Tootfinder

Reasoning about Uncertainty: Do Reasoning Models Know When They Don't Know?
Zhiting Mei, Christina Zhang, Tenny Yin, Justin Lidard, Ola Shorinwa, Anirudha Majumdar
https://arxiv.org/abs/2506.18183

Reasoning about Uncertainty: Do Reasoning Models Know When They Don't Know?
Reasoning language models have set state-of-the-art (SOTA) records on many challenging benchmarks, enabled by multi-step reasoning induced using reinforcement learning. However, like previous language models, reasoning models are prone to generating confident, plausible responses that are incorrect (hallucinations). Knowing when and how much to trust these models is critical to the safe deployment of reasoning models in real-world applications. To this end, we explore uncertainty quantification…

The #OpenAI paper by Baker et al, "Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation" comes to a troubling conclusion: #LLM s with #reasoning or

Gesetzentwurf: Bankkunden sollen mehr Rechte beim Dispo bekommen
Online-Shopping auf Rechnung soll eingeschränkt werden, da vor allem junge Menschen dadurch leicht den Überblick verlieren und in die Schuldenfalle geraten.

Architecture is All You Need: Improving LLM Recommenders by Dropping the Text
Kevin Foley, Shaghayegh Agah, Kavya Priyanka Kakinada
https://arxiv.org/abs/2506.15833

Architecture is All You Need: Improving LLM Recommenders by Dropping the Text
In recent years, there has been an explosion of interest in the applications of large pre-trained language models (PLMs) to recommender systems, with many studies showing strong performance of PLMs on common benchmark datasets. PLM-based recommender models benefit from flexible and customizable prompting, an unlimited vocabulary of recommendable items, and general ``world knowledge'' acquired through pre-training on massive text corpora. While PLM-based recommenders show promise in settings whe…

ConciseHint: Boosting Efficient Reasoning via Continuous Concise Hints during Generation
Siao Tang, Xinyin Ma, Gongfan Fang, Xinchao Wang
https://arxiv.org/abs/2506.18810

ConciseHint: Boosting Efficient Reasoning via Continuous Concise Hints during Generation
Recent advancements in large reasoning models (LRMs) like DeepSeek-R1 and OpenAI o1 series have achieved notable performance enhancements on complex reasoning tasks by scaling up the generation length by Chain-of-Thought (CoT). However, an emerging issue is their inclination to produce excessively verbose reasoning processes, leading to the inefficiency problem. Existing literature on improving efficiency mainly adheres to the before-reasoning paradigms such as prompting and reasoning or fine-t…

Galaxy Z Fold 7 und mehr: Samsung kündigt Unpacked-Event für 9. Juli an
Samsung will Anfang Juli im Zuge eines Unpacked-Events neue Produkte vorstellen. Neben Foldables können Konsumenten auch mit Galaxy-Watches rechnen. 

A Framework for Generating Conversational Recommendation Datasets from Behavioral Interactions
Vinaik Chhetri, Yousaf Reza, Moghis Fereidouni, Srijata Maji, Umar Farooq, AB Siddique
https://arxiv.org/abs/2506.17285

A Framework for Generating Conversational Recommendation Datasets from Behavioral Interactions
Modern recommendation systems typically follow two complementary paradigms: collaborative filtering, which models long-term user preferences from historical interactions, and conversational recommendation systems (CRS), which interact with users in natural language to uncover immediate needs. Each captures a different dimension of user intent. While CRS models lack collaborative signals, leading to generic or poorly personalized suggestions, traditional recommenders lack mechanisms to interacti…

PhysUniBench: An Undergraduate-Level Physics Reasoning Benchmark for Multimodal Models
Lintao Wang, Encheng Su, Jiaqi Liu, Pengze Li, Peng Xia, Jiabei Xiao, Wenlong Zhang, Xinnan Dai, Xi Chen, Yuan Meng, Mingyu Ding, Lei Bai, Wanli Ouyang, Shixiang Tang, Aoran Wang, Xinzhu Ma
https://arxiv.org/abs/2506.17667

PhysUniBench: An Undergraduate-Level Physics Reasoning Benchmark for Multimodal Models
Physics problem-solving is a challenging domain for large AI models, requiring integration of conceptual understanding, mathematical reasoning, and interpretation of physical diagrams. Current evaluation methodologies show notable limitations in capturing the breadth and complexity of undergraduate-level physics, underscoring the need for more rigorous assessments. To this end, we present PhysUniBench, a large-scale multimodal benchmark designed to evaluate and improve the reasoning capabilitie…

Pyramid Mixer: Multi-dimensional Multi-period Interest Modeling for Sequential Recommendation
Zhen Gong, Zhifang Fan, Hui Lu, Qiwei Chen, Chenbin Zhang, Lin Guan, Yuchao Zheng, Feng Zhang, Xiao Yang, Zuotao Liu
https://arxiv.org/abs/2506.16942

Pyramid Mixer: Multi-dimensional Multi-period Interest Modeling for Sequential Recommendation
Sequential recommendation, a critical task in recommendation systems, predicts the next user action based on the understanding of the user's historical behaviors. Conventional studies mainly focus on cross-behavior modeling with self-attention based methods while neglecting comprehensive user interest modeling for more dimensions. In this study, we propose a novel sequential recommendation model, Pyramid Mixer, which leverages the MLP-Mixer architecture to achieve efficient and complete modelin…

LLM-Enhanced Multimodal Fusion for Cross-Domain Sequential Recommendation
Wangyu Wu, Zhenhong Chen, Xianglin Qiu, Siqi Song, Xiaowei Huang, Fei Ma, Jimin Xiao
https://arxiv.org/abs/2506.17966

LLM-Enhanced Multimodal Fusion for Cross-Domain Sequential Recommendation
Cross-Domain Sequential Recommendation (CDSR) predicts user behavior by leveraging historical interactions across multiple domains, focusing on modeling cross-domain preferences and capturing both intra- and inter-sequence item relationships. We propose LLM-Enhanced Multimodal Fusion for Cross-Domain Sequential Recommendation (LLM-EMF), a novel and advanced approach that enhances textual information with Large Language Models (LLM) knowledge and significantly improves recommendation performance…