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。
Compositional generalization remains a persistent limitation of transformer language models: even when a model learns to combine known facts correctly in-distribution (ID), the same compositional…
Images produced by generative models appear strikingly similar to real ones. In this work, we study whether perfection has been reached by generated content in terms of matching the properties of…
While vast literature on high-dimensional data visualization is available, there are not many works regarding the visualization of feature scorers and their results. Feature scorers are algorithms…
Tabular-to-image encoding methods, which transform tabular data into image-like representations, have shown promising results in predictive tasks. Despite their benefits, these methods follow a…
Developing analog and hybrid systems requires substantial domain knowledge that is hard to articulate in a formal specification; without additional effort, this domain knowledge is also inaccessible…
Small language models (SLMs) offer an attractive alternative to frontier models (FMs) because they can be deployed with lower cost and latency. This makes SLMs especially appealing for terminal tasks…
Radio-frequency (RF) sensing enables robot ego-motion estimation in darkness, smoke, and fog, yet RF odometry remains challenging because multipath and moving reflectors make cross-frame matching…
Despite recent advancements in ASR, identifying effective architectures, fine-tuning approaches, and data adaptation strategies for low-resource languages remains challenging. We present a systematic…
Sparse-view computed tomography (CT) reduces the number of acquired projections, but conventional sampling strategies are designed primarily for image reconstruction rather than for downstream…
Severe blur, downsampling, noise, and compression can erase the identity cues needed to faithfully restore a person's face. We therefore use photographs of the same person as an external source of…
Learning independence is fundamental to statistical inference and machine learning, yet learning independence between entire time series by a test remains challenging when only a single observation…
Generative Flow Networks (GFlowNets) are models that learn to sample discrete objects proportional to a target reward. They are trained by minimizing balance errors over sampled trajectories, which…
Anticipating the motion of nearby objects is critical for safe and efficient robot navigation. Without a proper understanding of what may move, a robot may plan overly conservative, inefficient…
In procedural videogame level design, many existing techniques combine hand-authored level chunks. Some existing analysis techniques also rely on a higher-level graph structure which abstracts the…
Fast and accurate models for AC power flow (ACPF) are increasingly important as modern electrical grids require more frequent system analyses. Graph neural networks (GNNs) naturally exploit…
Speculative decoding (SD) accelerates autoregressive inference by leveraging the memory bound nature of decoding, verifying multiple draft tokens in a single forward pass. For mixture-of-experts…
World models let observers explore and interact with generated worlds. Recent work shows that when observers revisit a region, current models often fail to regenerate it consistently.
Large language models pass most functional-correctness benchmarks, but passing tests says little about whether their code is readable, efficient or secure. Many techniques claim to improve these…
Physics-informed machine learning (PIML) and hybrid modeling have attracted significant attention as approaches for combining physical knowledge with the flexibility of deep learning. In this work,…
Dungeons & Dragons (D&D) is a tabletop roleplaying game (TTRPG) in which a group of players, guided by a Game Master, roleplay a fantasy adventure with simulated combat and improvisational narrative.…
Current and emerging mobile networks face increasing privacy, scalability, and performance challenges as distributed learning becomes essential for advanced 6G services. These challenges are…
Speculative decoding speeds up large language model (LLM) serving only while the GPU has spare compute, so the best draft length, the number of tokens a small drafter guesses per step, shrinks as the…
Reliable obstacle avoidance is essential for safe quadrotor flight in unknown environments, yet conventional frame-based cameras remain challenged by motion blur, limited dynamic range, and latency…
Estimating conditional parameters, such as heterogeneous treatment effects, often requires rich covariate adjustment, even when the parameters are reported along only a few dimensions. Fitting…