MESA selects complementary memory structures per query, reaching 65.1% on AMA-Bench with 41% fewer evidence tokens.

Beidi Zhao, Yaoqi Chen, Yuru Feng et al.

XPolicyLab introduces a unified standard for robot policy interfaces, reducing integration complexity from O(NM) to O(N+M), enabling seamless evaluation of 42 diverse policies across platforms.

XPolicyLab Community, Tianxing Chen, Yue Chen et al.

Introduces the Space-Creation Index (SCI) combined with event-based junk possession index to evaluate spatial utilization quality in football, distinguishing dead possession from space creation.

Seongjin Choi

Exploiting cross-model compatibility of encrypted reasoning traces allows scalable extraction of proprietary reasoning from APIs without model hacking.

Alexander Panfilov, David Schmotz, Ilia Shumailov et al.

TIDE method corrects teacher-student mismatch via bounded Hellinger shaping and top-K injection, boosting Avg@8 from 6.9% to 20.3%.

Zichao Yu, Chengzhi Yu, Shengze Xu et al.

Macaron-V1 employs Mixture-of-LoRA architecture with recursive self-improvement, achieving continuous learning and outperforming benchmarks.

Mind Lab, :, Vin Bo et al.

Aicir is a full-stack quantum circuit simulator with native Huawei Ascend NPU support, enabling efficient multi-device and variational quantum algorithms.

Xian Lu, Xinying Li, Fei Wang et al.

Verifier-free 3D CAD consensus selection improves geometric metrics by 8-10% using model agreement over geometry and topology.

Aaron Haag, Altay Kacan, Bertram Fuchs et al.

Introduced a memory, circuit, and ansatz-efficient VQLS method, significantly accelerating CFD computations.

Chao Lu, Muralikrishnan Gopalakrishnan Meena, Eduardo Antonio Coello Perez et al.

MSP-Net uses manifold-guided spectral prompts to achieve AUC > 0.80 and Precision > 0.96 on HOT2020 and HOT2023 datasets.

Juliu Li, Hanlin Qin, Shuowen Yang et al.

Proposes a time-weighted distributed streaming data optimization framework with error bounds depending on network and weighting strategies.

Muhammad Faraz Ul Abrar, Nicolò Michelusi, Erik G. Larsson

This work demonstrates that random untrained transformers can achieve universal approximation via soft prompts, leveraging kernel methods for theoretical guarantees.

Alexander Hsu, Rongjie Lai

Proposes BCSD, a dual-view self-distillation framework, improving external skill utilization in LLMs; achieves state-of-the-art results on ALFWorld and WebShop.

Tianjun Pan, Yuan Li, Hongda Wang et al.

AlignXada uses verbal reinforcement learning for LLM personalization, achieving a 3.82-point gain while reducing 77.2% redundancy.

Yuting Liu, Wei Wu, Jianzhe Zhao et al.

Proposed TrackEFG algorithm achieves switching regret $ ilde{O}((1/ρ+ρK)√HAT)$ with per-trial complexity $O(HB)$.

Stephen Pasteris, Rahul Savani, Theodore Turocy

Coderlet employs a request lifecycle-driven architecture, explicitly separating model, execution, and state boundaries for continuous AI interaction.

Mengfan Li

RecoverFly introduces a failure-aware reinforcement learning post-training framework, boosting success rate by 3.12-8.37% on UAV VLN tasks.

Boxiong Wang, Hui Kang, Geng Sun et al.

CoRE uses graph-based dominant set extraction and replicator dynamics to improve test-time RL rewards, boosting accuracy by 21.7 points.

Ambuj Mehrish, Sebastiano Vascon

Proposes linearized 2-simplicial attention using random features for O(n) complexity, combined with Kimi Delta Attention, achieving state-of-the-art accuracy on long sequences.

Aritra Das, Dhruman Gupta, Debayan Gupta

This paper analyzes the validity of privileged likelihood as token credit, proposing three checks to validate its usefulness in on-policy self-distillation.

Xuan-Phi Nguyen, Shrey Pandit, Yiran Zhao et al.