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。
Interactive 3D segmentation models such as nnInteractive turn a few spatial prompts (points, scribbles, boxes) into accurate volumetric masks, but a human still does the annotation work: finding each…
Long-text image-text alignment is essential for fine-grained scene understanding, yet existing methods mainly focus on extending context length or improving local alignment. We identify an overlooked…
Ophthalmic clinical decision support requires fast, accurate, and privacy-preserving inference, yet autoregressive large language models (LLMs) incur substantial latency and computational overhead…
Mix-policy optimization incorporates off-policy expert data into the reinforcement learning (RL) loop to transcend the capability boundary of on-policy RL. However, existing methods either provide…
LLMs are increasingly used as AI tutors, yet existing benchmarks overlook the challenging behaviors common among students with learning and behavioral difficulties. We introduce TutorCaseBench, a…
Mixture-of-Experts (MoE) large language models reduce computation through sparse activation but still incur substantial storage costs. Mixed-precision post-training quantization (PTQ) reduces these…
Natural language querying for time series databases aims to let users find what they need in long histories of data by asking in plain language. Shape queries ask how a series moves.
LLM agents that act on live Web data must combine heterogeneous evidence, remember what they have done and improve from outcomes without weakening their own safeguards. We study this problem in…
Lyapunov functions and barrier certificates give state-space guarantees of stability and safety, but synthesizing and verifying them---especially for nonlinear, high-dimensional systems---remains an…
LLM agents are flexible in language interaction, but using them as long-horizon planners is costly and prone to hallucinated or invalid actions. This paper targets a different role for LLMs:…
Hallucinated citations make it harder to trace sources and verify the evidence behind scientific claims. Detecting them is difficult because bibliographic records can be incomplete or differ across…
LLMs can act as scientific agents using tools to consult specialists and run experiments. Yet specialist information must enter their context, generally as text, images, audio or video: a bottleneck…
Through a tangle of real-world interactions, from synthetic training pipelines to data shared on the open web, frontier LLMs absorb what their predecessors and competitors create. How well does each…
Calibrating large language models (LLMs) in open-ended generation is uniquely challenging because many distinct token sequences can express the same underlying meaning. Prior calibration techniques…
Literature-searching language agents are becoming a standard component of scientific assistants for the life sciences, yet there is little controlled evidence on which parts of their harness matter.…
Retrieval-Augmented Generation (RAG) improves the performance of Large Language Models (LLMs) by retrieving external knowledge. Recently, some RAG methods interleave reasoning and retrieval, enabling…
Large language models often answer from knowledge learned during training, even when a provided passage contradicts that knowledge. To address this problem, contrastive decoding contrasts the…
Text-to-Image models reproduce societal stereotypes, and existing mitigation applies one demographic correction to the whole scene. In multi-person scene generation this creates a trade-off: global…
Omni-modal large language models (LLMs) have achieved remarkable progress in audio and video understanding. However, existing models struggle with long-form, multi-speaker videos, especially in…
Large language model (LLM) agents increasingly use tools to complete tasks in stateful environments. However, many training environments remain largely static apart from changes caused by the agent's…
As LLM agents interact in the wild and shape each other's decisions, understanding how they converge toward agreement becomes important. We study this in multi-turn conversations where two LLMs…
Learning loco-manipulation policies requires demonstrations that capture coordinated base and arm motion on the target embodiment. Robot-free interfaces allow demonstrations to be collected…
Phone scams impose substantial and growing costs on individuals and financial systems worldwide, yet existing countermeasures impose no resource cost on perpetrators. Strategic scam-baiting, in which…
Scientific discovery does not follow a single fixed methodology: research methods vary across domains and evolve through experimentation as investigations unfold. Although LLM-guided evolutionary…