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。
Human cognition flexibly draws on a shared perceptual foundation to understand environments, attend to referenced entities, reason about spatial relationships, and act. Endowing aerial robots with an…
Online vectorized map construction provides autonomous vehicles with essential, real-time semantic and geometric scene understanding. While leveraging prior maps presents an opportunity to improve…
Computer-use agents plan on a screenshot for several seconds and then click at a position on the screen; if the page has changed in the meantime, the click lands on an unintended element. Prior work…
Generalist robot policies increasingly learn from data collected across diverse tasks and embodiments, yet typically assume a single controller for each robot. This assumption limits transfer because…
Lattice-type modular reconfigurable robots rearrange standardized modules across tasks. Dedicated transport robots reduce module weight and cost by eliminating module level reconfiguration actuators.
Predicting future physical states stands as a central challenge in embodied intelligence. Existing video world models leave 3D dynamics implicit, action-based formulations remain tied to specific…
Continuous Conditional Generative Modeling (CCGM) aims to synthesize high-dimensional data conditioned on continuously valued scalar labels. However, existing continuous diffusion models face severe…
An effective agent memory system should adapt to a user's history and task requirements. Human-annotated supervision can guide this adaptation by providing feedback for evaluating and improving…
Engineering design frequently involves redesigning a prior solution to adapt to changes in context, such as material prices or system requirements. Redesign often leverages simulators too complex…
Legged robots have demonstrated advanced capabilities across a wide range of real-world tasks, yet much of this progress concerns the robot controlling only itself. Once the robot is coupled to an…
Multi-image composition (MICo) is a critical yet challenging capability for large-scale image editing models, where consistency degrades rapidly as the number of reference images increases. While…
While frontier vision-language models demonstrate strong capabilities in user interface (UI) navigation, their high inference costs prohibit everyday use. Conversely, smaller models trained via…
Trajectory-level GRPO is a common approach for training multi-step GUI agents, but repeatedly rolling out complete trajectories from the task root can be inefficient: task-level rewards provide…
We introduce SocialArena, a benchmark for systematically defining and evaluating the social intelligence of large language models (LLMs). Although LLMs are increasingly deployed in socially…
Accurate time series forecasting (TSF) is essential for Web applications, such as traffic monitoring and online resource management. Recent advances in leveraging pre-trained large language models…
Reinforcement learning with verifiable rewards (RLVR) has become a powerful tool for improving multimodal reasoning. However, standard outcome supervision suffers from credit assignment ambiguity, as…
Large language model (LLM) agents have demonstrated strong capabilities in automating complex information-seeking and transactional tasks across the open web. However, their real-world reliability…
Embodied world models should not only imagine plausible futures, but also perceive the geometric, semantic, and motion structure of the evolving world. We present GenSight, a unified embodied world…
Financial AI systems must support decision-bearing questions involving payments, collections, cash flow, and compliance while ensuring numerical accuracy, traceability, and auditability. Large…
We present XLaw-JP-27B, an open-weight model specialized for Japanese law that runs on a single 48\,GB GPU under the Apache~2.0 licence. It adapts Qwen3.8-27B with hybrid retrieval over all current…
We study routing games in which competing mediators recommend routes to fixed nonatomic populations. Each mediator chooses a randomized flow allocation to minimize its population's expected travel…
Rotary Position Embedding (RoPE) typically uses uniform coverage across Transformer layers despite heterogeneous positional requirements. Phase-off interventions reveal non-uniform, model-specific…
We develop a fast method for the rigid alignment of voxelized three-dimensional density functions over $\mathsf{SO}(3)$ using sliced optimal transport. Our approach efficiently transforms each…
Learning task progress from robot demonstrations provides a practical way to construct dense shaping rewards for robotic reinforcement learning. A common approach uses normalized demonstration time…