Interviewed 18 disabled individuals; found safety and platform support crucial for disability representation in avatars; proposed inclusive design principles.

Kelly Mack, Rai Ching Ling Hsu, Andrés Monroy-Hernández et al.

Proposes Speculative Sampling, enabling 2-2.5x speedup in decoding 70B-parameter Chinchilla model by generating multiple tokens per call while maintaining distribution fidelity.

Charlie Chen, Sebastian Borgeaud, Geoffrey Irving et al.

N4SR method uses neural networks for symbolic regression, generating physically plausible models from small datasets.

Jiří Kubalík, Erik Derner, Robert Babuška

ADAPT, a Transformer-based multi-task model, jointly predicts driving actions and generates natural language explanations, achieving CIDEr 34.6 and reasoning 11.4 on BDD-X.

Bu Jin, Xinyu Liu, Yupeng Zheng et al.

Proposes text-guided video generation via diffusion models for universal decision policies, achieving significant generalization in multi-task and long-horizon planning.

Yilun Du, Mengjiao Yang, Bo Dai et al.

RL-based AI Clinician with interpretability explored ICU doctors' treatment decision behaviors for sepsis, revealing diverse trust and negotiation patterns.

Venkatesh Sivaraman, Leigh A. Bukowski, Joel Levin et al.

GSM-IC shows LLMs are easily distracted; SC and ignore-the-noise instructions partly recover accuracy.

Freda Shi, Xinyun Chen, Kanishka Misra et al.

In-Context RALM boosts language model performance by prepending documents, significantly reducing perplexity.

Ori Ram, Yoav Levine, Itay Dalmedigos et al.

Proposes Simplex Random Features (SimRFs) for optimal kernel approximation via geometric correlation, outperforming orthogonal RFs with minimal extra cost.

Isaac Reid, Krzysztof Choromanski, Valerii Likhosherstov et al.

Proposes Attend-and-Excite, an attention-based method to improve semantic fidelity in text-to-image diffusion models.

Hila Chefer, Yuval Alaluf, Yael Vinker et al.

Leveraging large language models (LLMs) as versatile decomposers through evidence and question decomposition significantly enhances table-based reasoning, surpassing human performance on TabFact.

Yunhu Ye, Binyuan Hui, Min Yang et al.

Flan-T5 enhances performance by 3-17% through mixed prompt settings.

Shayne Longpre, Le Hou, Tu Vu et al.

AdaTape enables dynamic computation in neural networks using adaptive tape tokens, excelling in image recognition tasks.

Fuzhao Xue, Valerii Likhosherstov, Anurag Arnab et al.

REPLUG enhances black-box large models like GPT-3 by simple retrieval-based input augmentation, boosting performance by 6.3% without parameter fine-tuning.

Weijia Shi, Sewon Min, Michihiro Yasunaga et al.

BLIP-2 leverages frozen image encoders and large language models via a lightweight Querying Transformer, achieving state-of-the-art zero-shot performance with minimal trainable parameters.

Junnan Li, Dongxu Li, Silvio Savarese et al.

AudioLDM employs latent diffusion models trained on audio-only data with CLAP embeddings, achieving state-of-the-art text-to-audio generation on a single GPU.

Haohe Liu, Zehua Chen, Yi Yuan et al.

Proposes decentralized entropic optimal transport (DEOT) with theoretical guarantees, suitable for distributed distribution comparison.

Xiangfeng Wang, Hongteng Xu, Moyi Yang

Applying Byte Pair Encoding (BPE) to symbolic music reduces sequence length by over 50%, enlarges vocabulary, and improves model performance and speed.

Nathan Fradet, Nicolas Gutowski, Fabien Chhel et al.

Proposes sample-efficient pretraining using child-inspired datasets (10M-100M words) with Transformer models and curriculum learning, improving low-resource NLP.

Alex Warstadt, Leshem Choshen, Aaron Mueller et al.

Proposes 3DShape2VecSet, a vector-set neural field for improved 3D shape encoding and diffusion-based generation.

Biao Zhang, Jiapeng Tang, Matthias Niessner et al.