Paper Archive

[object Object], [object Object], [object Object], [object Object] 6/29/2026 huggingface

Audio-video generation has recently gained unprecedented research attention, aiming to synthesize high-quality sounding video content with fine-grained synchronization and semantic alignment between the auditory and visual components. The preceding methods predominantly adopt a dual-branch design wi...

[object Object], [object Object], [object Object], [object Object], [object Object] 6/30/2026 huggingface

Generative models have achieved remarkable progress, yet applying them to satellite imagery remains challenging. Unlike natural imagery, satellite scenes are structured by spatially complex and semantically distinct geometries. Prior work addresses this complexity by adapting natural image framework...

[object Object], [object Object], [object Object], [object Object], [object Object] 6/29/2026 huggingface

Modern large-scale LLM pretraining benefits from utilizing Pipeline Parallelism; however, synchronous implementations leave GPUs idle during pipeline bubbles, wasting computational resources. Asynchronous Pipeline Parallelism eliminates these bubbles, maximizing throughput at the cost of gradient st...

[object Object], [object Object], [object Object], [object Object], [object Object], [object Object] 6/29/2026 huggingface

Generative molecular design is shaped by simple proxy benchmarks for drug-like properties and models pretrained on large pharmaceutical datasets. This combination yields strong benchmark metrics but limits transferability to domains structurally distinct from drug discovery. To overcome this limitat...

[object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object] 6/29/2026 huggingface

Blind image quality assessment (BIQA) is commonly built on two basic learning paradigms: regression and ranking. Regression calibrates absolute scores, whereas ranking recovers quality structure from ordinal relations. Although joint regression-ranking supervision often improves BIQA, the relation b...

Sergio Hernández-Gutiérrez, Matteo Merler, Ilze Amanda Auzina, Joschka Strüber, Ameya Prabhu, Matthias Bethge 6/30/2026 arxiv

LLM agents increasingly act over long horizons, where a single trajectory can contain hundreds or thousands of actions. In these settings, outcome-only rewards provide too sparse guidance, failing to inform the model about the goodness of intermediate actions. Dense supervision methods aim to solve ...

Yujie Guo, Yudong Jin, Lingteng Qiu, Zehong Shen, Zhen Xu, Jing Zhang, Xianchao Shen, Hujun Bao, Sida Peng, Xiaowei Zhou 6/30/2026 arxiv

Producing 3D human representations from input views on the fly is essential for immersive live streaming systems, where representation compactness is as critical as high fidelity given limited computational power and transmission bandwidth. Although recent feed-forward reconstruction methods achieve...

Or Hirschorn, Aaron Olender, Eli Alshan, Ianir Ideses, Lior Fritz, Sagie Benaim 6/30/2026 arxiv

We present a zero-shot, training-free and optimization-free framework for generating 360 panoramic images and videos by directly injecting spherical priors into pre-trained diffusion transformers. Existing methods either rely on costly fine-tuning on scarce panoramic data that limits generalization,...

Yuqing Yang, Qi Zhu, Zhen Han, Boran Han, Zhengyuan Shen, Shuai Wang, Vassilis N. Ioannidis, Huzefa Rangwala 6/30/2026 arxiv

While large language models (LLMs) perform well on table tasks, they still make data referencing errors (DREs), i.e., incorrectly citing or omitting table values, despite understanding the table structure. Beyond final-answer accuracy, DREs directly compromise the correctness and reliability of inte...

Gabrielle Kaili-May Liu, Avi Caciularu, Gal Yona, Idan Szpektor, Arman Cohan 6/30/2026 arxiv

Metacognition is a critical component of intelligence that describes the ability to monitor and regulate one's own cognitive processes. Yet LLMs exhibit systemic deficiencies in key metacognitive faculties: they hallucinate with high confidence, fail to recognize knowledge boundaries, and misreprese...