FlowCF enhances collaborative filtering accuracy using flow matching, achieving fastest inference speeds in experiments.

Chengkai Liu, Yangtian Zhang, Jianling Wang et al.

Study finds LLM reasoning accuracy follows an inverted U-shaped curve with CoT length; proposes length optimization methods.

Yuyang Wu, Yifei Wang, Ziyu Ye et al.

This survey unifies federated and continual learning, mapping heterogeneity, forgetting, communication, and privacy challenges; it reports no unified numerical experiments.

Parisa Hamedi, Roozbeh Razavi-Far, Ehsan Hallaji

Steel-LLM uses Soft MoE and enhanced FFN, excelling in CEVAL benchmarks.

Qingshui Gu, Shu Li, Tianyu Zheng et al.

LiveForesighter uses Transformers to forecast live-stream highlights and future products; it was deployed across Kuaishou services serving 400 million daily active users.

Yucheng Lu, Jiangxia Cao, Xu Kuan et al.

AMKOR fuses parametric and retrieved knowledge using probabilistic beam search, achieving state-of-the-art multi-hop QA performance.

Jackson Coleman, Isaiah Lawrence, Benjamin Turner

MMGDreamer introduces a dual-branch diffusion framework with a novel Mixed-Modality Graph, achieving high-precision geometry control in 3D indoor scene synthesis, outperforming state-of-the-art.

Zhifei Yang, Keyang Lu, Chao Zhang et al.

Proposes deep learning-based contextual scenario generation (CSG) for two-stage stochastic programming, improving distribution approximation and decision quality.

David Islip, Roy H. Kwon, Sanghyeon Bae et al.

Long-VITA is a multimodal model supporting 1 million tokens, achieving high short-sequence accuracy in image, video, and text understanding.

Yunhang Shen, Chaoyou Fu, Shaoqi Dong et al.

Proposes a latent recurrent-depth language model with 35B parameters, enabling test-time reasoning scale via iterative latent space inference, significantly boosting performance.

Jonas Geiping, Sean McLeish, Neel Jain et al.

Goku employs rectified flow Transformer for joint image-video generation, achieving top-tier performance with 0.76 on GenEval and 84.85 on VBench.

Shoufa Chen, Chongjian Ge, Yuqi Zhang et al.

Proposes the concept of coexistence for embodied agents, emphasizing continuous adaptation leveraging situated knowledge for long-term human interaction.

Hannah Kuehn, Joseph La Delfa, Miguel Vasco et al.

Proposes a convex-structured joint estimation method for states and noise covariance, with analytical solutions, applied to SLAM and robotics.

Kasra Khosoussi, Iman Shames

Introduces Sliding Tile Attention (STA), achieving 2.8-17× speedup in video diffusion models with minimal quality loss, based on local 3D attention patterns.

Peiyuan Zhang, Yongqi Chen, Runlong Su et al.

Proposes iterative importance fine-tuning of diffusion models via self-supervision, optimizing control for conditional sampling with theoretical guarantees.

Alexander Denker, Shreyas Padhy, Francisco Vargas et al.

Proposes Achieved Information Gain (AIG) as a metric for resource-aware cognition, with axiomatic foundation and applications in inference and communication.

Torsten Enßlin

Proposes IEE, an iterative exploitation-exploration framework, boosting importance scores for sparse pruning, achieving +1.3% Top-1 accuracy on ImageNet ResNet50.

Xinglong Sun, Maying Shen, Hongxu Yin et al.

DGPPO combines discrete graph CBFs with RL to achieve safe, high-performance multi-agent control under unknown discrete dynamics.

Songyuan Zhang, Oswin So, Mitchell Black et al.

Introduces ‘Platinum Benchmarks’ to reduce label noise, assesses LLM reliability, revealing even state-of-the-art models fail on simple tasks with 5% error rate.

Joshua Vendrow, Edward Vendrow, Sara Beery et al.

LIMO achieves complex reasoning with minimal data, scoring 63.3% on AIME24 and 95.6% on MATH500.

Yixin Ye, Zhen Huang, Yang Xiao et al.