MLINFO COLLECTION
日次更新の新着・公開記事を新しい順に掲載しています。
Understanding how gradient descent learns features remains a central challenge in neural network theory. We study this question in a minimal multi-index setting that already exhibits rich multi-phase…
In the random allocation sampling scheme each user's data is used in $k$ steps chosen randomly and uniformly from a sequence of $t$ steps. This scheme is known to improve on Poisson sampling in…
In real-world deployments, large language model (LLM) systems are increasingly evolving from single-model invocation toward heterogeneous deployments in which different models are dynamically invoked…
The quadratic scaling of attention is a fundamental bottleneck limiting the long-context capabilities of large language models (LLMs). A variety of approaches have attempted to circumvent this, but…
Atmospheric fronts are associated with much of the high-impact weather in the mid-latitudes, yet their identification and classification remain largely manual and subjective. Existing deep learning…
Distributionally robust optimization (DRO) minimizes worst-case risk under distributional uncertainty, but its decisions can be suboptimal in terms of their excess risk, or regret. We study this gap…
Physics informed machine learning provides a framework to study and simulate fluid dynamics, potentially at a fraction of the computational cost of traditional numerical methods, with the goal of…
Motivated by a broad literature in psychology, organizational behavior, and matching markets, we introduce strategic tanking: an agent deliberately makes themselves less attractive to selected…
Inverse reinforcement learning (IRL) seeks to infer the reward function underlying observed behavior, but its predictive accuracy and interpretability depend on how that reward is computed from the…
Deep reinforcement learning (RL) is a powerful framework for sequential decision-making. Despite many high-profile successes in recent years, deep RL is known to be brittle.
A fallen humanoid beneath an overhead obstacle faces a coupled recovery problem. It must create clearance while organizing support for a stable rise, since attempting to stand before making room can…
World action models (WAMs) learn latent variables from observations and use these to both predict the evolution of the scene and to generate actions. The prediction has to be of the whole scene,…
Self-supervised learning relies on asymmetry between what a model observes and what it must explain. Recent methods learn 3D geometry from unposed images by predicting cameras and scene structure,…
We show that, for a broad class of gradient-based learning rules, scalar zero-sum games form a complete test family for convergence in unconstrained network zero-sum games. Specifically, suppose a…
Freeze-thaw Bayesian optimization (BO) evaluates candidates in resumable increments but usually stops at a budget or convergence test. We maximize a budget-free utility, the best observed score minus…
Continuous diffusion language models show promising potential in text generation tasks, but are prone to problems such as text repetition, semantic drift, and generation quality degradation when the…
A panoramic video captures all directions around the camera, but relevant evidence can appear in different directions and at different times. Understanding it requires models to connect observations…
Research on practical differentially private (DP) synthetic data has largely focused on methods that approximately preserve low-dimensional marginals of a target distribution, and can thus only hope…
Low-Earth orbit (LEO) satellite networks present a challenging routing environment due to rapidly changing topology, traffic, and link conditions. Existing deep reinforcement learning (DRL) routing…
AI answers require more than apparent correctness: reviewers need to inspect their recorded basis. We introduce the Knowledge Layer Model (KLM), an open, implementation-neutral specification for…
Conversational assistants are expected to help people with diverse backgrounds, preferences, and communication styles. Yet evaluations centered on a single cooperative user provide limited insight…
Reinforcement learning with verifiable rewards (RLVR) has become the standard method for training language models to reason. However, RLVR typically relies solely on outcome correctness, which does…
Foundation models are becoming remarkably reliable at high-level reasoning, yet they remain too slow and costly to serve as fine-grained controllers. Conversely, fast policies like VLAs and…
Autonomous wheelchairs can improve the quality of life for individuals with mobility impairments by providing greater independence. However, reliable navigation especially in human environments is a…