CS3 framework enhances two-tower recommendation systems with Cycle-Adaptive Structure, Cross-Tower Synchronization, and Cascade-Model Sharing, achieving an 8.36% revenue increase.

Lixiang Wang, Shaoyun Shi, Peng Wang et al.

Fast estimation of Gaussian mixture components via centering and singular value thresholding without iteration.

Huan Qing

S2MAM uses bilevel optimization for robust estimation and variable selection, validated on 16 datasets.

Xuelin Zhang, Hong Chen, Yingjie Wang et al.

MathNet provides a global multimodal benchmark for mathematical reasoning and retrieval, covering 30,676 Olympiad-level problems from 47 countries.

Shaden Alshammari, Kevin Wen, Abrar Zainal et al.

MUA method achieves up to 2000X lower computational cost using Wavelet-guided Multi-level Spatial Factorized Blendshapes.

Heming Zhu, Guoxing Sun, Marc Habermann

Sessa enhances long-range memory by embedding selective attention in feedback paths.

Liubomyr Horbatko

Introduced Bounded Ratio Reinforcement Learning (BRRL) framework, outperforming PPO in environments like MuJoCo.

Yunke Ao, Le Chen, Bruce D. Lee et al.

BLF system achieves state-of-the-art binary forecasting performance on ForecastBench using sequential Bayesian updating of linguistic beliefs.

Kevin Murphy

Apollo model integrates 28 medical modalities and 12 specialties to predict disease risk up to 5 years in advance.

Andrew Zhang, Tong Ding, Sophia J. Wagner et al.

Revisiting active sequential prediction-powered mean estimation reveals smallest confidence width when constant probability weight is near one.

Maria-Eleni Sfyraki, Jun-Kun Wang

The study reveals dual alignment between language model layers and human sentence processing, with early layers suited for natural reading and later layers better modeling complex syntactic processing.

Tatsuki Kuribayashi, Alex Warstadt, Yohei Oseki et al.

ConforNets controls AF3 latent representations via channel-wise affine transforms, enhancing multi-state prediction success.

Minji Lee, Colin Kalicki, Minkyu Jeon et al.

SynAgent leverages Solo-to-Cooperative Agent Synergy for generalizable humanoid manipulation, significantly enhancing generalization across diverse object geometries.

Wei Yao, Haohan Ma, Hongwen Zhang et al.

GSQ achieves high-accuracy low-bit quantization using Gumbel-Softmax sampling, narrowing the accuracy gap with QTIP methods.

Alireza Dadgarnia, Soroush Tabesh, Mahdi Nikdan et al.

ClawEnvKit automates environment generation for claw-like agents, reducing costs by 13,800x.

Xirui Li, Ming Li, Derry Xu et al.

Transition-matrix regularization improves next dialogue act prediction in counseling conversations, boosting macro-F1 by 9-42%.

Eric Rudolph, Philipp Steigerwald, Jens Albrecht

MetaCloak-JPEG enhances JPEG robustness of adversarial perturbations for DreamBooth deepfake prevention, achieving 32.7 dB PSNR.

Tanjim Rahaman Fardin, S M Zunaid Alam, Mahadi Hasan Fahim et al.

Study of LLM jailbreaks via RLVR, SFT, and refusal-feature abliteration reveals RLVR models closely resemble base models.

Md Rysul Kabir, Zoran Tiganj

Document-as-image representations underperform in scientific retrieval; interleaved text+image representations are more effective.

Ghazal Khalighinejad, Raghuveer Thirukovalluru, Alexander H. Oh et al.

OneVL achieves one-step latent reasoning and planning with vision-language explanations, surpassing explicit CoT at answer-only latency.

Jinghui Lu, Jiayi Guan, Zhijian Huang et al.