MLINFO COLLECTION
工程条件、原料ロット、検査値から品質指標や不良リスクを予測するための技術です。
Predicting how many tokens a large language model (LLM) will decode, using only prefill-phase hidden states, is a key primitive for inference scheduling. We show that current benchmarks conflate…
Large language models support personalized tutoring, content generation, and adaptive learning paths. However, capability development requires these resources and interactions to form a coherent…
Audio descriptions (AD) are essential for making visual media accessible to blind and low-vision (BLV) users. While Multimodal Large Language Models (MLLMs) offer a scalable solution for generating…
Pretrained generative models, such as diffusion and flow matching models, have demonstrated exceptional capabilities in synthesizing high-quality data. However, steering their generative trajectories…
Video world models generate future visual observations from camera or action inputs, with the goal of synthesizing persistent 3D worlds that can be explored across time and space. Existing benchmarks…
Recent advances in test-time optimization have shown that the multimodal reasoning performance of large multimodal language models (MLLMs) can be improved during inference without modifying backbone…
Multimodal videos contain rich temporal cues that can facilitate faithful fusion. However, existing video fusion methods mainly rely on short-range temporal interactions, leaving valuable long-term…
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…
Vision-language models (VLMs) increasingly process multiple views of the same scene, but it remains unclear whether they integrate these observations into a coherent scene-level representation.…
Robust depth estimation aims to maintain high-quality depths across diverse conditions. However, most existing methods estimate depth without taking into account the object-level information.
Recent diffusion models have achieved impressive progress in single image to multi-view generation by synthesizing consistent novel views efficiently. Existing methods usually explicitly or…
Sparse-view cone-beam computed tomography is widely used for fast, low-dose volumetric imaging and lesion localization in dentistry and image-guided interventions, but it introduces severe artifacts.…
Time-series forecasters are ranked almost entirely by accuracy metrics, but a forecast's decision value, its effect on the downstream decision, need not track accuracy and is rarely measured. This…
Prior-Data Fitted Networks (PFNs) replace the hyperparameter refitting of Gaussian Process (GP) surrogates in Bayesian optimisation with a single forward pass, at the cost of a prior that is fixed at…
Prediction models degrade when the deployment population differs from the one used to train them, and training data cannot say which feature-response relationships will transfer. Expert elicitation…
Retrieval-augmented generation commonly serves separate models for reranking and answering, duplicating model residency and passage processing. We introduce Glance, which equips the generator with a…
Controllable 3D part generation is pivotal for digital asset creation, yet existing methods lack the flexibility to accommodate diverse user workflows requiring varying levels of control. In this…
The scarcity of positive cases remains a major bottleneck in developing automated diagnostic systems for fetal Congenital Heart Defects~(CHDs), particularly for rare subtypes. Although normal cases…
Generated robot videos can look convincing while depicting the wrong interac- tion: a different object is moved, a grasp disappears, or a placement ends out- side its destination. We introduce…
Diffusion language models generate multiple token positions in parallel, but few-step decoding makes parallel commitment difficult: tokens that appear reliable individually may be jointly…
Mixture-of-Experts (MoE) large language models reduce computation through sparse activation but still incur substantial storage costs. Mixed-precision post-training quantization (PTQ) reduces these…
Conditional generation is a key capability to be supported by Large Tabular Models, enabling a number of applications. Accurate conditional generation has to contend with two key challenges: $(i)$…
Through a tangle of real-world interactions, from synthetic training pipelines to data shared on the open web, frontier LLMs absorb what their predecessors and competitors create. How well does each…
Retrieval-Augmented Generation (RAG) improves the performance of Large Language Models (LLMs) by retrieving external knowledge. Recently, some RAG methods interleave reasoning and retrieval, enabling…