MLINFO COLLECTION
過去の実験ノート、技術報告書、特許、論文を探しやすくするための製造業向けRAG導線です。
Zero-shot vision-and-language navigation (VLN) requires an agent to use past observations without navigation-specific training. We study what information an 8B-scale navigation system should retain…
Language-model answers are often treated as a visible record of the internal decision that produced them. We test this assumption in conflicting-context question answering, where two supplied…
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…
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…
Robot-learning studies often compare position and velocity actions as though each label identified a single experimental treatment, yet the label alone does not determine what the robot executes.…
Recent advances in monocular depth estimation have demonstrated highly accurate 3D reconstructions within in-distribution terrestrial domains. This study investigates the efficacy of several…
Numbers computed from trained models, such as an example's difficulty or a model's benchmark lead, change with seed and prompt. We ask when such measurements can be corrected or compared.
We describe the QMUL_AK submission to AISA-ArabicFC 2026. The system adapts the Arabic-English ALLaM-7B-Instruct model to function calling with low-rank adaptation (LoRA).
Latent multi-agent systems reduce inference cost by keeping intermediate reasoning and inter-agent communication in continuous representations.\ Reusable skills, however, are commonly supplied as…
Metis is a bet that better data, better training methods and new architectures can buy what a bigger parameter count cannot, at a fraction of the cost. Metis-1.6 is its latest step: two language…
Retrieval-augmented generation (RAG) lets a large language model (LLM) answer questions by retrieving relevant passages from a large corpus. However, RAG struggles with multi-hop questions, which…
Large Language Models (LLMs) are increasingly used in multi-turn agentic workloads that require sustained interaction with complex environments. Existing reflective prompt optimizers such as GEPA…
Self-attention plays a key role in long-sequence modeling, but its quadratic time complexity fundamentally limits the scaling of Large Language Models. Recently, Multi-State Linear Attention (MSLA)…
Multi-robot control requires integrating distributed camera views while predicting separate action sequences. Most vision-language-action and world-action models target one robot.
As egocentric video becomes increasingly available for embodied learning, an important research question is how to turn this low-cost, scalable source of data into robot manipulation capabilities.…
Fine-tuning Large Language Models (LLMs) on instruction data can quietly erode their safety, even when no training example looks harmful. Because this safety-degrading data looks benign, standard…
Long-term memory enables Large Language Models (LLMs) to maintain coherent and personalized interactions across extended conversations. However, existing memory systems face two key challenges: (1)…
Vision-Language-Action (VLA) policies demonstrate remarkable semantic generalization, yet remain highly vulnerable to out-of-distribution (OOD) visual shifts during execution. While existing…
We trained four widely used imitation-learning policies, ACT, Diffusion Policy, SmolVLA and $π_{0.5}$, on nested subsets of 12, 25, 50, 100 and 200 teleoperated demonstrations of one pick-and-place…
Variational inference with normalizing flows provides a flexible posterior approximation for Bayesian model calibration, but struggles when the posterior has several modes separated by regions of low…
Joint-embedding predictive architectures (JEPAs) enable world models to plan from images by predicting future embeddings. However, their visual prediction objectives do not explicitly incorporate…
Typed decision models return a probability distribution over options supplied by the caller, and software tends to act on that number as if it were a guarantee. We measure what it licenses, comparing…
Two compass bearings near north can have an ordinary arithmetic mean pointing south: the difficulty is that angles live on a circle, not a straight line. Using real wind observations, diffusion-MRI…
We study score matching over finite-dimensional approximation spaces generated by gradients of eigenfunctions of the infinitesimal generator of a forward diffusion. We compare polynomial…