CodePDE framework leverages LLMs for PDE solver code generation, integrating reasoning, debugging, self-refinement, and scaling to surpass traditional methods.

Shanda Li, Tanya Marwah, Junhong Shen et al.

This survey reviews LLMs like GPT-4 and LLaMA in CAD, covering methods, datasets, experiments, and future directions, highlighting their industrial impact.

Licheng Zhang, Bach Le, Naveed Akhtar et al.

This study evaluates large language models' chemical reasoning via ChemIQ, with top models achieving 57% accuracy in structure understanding tasks.

Nicholas T. Runcie, Charlotte M. Deane, Fergus Imrie

Proposes paired autoencoders for inverse problems, integrating data-driven and model-based approaches to enhance reconstruction robustness and uncertainty quantification.

Matthias Chung, Bas Peters, Michael Solomon

A survey unifies CoT, RAG, and verifiers for complex LLM problem solving, but reports no new benchmark metrics.

Da Zheng, Lun Du, Junwei Su et al.

Proposes Absolute Zero, a zero-data reinforcement self-play framework with code-based reasoning, achieving SOTA in mathematical and coding tasks.

Andrew Zhao, Yiran Wu, Yang Yue et al.

VLoRP introduces multi-grained low-rank gradient projection, enhancing memory efficiency and stability in large language model fine-tuning.

Yezhen Wang, Zhouhao Yang, Brian K Chen et al.

DISCO combines hypernetworks with neural ODEs for multi-physics prediction, learning evolution operators from short trajectories with high accuracy.

Rudy Morel, Jiequn Han, Edouard Oyallon

StarPO and StarPO-S expose the Echo Trap in multi-turn agent RL; uncertainty filtering extends FrozenLake-PPO stability from 100 to 140 steps.

Zihan Wang, Kangrui Wang, Qineng Wang et al.

Proposes HOTET, combining Transformer embeddings and hypernetworks for efficient multi-distribution OT mapping.

Mingchen Jiang, Peng Xu, Xichen Ye et al.

π0.5 leverages multi-source heterogeneous data to enable robots to perform long-horizon, multi-step tasks in unseen environments with high success rates.

Physical Intelligence, Kevin Black, Noah Brown et al.

Proposes new methods to enhance spatial reasoning in MLLMs, significantly improving performance on spatial tasks.

Huanyu Zhang, Chengzu Li, Wenshan Wu et al.

Miras framework unifies sequence models via associative memory, diverse attentional biases, and retention gates, outperforming some SOTA models.

Ali Behrouz, Meisam Razaviyayn, Peilin Zhong et al.

Deep neural networks excel in representation learning for tabular data, enhancing accuracy in classification and regression tasks.

Jun-Peng Jiang, Si-Yang Liu, Hao-Run Cai et al.

RLHF uses preference models and PPO to align language models with human preferences, improving safety and style consistency.

Nathan Lambert

TRELAWNEY rearranges training sequences, raising Star Graph accuracy from 0.05 to 1.00 on G(20,5).

Abitha Thankaraj, Yiding Jiang, J. Zico Kolter et al.

Proposes Wasserstein barycenter-based collaborative Bayesian optimization, effectively preserving data privacy while maintaining high performance.

Donglin Zhan, Haoting Zhang, Rhonda Righter et al.

Proposes Energy Matching, unifying flow matching and energy-based models, achieving state-of-the-art fidelity on CIFAR-10 and ImageNet.

Michal Balcerak, Tamaz Amiranashvili, Antonio Terpin et al.

GTBO algorithm identifies active dimensions to enhance high-dimensional Bayesian optimization performance.

Erik Hellsten, Carl Hvarfner, Leonard Papenmeier et al.

AdaRFT uses adaptive curriculum learning to halve training time and boost reasoning accuracy in large language models.

Taiwei Shi, Yiyang Wu, Linxin Song et al.