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。
Vehicle-to-everything (V2X) communication enables connected vehicles to make safety-critical decisions, but delayed, missing, or incorrect information can compromise driving safety. Systematically…
Many language-model pipelines end in a closed-set decision, such as selecting a tool. Prompting a large language model for it is slow and order-sensitive.
Large Language Models (LLMs) can generate UML class diagrams from natural language requirements, but hallucinations may compromise the correctness and completeness of the resulting diagrams. Existing…
General-purpose embeddings trained on profile similarity often misrank candidates in professional networks, where relevance is inherently complementary rather than symmetric. For example, job seekers…
The security of modern public-key cryptographic systems, such as RSA, Diffie-Hellman, and ECC, depends entirely on the computational intractability of the integer factorization and discrete logarithm…
Activation verbalizers translate the internal representations of large language models into human-readable text. The recently proposed natural language autoencoders (NLAs) learn this by…
With external tools, large language models (LLMs) can tackle complex tasks through sustained environmental interaction. LLM-based agents are therefore increasingly used to tackle complex long-horizon…
Space data centers (SpaceDCs) are emerging as platforms for large language models (LLMs), supported by continuous solar-energy harvesting and high-speed interconnections. The mixture-of-experts (MoE)…
Vision-language models (VLMs) struggle with in context learning compared to their textual counterparts. Our preliminary study shows that VLMs rely on textual shortcuts and underutilize the visual…
Chemical AI workflows routinely represent the same molecule through multiple co-referring identifiers, including trivial names, IUPAC names, and SMILES, implicitly assuming that these representations…
Silicon sampling generates survey respondents by having a large language model (LLM) answer a survey as a person with given demographic attributes, and the resulting synthetic populations are…
PowerPoint presentations (PPTs) are a dominant medium for communication across diverse domains, yet high-quality PPT generation still depends heavily on labor-intensive human effort. Recent advances…
Humanoid robots must coordinate locomotion and manipulation in everyday environments, yet progress is difficult to assess across differing policies, controllers, and task settings. LocoManiLab…
We introduce Lean Finder V2, a semantic search framework for Mathlib that disambiguates user queries through complementary model-level adversarial training and input-level query rewriting. Human…
Ambiguity is a central feature of natural communication: a sentence, image, or sound may remain underspecified until evidence from the other channels is considered. Yet current multimodal benchmarks…
Long chain-of-thought reasoning improves vision-language models (VLMs), but it also exposes a temporal grounding failure: as generation unfolds, models may drift from image evidence while…
The increasing adoption of generative AI presents new opportunities while raising AI governance and regulatory challenges, particularly for small and medium-sized enterprises (SMEs) navigating the…
Loco-manipulation extends the workspace of conventional manipulation by combining mobility with physical interaction, while aerial loco-manipulation further expands this capability into…
Large language models (LLMs) achieve high inference efficiency using optimized GPU kernels generated by just-in-time (JIT) compilation frameworks such as Triton. Triton compiles GPU kernels through…
KV caching reduces the serving cost of large language models (LLMs), but the growing KV cache footprint is increasingly exceeds GPU and host-memory capacity. Therefore, people use SSD to expand the…
LLM agents can evolve by learning from accumulated experience. Existing approaches extract reusable external knowledge, such as skills and memories, from experience to guide subsequent task solving,…
Language models are aligned to avoid using protected attributes such as race, ethnicity, and gender to inform their responses. Therefore, they increasingly refuse or hedge when such attributes appear…
Large language models (LLMs) increasingly operate in multi-agent systems where they collaborate by responding to others' choices, creating endogenous feedback loops with vulnerability to social…
We study generative reward models (GenRMs) as online preference providers for policy optimization in creative writing. Across Qwen3 reward-model sizes from 0.6B to 14B, Thinking judges trained with…