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。
Short video platforms have become a primary channel for black and gray industry operations in internet finance, where inducements such as prompts to like, follow, join private chat groups, or click…
Future planetary exploration missions require teams of robots to collaboratively map unknown environments under severe communication limits, constrained onboard computation, and no central…
When a language model returns engineering quantities with the status "solved", software that trusts it passes them on, even when the requested design is physically impossible. Such failures could…
We introduce Nemotron 3.5 Super and Nemotron 3.5 Lightning, open and efficient Mixture-of-Experts Hybrid Mamba-Transformer models designed for reasoning, long-context understanding, and agentic…
We propose a neural exploratory framework for variational problems over graphons, i.e., symmetric measurable functions $[0,1]^2 \to [0,1]$, that arise as limits of dense graph sequences. Such…
Robots must act under physical and social constraints while adapting to changes in their environment and human needs. Existing embodied-agent systems often focus on specified goals or abstract…
Feature extraction from unstructured data typically relies on opaque embeddings unsuited to interpretable decision-making. Interpretable features, on the other hand, typically require costly, and…
LLM-as-a-Judge has become a standard for evaluating large language models, yet most approaches implicitly assume that a single judge prompt functions as a stable evaluation instrument. Prior work has…
Ship-to-home fulfillment requires a retailer to select a fulfillment location and carrier before the delivery time is known. These decisions often rely on static transit-time estimates, which cannot…
Reinforcement learning holds the promise of robots that learn manipulation skills from interaction alone, without pretrained priors or demonstration data. In practice, on-policy methods such as PPO…
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.
Medical chart abstraction transforms unstructured clinical narratives into structured variables for research and quality monitoring. We evaluated a prompting-based large language model (LLM)…
Vision-language-action (VLA) policies can learn to follow execution preferences, such as where to grasp an object or how to move around an obstacle, from demonstrations annotated with preference…
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).
Large language model agents are increasingly used for scientific discovery. However, existing benchmarks mix law inference with programming, score data fitting instead of prediction on unseen inputs,…
Vision-Language-Action (VLA) models offer a promising paradigm for general-purpose household robotics. However, inference and data-collection strategies that have been deployed in smaller-scale…
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…
Large language models (LLMs) are widely used as automated judges, yet most alignment methods target aggregated human judgments and overlook variation among individual annotators. Existing approaches…
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…
Language model assistants sometimes change a correct answer when the user suggests a wrong one. The behavior, called sycophancy, is usually attributed to preference-based post-training, yet early…
Large language models (LLMs) have shown increasing promise in research-level problem solving, yet a comprehensive collection of such problems is still missing, and evaluating them on research-level…
We introduce Heads of Security (HoS), a prompt injection defense that enforces instruction-data separation via a small set of learned per-head attention gates. HoS learns how each head should…
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…
Artificial intelligence offers statisticians a new paradigm for modelling and analysing complex datasets. Agents based on large language models can reason about data and automate key stages of the…