Understanding DNNs through differential equations to enhance performance and applications.

Hongjue Zhao, Yizhuo Chen, Yuchen Wang et al.

This review discusses how synthetic data, virtual environments, and domain adaptation improve autonomous driving perception and planning, emphasizing digital twins and vision-language models.

A. Humnabadkar, A. Sikdar, B. Cave et al.

Adaptive Domain Models leverage Bayesian distillation and warm rotation for efficient training in geometric and neuromorphic AI.

Houston Haynes

LEAFE framework internalizes recovery agency from reflective experience, enhancing Pass@k performance in long-horizon tasks.

Rui Ge, Yichao Fu, Yuyang Qian et al.

The study finds that counterfactual explanation metrics do not align with user perception, necessitating more human-centered evaluation methods.

Felix Liedeker, Basil Ell, Philipp Cimiano et al.

OpenSeeker democratizes frontier search agents by fully open-sourcing training data, utilizing controllable QA synthesis and denoised trajectory synthesis.

Yuwen Du, Rui Ye, Shuo Tang et al.

Proposes a cognitive architecture viewing the psyche as an operating system for constructing AGI.

Anton Kolonin, Vladimir Krykov

DataEvolve employs evolutionary algorithms and sample evaluation to autonomously optimize pretraining data strategies, boosting model performance.

Tiantian Mi, Dongming Shan, Zhen Huang et al.

Developed a chatbot for maternal health in India using stage-aware triage and hybrid retrieval, achieving 86.7% emergency recall.

Smriti Jha, Vidhi Jain, Jianyu Xu et al.

CRYSTAL benchmark evaluates multimodal reasoning transparency using Match F1 and Ordered Match F1, revealing systematic flaws in existing models.

Wayner Barrios, SouYoung Jin

Structured distillation reduces personalized agent memory tokens by 11x while preserving retrieval capabilities.

Sydney Lewis

AMRO-S uses Ant Colony Optimization for efficient, interpretable multi-agent LLM routing, achieving 4.7x speedup.

Xudong Wang, Chaoning Zhang, Jiaquan Zhang et al.

The study enhances performance in non-verifiable LLM post-training using reasoning LLM judges, with gpt-oss-120b as the gold standard.

Yixin Liu, Yue Yu, DiJia Su et al.

Porfolio-CEGAR-SEQ algorithm optimizes object packing and scheduling in 3D printing, reducing the number of printing plates used.

Pavel Surynek

Omni Parsing framework standardizes multimodal data parsing via a unified taxonomy and progressive parsing paradigm.

Xin An, Jingyi Cai, Xiangyang Chen et al.

MEMO enhances multi-agent LLM game performance by memory-augmented context optimization, boosting win rate from 25.1% to 49.5% with reduced variance.

Yunfei Xie, Kevin Wang, Bobby Cheng et al.

HILA framework with Dual-Loop Policy Optimization enables adaptive human–agent collaboration, outperforming state-of-the-art multi-agent systems by 10%+ on reasoning benchmarks.

Wei Yang, Defu Cao, Jiacheng Pang et al.

Proposes a write–manage–read-based multi-dimensional memory framework, significantly enhancing LLM agent long-term memory capabilities.

Pengfei Du

The study reveals massive activations and attention sinks in Transformers as architectural artifacts.

Shangwen Sun, Alfredo Canziani, Yann LeCun et al.

WebChain is the largest real-world web interaction dataset with multi-modal alignment, enabling state-of-the-art web agent training.

Sicheng Fan, Rui Wan, Yifei Leng et al.