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。
Precise camera control is essential for cinematic character video generation, yet existing methods struggle to follow large-angle trajectories with combined rotation, translation, and radius…
We introduce RynnUnify, a 16B unified embodied model that combines strong embodied understanding with long-horizon visual planning through interleaved video--language reasoning. With capabilities…
HoloBoxing presents a simple recipe for learning humanoid boxing by building on a pretrained whole-body controller. The recipe separates reusable motor skills from task decisions: a compact planner…
Location encoders map geographic coordinates to high-dimensional descriptors through contrastive alignment with paired Earth Observation imagery. We prove that this construction is structurally…
On-policy self-distillation enables post-training foundation models without relying on stronger external teachers. However, existing approaches rely on ground-truth question-answer pairs,…
Streaming audio-visual target speaker extraction (AVTSE) is essential for latency-sensitive applications. However, current causal systems face two coupled gaps.
Locating relevant evidence in long inputs is a core capability of Multimodal Large Language Models. Prior studies attribute this capability to retrieval heads, a sparse set of attention heads that…
LLM agents are increasingly used to solve real-world problems, and their effectiveness depends on both the underlying models and the harnesses that support their operation. However, most existing…
Agent-evolution methods use execution feedback to improve prompts, skills, tools, and orchestration, but their implementations often rebuild the same experimental machinery. We present RSIHub, an…
Single-image 3D scene construction is a fundamental problem in 3D vision. Recent methods such as SAM-3Dfy enable end-to-end reconstruction of 3D assets and their scene layouts, but still struggle…
Scientific discovery requires identifying the scientific principles underlying observed phenomena to guide further investigation. As these empirical principles are often unknown in complex discovery…
Behavior cloning for robotic manipulation is highly sensitive to the coverage of its training data, yet collecting diverse successful demonstrations remains costly. We study reinforcement learning…
Recent test-time training (TTT) frameworks have enabled open-weight large language models (LLMs) to outperform inference-only frameworks powered by frontier models on scientific discovery tasks.…
Deploying language agents in real applications demands more than the right answer: an agent must execute a multi-step business process correctly, follow domain-specific rules, and interact with a…
Robot foundation models are typically evaluated through costly closed-loop rollouts, motivating low-cost offline proxies for model capability. The Platonic Representation Hypothesis (PRH) suggests…
Developing general-purpose algorithms with global asymptotic convergence guarantees for Nash equilibria of general-sum games remains a longstanding challenge. This paper extends the fixed-point…
Developing general-purpose algorithms with global asymptotic convergence guarantees for variational inequalities (VIs) remains a longstanding challenge. This paper proposes a path-following framework…
Standard sequence models encode position by token rank rather than physical coordinate, typically forcing practitioners to destructively resample continuous physical signals such as spectra observed…
大規模言語モデルのテスト時間調整に関する調査のリポジトリ。
ModelScopeは、モデルをサービス化するためのプラットフォームです。モデルを作成し、ホスティングし、管理し、配信することができます。
AIの入門コースを提供する。
强化学习中文教程（蘑菇书🍄），在线阅读地址：https://datawhalechina.github.io/easy-rl/
《李宏毅深度学习教程》（李宏毅老师推荐👍，苹果书🍎），PDF下载地址：https://github.com/datawhalechina/leedl-tutorial/releases
Hardware-aware neural architecture search (NAS) requires jointly optimizing predictive accuracy and device-specific latency over discrete search spaces. While multi-objective swarm optimizers show…