ALLaVA uses GPT-4V to generate 1.3M high-quality vision-language samples, enabling lightweight models to match large-scale model performance.

Guiming Hardy Chen, Shunian Chen, Ruifei Zhang et al.

Proposed NESCL model improves collaborative filtering via neighborhood-enhanced supervised contrastive learning, achieving 10.09% NDCG@20 improvement on Yelp2018.

Peijie Sun, Le Wu, Kun Zhang et al.

LIMP translates complex natural language instructions into temporal logic, enabling robots to verify behaviors without prebuilt semantic maps, achieving 79% success in real-world tests.

Benedict Quartey, Eric Rosen, Stefanie Tellex et al.

Momentor enhances video LLMs with fine-grained temporal reasoning using the Moment-10M dataset.

Long Qian, Juncheng Li, Yu Wu et al.

Proposes an exploration-based fair classification framework with theoretical guarantees on exploration, FDR control, and convergence to optimal classifiers.

Vijay Keswani, Anay Mehrotra, L. Elisa Celis

Introduced Rectify-Router method to enhance MoE model performance, achieving a 4.7% accuracy improvement.

Zhiyuan Zeng, Qipeng Guo, Zhaoye Fei et al.

Proposes LowPopArt for low-rank matrix estimation with experimental design, achieving tighter recovery guarantees.

Kyoungseok Jang, Chicheng Zhang, Kwang-Sung Jun

TimeSeriesBench offers 168 evaluation settings to enhance the industrial applicability of time series anomaly detection models.

Haotian Si, Jianhui Li, Changhua Pei et al.

Proposes StableLego, a force-balance optimization method, accurately predicting the stability of 3D block structures with over 99% accuracy on large datasets.

Ruixuan Liu, Kangle Deng, Ziwei Wang et al.

BitDistiller enhances sub-4-bit LLM performance via self-distillation, significantly reducing data and training resource needs.

Dayou Du, Yijia Zhang, Shijie Cao et al.

SpLiCE transforms CLIP embeddings into sparse, interpretable semantic concepts, maintaining high zero-shot accuracy.

Usha Bhalla, Alex Oesterling, Suraj Srinivas et al.

UMI framework enables direct skill transfer from human demonstrations to robot policies with a 70% success rate.

Cheng Chi, Zhenjia Xu, Chuer Pan et al.

StrongREJECT benchmark uses high-quality forbidden prompts and an automated evaluator to accurately measure jailbreak effectiveness, reducing overestimation issues.

Alexandra Souly, Qingyuan Lu, Dillon Bowen et al.

Proposes a data engineering strategy using 80K sequence continual pretraining to extend language models' context to 128K, achieving near GPT-4 performance.

Yao Fu, Rameswar Panda, Xinyao Niu et al.

Proposes Any-Shift Prompting, a hierarchical Bayesian framework, achieving significant improvements over 23 datasets in cross-distribution generalization.

Zehao Xiao, Jiayi Shen, Mohammad Mahdi Derakhshani et al.

Zero-shot unsupervised and text-based audio editing using DDPM inversion enhances audio editing flexibility.

Hila Manor, Tomer Michaeli

Proposes LoraRetriever, an input-aware LoRA retrieval and composition framework, achieving significant performance gains over baselines in multi-task scenarios, with detailed experimental validation.

Ziyu Zhao, Leilei Gan, Guoyin Wang et al.

Meta-SpikeFormer achieves 80% accuracy on ImageNet-1K, surpassing SOTA by 3.7%.

Man Yao, Jiakui Hu, Tianxiang Hu et al.

Proposes semantic subtree inheritance and greedy child selection to improve GP-GOMEA's efficiency with high-arity operators.

Thalea Schlender, Mafalda Malafaia, Tanja Alderliesten et al.

Introduced AI Hospital multi-agent framework; models achieve <50% of GPT-4 one-step accuracy; highlights gaps in multi-turn clinical reasoning.

Zhihao Fan, Jialong Tang, Wei Chen et al.