Efficient text-to-image generation requires both reinforcement-learning (RL)-based reward alignment and few-step distillation, yet these procedures are typically performed sequentially, increasing training cost and risking the loss of reward gains during compression. We instead take an RL-native perspective: diffusion RL already generates reward-scored finite-step trajectories, whose intermediate states provide a natural source of distillation supervision rather than a disposable byproduct of sampling.
Reinforcement learning (RL) has become a central post-training paradigm for eliciting reasoning capabilities in large language models, yet uniform task sampling allocates compute without regard to differences in how tasks respond to optimization. Existing task-valuation methods mostly rely on snapshot-based signals such as current pass rate or reward, which estimate how solvable a task is under the current policy.
Neural language models trained on large crowdsourced corpora frequently exploit spurious surface patterns tied to target labels without true linguistic or causal relevance, boosting benchmark performance while failing on adversarial or out-of-distribution inputs. Existing approaches either require manual specification of the feature vocabulary or automate discovery only partially, leaving the gap between dataset-level correlation and model-level exploitation unaddressed.
While learned robotic policies hold promise for advancing generalizable manipulation, their practical deployment is often hindered by suboptimal execution speeds. Imitation learning policies are inherently limited by hardware constraints and the speed of the operator during data collection.
We introduce Motif 3, a decoder-only Mixture-of-Experts language model with 314 billion total parameters and 13. 2 billion activated per token.
arXiv:2608. 07148v1 Announce Type: new Abstract: Modern manufacturing imposes six coupled demands on adaptive control: local decisions with global consequences, partial observability, nonstationarity, reflex speed response with long horizon effects, delayed and diffuse outcomes, and dynamics that resist explicit modeling.
By Fouad Bahrpeyma, Dirk Reichelt
arXiv:2608. 06756v1 Announce Type: new Abstract: Vision-language models are increasingly serving as the reasoning core of embodied agents.
By Ying Chen, Weizhen Li, Zhe Hu, Zhenjiang Li, Rui Jiang, Zhifeng Gu, Lihuang Fang, Jiangping Liu, Lei Yi, Jie Chen
arXiv:2608. 07460v1 Announce Type: cross Abstract: While post-training improves the capabilities of large language models (LLMs), it generally lowers their output diversity and creativity, negatively impacting tasks that explicitly require creativity (e.
By Ananya Sahu, Mohit Bansal, Elias Stengel-Eskin
arXiv:2608. 06445v1 Announce Type: cross Abstract: Capturing the strategic decision-making inherent in competitive human driving is critical for autonomous vehicle safety and traffic simulation.
By Yu Song
arXiv:2608. 07139v1 Announce Type: new Abstract: Uncertainty quantification is essential when deploying machine learning models in safety-critical applications.
By Joar Skalse, Edoardo Pona, Osvaldo Simeone, Nicola Paoletti
arXiv:2608. 07418v1 Announce Type: new Abstract: In medical education, physicians convert academic knowledge into clinical expertise through residency: years of training across thousands of encounters, with diverse sources of feedback and progressively greater autonomy.
By Valentin Li\'{e}vin, Samuel Schmidgall, Tim Strother, Alex Bijamov, Akshay Goel, Anil Palepu, Chunjong Park, Vahid Balazadeh, Min Woo Sun, Marius Guerard, Justin Chen, Dave Steiner, Vikram Dhillon, Ibrahim Azar, Akhil Mehta, Nicholas Spetsieris, Shilpan Shah, Maen Abdelrahim, Amit Dahiya, Yun Liu, Katherine Chou, Yossi Matias, Avinatan Hassidim, Dale R. Webster, Quoc V. Le, Raia Hadsell, Joelle Barral, Carey Radebaugh, Aleksandra Faust, Shekoofeh Azizi, Mike Schaekermann, Po-Hsuan Cameron Chen, Tao Tu, David Racz, Lin Yang
arXiv:2506. 03392v2 Announce Type: replace Abstract: We propose a new ternary spiking neuron model to improve the representation capacity of binary spiking neurons in deep Q-learning.
By Aref Ghoreishee, Abhishek Mishra, John Walsh, Anup Das, Nagarajan Kandasamy
arXiv:2601. 18904v3 Announce Type: replace-cross Abstract: Generative AI for speech and audio is increasingly expected to serve users across languages, cultures, and communities, yet current auditory Large Language Models (LLMs) are still largely trained and evaluated on high-resource data.
By Haolong Zheng, Siyin Wang, Zengrui Jin, Mark Hasegawa-Johnson
arXiv:2608. 07086v1 Announce Type: cross Abstract: Reinforcement learning systems are significantly more complex than other machine learning paradigms due to inherent properties, causing RL system design to jointly account for many tightly coupled factors.
By Qi Zhao, Guozheng Ma, Yilun Kong, Lu Li, Haoyu Wang, Zilin Wang, Tiantian Zhang, Yuxing Wang, Jian Sha, Yongzhe Chang, Xueqian Wang, Dacheng Tao
arXiv:2608. 07180v1 Announce Type: cross Abstract: Recent advances in deep reinforcement learning (RL) have shown that improving neural network architectures can yield substantial gains in sample efficiency and asymptotic performance without altering the underlying algorithms.
By Adam \v{S}tafa, Santeri Heiskanen, Petr Novotn\'y, Joni Pajarinen
arXiv:2509. 05208v2 Announce Type: replace-cross Abstract: Large language models (LLMs) excel at program synthesis, yet their ability to produce symbolic graphics programs (SGPs) that render into precise visual content remains underexplored.
By Yamei Chen, Haoquan Zhang, Yangyi Huang, Zeju Qiu, Kaipeng Zhang, Yandong Wen, Weiyang Liu
arXiv:2608. 06545v1 Announce Type: new Abstract: Distributionally robust Markov decision processes provide a principled framework for sequential decision making under model uncertainty.
By Yuepeng Yang, Yuxin Chen, Yuejie Chi
arXiv:2608. 06762v1 Announce Type: new Abstract: Bisimulation metrics quantify behavioral similarity in Markov decision processes, but their Wasserstein fixed-point operator updates every state pair and incurs quadratic pairwise work.
By Ibne Farabi Shihab, Joyanta Jyoti Mondal
arXiv:2608. 06582v1 Announce Type: new Abstract: Flow-based generative models can efficiently produce candidate structures for crystal structure prediction (CSP), but their pretrained objectives do not directly optimize downstream target recovery.
By Kaixiang Su, Hongfei Xue, Qiang Zhu
arXiv:2608. 06520v1 Announce Type: new Abstract: We study online cooperative control of a multi-agent system under Byzantine attacks.
By Ximing Sun, Yue Wang