Paper Archive

[object Object], [object Object], [object Object], [object Object], [object Object], [object Object] 9/28/2026 huggingface

Frontier general-purpose systems are rapidly expanding beyond visual understanding into capabilities traditionally handled by dedicated computer-vision models. As these capabilities expand, a central question for the computer-vision community is how far this reach extends, and what remains hard. We ...

[object Object], [object Object], [object Object], [object Object], [object Object] 9/28/2026 huggingface

Distillation attacks copy the reasoning capabilities of closed-source large language models, allowing bad actors to replicate state-of-the-art performance at low cost. Attackers systematically collect a large volume of frontier model reasoning traces and then train (i.e., "distill") their own models...

[object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object] 9/28/2026 huggingface

Novel view synthesis from sparse images must reconcile faithful reconstruction of observed regions with plausible completion of unseen content, while maintaining world consistency across viewpoints. Existing geometry-based methods preserve observed scene structure but often struggle to complete unse...

[object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object] 9/28/2026 huggingface

Large language models (LLMs) excel at structured, verifiable tasks, but their low-entropy bias can produce homogeneous and predictable outputs, limiting their utility for open-ended scientific ideation. Effective discovery, however, spans a broader creative spectrum: from structured day science to l...

[object Object] 9/28/2026 huggingface

Continuous diffusion generates complete reasoning solutions through iterative refinement in latent space. We introduce Latent Flow Reasoning Models (LFRMs), an ELF-based training and inference recipe. Our experiments show that accurate decoding alone does not ensure strong reasoning performance. We ...

Zimo Wang, Junkun Yuan, Angtian Wang, Haotian Yang, Canyu Zhang, Siyuan Yuan, Xingchang Huang, Bo Liu, Yizhi Wang, Yiding Yang, Chongyang Ma, Gordon Guocheng Qian 9/28/2026 arxiv

Modern video diffusion models require tens of denoising evaluations over long spatiotemporal token sequences. Distribution Matching Distillation (DMD) reduces the number of function evaluations (NFE) to just a few. However, DMD samples can degrade during training, exhibiting progressive oversaturati...

Min Kim, José Leonardo Brenes, Fred Hadaegh, Soon-Jo Chung 9/28/2026 arxiv

We present a representation-learning framework for composite adaptive tracking control under dynamically coupled disturbances. The framework connects classical disturbance-accommodating control (DAC) to recent last-layer adaptive disturbance-rejection methods. Specifically, we introduce a statistica...

Srinjay Sarkar, Prakhar Kaushik, Soumava Paul, Alan Yuille 9/28/2026 arxiv

Realistic and editable animal fur reconstruction from multi-view images is challenging due to fine-scale detail, self-occlusion and obfuscation, and, unlike human hair, the lack of animal-fur datasets. Fur usually covers most of an animal's body, with large inter-species and intra-species variabilit...

Zhilin Guo, Boqiao Zhang, Hakan Aktas, Kyle Fogarty, Nursena Koprucu Aslan, Wenzhao Li, Canberk Baykal, Albert Miao, Siyu Hong, Yixiao Liu, Adam Wu, Ashish Kumar Singh, Sakar Khattar, Chenliang Zhou, Weihao Xia, Cristina Nader Vasconcelos, Cengiz Oztireli 9/28/2026 arxiv

One deployed language model must often serve many compute budgets, yet serving each budget still means a separate training or compression run per point. We train a Telescopic Language Model (TLM) to be that continuum: a nested-capacity Transformer supervised by stochastic prefix supervision with a f...

Yijia Fan, Ziqi Huang, Zhongang Cai, Yan Li, Zimo Wen, Wanqi Yin, Haiwen Diao, Ziwei Liu 9/28/2026 arxiv

Unified multimodal models can both look at and render images, so in principle they can repair their own generations: diagnose what an image gets wrong, revise it, observe the result, and diagnose again. Whether a revision helps is known only after it is rendered, so the reflection text and the image...