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。
We propose \emph{Déjà Vu}, a test-time decoding module for semantic correspondence. Matching semantically equivalent keypoints across images of the same object category is challenging due to…
Audio-language models (ALMs) are evaluated on their understanding of both speech and environmental sounds. What remains underexplored is how they respond when spoken claims contradict acoustic…
This paper introduces \emph{catenary visibility}, a new geometric visibility concept for a robotic system consisting of a ground robot tethered to an aerial drone. The tether is modeled as an…
Recommending creators that a user does not yet follow is a cold-start problem: from hundreds of thousands of popular creators and only a short trail of prior engagements, the system must predict the…
A child learns which words name which things from roughly 100 million words of input. Vision-language models trained at a comparable scale bind words to referents far less reliably, and we argue that…
Improving situational awareness within the Smart Grid is an effective preventive measure to detect potential anomalies, and avoid their adverse consequences. A wide area measurement system (WAMS)…
Coding agents working in shared repositories may receive separate, independently-motivated requests from human developers, creating a setting that is multi-agent by necessity. When this scenario…
Multi-objective Bayesian optimization (MOBO) maximizes $M$ expensive black-box objectives with the goal of approximating the Pareto set, whose objective vectors cannot be improved in one component…
Floating point computing has dominated scientific computations since the 1950s because of its versatile ability to approximate real numbers with both sufficiently high precision and sufficiently…
Tell an LLM negotiator to be "headstrong" and it should hold firm on price, but does that instruction retain the same behavior in every language? To test this, we use identical buyer and seller…
Bias in transformer-based models is a growing concern as these architectures become more prevalent in automated decision-making systems, such as prediction models for hiring, lending, and clinical…
Collaborative robots (cobots) are designed to be safer and more interactive than traditional industrial robots, share the same workspace as humans, and assist them in a range of shop-floor tasks such…
Recent advances in video generation have achieved impressive visual quality, yet they often fail to produce physically consistent dynamics due to the lack of explicit modeling of underlying physical…
Deep neural network (DNN) accelerators for edge inference must meet tight energy, latency, and area (EDP) constraints, and their optimal hardware architecture and dataflow configuration is typically…
AI agents write and execute code, manipulate user interfaces, and transact on their users' behalf. We ask what forms failure takes in human-agent interaction, and how those forms change as agents act…
Dimension reduction methods are chosen by a common claim: t-SNE and UMAP preserve local structure, and PCA preserves global structure. Checking it on given data takes local and global scores on one…
Cross-view geolocalization aims to determine the geographic location of a ground-level image by retrieving its corresponding satellite image, offering a promising alternative for localization in…
Concurrent software underpins critical infrastructure, including operating systems and databases, yet thread interactions can have bugs that bypass conventional testing. Verus extends Rust with…
Post-training quantization (PTQ) reduces the memory burden of large model deployment by casting the high precision trained weights to fewer bits. While this promotes memory-efficient inference, it…
Large-scale repositories of species observations now contain billions of occurrence records from around the world, but these sightings cluster heavily in human-accessible areas. Existing models use…
Held-out validation loss is the standard offline signal for choosing checkpoints and comparing models, but its relation to closed-loop success on a real robot is rarely measured. We measure it for…
We present DELBERT-2, a pretrained fingerprint language model that converts sparse molecular fingerprints into unified token sequences using a ModernBERT encoder trained with masked language…
Automated theorem generation (ATG) seeks to construct new theorems rather than merely prove given conjectures. Existing approaches typically generate candidate statements that require subsequent…
Estimating the causal effect of a treatment $X$ on an outcome $Y$ from observational data in the presence of unobserved confounding requires additional structure or assumptions. Existing…