DriveLM integrates graph-structured visual QA with pre-trained VLMs for end-to-end autonomous driving, achieving superior zero-shot generalization on nuScenes and CARLA.

Chonghao Sima, Katrin Renz, Kashyap Chitta et al.

VideoPoet uses a decoder-only Transformer for zero-shot video generation, producing high-quality motions.

Dan Kondratyuk, Lijun Yu, Xiuye Gu et al.

A GPT-4-based multimodal agent achieves 84.4% success on 50 diverse smartphone tasks, operating without backend access.

Chi Zhang, Zhao Yang, Jiaxuan Liu et al.

Align Your Gaussians (AYG) combines dynamic 3D Gaussian splatting with deformation fields and multi-modal diffusion feedback to achieve state-of-the-art text-to-4D scene synthesis, outperforming prior methods.

Huan Ling, Seung Wook Kim, Antonio Torralba et al.

NeuralFeels integrates vision and touch, online learning neural fields for real-time unknown object pose and shape reconstruction, enhancing robotic in-hand perception.

Sudharshan Suresh, Haozhi Qi, Tingfan Wu et al.

Introduces Time Vectors, using fine-tuned weight differences and interpolation to encode temporal information, improving model performance across time.

Kai Nylund, Suchin Gururangan, Noah A. Smith

Emu2, with 3.7 billion parameters, significantly enhances few-shot and zero-shot multimodal understanding and generation capabilities.

Quan Sun, Yufeng Cui, Xiaosong Zhang et al.

Study uses police-reported data to benchmark ADS crash rates, addressing data selection and reporting bias issues.

John M. Scanlon, Kristofer D. Kusano, Laura A. Fraade-Blanar et al.

Waymo ADS achieved an 80% lower crash rate (0.6 IPMM) than human benchmarks (2.80 IPMM) over 7.14M miles, demonstrating significant safety improvements.

Kristofer D. Kusano, John M. Scanlon, Yin-Hsiu Chen et al.

pixelSplat employs probabilistic 3D Gaussian primitives with reparameterization for scalable, real-time scene reconstruction, outperforming SOTA with 2.5× faster rendering and explicit 3D representations.

David Charatan, Sizhe Li, Andrea Tagliasacchi et al.

Using model artifacts like Softmax, attention, and input attribution to predict hallucinations in QA with up to 0.80 AUROC, before they occur.

Ben Snyder, Marius Moisescu, Muhammad Bilal Zafar

Pose2Gaze combines CNN and ST-GCN to predict eye gaze from full-body poses, reducing mean angular error by 24% across datasets.

Zhiming Hu, Jiahui Xu, Syn Schmitt et al.

Proposed iterative preference learning algorithm significantly enhances RLHF performance, achieving a 34.79% win rate in AlpacaEval2.

Wei Xiong, Hanze Dong, Chenlu Ye et al.

Introduces a quantum-inspired iterative refinement method for semidefinite optimization with quadratic convergence.

Mohammadhossein Mohammadisiahroudi, Brandon Augustino, Pouya Sampourmahani et al.

RAG combines retrieval and generation, significantly improving factual accuracy in LLMs; key techniques include indexing, retrieval, and augmentation.

Yunfan Gao, Yun Xiong, Xinyu Gao et al.

PowerInfer leverages neuron activation power-law distribution, enabling single-GPU inference with up to 11.69× speedup, maintaining accuracy on large LLMs.

Yixin Song, Zeyu Mi, Haotong Xie et al.

Proposes Meta-CPO, integrating differentiable convex programming for safe, rapid adaptation in non-stationary environments.

Minjae Cho, Chuangchuang Sun

Proposed 3DAxiesPrompts (3DAP) embeds 3D coordinate info into images, significantly enhancing GPT-4V's performance in 3D point reconstruction, matching, and object detection.

Dingning Liu, Xiaomeng Dong, Renrui Zhang et al.

DriveMLM aligns multimodal LLMs with behavioral states, enabling closed-loop autonomous driving with 3.2-4.7 point improvements on CARLA.

Erfei Cui, Wenhai Wang, Zhiqi Li et al.

Proposes 3D Gaussian Splatting for animatable avatars, training in 30 min, real-time at 50+ FPS, outperforming SOTA in speed and quality.

Zhiyin Qian, Shaofei Wang, Marko Mihajlovic et al.