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。
Modern visual tokenizers aim to preserve fine-grained visual details while learning high-level semantic representations for downstream generation and understanding. Query-based 1D visual tokenizers…
Large-scale behavioral pretraining offers a promising route to generalizable representations in online payment systems. However, high-cardinality identity fields such as card, device, and account…
Human vision is foveated and active: resolution is highest at the fovea and falls off towards the periphery, and fixations are actively directed to locations of interest. Building a machine system…
High accuracy on streaming video benchmarks does not establish whether a model uses visual history. Our review of OVO-Bench and StreamingBench finds that recent frames suffice for 32% of sampled…
Robotic Manipulation Surfaces (RMS) reposition objects by deforming the surface on which they rest. A recent class of RMS suspends a continuous fabric sheet from a sparse grid of vertical linear…
Data-driven controllers have enabled lower-limb robotic exoskeletons to adapt assistance to the user across many tasks. A leading example is biological torque control, which estimates the user's own…
We study realizable PAC learning under approximate differential privacy, and give a framework for proving lower bounds on its sample complexity. We construct classes with identical VC and Littlestone…
Automated endoscope guidance reduces the need for continuous manual camera control during minimally invasive surgery. However, the desired camera motion depends on the surgeon's immediate intentions…
World-action models increasingly apply test-time scaling, spending extra inference computation on candidate selection and adaptive allocation to improve control. Such gains are credible only when…
Weight pruning can reduce the storage and inference cost of large language models (LLMs), but preserving quality at high sparsity levels remains challenging. Existing methods face a quality-cost…
Reinforcement learning and game theory describe the same object from two sides. Game theory says what a rational outcome of a strategic interaction is; reinforcement learning says how an agent could…
We develop a new algorithmic framework for learning Boolean concept classes under logconcave distributions. Our framework applies to broad families of multi-index models and yields significantly…
Sampling from Boltzmann distributions is a fundamental problem in physics, chemistry, and biology. We introduce WAsserstein SAmpling via Bridge Interpolants (WASABI), a method that trains a diffusion…
Accurate forecasting with uncertainty quantification is critical in a variety of scientific applications ranging from epidemiology and economics to energy systems and earth sciences. Yet most…
Multimodal Large Language Models (MLLMs) have achieved impressive performance across a wide range of reasoning tasks, yet it remains unclear whether their internal representations and decision…
Few-step flow models generate samples through a handful of large denoising transitions. Applying GRPO to such models requires introducing stochasticity into the denoising transitions, and when a…
Embodied surgical AI requires reliable multimodal data, yet surgical data collection remains costly, difficult to repeat, and strongly dependent on the hardware setup. We present Sensorium, an…
An approximation can reproduce an energy while missing its response, or satisfy an error tolerance without being certified by a given bound. We formulate observable-specific validity records for…
This paper extends an existing framework for the coordination of mobile agents in unknown worlds, by considering the possibility of dynamic instability. In the original problem, known as the…
With the surge of machine vision applications, image compression for both machine and human vision (ICMH) has become an important research area. Existing studies mainly focus on task-specific…
Large Language Models (LLMs) can turn natural-language optimization tasks into solver-checked answers, but current agents remain brittle under narrative rewrites and often store reusable experience…
An agent that must call several tools to fulfill a request fails when the tool retriever omits any one of them, yet tool retrievers are mostly built and evaluated on queries requiring a single tool.…
Reinforcement learning (RL) embodies a foundational paradigm for sequential decision-making in the face of uncertainty. The rapid growth of model complexity in emerging applications has significantly…
Current LLM ensemble frameworks focus on multi-step setups with additional modules for answer ranking, often opting for token and span analysis rather than structured outputs, leading to heavyweight…