Semantic Flip synthesizes out-of-distribution samples to improve embodied refusal, achieving an F1 of 0.9559 on spatial localization.

Dongbin Na, Chanwoo Kim, Giyun Choi et al.

Reversible migration path and taxonomy enable expert LLM workflows to become self-evolution-ready, validated through low-cost, auditable case study.

Yimo Lin, Zhen Zhang, Yibin Li

OpenClaw-Skill enhances large language models in tool use and multi-step reasoning via Collective Skill Tree Search.

Tianyi Lin, Chuanyu Sun, Jingyi Zhang et al.

Skill-to-LoRA transforms skill text into LoRA adapters, improving pass rate by 5.2 percentage points.

Tianyi Zhang, Zhonghao Qi

MyPCBench tests personal intelligent computing agents; Claude Opus 4.6 solves 55.4% of tasks.

Lawrence Keunho Jang, Andrew Keunwoo Jang, Jing Yu Koh et al.

Disproves the near-quadratic Elekes-Rónyai expander conjecture using fixed nonspecial quadratic polynomials and algebraic integers.

Jihao Liu

Introduces Entropy-Gated Latent Recursion (EGLR), leveraging layer span L for deterministic inference diversity, boosting reasoning accuracy.

Soham Bhattacharjee, Dushyant Singh Chauhan, Salem Lahlou et al.

Proposed audio-adapted Context-Aware Decoding (CAD) method enhances context adherence in spoken dialogue systems.

Che Hyun Lee, Heeseung Kim, Sungroh Yoon

MUNI employs an end-to-end multimodal latent diffusion framework for arbitrary-to-arbitrary generation, surpassing baselines in both conditional and unconditional tasks.

Kyeongmin Yeo, Yunhong Min, Minhyuk Sung

ART-Glove integrates 16 rigid functional surfaces and 22-DoF joint sensing with 2048-taxel tactile arrays, enabling contact-grounded dexterous demonstration capture at 120Hz.

Changyi Lin, Ding Zhao

GraphBEV++ integrates LocalAlign-v2 and GlobalAlign-v2 modules, systematically mitigating sensor calibration errors to enhance multi-modal perception robustness.

Ziying Song, Caiyan Jia, Lin Liu et al.

SelectStream enhances streaming video understanding with selective memory, achieving 82.67% on StreamingBench.

Haonan Ge, Yiwei Wang, Hang Wu et al.

GraphWorld leverages latent world models for end-to-end autonomous driving, reducing collision rates by 19.5% on nuScenes 6s horizon.

Ziying Song, Caiyan Jia, Lin Liu et al.

TopoRetarget enhances RL policy training success by 40.6% by preserving hand-object interaction.

Jielin Wu, Shenzhe Yao, Guanqi He et al.

Deep learning-optimized multilayer passive diffractive network achieves 625 channels of 2D beam steering across 400-750nm with subwavelength accuracy.

Che-Yung Shen, Yuhang Li, Cagatay Isil et al.

NAG architecture separates magnitude and direction in residual streams to address norm growth in deep models.

Tomás Figliolia, Beren Millidge

Proposes GhostPrint, a parameter-efficient attack framework that enables weak models to mimic strong LLMs, exposing fingerprint spoofing vulnerabilities.

Jiahao Zhang, Xiuyu Li, Suhang Wang

VinQA introduces two visual encoding methods, significantly improving visual citation accuracy in long-form multimodal document QA.

Young Rok Jang, Hyesoo Kong, Kyunghwan An et al.

Introduces active learning with low-rank structure for data selection, enhancing training efficiency.

Vincent Cohen-Addad, Sasidhar Kunapuli, Vahab Mirrokni et al.

SAG employs SQL-driven dynamic hyperedges, boosting multi-hop reasoning with 80% Recall@5 on MuSiQue, surpassing prior methods.

Yuchao Wu, Junqin Li, XingCheng Liang et al.