MLINFO COLLECTION
工程条件、原料ロット、測定値から、品質指標や不良リスクを予測するための実装ガイドです。
Large language models (LLMs) have shown strong potential for cybersecurity, leading to growing interest in LLM-based automated cybersecurity log analysis. However, current datasets (1) are limited in…
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…
Activation verbalizers translate the internal representations of large language models into human-readable text. The recently proposed natural language autoencoders (NLAs) learn this by…
Auxiliary patient data can improve chest X-ray report generation, but directly concatenating heterogeneous clinical information with visual tokens produces long, variable-length decoder prompts and…
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…
Few-step autoregressive video generation enables low-latency streaming, yet prevailing training pipelines separate causal adaptation from distribution matching. Recent representation-based…
Real-image editing commonly relies on inversion and iterative sampling, while efficient one-step editors often stabilize a large update by estimating and averaging editing fields at multiple noise…
Graphs play a crucial role in many applications, ranging from drug discovery to social network modeling and astronomy. Generative models for graphs have substantially advanced in recent years, but we…
We study episodic linear Markov decision processes with unknown transitions, adversarial losses, and bandit feedback. The state-of-the-art result for this setting (Liu et al., 2024) either achieves…
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,…
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…
Masked diffusion models (MDMs) generate sequences by progressively unmasking tokens, but errors introduced during decoding are typically irreversible. Recent work has shown that iterative correction…
Video provides a natural source of supervision: what happens next serves as a learning signal for visual world modeling. Yet masked video pretraining focuses on recovering missing content from…
An LLM agent can retrieve a memory correctly yet use it incorrectly after its validity state changes. We study governance-state corruption: faults that alter which retained records enter…
Contrastive Language-Image Pre-training (CLIP) has shown superior performance in the image-level open-vocabulary classification task, benefiting from its powerful alignment of visual features and…
Many problems in signal processing, machine learning, and neuroimaging provide several jointly observed measurements of one process, each mixing a component common to all of them with a component…
Trajectory tracking for compliant robots is challenging due to nonlinear dynamics and modeling uncertainties, often requiring learning-based methods to avoid explicit parameter identification.…
Offline reinforcement learning is fundamentally limited by the coverage of the available data, while collecting additional trajectories through online exploration may be costly, unsafe, or…
Ranking data in modern applications often involves covariate vectors whose dimension grows with the number of objects. Identifying relevant covariates and integrating them with item-specific…
The goal of this paper is to distill insight around the trade-offs present on Bayesian equilibria of transaction fee mechanism (TFM) design under $n$ multiple concurrent proposers (MCP). We…
Allocating renewable resources fairly requires accounting for how present decisions affect future availability. We introduce Sustainable and Envy-Free Multi-Period Allocation, in which agents are…
Exact demographic parity requires the same prediction distribution across sensitive groups. In regression, this can be too restrictive and reduce predictive accuracy.
Trust and reputation mechanisms can reduce the influence of malicious clients in federated learning (FL), but strict update filtering is difficult under non-independent and identically distributed…
Direct Preference Optimization (DPO) is widely used for offline Reinforcement Learning from Human Feedback. However, recent works have shown that DPO can be easily manipulated by adversarial…