This study questions whether ego status alone suffices for open-loop end-to-end autonomous driving, revealing dataset bias and metric limitations that favor ego-only reliance.

Zhiqi Li, Zhiding Yu, Shiyi Lan et al.

TimeChat is a time-sensitive multimodal large language model improving long video understanding, notably achieving a 2.8 CIDEr increase on YouCook2.

Shuhuai Ren, Linli Yao, Shicheng Li et al.

Proposes SCLIP with Correlative Self-Attention, boosting zero-shot semantic segmentation from 14.1% to 38.2% mIoU.

Feng Wang, Jieru Mei, Alan Yuille

Proposed RaIR as an intrinsic reward signal, significantly improving zero-shot performance in robotic assembly tasks.

Cansu Sancaktar, Justus Piater, Georg Martius

VideoBooth enables feed-forward image-prompted video generation, reaching 65.0979 DINO and 74.7971 CLIP-Image.

Yuming Jiang, Tianxing Wu, Shuai Yang et al.

Mamba employs selective state space models for linear-time sequence modeling, achieving 5× inference throughput over Transformers.

Albert Gu, Tri Dao

DeepCache accelerates diffusion models by caching features, achieving 2.3× speedup on Stable Diffusion v1.5 with minimal quality loss without retraining.

Xinyin Ma, Gongfan Fang, Xinchao Wang

DREAM integrates diffusion rectification and estimation adaptation, boosting training speed (2-3×) and reducing sampling steps (10-20×) in super-resolution tasks.

Jinxin Zhou, Tianyu Ding, Tianyi Chen et al.

GraphDreamer uses scene graphs to generate disentangled 3D scenes, outperforming prior methods with CLIP score 0.3326.

Gege Gao, Weiyang Liu, Anpei Chen et al.

PI-ViT integrates 2D/3D skeleton info during training to enhance video transformer-based activity recognition, achieving SOTA without extra inference cost.

Dominick Reilly, Srijan Das

ChatPose employs multimodal LLMs with embedded SMPL parameters for 3D human pose understanding and generation.

Yao Feng, Jing Lin, Sai Kumar Dwivedi et al.

Distribution Matching Distillation (DMD) converts diffusion models into one-step generators, achieving FID 2.62 on ImageNet 64×64 at 20 FPS.

Tianwei Yin, Michaël Gharbi, Richard Zhang et al.

X-InstructBLIP aligns multi-modal data to LLMs, enabling cross-modal reasoning with significant performance gains.

Artemis Panagopoulou, Le Xue, Ning Yu et al.

CritiqueLLM employs Eval-Instruct with pseudo-references to train a critique model, achieving near GPT-4 performance in fine-grained evaluation of LLM outputs, outperforming open-source baselines.

Pei Ke, Bosi Wen, Zhuoer Feng et al.

DiffCAD employs diffusion models for weakly-supervised CAD retrieval and alignment from RGB images, surpassing supervised SOTA with synthetic training.

Daoyi Gao, Dávid Rozenberszki, Stefan Leutenegger et al.

HOT combines 2-hop structure with Block-Recurrent Transformers, improving MOOC accuracy by 9% over DyGFormer.

Maciej Besta, Afonso Claudino Catarino, Lukas Gianinazzi et al.

MGProto uses Gaussian-distributed prototypes for interpretable and trustworthy image recognition, excelling on CUB-200-2011.

Chong Wang, Yuanhong Chen, Fengbei Liu et al.

HOLD is a category-agnostic monocular method for joint 3D reconstruction of hands and objects, outperforming supervised baselines.

Zicong Fan, Maria Parelli, Maria Eleni Kadoglou et al.

Ego-Exo4D leverages multimodal multiview video datasets for fine-grained human activity understanding, achieving 85% accuracy in activity recognition.

Kristen Grauman, Andrew Westbury, Lorenzo Torresani et al.

Unified definition and hierarchical taxonomy of transfer learning in robotics, analyzing applications across robot, task, and environment dimensions with specific algorithms and datasets.

Noémie Jaquier, Michael C. Welle, Andrej Gams et al.