DSSM-CRF achieves 75.81% UA on IEMOCAP, addressing cross-speaker influence in conversational emotion recognition.

Guan-Hua Wen, Hou-Chiang Tseng, Kuan-Yu Chen

GAN-Diff combines pretrained WGAN-GP features with conditional diffusion U-Nets, achieving PSNR gains of 4.40dB for denoising and 3.70dB for super-resolution.

Saif Ahmed, Asadullah Hil Galib, S. M. Riaz Rahman Antu et al.

BehaviorWorldGen uses BehaviorFlow to generate controllable interactive rollouts; gains are reported, but exact benchmark percentages are absent.

Jiaqi Wang, Zhuo Zhang, Haining Guan et al.

ARCHER employs Fourier-space features for zero-shot protein pose estimation, achieving median error of 5.0° across unseen structures.

Nhan D. Nguyen, Bao Pham

Proposed HeteroGNN for multi-objective food substitution, improving recommendation accuracy.

Naimur Rahman Chowdhury, Limon Bin Hossain

Proposes K-DCT covariance model to accelerate DDPM sampling, capturing non-diagonal correlations in natural images, improving quality with fewer steps.

Rui Xia, Ayan Das, Artem Artemev et al.

Bulbul dataset supports dialectal Arabic speech recognition across 11 Arab countries.

Ahmed Ashraf, Aisha Alansari, Fadel Al Abbas et al.

GuardPaint uses speculative decoding to repair unsafe regions during diffusion, reducing attack success rates while preserving image quality.

Shreyash Dhoot, Paras Dhiman, Arsh Abbas Naqvi et al.

GUI-Primitives benchmark reveals limitations in spatial reasoning of vision-language models, with max accuracy of 32%.

Md Abrar Jahin, Md Rizwan Parvez

Using LaBSE and other encoders, the study examines framing differences in religious and scientific concepts across Wikipedia's language editions.

Hung-Hsuan Chen

DefaultShift quantifies semantic default shift in accelerated text-to-image models, reducing human-measured shift by 10.3%-35.1%.

Xuanhua Yin, Chuanzhi Xu, Shunqi Mao et al.

PowerSlider exploits phase heterogeneity with online KKT solver to optimize GPU frequency and KV cache under dynamic power caps, maintaining high throughput.

Yueying Li, Jiayang Chen, Yuanfan Chen et al.

Proposed a stochastic alternating least-squares algorithm for sparse data analysis, applied to Drosophila connectome data.

Lawrence K. Saul, Ningyuan Huang, Dennis Bollweg et al.

Introduces OmniAssistBench, a dataset built via reverse engineering of internet videos, to evaluate Omni-LLMs in multi-turn multimodal interactions.

Xianyun Sun, Chaoyou Fu, Zhengye Zhang et al.

Proposes a primal accelerated Newton method with only one linear solve per iteration achieving O(1/k^3) convergence.

Nikita Doikov

VIALS benchmark evaluates scientific artifact interpretation, with top models achieving only 26.5% accuracy, highlighting major gaps.

Elaine Lau, Thanuka Udumulla, Lee Izhaki-Tavor et al.

The Salt method enables end-to-end hardware verification from application to silicon in five weeks, led by a single researcher using AI-driven formal methods.

Jason Hickey

ViTacPhys uses multimodal visual-tactile modeling and VLM priors to predict object mass, stiffness, and friction with 97.2% accuracy, enabling adaptive robotic grasping.

Yiwen Liu, Yujun Zhu, Kui Jia et al.

PerturbRx learns drug-induced latent transitions, boosting patient drug response prediction accuracy.

Yoshitaka Inoue, Minoh Jeong, Alfred Hero et al.

First systematic analysis of model capacity distribution in self-refinement; larger generator and refiner models improve performance, critic size less impactful.

Zhuoyi Yang, Ian G. Harris, Salar Hashemitaheri et al.