Text2Motion combines LLMs and geometric planning to generate feasible robot action sequences for long-horizon tasks, achieving 82% success rate.

Kevin Lin, Christopher Agia, Toki Migimatsu et al.

Proposes CAT-Seg, a cost aggregation-based open-vocabulary semantic segmentation framework, fine-tuning CLIP encoders to improve pixel-level recognition of seen and unseen classes, outperforming state-of-the-art.

Seokju Cho, Heeseong Shin, Sunghwan Hong et al.

E3Net-based deep noise suppression with speaker embedding improves signal quality by 0.145 score points and WAcc to 85.3% in ICASSP 2023 challenge.

Harishchandra Dubey, Ashkan Aazami, Vishak Gopal et al.

Text2Tex uses depth-aware diffusion models with auto view selection to synthesize high-quality 3D textures from text prompts.

Dave Zhenyu Chen, Yawar Siddiqui, Hsin-Ying Lee et al.

MM-REACT integrates ChatGPT with vision experts via prompts for advanced multimodal reasoning without training.

Zhengyuan Yang, Linjie Li, Jianfeng Wang et al.

Reflexion employs verbal self-reflection to enhance LLMs without fine-tuning, achieving 91% pass@1 on HumanEval, surpassing GPT-4's 80%.

Noah Shinn, Federico Cassano, Edward Berman et al.

Zero-1-to-3 leverages pre-trained diffusion models for zero-shot single-image 3D view synthesis and reconstruction, with strong generalization.

Ruoshi Liu, Rundi Wu, Basile Van Hoorick et al.

Enhance LLMs' contextual faithfulness using opinion-based prompts and counterfactual demonstrations, significantly reducing memorization ratio.

Wenxuan Zhou, Sheng Zhang, Hoifung Poon et al.

GPT-4 surpasses USMLE passing scores by over 20 points without domain-specific tuning, demonstrating strong reasoning and calibration.

Harsha Nori, Nicholas King, Scott Mayer McKinney et al.

Proposes a decoupled encoder-decoder framework with StyleGAN for photorealistic image synthesis from abstract sketches, achieving state-of-the-art results.

Subhadeep Koley, Ayan Kumar Bhunia, Aneeshan Sain et al.

Introduced a foresightful dense visual affordance method, enhancing efficiency in deformable object manipulation.

Ruihai Wu, Chuanruo Ning, Hao Dong

Using TextFlint across 21 datasets, the study finds RLHF improves human-like dialogue but not overall NLU accuracy or robustness.

Junjie Ye, Xuanting Chen, Nuo Xu et al.

HIVE leverages human feedback to enhance instruction-based visual editing via reward modeling and offline RL, significantly improving alignment.

Shu Zhang, Xinyi Yang, Yihao Feng et al.

Proposes Min-SNR-γ weighting strategy, accelerating diffusion model training by 3.4×, achieving FID 2.06 on ImageNet 256×256.

Tiankai Hang, Shuyang Gu, Chen Li et al.

Proposes a model-based explanation framework for concept drift, leveraging spatial feature changes and explanation tools like LIME and SHAP.

Fabian Hinder, Valerie Vaquet, Johannes Brinkrolf et al.

Proposes DIRE, leveraging diffusion model reconstruction error for high-accuracy detection of diffusion-generated images, outperforming existing methods.

Zhendong Wang, Jianmin Bao, Wengang Zhou et al.

Introduces MATH 401 dataset, evaluates GPT-4, ChatGPT on arithmetic tasks, showing GPT-4's superior performance with 83.54% accuracy.

Zheng Yuan, Hongyi Yuan, Chuanqi Tan et al.

ART enables automatic multi-step reasoning and tool use in LLMs, improving unseen task performance by over 22%.

Bhargavi Paranjape, Scott Lundberg, Sameer Singh et al.

SelfCheckGPT detects factual hallucinations via multi-sample response consistency without external data.

Potsawee Manakul, Adian Liusie, Mark J. F. Gales

GPT-4 is a multimodal Transformer trained with predictive and RLHF methods, achieving human-level performance and scalable predictability.

OpenAI, Josh Achiam, Steven Adler et al.