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。
Vision Transformers (ViTs) achieve strong image recognition performance, but their self-attention increases quadratically with the number of input tokens and makes them computationally expensive. The…
Automatic judges offer inexpensive information about model outputs, but an evaluation team must decide how to turn that information into fewer human annotations. Scores can guide sampling, correct an…
Feed-forward 3D Gaussian Splatting has recently emerged as a promising alternative to per-scene optimization, enabling fast novel view synthesis by predicting Gaussian primitives directly from input…
Text summarization is an important task for advancing natural language processing (NLP) research and applications in Indic languages. Despite progress in extractive and abstractive summarization,…
Embodied systems can update policies, world models, skills, and executable programs from deployment experience, allowing one interaction to benefit later tasks. When a system also revises and reuses…
Data augmentation improves visual recognition by exposing models to synthetic training examples that encourage generalization beyond the observed data. Mixed-sample methods extend this idea by…
Topology-agnostic motion generation aims to synthesize motions for diverse characters with arbitrary skeletons. Unlike conventional motion generation, which assumes a fixed skeletal template, this…
Large language models hold promise for delivering safe, scientifically grounded, and personalized exercise guidance at scale, yet the sports-and-health domain still lacks curated training corpora and…
Vision-and-Language Navigation in Continuous Environments (VLN-CE) requires instruction-consistent planning and reliable execution under collision constraints. Yet many hierarchical approaches…
We study adversarial linear bandits with strong corruption, in which an adaptive adversary chooses the reward vectors and a strong adversary corrupts each observed reward after seeing the learner's…
Current datasets for text-to-video generation are largely limited to short clips depicting a single event or coarse-grained captions. As a result, they provide limited supervision for modeling…
We demonstrate the first zero-shot sim-to-real transfer for a surgeon-robot collaboration task in open surgery: retractor take-over. A robot arm takes a retractor from the surgeon's hand and…
Mobile manipulator robots rarely reposition their base during manipulation, because doing so requires real-time knowledge of how well the arm can reach its surroundings among obstacles. Reachability…
Language models increasingly create 3D content through code, with practical workflows often relying on editing existing programs rather than regenerating them, for speed and precise control. Such…
Walking offers a window into physical function that may support interpretable video-based frailty assessment. We developed silhouette-based "gaitomics" to connect frailty predictions with measurable…
Robot imitation learning uses demonstrations from operators of varying skill, but selecting training data remains challenging. Existing methods score demonstrations using smoothness, diversity, or…
Kernel methods face two recurrent bottlenecks: the cubic cost of inverting an $n\times n$ kernel matrix, as in kernel ridge regression, and the evaluation of kernel integrals, as required in kernel…
Skills, as reusable external knowledge, have demonstrated substantial potential to enhance the ability of Large Language Models (LLMs) to solve complex tasks. However, existing skill-augmented…
Behavior Cloning has demonstrated promising generalization capabilities for robotic manipulation in terrestrial environments. However, marine visual distortions and dynamic currents create a severe…
Short video platforms have become a primary channel for black and gray industry operations in internet finance, where inducements such as prompts to like, follow, join private chat groups, or click…
Whole-prompt translation evaluates a request in different languages but does not compare which component carries a language. We introduce a paired reversal: translate the complete request component…
We present an experimental framework for determining sufficient communication in robot teams running fixed, independent Behaviour Trees with private blackboards. Within a declared policy family, we…
We present EasyProver, a Lean proving system built from recursive agents with isolated contexts, asynchronous search, parallel tactic probing, and an elastic elaboration service. Using an…
On-policy distillation (OPD) trains a student on its own responses using token-level feedback from a teacher. As responses grow longer, the student's prefix can depart from the teacher's own…