Proposed logical tasks to assess reasoning capabilities, highlighting limitations in large-scale models like PaLM in mathematical reasoning.

Ippei Fujisawa, Ryota Kanai

Latent-NeRF integrates shape and texture guidance via latent diffusion, enabling fast, controllable 3D generation.

Gal Metzer, Elad Richardson, Or Patashnik et al.

Proposes a nonconvex distributed dual averaging algorithm with O(1/t) convergence rate over stochastic networks.

Changxin Liu, Xuyang Wu, Xinlei Yi et al.

CRINGE loss leverages contrastive negative generation with iterative self-labeling, significantly improving safety and coherence in language models, outperforming baselines.

Leonard Adolphs, Tianyu Gao, Jing Xu et al.

Unified dense correspondence model using Transformer surpasses SOTA in optical flow, stereo, and depth tasks with shared parameters and no cost volume.

Haofei Xu, Jing Zhang, Jianfei Cai et al.

Proposes a comprehensive taxonomy of deep learning models for time series anomaly detection, covering forecasting, reconstruction, representation, and hybrid methods.

Zahra Zamanzadeh Darban, Geoffrey I. Webb, Shirui Pan et al.

Proposes multi-dimensional partitioning and communication optimization for TPU v4, achieving 29ms/token latency and 76% MFU on 540B models.

Reiner Pope, Sholto Douglas, Aakanksha Chowdhery et al.

BLOOM is a 176B-parameter open-source multilingual language model based on Transformer, trained on ROOTS corpus, excelling in diverse NLP tasks.

BigScience Workshop, :, Teven Le Scao et al.

PASTA employs sentence-table cloze pre-training with six operation types, achieving 85.6% accuracy on TabFact's complex set, surpassing previous SOTA by 4.7%.

Zihui Gu, Ju Fan, Nan Tang et al.

Using Teacher Forcing and Curriculum Learning improves FNO and UNet model accuracy by over 50%.

Lalit Ghule, Rishikesh Ranade, Jay Pathak

CFEAR-based radar odometry with motion compensation and multi-scan registration achieves 1.09% error at 5Hz, near lidar SLAM accuracy.

Daniel Adolfsson, Martin Magnusson, Anas Alhashimi et al.

Waveformer combines dilated causal convolution and Transformer for real-time target sound extraction, improving SI-SNRi by up to 3.3dB.

Bandhav Veluri, Justin Chan, Malek Itani et al.

DPM-Solver++: Data-prediction-based high-order solver, generates high-quality images in 15 steps with guided diffusion models.

Cheng Lu, Yuhao Zhou, Fan Bao et al.

Proposes LADDER, an NLP and knowledge graph framework, for automatic extraction of attack patterns from CTI reports, mapped to MITRE ATT&CK.

Md Tanvirul Alam, Dipkamal Bhusal, Youngja Park et al.

Self-Correction method enhances sequence generation quality, achieving 99% accuracy in mathematical program synthesis.

Sean Welleck, Ximing Lu, Peter West et al.

SSD-LM is a diffusion-based language model excelling in text generation and modular control.

Xiaochuang Han, Sachin Kumar, Yulia Tsvetkov

GPTQ is a second-order based post-training quantization method that compresses 175B parameter models to 4 bits with minimal accuracy loss.

Elias Frantar, Saleh Ashkboos, Torsten Hoefler et al.

CoRe method enhances math problem-solving via cooperative reasoning, achieving a 9.6% improvement.

Xinyu Zhu, Junjie Wang, Lin Zhang et al.

Proposes adaptive physics-informed neural operator, achieving 4.5% max error, doubling speed.

Ivan Zanardi, Simone Venturi, Marco Panesi

Survey of deep neural network methods (PINNs, Neural Operators) for solving PDEs, highlighting algorithms, applications, and future directions.

Shudong Huang, Wentao Feng, Chenwei Tang et al.