Optimally Curating an Event
We study the optimal design of a self-financing event, a problem that requires balancing the recruitment of costly, positive-value participants with revenue-generating agents who may impose negative…
math-theory
MLINFO COLLECTION
品質予測
工程条件、原料ロット、検査値から品質指標や不良リスクを予測するための技術です。
記事一覧
24 / 27ReAPO: Retry-Aware Policy Optimization for Efficient Exploration in LLM Reasoning
RLVR improves language-model reasoning, but commonly relies on independent stochastic rollouts for exploration, which can repeatedly sample similar failed strategies. Prior work has seen success with…
deep-learning
MAPLE: Mondrian-Anchored Prior for Learning-free Indoor Exploration
Robots exploring unknown indoor environments must decide where to move while much of the environment remains unseen. Predicting the occupancy of unseen space beyond the current sensor range can…
deep-learning
Fast Motion Retargeting Pipeline for Scalable Humanoid Robot Learning
While large-scale human motion capture datasets provide a rich source of demonstrations for humanoid robot learning, retargeting the diverse motions to different humanoid robots remains a nontrivial…
mlops
Temporal Difference Learning of Probabilistic Reach-Avoid Value Functions
Reach-avoid sets, defining the states from which a task can be completed while avoiding unsafe regions, are fundamental tools for deploying robots in environments subject to disturbances and…
computer-vision
When Does Training on Synthetic Data Provably Work?
High-quality training data are a major bottleneck in machine learning, motivating increasing use of artificially generated data. We study when a binary classifier trained on synthetic data transfers…
computer-vision
AWLS: Advantage-Weighted Latent Steering for One-Step Generative Robotic Manipulation Policies
Human-collected real-world robotic manipulation demonstrations often contain mixed-quality trajectories, including hesitant, indirect, or inefficient action segments. While diffusion- and flow-based…
deep-learning
Prescribed Performance Guided Safe Reinforcement Learning for Roundabout Navigation of Autonomous Vehicles
Connected and Autonomous Vehicles (CAVs) face significant challenges in roundabout navigation due to dense traffic interactions and unpredictable agent behaviors, necessitating high levels of…
nlp
When Does Experience Memory Help Closed-Loop LLM Driving Agents? A Controlled Evaluation with Resampled Warmup Pools, Token-Matched Fillers, and Audited Baselines
When does experience memory help a closed-loop LLM driving agent? Published gains cannot say, because the two factors we find to matter most, which warmup experiences the pool contains and what any…
nlp
Privacy Accounting for Empirical Denoisers
Diffusion models have emerged as the foundation of modern generative systems, yet their high memorization capacity raises privacy concerns. While differentially private (DP) training provides formal…
deep-learning
CovNav: Conformal Prediction-Guided Adaptive Inference for Object Goal Navigation
In object goal navigation (ObjectNav), an embodied agent must find a target object (e.g., "find a bed") in a previously unseen environment, relying on spatial commonsense such as object…
nlp
Divide-and-Conquer Neural Bayes Estimation for Spatial and Spatiotemporal Point Process Models
Spatial and spatiotemporal point process models are widely used to analyze event data across many scientific disciplines, but likelihood-based Bayesian inference is often computationally prohibitive…
deep-learning
Source-Aware Dynamic Pricing with Strategic Buyers
In modern commerce, firms and platforms typically use customer features from different sources to personalize prices: some features are verified using seller records or third-party data, while others…
nlp
The Tilted Sampling Problem: Optimism, Posterior Sampling, and Logarithmic Regret
Many modern learning systems are used not to select a single best action, but to sample diverse high-quality outputs. Examples include entropy-regularized reinforcement learning, RLHF, and…
computer-vision
Diffusion Score Estimation with Shallow Neural Networks: Regularity, Approximation, and Finite-Sample Rates
We study the sample complexity of estimating Ornstein--Uhlenbeck diffusion scores in $\mathbb R^d$ using denoising score matching (DSM) with finite-width shallow ReLU networks, and its implications…
computer-vision
Gaussian Approximation of Besov Functions for Logistic Classification on Manifolds
We study Gaussian kernel approximation and regularized logistic classification on a connected compact smooth embedded manifold $X\subset\mathbb R^d$ without boundary and of intrinsic dimension…
computer-vision
Learning to Refer: Inference-Time Collaboration in Decentralized Federated Learning
In decentralized federated learning, heterogeneous clients may develop complementary expertise, yet each query is typically evaluated only by the client where it arrives. To exploit this distributed…
deep-learning
Which Model for Which Role? Cost-Efficient Pareto Recommendation for LLM Agentic Workflows
LLM agentic workflows increasingly employ different models for specialized roles. Users may prefer different trade-offs between task quality and deployment cost, sometimes also considering latency.
deep-learning
Selecting the Best Few with Human Evaluators: Adaptively Combining Ratings and Pairwise Comparisons
This paper considers a decision-maker tasked with identifying the $k$ best items from a large pool of candidates, such as job applicants, LLMs, award nominees, or new product ideas. The…
deep-learning
Keep the Lineages Alive: Diversity-Preserving SMC for Diffusion LLM Decoding
Inference-time sequential Monte Carlo (SMC) decoding can improve the reasoning accuracy of masked diffusion language models (diffusion LLMs) without post-training by resampling a population of…
nlp
An autocomplete model for elections
We consider two linked problems for ranked choice elections: building a compact summary of a preference profile $P$, and generating synthetic profiles that resemble $P$ in key ways. We introduce a…
reinforcement-learning
Divergence based Ranked Preference Alignment for LLMs
Alignment of large language models typically relies on pairwise preference feedback, though ranked feedback can capture more comprehensive information across multiple responses within a single…
nlp
The Voter Model with Opinion Graph
We study the \emph{voter model with opinion graph}, a generalization of the standard (pull) voter model that adds a notion of bounded confidence. In this process, we consider a finite set $A$ of $n$…
computer-vision
Asymmetric Information in Dynamic Lending Games
We study a dynamic lending game with limited but reusable supply. Borrower arrivals and loan durations are stochastic.
computer-vision