Tootfinder

Diversity-Incentivized Exploration for Versatile Reasoning
Zican Hu, Shilin Zhang, Yafu Li, Jianhao Yan, Xuyang Hu, Leyang Cui, Xiaoye Qu, Chunlin Chen, Yu Cheng, Zhi Wang
https://arxiv.org/abs/2509.26209

Diversity-Incentivized Exploration for Versatile Reasoning
Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a crucial paradigm for incentivizing reasoning capabilities in Large Language Models (LLMs). Due to vast state-action spaces and reward sparsity in reasoning tasks, existing methods often struggle with deficient exploration and poor sample efficiency. In the paper, we propose \textbf{DIVER} (\textbf{D}iversity-\textbf{I}ncentivized Exploration for \textbf{V}ersatil\textbf{E} \textbf{R}easoning), an innovative framework that hi…

One of the world’s premier security organizations has canceled the results of its annual leadership election
-- after an official lost an encryption key needed to unlock results stored in a verifiable and privacy-preserving voting system.
The International Association of Cryptologic Research (IACR) said Friday that the votes were submitted and tallied using Helios,
an open source voting system that uses peer-reviewed cryptography to cast and count votes in a verifiable, con…

Oops. Cryptographers cancel election results after losing decryption key.
Voting system required three keys. One of them has been “irretrievably lost.”…

Verifiable blind observable estimation: A composably secure protocol for near-term quantum advantage tasks
Bo Yang, Elham Kashefi, Harold Ollivier
https://arxiv.org/abs/2510.08548

Verifiable blind observable estimation: A composably secure protocol for near-term quantum advantage tasks
The rapid advance of quantum hardware is spotlighting pre-fault-tolerant tasks that may no longer be efficiently validated by classical means and are likely to run on potentially untrusted remote quantum servers. This motivates problem-independent verification protocols with rigorous guarantees. The Verifiable Blind Quantum Computation (VBQC) protocol provides delegated computation where the composable security spans the confidentiality and integrity of the computation. However, the success o…

Gnadenlos ausgepfiffen - Trumps Polit-Show verpufft: Buhrufe statt Applaus #News #Nachrichten

Persuasion with Verifiable Information
Maria Titova, Kun Zhang
https://arxiv.org/abs/2510.08251 https://arxiv.org/pdf/2510.08251

Persuasion with Verifiable Information
This paper studies a game in which an informed sender with state-independent preferences uses verifiable messages to convince a receiver to choose an action from a finite set. We characterize the equilibrium outcomes of the game and compare them with commitment outcomes in information design. We provide conditions under which a commitment outcome is an equilibrium outcome and identify environments in which the sender does not benefit from commitment power. Our findings offer insights into the i…

CWM: An Open-Weights LLM for Research on Code Generation with World Models
FAIR CodeGen team, Quentin Carbonneaux, Gal Cohen, Jonas Gehring, Jacob Kahn, Jannik Kossen, Felix Kreuk, Emily McMilin, Michel Meyer, Yuxiang Wei, David Zhang, Kunhao Zheng, Jordi Armengol-Estap\'e, Pedram Bashiri, Maximilian Beck, Pierre Chambon, Abhishek Charnalia, Chris Cummins, Juliette Decugis, Zacharias V. Fisches, Fran\c{c}ois Fleuret, Fabian Gloeckle, Alex Gu, Michael Hassid, Daniel Haziza, Badr You…

CWM: An Open-Weights LLM for Research on Code Generation with World Models
We release Code World Model (CWM), a 32-billion-parameter open-weights LLM, to advance research on code generation with world models. To improve code understanding beyond what can be learned from training on static code alone, we mid-train CWM on a large amount of observation-action trajectories from Python interpreter and agentic Docker environments, and perform extensive multi-task reasoning RL in verifiable coding, math, and multi-turn software engineering environments. With CWM, we provide …