd273f5c15a4 - Scaling Direct Feedback Learning with Jacobian Alignment Guarantees
掲載ID:
iclr:2026:2b1c608556ce011d3a3381fe0c527136 - Stopping Computation for Converged Tokens in Masked Diffusion-LM Decoding
掲載ID:
iclr:2026:e82cfb0ee6ce329759d0d3c90fbbccc4 - Toward Safer Diffusion Language Models: Discovery and Mitigation of Priming Vulnerability
掲載ID:
iclr:2026:257c140d25d1f7fc10f8ae5e17296299 - Towards Quantization-Aware Training for Ultra-Low-Bit Reasoning LLMs
掲載ID:
iclr:2026:209423f076b6479ab3a4f45886e30306 - TrustJudge: Inconsistencies of LLM-as-a-Judge and How to Alleviate Them
掲載ID:
iclr:2026:ecb87120e1e9c68ad186385e146094f4 - Understanding Cross-layer Contributions to Mixture-of-Experts Routing in LLMs
掲載ID:
iclr:2026:3efdd3cd3d70da09ec6ed3b3d17d2fd5 - Understanding Sensitivity of Differential Attention through the Lens of Adversarial Robustness
掲載ID:
iclr:2026:7514354a089c7df0d9746c0c4ae759f2 - Aligning Tree-Search Policies with Fixed Token Budgets in Test-Time Scaling of LLMs
掲載ID:
openreview:tgavubx8dx - Autoregressive Direct Preference Optimization
掲載ID:
openreview:dmefafuo6f - Beyond Model Base Retrieval: Weaving Knowledge to Master Fine-grained Neural Network Design
掲載ID:
openreview:96vowrwmqr - Beyond Perplexity: UTF-8 Validity in Byte-aware Language Models
掲載ID:
openreview:mvlwhrg71j - Certified Robustness under Heterogeneous Perturbations via Hybrid Randomized Smoothing
掲載ID:
openreview:nf7jt1jcsy - Context-Driven Incremental Compression for Multi-Turn Dialogue Generation
掲載ID:
openreview:zgevmaiilb - FreeRet: MLLMs as Training-Free Retrievers
掲載ID:
openreview:0cq8cqvuq4 - From Correspondence to Actions: Human-Like Multi-Image Spatial Reasoning in Multi-modal Large Language Models
掲載ID:
openreview:wcqevbldlz - Multi-Adapter Representation Interventions via Energy Calibration
掲載ID:
openreview:qooamouixn - PhotoAgent: Exploratory Visual Aesthetic Planning with Large Vision Models
掲載ID:
openreview:ws8swql5ob - Systematic Failures in Collective Reasoning under Distributed Information in Multi-Agent LLMs
掲載ID:
openreview:ighbkqallp - Trading Complexity for Expressivity Through Structured Generalized Linear Token Mixing
掲載ID:
openreview:mcjwxaoyrl - Training-Free Guided Diffusion for Planning: A Unified Framework via Doob’s h-Transform with Safety Guarantees
掲載ID:
openreview:9valxstwcg - cMoLLM at Scale: Horizontal Scaling Laws for Convolutionally-Gated Mixture-of-LLMs
掲載ID:
openreview:sfjleibtai
2025年
- A General Framework for Off-Policy Learning with Partially-Observed Reward
掲載ID:
iclr:2025:098491b37deebbe6c007e69815729e09 - Agent Skill Acquisition for Large Language Models via CycleQD
掲載ID:
iclr:2025:755acd0c7c07180d78959b6d89768207 - CofCA: A STEP-WISE Counterfactual Multi-hop QA benchmark
掲載ID:
iclr:2025:2628d4d3b054c2d7ad33ab03435204f4 - Drop-Upcycling: Training Sparse Mixture of Experts with Partial Re-initialization
掲載ID:
iclr:2025:d24b7366d714b09a977946ef0d9bf3ad - Enhancing Federated Domain Adaptation with Multi-Domain Prototype-Based Federated Fine-Tuning
掲載ID:
iclr:2025:23a081d2dbdeb531080ced0c2942103a - HALL-E: Hierarchical Neural Codec Language Model for Minute-Long Zero-Shot Text-to-Speech Synthesis
掲載ID:
iclr:2025:e32aefe039c94b95505b243e4cff8aa2 - Local Loss Optimization in the Infinite Width: Stable Parameterization of Predictive Coding Networks and Target Propagation
掲載ID:
iclr:2025:7ab63a5314680e2f083cb288abeaeb8e - MMQA: Evaluating LLMs with Multi-Table Multi-Hop Complex Questions
掲載ID:
iclr:2025:794a425a2e47e05d29d30f79b79a692d - Mastering Task Arithmetic: $\tau$Jp as a Key Indicator for Weight Disentanglement
掲載ID:
iclr:2025:47fee9cd8a252161dec7cb48ec0ca2f2 - Multiplicative Logit Adjustment Approximates Neural-Collapse-Aware Decision Boundary Adjustment
掲載ID:
iclr:2025:f3024ea88cec9f45a411cf4d51ab649c - On the Optimal Memorization Capacity of Transformers
掲載ID:
iclr:2025:a6fb8b1284a412543d853bfdddfc8f8e - PhiNets: Brain-inspired Non-contrastive Learning Based on Temporal Prediction Hypothesis
掲載ID:
iclr:2025:ab41313eaa3cbedbe491c24cbfe6547d東京科学大学 / 京都大学 / 沖縄科学技術大学院大学
- T2V2: A Unified Non-Autoregressive Model for Speech Recognition and Synthesis via Multitask Learning
掲載ID:
iclr:2025:746d2254f6892f3badadb07cc9c0f0da - Algorithmic Recourse for Long-Term Improvement
掲載ID:
pmlr:v267:kanamori25a - Distributionally Robust Active Learning for Gaussian Process Regression
掲載ID:
pmlr:v267:takeno25a - Enhancing Graph Contrastive Learning for Protein Graphs from Perspective of Invariance
掲載ID:
pmlr:v267:wang25cv - Masked Autoencoders Are Effective Tokenizers for Diffusion Models
掲載ID:
pmlr:v267:chen25v - Reasoning Through Execution: Unifying Process and Outcome Rewards for Code Generation
掲載ID:
pmlr:v267:yu25f - Scaling Laws for Floating–Point Quantization Training
掲載ID:
pmlr:v267:sun25j - Semantic Shift Estimation via Dual-Projection and Classifier Reconstruction for Exemplar-Free Class-Incremental Learning
掲載ID:
pmlr:v267:he25d - AegisGuard: RL-Guided Adapter Tuning for TEE-Based Efficient & Secure On-Device Inference
掲載ID:
neurips:2025:f308b5f207348484552997c536375654 - Binary Quadratic Quantization: Beyond First-Order Quantization for Real-Valued Matrix Compression
掲載ID:
neurips:2025:e7cf82c8f34920d20299a84b16b720e8 - DyG-Mamba: Continuous State Space Modeling on Dynamic Graphs
掲載ID:
neurips:2025:bbba680acd2826f23928c6675a19f0e7 - From Pose to Muscle: Multimodal Learning for Piano Hand Muscle Electromyography
掲載ID:
neurips:2025:a7d80c990c77ae2570087243ec802314 - Learning Gradient Boosted Decision Trees with Algorithmic Recourse
掲載ID:
neurips:2025:6ecd51685e2d765bc0ad32a2e73faf62 - Masked Gated Linear Unit
掲載ID:
neurips:2025:dd73f39426a03131c38c8d943153d44b - Provably Efficient RL under Episode-Wise Safety in Constrained MDPs with Linear Function Approximation
掲載ID:
neurips:2025:435e8fbbfc2c6072d4f3a5cb6e56a39a - Rethinking Optimal Verification Granularity for Compute-Efficient Test-Time Scaling
掲載ID:
neurips:2025:8011b23e1dc3f57e1b6211ccad498919 - SAEMark: Steering Personalized Multilingual LLM Watermarks with Sparse Autoencoders
掲載ID:
neurips:2025:e8ddc03b001d4c4b44b29bc1167e7fdd - The Effect of Optimal Self-Distillation in Noisy Gaussian Mixture Model
掲載ID:
neurips:2025:18ddfb199d71a8a24f83abc1ced077b7 - UMoE: Unifying Attention and FFN with Shared Experts
掲載ID:
neurips:2025:34bafcb1e8b7ee231c5a796e83d33f9b - Variational Learning Finds Flatter Solutions at the Edge of Stability
掲載ID:
neurips:2025:6b61c278e483954fee502b49fe71cd14 - Visual Thoughts: A Unified Perspective of Understanding Multimodal Chain-of-Thought
掲載ID:
neurips:2025:8a57d66b8e0cc468dbb6574114f60f0c - Wider or Deeper? Scaling LLM Inference-Time Compute with Adaptive Branching Tree Search
掲載ID:
neurips:2025:32dff2e27b0da1fb5f4209216a948544
2024年
- Adversarial Training on Purification (AToP): Advancing Both Robustness and Generalization
掲載ID:
iclr:2024:ae5bf4f35236240c9460e761c60fa53d - Are Transformers with One Layer Self-Attention Using Low-Rank Weight Matrices Universal Approximators?
掲載ID:
iclr:2024:96ee35c170cb8720033b16259c305da9 - Diffusion Sampling with Momentum for Mitigating Divergence Artifacts
掲載ID:
iclr:2024:18561617ca0b4ffa293166b3186e04b0 - Exploring Weight Balancing on Long-Tailed Recognition Problem
掲載ID:
iclr:2024:b2647998bc953781490049fe2ac28bf0 - Towards Assessing and Benchmarking Risk-Return Tradeoff of Off-Policy Evaluation
掲載ID:
iclr:2024:b54532b0e57eb963b19e00583376cda3 - A General Framework for Learning from Weak Supervision
掲載ID:
pmlr:v235:chen24ar - Community-Invariant Graph Contrastive Learning
掲載ID:
pmlr:v235:tan24b - Learning Decision Trees and Forests with Algorithmic Recourse
掲載ID:
pmlr:v235:kanamori24a - Noise-Aware Algorithm for Heterogeneous Differentially Private Federated Learning
掲載ID:
pmlr:v235:malekmohammadi24a - Position: Towards Implicit Prompt For Text-To-Image Models
掲載ID:
pmlr:v235:yang24o - RVI-SAC: Average Reward Off-Policy Deep Reinforcement Learning
掲載ID:
pmlr:v235:hisaki24a - Statistical Test for Attention Maps in Vision Transformers
掲載ID:
pmlr:v235:shiraishi24a - Variational Learning is Effective for Large Deep Networks
掲載ID:
pmlr:v235:shen24b - ADOPT: Modified Adam Can Converge with Any $\beta_2$ with the Optimal Rate
掲載ID:
neurips:2024:84d286e32bbee8fa3a86ee9c50e00081 - Advancing Cross-domain Discriminability in Continual Learning of Vision-Language Models
掲載ID:
neurips:2024:5c34c2a3462cbfd5e258c29974d60cca - AutoSurvey: Large Language Models Can Automatically Write Surveys
掲載ID:
neurips:2024:d07a9fc7da2e2ec0574c38d5f504d105 - Flipping-based Policy for Chance-Constrained Markov Decision Processes
掲載ID:
neurips:2024:760b5def8dcb1156aac454e9c0f5f406 - Imprecise Label Learning: A Unified Framework for Learning with Various Imprecise Label Configurations
掲載ID:
neurips:2024:6de71272e0be559af3f76b884e94794b - Integrating GNN and Neural ODEs for Estimating Non-Reciprocal Two-Body Interactions in Mixed-Species Collective Motion
掲載ID:
neurips:2024:84f44b36ceb4fbc9bb269959f4796eed - On Softmax Direct Preference Optimization for Recommendation
掲載ID:
neurips:2024:30732ddb12d9faf7180f5d0e8b5b5da7 - Parameter Symmetry and Noise Equilibrium of Stochastic Gradient Descent
掲載ID:
neurips:2024:aa933b5abc1be30baece1d230ec575a7 - Taming the Long Tail in Human Mobility Prediction
掲載ID:
neurips:2024:6294e6ec40d3599dcc9e9d584d959f5c
2023年
- Cross-Level Distillation and Feature Denoising for Cross-Domain Few-Shot Classification
掲載ID:
openreview:kn-ha8dfik - FreeMatch: Self-adaptive Thresholding for Semi-supervised Learning
掲載ID:
openreview:pdruptxji_a - Neural Episodic Control with State Abstraction
掲載ID:
openreview:c2fssj3zgiu - Neural Lagrangian Schr\"{o}dinger Bridge: Diffusion Modeling for Population Dynamics
掲載ID:
openreview:d3qnwd_pcfv - SoftMatch: Addressing the Quantity-Quality Tradeoff in Semi-supervised Learning
掲載ID:
openreview:ymt1zqxbdif - End-to-end Training of Deep Boltzmann Machines by Unbiased Contrastive Divergence with Local Mode Initialization
掲載ID:
pmlr:v202:taniguchi23a - Bandit Task Assignment with Unknown Processing Time
掲載ID:
neurips:2023:1c5ee7343f396954377c2c16dda33a96 - Demographic Parity Constrained Minimax Optimal Regression under Linear Model
掲載ID:
neurips:2023:1b4acad19cc425a7352a71d4e4468393 - ImageBrush: Learning Visual In-Context Instructions for Exemplar-Based Image Manipulation
掲載ID:
neurips:2023:98530736e5d94e62b689dfc1fda89bd1 - Rethinking Tokenizer and Decoder in Masked Graph Modeling for Molecules
掲載ID:
neurips:2023:51fd9a7d1706023cb9f8210cc6ac357c - Transfer Learning with Affine Model Transformation
掲載ID:
neurips:2023:3819a070922cc0d19f3d66ce108f28e0
2022年
- Disentanglement Analysis with Partial Information Decomposition
掲載ID:
iclr:2022:eb86d510361fc23b59f18c1bc9802cc6 - Dropout Q-Functions for Doubly Efficient Reinforcement Learning
掲載ID:
iclr:2022:d61e4bbd6393c9111e6526ea173a7c8b - A Unified Weight Initialization Paradigm for Tensorial Convolutional Neural Networks
掲載ID:
pmlr:v162:pan22b - Feature Space Particle Inference for Neural Network Ensembles
掲載ID:
pmlr:v162:yashima22a - Multicoated Supermasks Enhance Hidden Networks
掲載ID:
pmlr:v162:okoshi22a - PoF: Post-Training of Feature Extractor for Improving Generalization
掲載ID:
pmlr:v162:sato22a - Learning Deep Input-Output Stable Dynamics
掲載ID:
neurips:2022:364721b3d5d9da2aaa19adafd7b0f49c
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。