Tootfinder

Opt-in global Mastodon full text search. Join the index!

No exact results. Similar results found.
@heiseonline@social.heise.de
2025-06-27 11:16:00

Unihertz Titan 2: "Blackberry"-Revival aus China mit zwei Bildschirmen
Blackberry-Revival aus China: Das Titan 2 des Herstellers Unihertz hat eine physische Tastatur unter dem Display. Auf der Rückseite ist ein zweiter Bildschirm. 

@arXiv_csCL_bot@mastoxiv.page
2025-06-27 09:59:09

Enhancing User Engagement in Socially-Driven Dialogue through Interactive LLM Alignments
Jiashuo Wang, Kaitao Song, Chunpu Xu, Changhe Song, Yang Xiao, Dongsheng Li, Lili Qiu, Wenjie Li
arxiv.org/abs/2506.21497 arxiv.org/pdf/2506.21497 arxiv.org/html/2506.21497
arXiv:2506.21497v1 Announce Type: new
Abstract: Enhancing user engagement through interactions plays an essential role in socially-driven dialogues. While prior works have optimized models to reason over relevant knowledge or plan a dialogue act flow, the relationship between user engagement and knowledge or dialogue acts is subtle and does not guarantee user engagement in socially-driven dialogues. To this end, we enable interactive LLMs to learn user engagement by leveraging signals from the future development of conversations. Specifically, we adopt a more direct and relevant indicator of user engagement, i.e., the user's reaction related to dialogue intention after the interaction, as a reward to align interactive LLMs. To achieve this, we develop a user simulator to interact with target interactive LLMs and explore interactions between the user and the interactive LLM system via \textit{i$\times$MCTS} (\textit{M}onte \textit{C}arlo \textit{T}ree \textit{S}earch for \textit{i}nteraction). In this way, we collect a dataset containing pairs of higher and lower-quality experiences using \textit{i$\times$MCTS}, and align interactive LLMs for high-level user engagement by direct preference optimization (DPO) accordingly. Experiments conducted on two socially-driven dialogue scenarios (emotional support conversations and persuasion for good) demonstrate that our method effectively enhances user engagement in interactive LLMs.
toXiv_bot_toot

@arXiv_mathKT_bot@mastoxiv.page
2025-05-27 13:37:38

This arxiv.org/abs/2409.16556 has been replaced.
initial toot: mastoxiv.page/@arXiv_mat…

@Techmeme@techhub.social
2025-06-27 22:35:57

Anthropic tested Claude's ability to manage a physical "storefront" to mixed results, as the AI struggled with pricing strategy and inventory management (Ryan Daws/AI News)
artificialintelligence-news.co

@arXiv_mathOA_bot@mastoxiv.page
2025-05-27 07:33:04

Strict comparison for twisted group C*-algebras
Sven Raum, Hannes Thiel, Eduard Vilalta
arxiv.org/abs/2505.18569 arxi…

@arXiv_mathNT_bot@mastoxiv.page
2025-06-26 08:22:40

Values at non-positive integers of partially twisted multiple zeta-functions II
Driss Essouabri, Kohji Matsumoto, Simon Rutard
arxiv.org/abs/2506.20150

@arXiv_condmatmeshall_bot@mastoxiv.page
2025-06-27 08:29:29

The Interacting Energy Bands of Magic Angle Twisted Bilayer Graphene Revealed by the Quantum Twisting Microscope
J. Xiao, A. Inbar, J. Birkbeck, N. Gershon, Y. Zamir, T. Taniguchi, K. Watanabe, E. Berg, S. Ilani
arxiv.org/abs/2506.20738

@frostpoem@mastodon.art
2025-04-28 12:18:36

The cauldron bubbled aggressively to greet me as I opened the tower door, black and gleaming in the firelight. Beside it, I caught a wisp of white hair, a bent, bony silhouette and took a retreating step back. this was not where I was supposed to be.
"Don't go:"
The voice was harsh, cracking with sharpness as the woman lifted her head and twisted around to look at me: I cowered at the sight of that hooked nose, those dark eyes, but her smile was... kind? 1/
#MastoPrompt #MicroPrompt #WSS366

@heiseonline@social.heise.de
2025-06-26 10:48:00

Xbench: Chinesischer KI-Benchmark prüft Modelle auf Alltagstauglichkeit
Ein neuer Benchmark aus China testet KI-Modelle auf ihre Fähigkeit, reale Aufgaben zu lösen. Er soll Unternehmen bei Investitionsentscheidungen in KI helfen.

@frostpoem@mastodon.art
2025-04-28 12:18:36

The cauldron bubbled aggressively to greet me as I opened the tower door, black and gleaming in the firelight. Beside it, I caught a wisp of white hair, a bent, bony silhouette and took a retreating step back. this was not where I was supposed to be.
"Don't go:"
The voice was harsh, cracking with sharpness as the woman lifted her head and twisted around to look at me: I cowered at the sight of that hooked nose, those dark eyes, but her smile was... kind? 1/
#MastoPrompt #MicroPrompt #WSS366