Paper Archive

Yana Wei, Hongbo Peng, Yanlin Lai, Liang Zhao, Kangheng Lin, En Yu, Keyu Lv, Han Zhou, Yin Tang, Haodong Li, Mitt Huang, Hangyu Guo, Jianjian Sun, Zheng Ge, Xiangyu Zhang, Daxin Jiang, Vishal M. Patel 6/26/2026 arxiv

We introduce PerceptionRubrics, a rubric-based evaluation framework that addresses the gap between saturated benchmark scores and real-world brittleness. Shifting evaluation from holistic semantic matching to rigorous atomic auditing, PerceptionRubrics pairs 1,038 information-dense images with over ...

Jia-Chen Zhao, Beiqi Chen, Xinyang Chen, Guangcong Wang, Liqiang Nie 6/26/2026 arxiv

We present StructSplat, a feed-forward and generalizable 3D Gaussian reconstruction framework that operates directly on uncalibrated images without requiring camera parameters. Existing methods either rely on per-scene optimization or assume known camera poses, and often entangle geometry and appear...

Shai Ben-David, Farnam Mansouri, Anay Mehrotra, Manolis Zampetakis 6/26/2026 arxiv

Binary classification from positive-only samples is a variant of PAC learning in which the learner receives i.i.d. samples from the positive region of an unknown target concept, but is evaluated under the original distribution (which places mass on both positive and negative regions). This model dat...

Luis Leal 6/26/2026 arxiv

Many two-player zero-sum games admit not a unique Nash equilibrium but a convex set of them: a polytope of profiles that all share the minimax value V* yet prescribe different behaviour. Standard solvers each converge to some equilibrium and are treated as interchangeable. We ask whether they instea...

Kijung Jeon, Thuy-Duong Vuong, Molei Tao 6/26/2026 arxiv

Inference-time scaling is a promising paradigm to improve generative models, especially when outputs must satisfy structural constraints or optimize downstream rewards. We consider Masked Diffusion Model (MDM) and introduce MDM-VGB, a discrete diffusion sampler that augments unmasking generation wit...

Kevin Kingslin, Anish Natekar, Ashutosh Ranjan, Vivek Srivastava, Savita Bhat, Shirish Karande 6/26/2026 arxiv

Preference-based alignment often struggles to capture the reasoning that underlies human judgments. Many evaluations rely on multiple interacting criteria, yet pairwise labels reveal only the final choice rather than the considerations that shape preferences. Inverse Constitutional AI (ICAI) improve...

Phong Dang, Evander Espinoza, Xiaoliang Wan, Michela Negro, Jerry P. Draayer, Feng Pan, Tomas Dytrych, Daniel Langr, David Kekejian 6/26/2026 arxiv

Ab initio modeling has established Wigner's SU(4) and Elliott's SU(3) as dominant symmetries of the nuclear force in light and intermediate-mass nuclei. We ask whether they also govern nuclear binding across the entire chart. Our aim is not high-precision prediction but physical insight, through int...

Rajesh Jayaram, Drew Tyler, David Woodruff, Corinna Cortes, Yossi Matias, Vahab Mirrokni, Vincent Cohen-Addad 6/26/2026 arxiv

Artificial intelligence is driving a revolution in scientific discovery, accelerating everything from hypothesis generation to mathematical theorem proving. However, this rapid acceleration is creating a systemic challenge: traditional human peer review cannot scale to match the influx of AI-assiste...

Nadun Ranawaka, Josiah Wong, Wei-Lin Pai, Wei-Teng Chu, Tianyuan Dai, Masoud Moghani, Hang Yin, Yunfan Jiang, Wesley Durbano, Brandon Huynh, Yu Fang, Linxi Fan, Danfei Xu, Ruohan Zhang, Li Fei-Fei, Bowen Wen, Ajay Mandlekar, Yuke Zhu 6/26/2026 arxiv

Training and evaluating robot policies in the real world is costly and difficult to scale. We introduce SimFoundry, a modular and automated system for zero-shot real-to-sim scene construction from a video. SimFoundry generates sim-ready digital twins and supports object, scene, and task editing, ena...

[object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object] 6/26/2026 huggingface

Extracting dynamic 4D object interactions from massive, in-the-wild monocular videos offers a highly efficient data collection pathway for scaling Embodied AI and training VLAs. However, existing monocular 4D reconstruction methods primarily focus on isolated objects, often failing under the severe ...