MLINFO COLLECTION
RAG、埋め込み、検索評価、要約を使って文書検索や社内QAを作るための技術です。
Mathematical expressions and the numerical behavior they produce are two views of the same underlying function, and connecting them is central to scientific discovery. Symbolic Regression (SR) relies…
Quantum-inspired evolutionary optimization (QIEO) represents design variables as a set of qubits and searches a continuous, multi-dimensional landscape through rotation of the qubit's amplitude pair.…
Modern deep neural networks treat parameters as static floating-point matrices stored in physical memory, incurring Von Neumann memory bottlenecks and representation collapse. We formulate Orbital…
How much information can a single neuron remember? How many memories can neural networks retrieve without creating false memories?
Vector Symbolic Algebras project data structures into a hyperdimensional vector space through the application of their vector algebras to randomly generated atomic vector symbols and fractional power…
Automatically generating test inputs for games is challenging, as test generators must master the game to reach advanced program states while also ensuring robustness against the heavy program…
Brain-to-language decoding translates neural activity associated with language production, internal speech and perception into linguistic or expressive outputs. It offers a route to restoring…
Faithfulness is a central concern in legal text summarization, which motivates extractive approaches that select verbatim content traceable to its source. Such methods typically rank paragraphs or…
Multi-task optimization (MTO) addresses a set of optimization tasks simultaneously, often suffering from inaccurate inter-task relationship estimation under limited evaluation budgets, leading to…
Human motion retargeting bridges the embodiment gap between humans and humanoid robots by converting human demonstrations into reference trajectories for whole-body control and loco-manipulation. For…
Frontier language models now score above 90% on popular knowledge benchmarks and are increasingly deployed as agents that carry out multi-hour professional work. Yet no existing benchmark tests…
Industry Foundation Classes (IFC), the standard for building information exchange in architecture, engineering, and construction (AEC), is increasingly queried through large language models (LLMs)…
Real-world data often exhibits cluster structure at multiple resolutions, yet existing methods typically learn a single partition or construct an explicit hierarchy. Inspired by Matryoshka…
Which pretraining objective yields the best representation for downstream tasks under an information budget? We formalize this problem as a multitask information bottleneck, using a mutual…
Personal intelligence systems are taking on increasingly complex everyday tasks, yet repeated questions, unnecessary confirmations, and unwanted outreach can turn capable assistance into interaction…
Should an embodied agent's experience be baked into its policy weights, or kept external and retrieved at inference? A memory-augmented teacher (a VLM that retrieves lessons, with their episode…
Multi-task generalization is an important yet underexplored problem in multi-agent reinforcement learning (MARL). Many real-world applications require multi-agent systems to generalize across…
Recent advances in search agents have enabled large language models to tackle complex tasks by retrieving and synthesizing external information. However, existing search agents often lack…
Large language model (LLM) based multi-agent systems often rely on predefined collaboration structures, limiting their adaptability to evolving task requirements. Although recent approaches enable…
Training Arabic large language models faces challenges from noisy web data, dialectal variation, and the high cost of continual pretraining (CPT). We introduce AQL-Lite (AQL: Arabic Quality…
Generating an articulated object from a single image requires recovering both its appearance and the mechanism governing its parts. A compact encoding of joint attributes does not by itself ensure…
Dynamic representations based on 4D Gaussian Splatting (4DGS) have shown strong capabilities in reconstruction and rendering, yet current methods remain limited in supporting complex natural-language…
Existing 3D generative approaches are typically developed for individual imaging modalities, requiring substantial modality-specific data and limiting their ability to exploit shared structure across…
Reinforcement learning (RL) is an effective way to strengthen the long-context reasoning of large language models (LLMs), but it needs training data that are long, diverse, challenging, and…