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。
Human demonstrations offer an efficient and scalable source of data for dexterous robot manipulation, but differences in sensing and hand morphology complicate the transfer of contact-rich…
Radiological risk stratification and management planning are essential downstream tasks in medical imaging. Automating these tasks is challenging because clinical guideline criteria are distributed…
Objectives: To evaluate the accuracy and calibration of Decision and System One models on rheumatology examination questions and diagnostic vignettes. Methods: Two benchmarks were analysed: 172…
Vision-language models (VLMs) exhibit strong zero-shot generalization but remain vulnerable to adversarial attacks. Existing adversarial fine-tuning methods often use pre-trained model guidance to…
Modern LLMs strain device memory through large model weights and attention states, particularly in resource-constrained scenarios. Existing systems separately provision memory for model weights and…
Prefill-decode (PD) disaggregation isolates the two phases of large language model serving, but request-level path selection must account for prefill work, cache reuse, and decode demand. We present…
Large language model serving is limited by facility power. Energy per token determines how many tokens a datacenter can serve, while a latency target bounds how quickly each user receives them.
Large language models (LLMs) are increasingly capable, yet they produce wrong answers indistinguishable from correct ones. In question answering (QA), such an error propagates unnoticed into…
Synthetic data are widely used for training modern AI systems. However, their statistical understanding remains limited.
Reaction precedents guide retrosynthesis, but how far they can compensate for gaps in task-specific training coverage remains unclear. Using 2.71 million reactions, we restricted training and…
Robotic navigation typically assumes a collision-free route to the goal exists; in cluttered environments with movable obstacles, however, reaching the goal may require physical interaction.…
Computer-use agents built on large language models (LLMs) work in software that can change while they act: an appointment moves, a policy is revised, a record is updated. Testing agents under such…
To save cost, practitioners often ask a language model to grade many independent items in one prompt. This assumes that verdicts are separable: that the verdict on an item does not depend on the…
Sentence-level scientific claim verification determines whether each sentence in an AI-generated scientific paragraph is supported by a given multimodal evidence bundle. Fine-grained reporting errors…
While mining parallel sentences from web pages has proven effective for low-resource machine translation, the majority of the world's languages have little to no web presence. What they do have,…
Epistemic game theory explains an agent's strategic behavior via the beliefs it holds about others and how these beliefs are updated as the interactions unfold. Modern LLM-based agents, however,…
Multimodal large language models (MLLMs) are now used as zero-shot judges of image quality, but their color judgments are rarely tested with colorimetric ground truth. We present a five-task…
Argument mining in full-text scholarly articles remains an important yet challenging task. This difficulty stems not only from the need to model long-distance dependencies but also from the…
Multi-step Web tasks often require several LLM agents to gather and combine evidence. The communication graph of a fixed workflow restricts which agents can read each other's outputs: evidence…
Increasingly, users express their needs as natural-language intents rather than structured requests. These intents may be incomplete, high-level, or internally conflicting.
Multimodal large language models (MLLMs) can now process hour-long videos, making extended multi-turn dialogue over a single video a natural mode of use. Sustaining such a dialogue requires more than…
Vision--language models (VLMs) are tested for fine-grained understanding with image--text matching probes, a model must prefer the correct image or caption over handcrafted negative. In retrieval,…
The pursuit of fair and equitable AI in human-centric tasks is critically hindered by the inherent biases and privacy risks of real-world datasets, which offer imbalanced representations of identity…
Effective multi-domain adaptation of large language models requires prioritizing relevant domain knowledge while minimizing interference from irrelevant domains. Existing approaches commonly use…