Introduces BadRobot attack framework exploiting embodied LLM vulnerabilities, achieving over 85% success in real-world robot jailbreaks and malicious actions.

Hangtao Zhang, Chenyu Zhu, Xianlong Wang et al.

Using MidEast-TE-mini, the study compares graph, text, and mixed LLM forecasters; GPT-4 extraction reaches 72.60%, while tuning and RAG help most.

He Chang, Chenchen Ye, Zhulin Tao et al.

Proposes a unified stochastic map framework for tokenization, ensuring estimator consistency in language models.

Juan Luis Gastaldi, John Terilla, Luca Malagutti et al.

VISA integrates large multimodal language models with segmentation decoders to enable reasoning-based video object segmentation, outperforming state-of-the-art methods.

Cilin Yan, Haochen Wang, Shilin Yan et al.

FLAMe, a large-scale general auto-evaluator trained on 5.3M human judgments, outperforms proprietary models in multiple benchmarks.

Tu Vu, Kalpesh Krishna, Salaheddin Alzubi et al.

This study evaluates LLM non-determinism, showing greedy decoding outperforms sampling; small models can match larger ones with best-of-N and reward models.

Yifan Song, Guoyin Wang, Sujian Li et al.

Proposed MTAD framework combines auxiliary models with joint multi-token decoding, boosting efficiency and quality.

Zongyue Qin, Ziniu Hu, Zifan He et al.

Introduces non-Euclidean geometry, topology, and algebra into machine learning, enabling analysis of complex structured data with geometric, topological, and algebraic methods.

Mathilde Papillon, Sophia Sanborn, Johan Mathe et al.

Introduced SPIQA dataset, combining multimodal large models for scientific figure understanding, with chain-of-thought reasoning, significantly advancing research comprehension.

Shraman Pramanick, Rama Chellappa, Subhashini Venugopalan

FANet employs the AFE module combining SCM and FRM to enhance multi-scale features, achieving state-of-the-art semantic segmentation in cluttered scenes.

Muhammad Ali, Mamoona Javaid, Mubashir Noman et al.

IGOR combines LLM subtask planning with goal-conditioned asynchronous PPO, outperforming reported IGLU and Crafter baselines.

Zoya Volovikova, Alexey Skrynnik, Petr Kuderov et al.

LightenDiffusion combines Retinex theory with diffusion models for unsupervised low-light image enhancement, outperforming existing methods.

Hai Jiang, Ao Luo, Xiaohong Liu et al.

AIR-Bench 2024 constructs a four-tier safety taxonomy with 314 granular risk categories, evaluating models' alignment with regulations across 5694 prompts.

Yi Zeng, Yu Yang, Andy Zhou et al.

MAGNET employs script-specific boundary predictors with adaptive gradient optimization, reducing over-segmentation in non-Latin scripts and improving efficiency.

Orevaoghene Ahia, Sachin Kumar, Hila Gonen et al.

EfficientQAT combines Block-AP and E2E-QP, significantly improving low-bit quantization of large models with reduced training time.

Mengzhao Chen, Wenqi Shao, Peng Xu et al.

PaliGemma combines SigLIP-So400m and Gemma-2B, with 3B parameters, demonstrating broad transfer capabilities across tasks.

Lucas Beyer, Andreas Steiner, André Susano Pinto et al.

Proposes 'Knowledge Boosting' to enhance small models during low-latency inference using delayed hints from remote large models, achieving up to 3.53dB SI-SDR gain.

Vidya Srinivas, Malek Itani, Tuochao Chen et al.

Proposed SEA framework integrates GPT-4 standardization, Mistral-7B evaluation, and self-correction, enhancing automated paper review quality.

Jianxiang Yu, Zichen Ding, Jiaqi Tan et al.

Comprehensive review of embodied AI leveraging MLMs and WMs, focusing on perception, interaction, and sim-to-real transfer, with experimental benchmarks.

Yang Liu, Weixing Chen, Yongjie Bai et al.

Introducing EVI-MAE, combining video and IMU data, achieving 92.78% accuracy in action recognition.

Mingfang Zhang, Yifei Huang, Ruicong Liu et al.