Objaverse 1.0 is a large-scale dataset with over 800K annotated 3D models, enabling advances in 3D generative modeling, fine-grained classification, and embodied AI navigation.

Matt Deitke, Dustin Schwenk, Jordi Salvador et al.

Introduces EDAtt, an attention-based policy for SimulST, improving BLEU by up to 7 points and reducing latency by 1.4s.

Sara Papi, Matteo Negri, Marco Turchi

Imagen Editor enhances text-guided image inpainting using cascaded diffusion models and EditBench benchmark.

Su Wang, Chitwan Saharia, Ceslee Montgomery et al.

ISVOS combines instance understanding with memory matching, reaching 87.1% J&F on DAVIS 2017 validation.

Junke Wang, Dongdong Chen, Zuxuan Wu et al.

Fine-tuned CodeGen-16B achieves 25.9% syntax correctness and outperforms commercial models in functional accuracy for Verilog code generation.

Shailja Thakur, Baleegh Ahmad, Zhenxing Fan et al.

Proposes LMQL, a scripting-based query language that constrains and optimizes large language model calls, reducing costs by up to 85%.

Luca Beurer-Kellner, Marc Fischer, Martin Vechev

Proves Sinkhorn convergence rate as O(t^{-1}) in relative entropy, applicable to unbounded costs and marginals.

Promit Ghosal, Marcel Nutz

Proposes doubly robust kernel statistics for testing distributional causal effects, combining counterfactual mean embeddings with permutation tests.

Jake Fawkes, Robert Hu, Robin J. Evans et al.

BEVBert introduces spatial-aware multimodal map pre-training, boosting VLN success rates by over 4% on benchmarks.

Dong An, Yuankai Qi, Yangguang Li et al.

LLM-Planner uses few-shot learning with GPT-3 for grounded hierarchical planning, achieving competitive results with less than 0.5% training data.

Chan Hee Song, Jiaman Wu, Clayton Washington et al.

Introduces Contrast-Consistent Search (CCS), an unsupervised method to discover latent knowledge in language models, improving question-answering accuracy by 4%.

Collin Burns, Haotian Ye, Dan Klein et al.

Hierarchical multimodal transformer Hi-VT5 processes multi-page documents, achieving 50.01% accuracy and 0.6572 ANLS on MP-DocVQA.

Rubèn Tito, Dimosthenis Karatzas, Ernest Valveny

Whisper2, a large-scale weakly supervised speech model trained on 680,000 hours, achieves near-human zero-shot recognition across multiple languages and tasks.

Alec Radford, Jong Wook Kim, Tao Xu et al.

InternVideo combines generative and discriminative self-supervised learning, achieving 91.1% top-1 accuracy on Kinetics-400 across 39 video tasks.

Yi Wang, Kunchang Li, Yizhuo Li et al.

Proposed ASDK combines deep kernel learning and entropy maximization for efficient high-dimensional yield estimation, achieving up to 10.3x speedup.

Shuo Yin, Guohao Dai, Wei W. Xing

A knowledge graph-based system for short-term, episodic, and semantic memory improves RL agent performance.

Taewoon Kim, Michael Cochez, Vincent François-Lavet et al.

CoupAlign couples sentence-mask and word-pixel alignments, improving oIoU by ~2% on RIS datasets.

Zicheng Zhang, Yi Zhu, Jianzhuang Liu et al.

Proposes CSCG model, viewing space as a latent sequence learning framework, explaining hippocampal phenomena with a unified approach.

Rajkumar Vasudeva Raju, J. Swaroop Guntupalli, Guangyao Zhou et al.

DIP algorithm uses monocular camera and pose estimation to interpret diver pointing gestures for underwater target localization.

Chelsey Edge, Junaed Sattar

Introduced flip graphs to reduce matrix multiplication steps.

Manuel Kauers, Jakob Moosbauer