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。
Recent progress in visual scene generation has extended beyond static 3D scenes toward the more challenging problem of generating dynamic 4D scenes from minimal input. However, sound, despite being…
World models can achieve strong control performance without faithfully capturing the dynamics of their environment, limiting their potential for mechanistic interpretability and scientific discovery.…
An observer sees only part of the surrounding world, yet must keep track of what lies beyond the current view. Spatial perception therefore involves more than recognizing individual images: it calls…
As robots and intelligent systems increasingly interact with humans, they must anticipate long sequences of future actions from only brief observations. While purely neural models typically require…
Safety alignment has enabled large language models to reliably refuse harmful requests directly, yet the same request distributed across a multi-turn conversation still succeeds far too often. This…
We study equilibrium computation in multi-unit trading networks with valuations satisfying generalized full substitutes and agent- and transaction-specific piecewise-linear transfer functions. These…
Ask a language model whether sales tend to dip after a product recall, or whether one side effect tends to follow another after a vaccine, and it answers in a fluent sentence that reads like a…
The marginals of a continuous diffusion model can be reproduced by a deterministic ordinary differential equation (ODE), known as the probability flow ODE, which provides a foundation for accelerated…
Modern diffusion models are trained on massive datasets that often include copyrighted or private images. Membership inference attacks (MIAs) address this by testing whether a given image was in a…
Interactive world models generate visual content conditioned on user actions, yet maintaining spatial consistency over long-horizon exploration in real time remains challenging. Existing approaches…
We present TextSeal2, a distortion-free watermark for large language models that keeps its signal under speculative decoding: tokens that replace rejected drafts remain watermarked with the same…
Proactive assistants offer short, memory-grounded hints during a conversation, deciding when to assist and what to suggest. Current systems split this between a gate and a larger generator; we…
A playable, programmable game world must maintain persistent state, enforce executable rules, and support extensible gameplay mechanics. Existing video world models can generate plausible combat, yet…
This work proposes a novel conveyor belt mechanism enabling continuous, active repositioning of functional elements along the body of a tendon-driven continuum robot. Up to three conveyor belt…
The hair of stylized characters in games and avatars is built from hair cards: artist-placed ribbons whose geometry is the visible hair, animated by spring bones. Existing image-based methods produce…
An autonomous research laboratory could conduct an entire study, from formulating questions to preparing manuscripts. Artificial intelligence (AI) offers one route towards this goal.
When AI agents share channels and credentials, one agent can press another to break its operator's rule, a first step towards collusion. Output filters check only what an agent has already written.
In real-world clinical settings, dental X-ray segmentation using deep learning methods suffers from reliability issues. Even when the segmentation quality is bad, deep learning models show high…
Integrated sensing and communications (ISAC) systems using 5G and beyond signals of opportunity enable joint wireless sensing and communication using shared infrastructure and spectrum resources.…
Current zero-shot anomaly detection methods often rely on complex prompt-learning techniques or computationally expensive sliding-window strategies to achieve fine-grained visual alignment to detect…
Building and scaling computer-using agents (CUAs) across desktop, mobile, and web environments requires reliable task-completion verification for data curation, evaluation, and reinforcement…
Sparse mixture-of-experts (MoE) models expand parameter capacity by activating a small subset of experts per token. Expert selection directly affects model capabilities under a fixed active-expert…
Reinforcement learning from verifiable rewards (RLVR) is limited by sparse outcome-level feedback on hard reasoning tasks: when all rollouts in a group fail, rewards provide no learning signal.…
On-policy Self-distillation (OPSD) has proven effective for post-training large language models by constructing a teacher conditioned on privileged references. However, existing approaches keep the…