Self-distillation improves reasoning in large language models by using the model's own rollouts as training signal, typically through implicit logit-level alignment that minimizes KL divergence toward a privileged target distribution. However, because this supervision is generated via uncontrolled sampling, it provides no diagnostic insight into the model's specific errors or corrective guidance for its individual failure patterns.
Reinforcement learning with verifiable rewards (RLVR) has driven substantial progress in training LLMs for reasoning tasks, but representative methods such as GRPO assign uniform credit across all tokens, wasting gradient on routine tokens while under-crediting pivotal reasoning steps. Existing token-level credit assignment methods require resources beyond the model's own rollouts.
Autoregressive video diffusion models have emerged as a promising approach for long video generation, achieving strong performance in streaming settings. However, existing methods are restricted to forward temporal generation, whereas practical video creation often requires flexible generation order, e.
Scalable, all-weather place recognition increasingly relies on heterogeneous radar place recognition to bridge diverse hardware platforms. A notable application is matching queries from cost-effective 4D automotive radars against high-fidelity reference maps built by dense spinning radars.
arXiv:2606. 17249v1 Announce Type: cross Abstract: The dominant trajectory of modern machine learning has been to scale up: larger models, larger accelerators, larger memory budgets.
By Emre Can Kizilates
arXiv:2510. 23798v2 Announce Type: replace-cross Abstract: The proliferation of floating anthropogenic debris in rivers has emerged as a pressing environmental concern, exerting a detrimental influence on biodiversity, water quality, and human activities such as navigation and recreation.
By Gauthier Grimmer, Romain Wenger, Cl\'ement Flint, Germain Forestier, Gilles Rixhon, Valentin Chardon
arXiv:2507. 11178v3 Announce Type: replace-cross Abstract: With the advancement of deep learning technologies, various neural network-based Granger causality models have been proposed.
By Meiliang Liu, Huiwen Dong, Xiaoxiao Yang, Yunfang Xu, Mingbao Yang, Zijin Li, Zhengye Si, Xinyue Yang, Zhiwen Zhao
arXiv:2606. 18203v1 Announce Type: cross Abstract: The LLM-empowered personal health agents with user health (sensor) metrics have offered a promising pathway to alleviate global disparities in healthcare access.
By Weizhi Zhang, Zechen Li, Hamid Palangi, Ben Graef, A. Ali Heydari, Simon A. Lee, Salman Rahman, Ray Luo, Zeinab Esmaeilpour, Erik Schenck, Chloe Zhang, Yamin Li, Menglian Zhou, Philip S. Yu, Daniel McDuff, Lindsey Sunden, Mark Malhotra, Shwetak Patel, Ahmed A. Metwally
arXiv:2606. 17579v1 Announce Type: cross Abstract: Adding LLM-generated node features to graph neural networks (GNNs) is widely reported to improve accuracy on standard benchmarks.
By Zhongyuan Wang, Pratyusha Vemuri
arXiv:2606. 17104v1 Announce Type: cross Abstract: As large language models (LLMs) are increasingly deployed in latency- and cost-sensitive settings, inference efficiency has become a central systems challenge.
By Shun Usami, Venkatram Vishwanath, E. Wes Bethel
arXiv:2606. 17199v1 Announce Type: cross Abstract: Standard on-policy distillation (OPD) for large language models estimates the reverse-KL objective using student-sampled tokens, yielding an unbiased single-sample Monte Carlo estimator that avoids vocabulary-wide computation.
By Anhao Zhao, Junlong Tong, Yingqi Fan, Ping Nie, Wenjie Li, Xiaoyu Shen
arXiv:2604. 18701v3 Announce Type: replace-cross Abstract: Local prediction-error-based curiosity rewards focus on the current transition without considering the world model's cumulative prediction error across all visited transitions.
By Vin Bhaskara, Haicheng Wang
arXiv:2603. 18104v5 Announce Type: replace Abstract: Prevailing AI training assumes reverse-mode automatic differentiation over IEEE-754 arithmetic.
By Houston Haynes
arXiv:2603. 18492v3 Announce Type: replace Abstract: Mixture-of-Experts (MoE) language models increase parameter capacity without proportional per-token computation, yet deployment still requires storing the full expert pool, making expert pruning important for reducing memory and serving overhead.
By Zongfang Liu, Guangyi Chen, Shengkun Tang, Yifan Shen, Huan Wang, Xin Yuan
arXiv:2606. 17445v1 Announce Type: new Abstract: Inverse design of heterogeneous catalysts remains challenging because catalyst surfaces exhibit substantial structural complexity with coupled surface-adsorbate interactions across a vast chemical space that is difficult to explore efficiently through conventional screening alone.
By Dong Hyeon Mok, Jonggeol Na, Seoin Back
arXiv:2605. 31286v2 Announce Type: replace-cross Abstract: Real-world household robots require Vision-Language-Action (VLA) foundation models that can acquire reusable manipulation skills across diverse objects, task conditions, and household environments.
By Taiyi Su, Jian Zhu, Tianjian Wang, Youzhang He, Zitai Huang, Jianjun Zhang, Chong Ma, Hanyang Wang, Tianjiao Zhang, Munan Yin, Weihao Ding, Yi Xu
arXiv:2605. 20708v2 Announce Type: replace-cross Abstract: Diffusion Transformers (DiTs) have become a de facto backbone of modern visual generation, and nearly every major axis of their design -- tokenization, attention, conditioning, objectives, and latent autoencoders -- has been extensively revisited.
By Chao Xu, Maohua Li, Qirui Li, Yixuan Xu, Yanke Zhou, Yunhe Li, Cuifeng Shen, Hanlin Tang, Kan Liu, Tao Lan, Lin Qu, Shao-Qun Zhang
arXiv:2606. 17872v1 Announce Type: cross Abstract: Large language models (LLMs) outperform earlier architectures on generative inference and long-context tasks, but their large size introduces significant challenges in memory usage, energy cost, and on-device deployment.
By Ning Ni, Yingjie Lao
arXiv:2606. 17781v1 Announce Type: cross Abstract: The rapid growth of Large Language Models (LLMs) has intensified the need for specialized hardware accelerators that can satisfy stringent inference latency and power constraints.
By Kosmas Alexandridis, Giorgos Dimitrakopoulos
arXiv:2606. 17107v1 Announce Type: cross Abstract: Prefix caching reuses prefill only across an exactly shared prefix, so one changed field invalidates the entire downstream cache.
By Bojie Li