Paper Archive

Luca Avena, Gianmarco Bet, Bernardo Busoni 6/5/2026 arxiv

We investigate the probabilistic reasoning capabilities of large language models through a controlled benchmarking study on discrete probability problems. We constructed two datasets, respectively a set of standard exercises and a set of counterintuitive exercises, designed to trigger heuristic reas...

Meixi Song, Dizhe Zhang, Hao Ren, Ruiyang Zhang, Bo Du, Ming-Hsuan Yang, Lu Qi 6/5/2026 arxiv

In this work, we focus on extending SHARP, the popular photorealistic view synthesis method, for universal monocular rendering across a continuum of camera systems, from conventional perspective cameras to wide-field-of-view, fisheye and omnidirectional panoramic settings. To overcome the pinhole-sp...

Xintao Wang, Sirui Zheng, Hongqiu Wu, Weiyuan Li, Jen-tse Huang, Minghao Zhu, Can Zu, Qi Deng, Jiawei Wang, Qianyu He, Heng Wang, Xiaojian Wu, Yunzhe Tao 6/5/2026 arxiv

Humans learn from social life. Simulating this process with LLM-powered agents represents a promising research direction, raising a natural question: whether LLMs can learn from such simulated social experience to better understand and replicate human behavior. However, prior agent society simulatio...

Cong Chen, Guo Gan, Kaixiang Ji, ChaoYang Zhang, Zhen Yang, Guangming Yao, Hao Chen, Jingdong Chen, Yi Yuan, Chunhua Shen 6/5/2026 arxiv

Current Vision-Language Models struggle with hours-long videos because processing full-length visual sequences induces prohibitive token explosion and attention dilution. To overcome this, we introduce MemDreamer to decouple perception and reasoning, shifting long-video understanding into an agentic...

Hanhui Wang, Yiming Xie, Haiwen Feng, Zhaoyang Lv, Shenlong Wang, Huaizu Jiang 6/5/2026 arxiv

We introduce StreamForce, a streaming video generation framework that enables physically grounded control through continuous force inputs. Unlike prior video models that train separate models for different force types, assume fixed forces, or rely on non-causal processing, StreamForce is a causal an...

Tuba Girgin, Jose Castelblanco, Gabriel Rodriguez, Emre Girgin, Cagri Kilic 6/5/2026 arxiv

The object manipulation capabilities of quadruped robots is an open research challenge. While previous studies have focused on low-level policy learning, task execution still relies on expert-designed high-level trajectories. Autonomous selection of both an affordable interaction point on the target...

Johannes Theodoridis, Johannes Maucher, Andreas Schilling 6/5/2026 arxiv

We propose Differences in Detection (DnD), an intuitive method to compare two object detection models. Based on the same matching algorithm, it complements the standard metrics of mean Average Precision ($mAP$) and TIDE error analysis with the ability to compare two models directly. More specificall...

Songhao Wu, Zhongxin Chen, Yuxuan Liu, Heng Cui, Cong Li, Rui Yan 6/5/2026 arxiv

Large language models exhibit impressive zero-shot capabilities across a wide range of downstream tasks. However, they struggle to function as off-the-shelf embedding models, leading to suboptimal performance on massive text embedding benchmarks. In this paper, we identify a potential cause underlyi...

Fatema Siddika, Md Anwar Hossen, Tanwi Mallick, Ali Jannesari 6/5/2026 arxiv

Continual learning in Large Language Models (LLMs) is hindered by the plasticity-stability dilemma, where acquiring new capabilities often leads to catastrophic forgetting of previous knowledge. Existing methods typically treat parameters uniformly, failing to distinguish between specific task knowl...

Patrick Kage, Trevor Hedges, N. Siddharth, Pavlos Andreadis 6/5/2026 arxiv

Scientific observations generate large quantities of unlabeled data which is laborious to hand-label, making unsupervised learning techniques valuable for processing datasets. Among these approaches, contrastive learning provides a convenient mechanism for extracting structural representations from ...