A fully parallel probabilistic Ising machine with inertia achieves significant speedup and improved success rate for real-time applications.

Ruomin Zhu, Abhishek Kumar Singh, Jérémie Laydevant et al.

Token-efficient, self-evolving LLM agent using context density maximization with four core mechanisms.

Jiaqing Liang, Jinyi Han, Weijia Li et al.

Proposes grounded multi-turn social simulation with SSBC to analyze LLM support strategy shifts based on estimated user distress.

Michelle Star, Andrew Aquilina, Yu-Ru Lin

VS-WNO fails to translate spike sparsity into deployment cost advantage on Jetson Orin Nano.

Jason Yoo, Shailesh Garg, Souvik Chakraborty et al.

LIVE framework combines image manipulation priors with video data, enabling multi-task instruction-based video editing with state-of-the-art performance.

Weicheng Wang, Zhicheng Zhang, Zhongqi Zhang et al.

CaOPD framework decouples capability and calibration, reducing overconfidence by using empirical success rates, achieving better calibration without sacrificing accuracy.

Jiaxin Zhang, Xiangyu Peng, Qinglin Chen et al.

LaviGen framework repurposes 3D generative models for autoregressive layout generation, achieving 19% higher physical plausibility on LayoutVLM benchmark.

Haoran Feng, Yifan Niu, Zehuan Huang et al.

A smaller model post-trained with reinforcement learning excels in small-molecule drug design tasks, rivaling state-of-the-art frontier models.

Shriram Chennakesavalu, Kirill Shmilovich, Hayley Weir et al.

Proposed DeepInsightTheorem framework enhances informal theorem proving by identifying core techniques, significantly outperforming baselines.

Yunhe Li, Hao Shi, Bowen Deng et al.

A dual-aspect evaluation framework analyzes LLMs on Vietnamese legal text, revealing readability-accuracy trade-offs.

Van-Truong Le

Proposed SAGR framework coordinates multi-robot language-guided search using semantic area graphs, improving efficiency by 18.8% in large environments.

Ruiyang Wang, Hao-Lun Hsu, Jiwoo Kim et al.

Task-reward optimization enhances Llama-3.2-3B-Instruct's performance on math datasets.

Sarthak Mittal, Leo Gagnon, Guillaume Lajoie

Using the CompCQ framework, this study analyzes LLM-generated competency questions across domains, revealing generation characteristics.

Reham Alharbi, Valentina Tamma, Terry R. Payne et al.

CrossMath benchmark reveals VLMs' limitations in visual reasoning; text reasoning outperforms visual.

Yige Xu, Yongjie Wang, Zizhuo Wu et al.

This study systematically evaluates various vision-language models for country-level image geolocalization, revealing their limitations in capturing fine-grained geographic cues.

Siddhant Bharadwaj, Ashish Vashist, Fahimul Aleem et al.

HILBERT framework achieves significant performance improvement in long-sequence audio-text representation learning through dual contrastive learning and information-balanced regularization.

Habibeh Naderi, Behrouz Haji Soleimani, Stan Matwin

Detect and suppress reward hacking using Gradient Fingerprints, achieving superior performance on math, code, and logical reasoning benchmarks.

Songtao Wang, Quang Hieu Pham, Fangcong Yin et al.

BAGEL benchmark evaluates language models' performance on animal knowledge using closed-book questions on taxonomy, morphology, etc.

Jiacheng Shen, Masato Hagiwara, Milad Alizadeh et al.

CollideNet enhances time-to-collision forecasting precision by disentangling temporal patterns in multi-scale video representation learning.

Nishq Poorav Desai, Ali Etemad, Michael Greenspan

Kometo algorithm achieves fast learning rates in multi-fidelity optimization without known smoothness or fidelity assumptions.

Come Fiegel, Victor Gabillon, Michal Valko