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。
The Sinkhorn divergence, a debiased form of entropic optimal transport, has been widely used in various scientific disciplines due to its computational and statistical tractability. Unlike the…
As expansion and scalability in underwater oper- ations becomes more important and challenging, autonomous underwater vehicles (AUVs) become more relevant and the necessity for reliable autonomy more…
While velocity-commanded RL policies are effective for controlling quadrupeds, they are a limited interface for humanoids that need to perform complex whole-body motions. Furthermore, RL tracking…
Drone-based 3D reconstruction and inspection require viewpoints that satisfy image-quality constraints while observing each surface region multiple times, which overlap-based planning heuristics do…
A track fitting pipeline is presented that converts a measured racetrack point cloud into a closed, $C^4$ differentiable, three-dimensional surface model suitable for high-fidelity Modelica race-car…
Are concepts and mechanisms unified across modalities in current AI models, or instead implemented separately for each one? We operationalize this broad question of modality unification by studying…
Learning velocity fields directly in pixel space is difficult and slow. We show that coarse second-order image statistics can ease this task: frozen Wiener estimates improve velocity learning, with…
The quality with which language models follow instructions falls as the load grows, yet there is still no quantity that expresses the limit of a model in units of load with an uncertainty. We propose…
Financial institutions operating under data-residency constraints are restricted to open-weight models small enough to locally host, which trail frontier systems on multi-step quantitative reasoning.…
Multimodal intelligence can be viewed as human-guided co-evolution between worlds and agents through interaction. However, scaling this process faces two bottlenecks: constructing heterogeneous,…
Action-conditioned world models offer a scalable alternative to costly real-world interaction for improving robot policies. However, existing world-model-based methods largely treat world models as…
Image and video generators can produce spatially consistent visual content, but how to use this capability to improve spatial understanding remains underexplored. We study this problem from two…
As foundation models evolve from information generation to digital work execution, agents are increasingly capable of completing complex tasks across tools, applications, and workflows. However,…
High-resolution video matting requires preserving fine details, such as hair strands and soft transparency, while maintaining consistency across frames. Memory-based methods achieve strong matting…
Generating videos of a specific subject from a few reference images remains challenging when the camera reveals surfaces that are not visible in the input. Early subject-to-video (S2V) methods…
As frontier language models grow increasingly capable and autonomous, independent third-party evaluations are critical for characterizing their systemic safety risks. While closed-source releases are…
Critic-free methods are widely used in reinforcement learning with verifiable rewards (RLVR) for long chain-of-thought (CoT) reasoning, avoiding difficult and costly critic training. Common…
Referring expression grounding in overhead imagery requires oriented bounding boxes rather than horizontal ones, since aerial objects appear at arbitrary orientations. Most grounding models emit box…
Omnimodal large language models (Omni-LLMs) are increasingly expected to assist users while observing continuous audiovisual streams. However, existing evaluations provide limited insight into how…
Recursive self-improvement (RSI), in which a system also improves the way it improves, is a long-standing aspiration on the path to AGI. Language agents increasingly store procedural knowledge in…
Embodied agents are expected to accomplish real-world goals by deciding for themselves how and when to interact with their surroundings. For many such goals, changing the physical state of the world…
Constrained decoding guarantees that Large Language Models (LLMs) produce outputs conforming to predefined formats, but is often assumed to inherently degrade reasoning. We examine this assumption…
AI systems built around large models increasingly use experience and feedback to make persistent changes to models, prompts, memories, tools, and workflows. Recursive self-improvement (RSI) extends…
Evaluating human-AI co-design requires testing whether coding agents can translate real users' multimodal requests into working application revisions. We introduce Co-Design Bench, a reference-free…