Paper Archive

Takuya Nakabayashi, Navami Kairanda, Hideo Saito, Vladislav Golyanik 10/13/2025 arxiv

Event cameras offer various advantages for novel view rendering compared to synchronously operating RGB cameras, and efficient event-based techniques supporting rigid scenes have been recently demonstrated in the literature. In the case of non-rigid objects, however, existing approaches additionally...

Chengqi Duan, Kaiyue Sun, Rongyao Fang, Manyuan Zhang, Yan Feng, Ying Luo, Yufang Liu, Ke Wang, Peng Pei, Xunliang Cai, Hongsheng Li, Yi Ma, Xihui Liu 10/13/2025 arxiv

Recent advances in Large Language Models (LLMs) and Vision Language Models (VLMs) have shown significant progress in mathematical reasoning, yet they still face a critical bottleneck with problems requiring visual assistance, such as drawing auxiliary lines or plotting functions to solve the problem...

Tsung-Han Wu, Mihran Miroyan, David M. Chan, Trevor Darrell, Narges Norouzi, Joseph E. Gonzalez 10/13/2025 arxiv

Large Reasoning Models (LRMs) excel at complex reasoning but are traditionally evaluated in static, "frozen world" settings: model responses are assumed to be instantaneous, and the context of a request is presumed to be immutable over the duration of the response. While generally true for short-ter...

Edward Stevinson, Lucas Prieto, Melih Barsbey, Tolga Birdal 10/13/2025 arxiv

Fundamental questions remain about when and why adversarial examples arise in neural networks, with competing views characterising them either as artifacts of the irregularities in the decision landscape or as products of sensitivity to non-robust input features. In this paper, we instead argue that...

Zhaochen Yu, Ling Yang, Jiaru Zou, Shuicheng Yan, Mengdi Wang 10/13/2025 arxiv

Recently, the emergence of agentic RL has showcased that RL could also effectively improve the agentic reasoning ability of LLMs, yet the key design principles and optimal practices remain unclear. In this work, we conduct a comprehensive and systematic investigation to demystify reinforcement learn...

Wei Huang, Yi Ge, Shuai Yang, Yicheng Xiao, Huizi Mao, Yujun Lin, Hanrong Ye, Sifei Liu, Ka Chun Cheung, Hongxu Yin, Yao Lu, Xiaojuan Qi, Song Han, Yukang Chen 10/13/2025 arxiv

We propose QeRL, a Quantization-enhanced Reinforcement Learning framework for large language models (LLMs). While RL is essential for LLMs' reasoning capabilities, it is resource-intensive, requiring substantial GPU memory and long rollout durations. QeRL addresses these issues by combining NVFP4 qu...

Lingfei Qian, Xueqing Peng, Yan Wang, Vincent Jim Zhang, Huan He, Hanley Smith, Yi Han, Yueru He, Haohang Li, Yupeng Cao, Yangyang Yu, Alejandro Lopez-Lira, Peng Lu, Jian-Yun Nie, Guojun Xiong, Jimin Huang, Sophia Ananiadou 10/13/2025 arxiv

Although Large Language Model (LLM)-based agents are increasingly used in financial trading, it remains unclear whether they can reason and adapt in live markets, as most studies test models instead of agents, cover limited periods and assets, and rely on unverified data. To address these gaps, we i...

Arjun Sahney, Ram Gorthi, Cezary Łastowski, Javier Vega 10/13/2025 arxiv

We present Operand Quant, a single-agent, IDE-based architecture for autonomous machine learning engineering (MLE). Operand Quant departs from conventional multi-agent orchestration frameworks by consolidating all MLE lifecycle stages -- exploration, modeling, experimentation, and deployment -- with...

Chenghao Xiao, Hou Pong Chan, Hao Zhang, Weiwen Xu, Mahani Aljunied, Yu Rong 10/13/2025 arxiv

Recent multimodal embedding approaches leveraging multimodal large language models (MLLMs) fine-tuned with contrastive learning (CL) have shown promising results, yet the underlying reasons behind their superiority remain underexplored. This work argues that a crucial advantage of MLLM-based approac...

Taira Tsuchiya 10/13/2025 arxiv

In two-player zero-sum games, the learning dynamic based on optimistic Hedge achieves one of the best-known regret upper bounds among strongly-uncoupled learning dynamics. With an appropriately chosen learning rate, the social and individual regrets can be bounded by $O(\log(mn))$ in terms of the nu...