Proposes a graph attention network-based deep reinforcement learning algorithm for stochastic vehicle routing with outsourcing, achieving 19.6% cost reduction.

Mohsen Dastpak, Fausto Errico, Ola Jabali

SPARK-VLN streams token-wise hidden states from slow VLM to fast planner, improving dynamic navigation safety and speed.

Tianshuai Hu, Yangyi Zhong, Zeying Gong et al.

Scene-SAM3D improves multi-view 3D scene generation without fine-tuning, reducing CD by 43.8% on Replica.

Yuqi Zhang, Yadan Luo, Xiangyu Sun et al.

This study distinguishes OC and SJ signals, showing SJ directions transfer better across domains, highlighting semantic ambiguity in correctness probes.

Yi-Long Lu

MultiLoReFT decouples shared and modality-specific information via low-rank representation fine-tuning, improving prediction and interpretability.

Sana Tonekaboni, Viktoria Schuster, Caroline Uhler

Proposed a knowledge-dependent linear truth direction via SVD, revealing relational laws and cross-model convergence, validated on multiple models including Gemma-2-2b.

Francesco Karim Vicidomini

Proposes diversity-oriented fine-tuning (SFT and DPO) to improve uncertainty-based hallucination detection, boosting AUROC by ~4.5%.

Qiuyuan Li, Hongliang Dai, Piji Li

Proposes PAVXploreRL, a reward-driven RL framework optimizing physical plausibility, action adherence, and visual fidelity, improving world model robustness by 5.6%.

Han Wang, Zijun Wang, Shuoshuo Xue et al.

Category-agnostic 3D editing framework using Coupled Neural Shape (CNS) with joint optimization of latent codes and neural feature volumes.

Jingyu Hu, Weilong Yan, Zhengzhe Liu et al.

TTCov uses test-side info to select training data, improving autonomous driving performance by 10% over baselines.

Nadine Chang, Maying Shen, Shizhe Diao et al.

B2B uses EnergyPlus to generate 6,000 buildings and evaluates RL transfer across goals, dynamics, action spaces, and domains.

Vincent Taboga, Justin Veilleux, Doseok Jang et al.

Proposes AoA, a proof agent over AST, reducing API costs 2.3-4.7x and improving speed and success rates significantly.

Qiyuan Xu, Joshua Ong Jun Leang, Renxi Wang et al.

MDND combines differentiable and non-differentiable methods for unsupervised shape correspondence, significantly improving accuracy on non-isometric shapes.

Qinsong Li, Jing Meng, Haibo Wang et al.

An applicability-aware surrogate with sensitivity analysis and Conformal Risk Control predicts remediation impacts on 5,188 configurations.

Nada Hanad, Mehdi Acheli, Ali NourEldin et al.

Proposes IoU-PD, leveraging true bounding boxes as privileged training guidance, significantly improving multimodal large model's visual grounding accuracy by ~4.25% in mIoU.

Xiuyuan Zhu, Ke Lu, Hao Wu et al.

Proposes asynchronous fast-slow vision-language-action inference, boosting route completion from 37.0 to 94.0.

Yun Li, Jiachen Gong, Simon Thompson et al.

ASK-NN uses an asymmetric nearest-neighbor test to detect distribution drifts in natural language.

Sergey Zakharov, Rodion Oblovatny, Alexey Zaytsev

Proposes Recursive Harness Self-Improvement (RHI), an iterative, lightweight method that significantly boosts low-reasoning agents' performance with minimal updates, reducing inference costs by up to 60%.

Hyunin Lee, Jinglue Xu, Jeffrey Seely et al.

Plover introduces a plan-centric vision-based GUI automation system with externalized, inspectable, and editable task plans, enhancing transparency and control.

Madhumitha Venkatesan, Shicheng Wen, Jiajing Guo et al.

Using mass-mean probing, the study demonstrates that neural language models encode grammaticality as a linearly separable dimension in sentence representations, with success rates from 13.4% to 94.0%.

Jane Li, Najoung Kim