Theorem 3 proves GELU-like activations achieve Sobolev super-convergence at error rate (NL)^−2(n−m)/d.

Yahong Yang, Juncai He

Proposed a method using Calibration Tokens to extend monocular depth estimators to fisheye cameras, significantly improving depth estimation accuracy.

Rit Gangopadhyay, Jung-Hee Kim, Xien Chen et al.

SEAgent employs autonomous exploration and experience-based reinforcement learning, achieving a 23.2% success rate increase (from 11.3% to 34.5%) across five novel software environments.

Zeyi Sun, Ziyu Liu, Yuhang Zang et al.

Proposes OSG Navigator, a structure-based open-world ObjectNav system leveraging foundation models and open scene graphs for zero-shot generalization.

Joel Loo, Zhanxin Wu, David Hsu

BridgeDepth uses bidirectional latent alignment with cross-attention transformers to fuse monocular and stereo depth, reducing zero-shot error by >40%.

Tongfan Guan, Jiaxin Guo, Chen Wang et al.

Event camera-based UAV detection leveraging sparse asynchronous data, achieving low latency and high robustness in challenging conditions.

Gabriele Magrini, Lorenzo Berlincioni, Luca Cultrera et al.

VITAL integrates visual tools with multimodal chain-of-thought for long video reasoning, achieving state-of-the-art results in QA and temporal grounding.

Haoji Zhang, Xin Gu, Jiawen Li et al.

HPSv3 uses a wide-spectrum dataset and VLM-based model with Bayesian ranking to improve human preference evaluation accuracy.

Yuhang Ma, Yunhao Shui, Xiaoshi Wu et al.

Goedel-Prover-V2 achieves new breakthroughs in automated theorem proving with scaffolded data synthesis and self-correction, reaching 88.1% accuracy on MiniF2F.

Yong Lin, Shange Tang, Bohan Lyu et al.

EvaDrive employs adversarial multi-objective reinforcement learning, achieving 94.9 PDMS on NAVSIM and diverse driving styles without external preferences.

Siwen Jiao, Kangan Qian, Hao Ye et al.

Developed ACES framework to evaluate AI shopping agents' biases, market share dependence, and stability across models, revealing volatile and model-dependent behaviors.

Amine Allouah, Omar Besbes, Josué D Figueroa et al.

Proposed a failure-aware multi-robot target tracking framework combining partial centralized and decentralized optimization, enhancing robustness under various failure scenarios.

Peihan Li, Jiazhen Liu, Yuwei Wu et al.

Quantum machine learning shows superior resilience to label noise and efficient unlearning capabilities.

Yu-Qin Chen, Shi-Xin Zhang

StreamAgent combines future event prediction and hierarchical KV-cache to enable proactive streaming video understanding with 15% accuracy boost.

Haolin Yang, Feilong Tang, Lingxiao Zhao et al.

CFRR employs inverse propensity scoring with self-normalization to correct bias in user-to-user matching, improving ranking accuracy and fairness.

Kazuki Kawamura, Takuma Udagawa, Kei Tateno

QCBench evaluates 24 large language models on quantitative chemistry, revealing the gap between language fluency and scientific computation accuracy.

Jiaqing Xie, Weida Wang, Ben Gao et al.

Developed a CLT for non-parametric transition estimators in controlled Markov chains, establishing asymptotic normality under specific conditions.

Ziwei Su, Imon Banerjee, Diego Klabjan

SPFSplat achieves SOTA performance in 3D Gaussian splatting without pose supervision using sparse views.

Ranran Huang, Krystian Mikolajczyk

Introduces UrBLiMP, a benchmark with 5696 minimal pairs for evaluating Urdu syntax in multilingual LLMs, achieving up to 94.73% accuracy.

Farah Adeeba, Brian Dillon, Hassan Sajjad et al.

Proposed MAO-ARAG multi-agent framework with reinforcement learning for adaptive retrieval-augmented generation, boosting QA performance.

Yiqun Chen, Erhan Zhang, Lingyong Yan et al.