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 motion transfer requires a model to extract motions from multiple reference videos, and apply each motion to a user-specified object in one target scene. Existing methods normally…
Graph analytics generates irregular, topology-dependent memory-access streams via indirect traversals, limiting data prefetching. Accurate prediction enables timely prefetches that hide memory…
AI coding agents now do long, multi-step and multi-session software work with little supervision. When a developer comes back to that work, the useful question is not what the model said but what was…
Unified Multimodal Models (UMMs) enable powerful multi-image synthesis but incur substantial computation from long visual contexts. While token pruning offers a direct route to accelerating…
In many real-world classification tasks, datasets exhibit class imbalance, which can degrade the generalization performance of conventional learning algorithms. Data complexity has recently been…
View- and target-specific echocardiography AI models capture useful but complementary information and may not achieve sufficient predictive performance in isolation. A learned ensemble is a natural…
We study first-order and best-of-both-worlds regret guarantees in multi-armed bandits. Pogodin and Lattimore (2019) proposed an algorithm that combines minimax-optimal worst-case regret with a…
Deep neural networks achieve strong performance across many tasks but remain vulnerable to adversarial perturbations. Adversarial training (AT) is one of the most effective defenses, yet it suffers…
Planning at run time, as in robots that re-plan while they act, needs a planner that reads the PDDL its users write (durative actions, numeric resources, time windows, continuous change), answers…
Imitation learning has become a widely adopted approach for vision-based robot policies, owing to its conceptual simplicity, scalability, and ability to leverage large-scale datasets. As these…
Giving embodied agents the freedom to act autonomously, initiate interactions, and understand their surroundings through experience is a step toward bringing them to life in the physical world.…
Masked diffusion models train a denoiser on masked cross-entropy and generate by unmasking many positions in parallel. Existing MDM sampling bounds assume an exact denoiser or leave its error…
Softmax routing in mixture-of-experts models can concentrate probability on a subset of experts, suppressing access to the others. We study how this concentration forms, why it persists, and how…
Medical AI learns from the answers doctors record, but rarely from how they interpret the evidence to reach them. Here we introduce PathCowork, a framework that turns pathologists' narrated…
Label-free test-time reinforcement learning adapts vision--language models using rewards derived from their own predictions. However, misinterpreted visual evidence and sensitivity to textual…
Reliable local search is essential for LLM agents to support everyday decisions and longer plans by finding places that meet users' needs at given times and locations. Yet existing benchmarks provide…
Large language models can often identify useful semantic structure in formal artifacts, but their outputs cannot be trusted as proofs or solver decisions. We study whether LLMs can instead guide…
Cyber threat intelligence (CTI) reports describe adversary behavior in natural language, but converting them into structured MITRE ATT&CK mappings remains difficult: existing methods decompose…
Multi-arm robot platforms, including bimanual and humanoid robots, have the capability to complete tasks with lower cycle times than single-arm systems, but they are more difficult to safely control…
Formula-Driven Supervised Learning (FDSL) enables vision pre-training without real images, but existing methods cast pre-training as classification on discretized labels, discarding continuity in the…
Multimodal large language models can recognize visual content yet struggle to reason reliably over it across multiple steps. In counting, a model may see all objects but lose track of which ones it…
Linear recurrences are emerging as practical alternatives to softmax attention in large language models, appearing in both standalone and hybrid architectures. However, despite their rapid emergence,…
Large language models (LLMs) have shown strong performance on software engineering (SE) tasks, driving the need for high-quality datasets for reliable training and evaluation. SWE-bench-style…
Predicting where to grasp and how to move is fundamentally a geometry problem. Vision-language models treat it as language generation instead.