MLINFO COLLECTION
LoRA、RLHF、SFT、軽量ファインチューニングなど、LLMを用途に合わせる技術を扱います。
The electric autonomous dial-a-ride problem (EADARP) extends the classical dial-a-ride problem by incorporating battery and charging constraints for electric vehicles. In practice, travel-time…
Large Language Models (LLMs) are increasingly used for automated algorithm design. However the computational cost of evaluating the generated algorithms can be excessive.
LLM-guided evolutionary methods, such as AlphaEvolve, have emerged as powerful approaches for challenging computational optimization problems, such as circle packing. However, prior work typically…
Large language model (LLM)-driven evolutionary search is a powerful paradigm for automated program and algorithm discovery, yet existing systems are largely memoryless: each run explores from…
Dynamic resource assignment, the real-time allocation of task streams to heterogeneous processing nodes, is the backbone of modern computing infrastructure. While learning-based schedulers excel in…
Large language model (LLM)-based automatic heuristic design (AHD) iteratively proposes and refines heuristics, pairing design rationales with executable code. Task-specific evaluators assess…
Parameter-efficient reinforcement learning aims to improve reasoning with a compact trainable interface to a pretrained model. We introduce the Thalamic Router (T-Router), which concentrates…
Evolutionary program search driven by large language models (LLMs) has produced record-breaking constructions for open problems in combinatorics and beyond. We apply this approach to the longstanding…
Adam and its variants dominate neural network training, but a single run only reveals whether a configuration works well after most of its budget is spent, a poor fit for hyperparameter or…
As large language models advance, AI agents are moving beyond isolated, domain-specific tasks toward long-horizon, cross-domain workflows. This transition exposes two challenges: increasing harness…
How phenotypic transformations are implemented by changes in underlying regulatory dynamics remains a central question in developmental biology. Inspired by D'Arcy Thompson's 1917 "On Growth and…
AI-driven scientific discovery accelerates research by autonomously developing solutions and designs. Large language model (LLM) agents support this process through iterative generation and…
LLMs can generate programs for ARC-AGI-2 tasks, but the provided compute only allows a small number of attempts to generate, debug and validate solutions. Genetic algorithms can search and test many…
Large language models (LLMs) enable automated algorithm design (AAD) through reasoning and code synthesis. However, most existing LLM-based AAD methods separate algorithm design from target…
Agent harnesses, the external systems that mediate model-environment interaction, can substantially improve agent performance, but their gains remain tied to the harness at deployment. Because the…
Functional annotation of newly sequenced proteins remains a bottleneck in molecular biology: the number of sequences in public repositories grows far faster than the capacity for manual curation.…
Most artificial neural systems are built to map given inputs to outputs. Adaptive agents face a prior problem: they must act without enough evidence, seek encounters with the world, and revise…