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。
With the development of deep learning, neural video compression (NVC) is gaining increasing interest and is currently under standardization in the AVS (Audio Video Coding Standard). Skip mode coding,…
Embodied agents are usually organized around individual tasks, yet the physical world keeps changing between tasks and during execution. We introduce LIFE (Lifelong Intelligence from Experience), a…
Simplifying large or noisy time-series is often a prerequisite for producing interpretable line charts, yet existing methods vary widely in how they alter visual features such as trends, extrema,…
Egocentric observations provide a robot-centric view of manipulation processes, capturing contact interactions and object-state changes that are important for visuomotor policy learning but difficult…
Graph-aware calibrators make graph neural networks (GNNs) more trustworthy by predicting a temperature for each node, usually with auxiliary networks whose decisions are hard to inspect. We propose…
Embedding models underpin virtually every modern AI system, from search engines to recommendation systems. Despite shared mathematical foundations, research on embedding models remains fragmented by…
Robots powered by foundation models are increasingly able to interpret open-ended language, recognize unfamiliar objects, and operate across diverse environments. Yet broader capability does not…
Fourier phase retrieval reconstructs images from magnitude measurements without phase information, but noise and channel ambiguities make natural color-image recovery challenging. Although…
Post-incident analysis of a robot foundation model poses a singular causal question: which internal components caused this failure, and to what degree? Mechanistic interpretability (MI), however,…
Chronic kidney disease is characterized by structural alterations in renal tissue and progressive loss of kidney function. While glomerular subtype ratios provide a compact and clinically meaningful…
Large astronomical surveys collect abundant light curves, but reliable class labels remain scarce. ASTROMER 2 learns from unlabeled light curves by reconstructing masked observations, yet this…
Radiologists' visual attention can supervise medical image learning, but how reader panel composition affects its value remains untested. We evaluated GazeRIB (Gaze-guided Radiologist-Informed…
Unified Multimodal Models (UMMs) achieve remarkable success on diverse multimodal understanding and generation tasks, yet they still struggle to effectively leverage language-based chain-of-thought…
Decision models such as Jev have emerged as a highly promising paradigm for LLM agent systems, providing lightweight and reliable categorical reasoning for rapid System One execution. However,…
Agentic workflows are increasingly shifting towards long-horizon tasks, such as open-ended scientific work, where models benefit from long context windows. However, at ultra-long context (above 1M…
Planning with world models enables test-time adaptation for embodied agents, offering superior generalization over direct policy learning. However, long-horizon tasks remain hindered by cumulative…
Representing 3D shapes using a set of primitives - known as shape abstraction - is an actively studied problem in computer graphics with wide applications in shape understanding, analysis, and…
Recent work shows that a frozen robot policy performs far better inside an agent harness, where control code decides when to query the policy, consult vision tools, or command the arm directly. Yet…
In many practical deployments of Differentially Private Stochastic Gradient Descent (DP-SGD), the server processes data in batches. Randomly sampling these batches allows for better privacy bounds…
Dense 3D tracking from monocular video requires establishing point correspondences over time, estimating their depth, and inferring their trajectories during occlusion. Existing methods typically…
Distribution Matching Distillation (DMD) trains a few-step student using the difference between a teacher's score and an online critic's estimate of the student distribution's score. We investigate…
Instance-dependent limits for bandit regret, sequential tests, best-arm identification and Markov decision processes are proved by one chain. It runs from a divergence decomposition through data…
Decision models target structured tasks by directly predicting choices or scores, avoiding autoregressive decoding latency. However, transferring a generative LLM's ranking knowledge to a decision…
Objective: To distinguish the transferable predictive value of physiological trajectories from that of observation patterns in ICU mortality prediction, and to assess whether measurement timing…