Point Bridge leverages unified point cloud representations for zero-shot sim-to-real transfer, achieving up to 44% performance gains.

Siddhant Haldar, Lars Johannsmeier, Lerrel Pinto et al.

Scaling text-to-image diffusion transformers with Representation Autoencoders, RAEs outperform VAEs across all model scales.

Shengbang Tong, Boyang Zheng, Ziteng Wang et al.

ActionMesh integrates temporal diffusion and autoencoder to rapidly generate topology-consistent animated 3D meshes.

Remy Sabathier, David Novotny, Niloy J. Mitra et al.

SAMTok discretizes masks into two tokens, enabling pixel-level understanding without architectural changes.

Yikang Zhou, Tao Zhang, Dengxian Gong et al.

HumanoidPF encodes humanoid-obstacle relationships, enabling collision-free navigation in cluttered indoor scenes with success rate over 93%.

Han Xue, Sikai Liang, Zhikai Zhang et al.

EvoCUA employs a self-evolving cycle combining verifiable synthetic task generation, large-scale asynchronous interaction, and iterative policy optimization, achieving 56.7% success on OSWorld.

Taofeng Xue, Chong Peng, Mianqiu Huang et al.

UXCascade enables scalable usability testing with simulated user agents, providing structured user feedback.

Steffen Holter, Eunyee Koh, Mustafa Doga Dogan et al.

PhysProver combines RLVR and PhysLeanData, enhancing physics theorem proving by 2.4%.

Hanning Zhang, Ruida Wang, Rui Pan et al.

Proposes an iterative self-correction framework using vision-language critics to improve complex prompt image generation, achieving 16.9% accuracy gain.

Shantanu Jaiswal, Mihir Prabhudesai, Nikash Bhardwaj et al.

RayRoPE employs projective ray encoding with depth prediction and uncertainty modeling, ensuring SE(3) invariance and scene geometry adaptation, boosting novel-view synthesis by 24%.

Yu Wu, Minsik Jeon, Jen-Hao Rick Chang et al.

MonoRace employs monocular camera and IMU for champion-level drone racing at speeds up to 100 km/h without external tracking.

Stavrow A. Bahnam, Robin Ferede, Till M. Blaha et al.

This work proves that Transformers can achieve minimax optimal nonparametric regression rates with Θ(log n) parameters, requiring Ω(n^{2α/(2α+d)} log^3 n) pretraining sequences.

Michelle Ching, Ioana Popescu, Nico Smith et al.

CorpusQA benchmark challenges LLMs' global reasoning over 10 million tokens.

Zhiyuan Lu, Chenliang Li, Yingcheng Shi et al.

TIDAL decouples semantic reasoning and high-frequency control via dual-frequency architecture, achieving 9Hz updates and 2x performance improvement in dynamic tasks.

Yuteng Sun, Haoran Wang, Ruofei Bai et al.

The paper reviews contingency planning for autonomous vehicles, proposing a logic-conditioned hybrid control framework emphasizing reactive and proactive safety methods.

Lei Zheng, Luyao Zhang, Peiqi Yu et al.

Proposes execution-guided automated AI research using evolutionary search and RL, achieving 69.4% success rate and reducing pretraining time to 19.7 min.

Chenglei Si, Zitong Yang, Yejin Choi et al.

Proposes Soft Tail-dropping Adaptive Tokenizer (STAT), dynamically adjusting token count based on image complexity, improving reconstruction and generation quality.

Zeyuan Chen, Kai Zhang, Zhuowen Tu et al.

Jet-RL framework improves RL training efficiency with unified FP8 precision flow, achieving 33% rollout speedup.

Haocheng Xi, Charlie Ruan, Peiyuan Liao et al.

Habibi introduces an open-source multi-dialect Arabic TTS framework using multi-step data curation and curriculum learning, covering 12+ dialects with performance surpassing specialized models.

Yushen Chen, Junzhe Liu, Yujie Tu et al.

Introduced a contrastive causality metric, revealing probabilistic metrics fail to capture causal reasoning.

Hojin Kim, Jaehyung Kim