Tootfinder

🇺🇦 #NowPlaying on KEXP's #VarietyMix
Erika de Casier:
🎵 Miss
#ErikadeCasier
https://jalenjones.bandcamp.com/track/erika-de-casier-miss-jalen-jones-ukg-bootleg
https://open.spotify.com/track/3iewIkYTvvaicW8iysqxuU

From Surface to Semantics: Semantic Structure Parsing for Table-Centric Document Analysis
Xuan Li, Jialiang Dong, Raymond Wong
https://arxiv.org/abs/2508.10311 https://

From Surface to Semantics: Semantic Structure Parsing for Table-Centric Document Analysis
Documents are core carriers of information and knowl-edge, with broad applications in finance, healthcare, and scientific research. Tables, as the main medium for structured data, encapsulate key information and are among the most critical document components. Existing studies largely focus on surface-level tasks such as layout analysis, table detection, and data extraction, lacking deep semantic parsing of tables and their contextual associations. This limits advanced tasks like cross-paragrap…

Learning to Detect Unknown Jailbreak Attacks in Large Vision-Language Models: A Unified and Accurate Approach
Shuang Liang, Zhihao Xu, Jialing Tao, Hui Xue, Xiting Wang
https://arxiv.org/abs/2508.09201

Learning to Detect Unknown Jailbreak Attacks in Large Vision-Language Models: A Unified and Accurate Approach
Despite extensive alignment efforts, Large Vision-Language Models (LVLMs) remain vulnerable to jailbreak attacks, posing serious safety risks. Although recent detection works have shifted to internal representations due to their rich cross-modal information, most methods rely on heuristic rules rather than principled objectives, resulting in suboptimal performance. To address these limitations, we propose Learning to Detect (LoD), a novel unsupervised framework that formulates jailbreak detecti…

🇺🇦 Auf radioeins läuft...
Jalen Ngonda:
🎵 All About Me
#NowPlaying #JalenNgonda
#newRelease 🆕 single
https://jalenngonda.bandcamp.com/album/all-about-me
https://open.spotify.com/track/60mXzhxdo3dtKYz1MNBLFD

'There's no feel-good moments out of this': Saints rally after half, still drop to 0-2 https://www.espn.com/nfl/story/_/id/46264410/new-orleans-saints-positives-winless-start-2025

Cross-Timeslot Optimization for Distributed GPU Inference Using Reinforcement Learning
Chengze Du, Zhiwei Yu, Heng Xu, Haojie Wang, Bo liu, Jialong Li
https://arxiv.org/abs/2507.10259

Cross-Timeslot Optimization for Distributed GPU Inference Using Reinforcement Learning
The rapid growth of large language model (LLM) services imposes increasing demands on distributed GPU inference infrastructure. Most existing scheduling systems rely on the current system state to make decisions, without considering how task demand and resource availability evolve over time. This lack of temporal awareness leads to inefficient GPU utilization, high task migration overhead, and poor system responsiveness under dynamic workloads. In this work, we identify the fundamental limitati…

Julmasti kettuja kohdelleet turkistarhurit saivat pysyvän eläintenpitokiellon - #eläinoikeudet

Julmasti kettuja kohdelleet turkistarhurit saivat pysyvän eläintenpitokiellon
Ketut olivat sairaita ja laihoja, eikä niistä pidetty huolta. Myöhemmässä tarkastuksessa tarhalta löydettiin kymmeniä muumioituneita eläimiä.

Towards Self-cognitive Exploration: Metacognitive Knowledge Graph Retrieval Augmented Generation
Xujie Yuan, Shimin Di, Jielong Tang, Libin Zheng, Jian Yin
https://arxiv.org/abs/2508.09460

Towards Self-cognitive Exploration: Metacognitive Knowledge Graph Retrieval Augmented Generation
Knowledge Graph-based Retrieval-Augmented Generation (KG-RAG) significantly enhances the reasoning capabilities of LargeLanguage Models by leveraging structured knowledge. However, existing KG-RAG frameworks typically operate as open-loop systems, suffering from cognitive blindness, an inability to recognize their exploration deficiencies. This leads to relevance drift and incomplete evidence, which existing self-refinement methods, designed for unstructured text-based RAG, cannot effectively r…

Dynamic Parameter Memory: Temporary LoRA-Enhanced LLM for Long-Sequence Emotion Recognition in Conversation
Jialong Mai, Xiaofen Xing, Yawei Li, Zhipeng Li, Jingyuan Xing, Xiangmin Xu
https://arxiv.org/abs/2507.09076

Dynamic Parameter Memory: Temporary LoRA-Enhanced LLM for Long-Sequence Emotion Recognition in Conversation
Recent research has focused on applying speech large language model (SLLM) to improve speech emotion recognition (SER). However, the inherently high frame rate in speech modality severely limits the signal processing and understanding capabilities of SLLM. For example, a SLLM with a 4K context window can only process 80 seconds of audio at 50Hz feature sampling rate before reaching its capacity limit. Input token compression methods used in SLLM overlook the continuity and inertia of emotions a…