Tootfinder

G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems
Guibin Zhang, Muxin Fu, Guancheng Wan, Miao Yu, Kun Wang, Shuicheng Yan
https://arxiv.org/abs/2506.07398

G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems
Large language model (LLM)-powered multi-agent systems (MAS) have demonstrated cognitive and execution capabilities that far exceed those of single LLM agents, yet their capacity for self-evolution remains hampered by underdeveloped memory architectures. Upon close inspection, we are alarmed to discover that prevailing MAS memory mechanisms (1) are overly simplistic, completely disregarding the nuanced inter-agent collaboration trajectories, and (2) lack cross-trial and agent-specific customiza…

Time to punish the new servers. Also, muxed the `m2ts` to `mkv` files so there are functional progress bars this time.
#homelab #ffmpeg #encoding

'Gegenlicht' #FotoVorschlag
Mirador Jesus Quintanal in Muxia #Spanien auf dem letzten Teil des Camino de Santiago #Jakobsweg. Denkmal an der Costa da Morte als Erinnerung an das Tankeru…

Anybody have a USB superspeed 2 port hub chipset you like?
No PD required, but if it includes the muxing for USB-C rotation that would be great.
Single row QFN package would be ideal, large (0.8/1mm pitch) BGA doable. TQFP and WLCSP/0.5mm BGA are no go.

Two-Sample Testing with Block-Wise Missingness in Multi-Source Data
Kejian Zhang, Muxuan Liang, Robert Maile, Doudou Zhou
https://arxiv.org/abs/2508.17411 https://

Two-Sample Testing with Block-Wise Missingness in Multi-Source Data
Multi-source and multi-modal datasets are increasingly common in scientific research, yet they often exhibit block-wise missingness, where entire data sources or modalities are systematically absent for subsets of subjects. This structured form of missingness presents significant challenges for statistical analysis, particularly for two-sample hypothesis testing. Standard approaches such as imputation or complete-case analysis can introduce bias or result in substantial information loss, especi…

MedReasoner: Reinforcement Learning Drives Reasoning Grounding from Clinical Thought to Pixel-Level Precision
Zhonghao Yan, Muxi Diao, Yuxuan Yang, Jiayuan Xu, Kaizhou Zhang, Ruoyan Jing, Lele Yang, Yanxi Liu, Kongming Liang, Zhanyu Ma
https://arxiv.org/abs/2508.08177

MedReasoner: Reinforcement Learning Drives Reasoning Grounding from Clinical Thought to Pixel-Level Precision
Accurately grounding regions of interest (ROIs) is critical for diagnosis and treatment planning in medical imaging. While multimodal large language models (MLLMs) combine visual perception with natural language, current medical-grounding pipelines still rely on supervised fine-tuning with explicit spatial hints, making them ill-equipped to handle the implicit queries common in clinical practice. This work makes three core contributions. We first define Unified Medical Reasoning Grounding (UMRG…

Evidence of scaling advantage on an NP-Complete problem with enhanced quantum solvers
Quanfeng Lu, Shijie Wei, Keren Li, Pan Gao, Bao Yan, Muxi Zheng, Haoran Zhang, Jinfeng Zeng, Gui-Lu Long
https://arxiv.org/abs/2508.08869

Evidence of scaling advantage on an NP-Complete problem with enhanced quantum solvers
Achieving quantum advantage remains a key milestone in the noisy intermediate-scale quantum era. Without rigorous complexity proofs, scaling advantage-where quantum resource requirements grow more slowly than their classical counterparts-serves as the primary indicator. However, direct applications of quantum optimization algorithms to classically intractable problems have yet to demonstrate this advantage. To address this challenge, we develop enhanced quantum solvers for the NP-complete one-i…

Pretty happy, first episode went from ~6GB to 250MB. Settings are still good, quality is outstanding, and the chapters, subtitles, and fonts all muxed in beautifully. Gonna let these encodes finish up on the cluster while I listen to some music and drink a few beers outside.
#homelab #encoding

🇺🇦 #NowPlaying on #BBC6Music's #FreakZonePlaylist
Smote:
🎵 The Linton Wyrm
#Smote
#newRelease 🆕 single
https://smote.bandcamp.com/track/the-linton-wyrm
https://open.spotify.com/track/488D0HZmUxg6ANtVVCRqan

Late Fusion Multi-task Learning for Semiparametric Inference with Nuisance Parameters
Sohom Bhattacharya, Yongzhuo Chen, Muxuan Liang
https://arxiv.org/abs/2507.07941

Late Fusion Multi-task Learning for Semiparametric Inference with Nuisance Parameters
In the age of large and heterogeneous datasets, the integration of information from diverse sources is essential to improve parameter estimation. Multi-task learning offers a powerful approach by enabling simultaneous learning across related tasks. In this work, we introduce a late fusion framework for multi-task learning with semiparametric models that involve infinite-dimensional nuisance parameters, focusing on applications such as heterogeneous treatment effect estimation across multiple da…