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。
For more than three decades, UPPAAL has supported the modelling and analysis of real-time and cyber-physical systems. Yet building a suitable model, formalising the intended properties, choosing…
Large language models (LLMs) can improve task performance during learning, yet these gains do not necessarily reflect learners' ability to thereafter apply the knowledge and skills independently. We…
Automatic operator design (AOD) has increasingly adopted large language models (LLMs) to generate problem-specific search and variation operators for multi-objective combinatorial optimization…
Vulnerable road user (VRU) prediction must operate under partial observability and distribution shift, so reliable uncertainty matters alongside accuracy. Masked pretraining is attractive in this…
When persona-conditioned responses are read as respondent-level simulations, each response should reflect the described persona's knowledge, and the respondent written to know nothing must act as if…
Novel view synthesis (NVS) in degraded scenes aims to reconstruct 3D scenes from multi-view observations affected by various degradations, and to generate clear and photorealistic images at unseen…
Reinforcement Learning with Verifiable Rewards has shown great promise in enhancing mathematical reasoning in large language models. However, existing approaches provide limited intermediate…
Clients observing different parts of a prediction task may learn locally equivalent models with incompatible behavior outside their observed support. We study whether redundant models permit local…
Industrial advertising agents must continually adapt their decision knowledge to changing product offerings, traffic patterns, and operating policies. We present KARMA (Knowledge-Atomic,…
We study post-training for dynamically routed mixture-of-experts (MoE) models, focusing on integrating independently optimized specialists while keeping consolidation efficient. Our approach combines…
New concepts based in interactional thinking are required to understand how humans are changed by relating to LLMs. Standard theories of technological impact upon users' autonomy are inadequate here,…
Unlike autoregressive large language models (AR-LLMs), diffusion LLMs (dLLMs) generate text by iteratively denoising many tokens in parallel, offering a promising path to efficient inference.…
Continual learning methods for large language models increasingly decide what to learn by surprise, keeping the inputs the model finds least predictable. This rule is unsafe when the stream contains…
Long-horizon consistency is essential for video world models, yet it becomes difficult to maintain once observed content falls outside the context window. Existing memory mechanisms either retrieve…
Large language model serving stacks, commercial inference APIs, vector databases, and agent orchestration gateways are now ex- posed on the public internet and indexed by commodity scanners within…
Over-refusal is a critical side effect of safety alignment in large language models (LLMs), causing harmless but superficially risky queries to be mistakenly rejected. Despite the effectiveness of…
As Large Language Model (LLM) agents increasingly participate in persistent social environments, understanding their long-term social interaction capabilities becomes increasingly important. While…
Autonomous mobile robots commonly pair a global planner with a local model predictive controller (MPC), but nonconvex obstacle avoidance and a limited horizon can make the robot freeze in complex…
Efforts to monitor advanced AI for rare misalignments face a data challenge: abundant aligned examples but only a handful of misaligned ones. We test activation probes in this "few vs.
In engineering, applications of artificial intelligence have so far been largely limited to surrogate models and optimization tasks. Large language models changed this, as they can write software…
Background: Contemporary healthcare institutions generate daily very large amounts of data, which contain highly useful information for the improvement of work organization, planning and overall…
Large language models (LLMs) draw on parametric knowledge and retrieval-augmented generation (RAG) to solve knowledge-intensive tasks. Yet problem solving in unfamiliar domains calls for tightly…
Thinking vision-language models reason for thousands of tokens, yet still miss small details in high-resolution images. Zooming methods pay for extra inference passes, and outcome rewards never tell…
The integration of Large Language Models (LLMs) into agentic architectures has substantially increased token consumption, raising concerns about their energy footprint. Yet, estimating the energy…