MLINFO COLLECTION
材料候補探索、分子生成、実験条件探索、ベイズ最適化に関係する技術です。
Large language model (LLM) agents have shown promising potential in coding tasks, and their performance is jointly determined by the policy model and the harness that mediates their interaction with…
Chemical chain-of-thought can contain hallucinated structural and property claims. We thereby introduce MolLean, a process-verifiable language that grounds chemical reasoning in an explicit molecular…
Large language model agents increasingly undertake long-horizon tasks in complex environments characterized by fragmented evidence, partially completed states, and dependencies across resources and…
Recent video generation models produce visually compelling outputs, yet their physical plausibility remains poorly measured. Physical plausibility asks whether generated objects obey geometry,…
Recent works show that LLMs can generate kernels with strong performance on server GPUs. Edge deployment presents distinct challenges because the hardware is heterogeneous, the software stacks are…
Large language models (LLMs) are increasingly used to automate AI research, including language-model (LM) development, offering a potential path toward recursive self-improvement. However, turning…
Industrial manipulation in flexible manufacturing, e.g., high-mix, low-volume (HMLV) electronics assembly, requires robot policies to adapt to changing products and production conditions. Such…
Recent advances in multimodal large language models (MLLMs) have enabled them to act as autonomous agents, creating and editing 3D models via code or direct software manipulation. In practical…
Neural simulation of high-fidelity deformable bodies is a foundational challenge in computer graphics and physical AI. Long-horizon prediction for high-resolution 3D volumetric meshes is hard:…
Language-model agents that run long tasks often redo work they have already done: they re-issue a tool call they made earlier and get back exactly the same observation, a step that adds no new…
Self-supervised monocular depth estimation is appealing for its potential to scale with unlabeled data, yet existing methods often degrade when trained on diverse scenes. This study finds that, under…
Few-shot semantic segmentation typically identifies target objects based on positive support examples of a single semantic class. In practice, however, positive cues alone are often underspecified:…
Improving every agent in an LLM-based multi-agent system can be prohibitively costly, making it important to identify which agent should be prioritized to achieve the greatest system-level gain with…
Memory has become integral to the LLM agent ecosystem, supporting information retention and reuse across interactions. However, most existing agent memory systems construct memory in a query-agnostic…
Reconstructing 3D scenes from sparse views without per-scene optimization remains highly challenging, especially for recovering accurate geometry and fine textures. While recent feedforward…
Forecasting an unresolved event requires finding relevant evidence and deciding how strongly it supports each outcome. Yet outcome-based training of Large Language Model (LLM) forecasters often…
Despite their extensive pretraining knowledge and strong reasoning capabilities, large language models (LLMs) struggle to adaptively gather information in experimental design tasks. We study how to…
Autoregressive (AR) image generators are powerful in principle but inflexible in practice: training with a fixed raster-scan order hardcodes a single factorization of the image distribution into the…
Statistical downscaling is the task of reconstructing high-resolution meteorological fields from coarse inputs. A principled approach formulates downscaling as a Bayesian inverse problem, using a…
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…
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…
Reinforcement fine-tuning has become an effective post-training paradigm for improving the reasoning ability of large language models, but it remains sample-inefficient when the training distribution…
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.…
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…