Academic

Academic · 1 min

EpiBench: Benchmarking Multi-turn Research Workflows for Multimodal Agents

arXiv:2604.05557v1 Announce Type: new Abstract: Scientific research follows multi-turn, multi-step workflows that require proactively searching the literature, consulting figures and tables, and integrating evidence across …

Xuan Dong, Huanyang Zheng, Tianhao Niu, Zhe Han, Pengzhan Li, Bofei Liu, Zhengyang Liu, Guancheng Li, Qingfu Zhu, Wanxiang Che

32 views Apr 8

Academic · 1 min

Context-Agent: Dynamic Discourse Trees for Non-Linear Dialogue

arXiv:2604.05552v1 Announce Type: new Abstract: Large Language Models demonstrate outstanding performance in many language tasks but still face fundamental challenges in managing the non-linear flow …

Junan Hu, Shudan Guo, Wenqi Liu, Jianhua Yin, Yinwei Wei

8 views Apr 8

Academic · 1 min

FastDiSS: Few-step Match Many-step Diffusion Language Model on Sequence-to-Sequence Generation--Full Version

arXiv:2604.05551v1 Announce Type: new Abstract: Self-conditioning has been central to the success of continuous diffusion language models, as it allows models to correct previous errors. …

Dat Nguyen-Cong, Tung Kieu, Hoang Thanh-Tung

45 views Apr 8

Academic · 1 min

AutoSOTA: An End-to-End Automated Research System for State-of-the-Art AI Model Discovery

arXiv:2604.05550v1 Announce Type: new Abstract: Artificial intelligence research increasingly depends on prolonged cycles of reproduction, debugging, and iterative refinement to achieve State-Of-The-Art (SOTA) performance, creating …

Yu Li, Chenyang Shao, Xinyang Liu, Ruotong Zhao, Peijie Liu, Hongyuan Su, Zhibin Chen, Qinglong Yang, Anjie Xu, Yi Fang, Qingbin Zeng, Tianxing Li, Jingbo Xu, Fengli Xu, Yong Li, Tie-Yan Liu

16 views Apr 8

Academic · 1 min

Stop Fixating on Prompts: Reasoning Hijacking and Constraint Tightening for Red-Teaming LLM Agents

arXiv:2604.05549v1 Announce Type: new Abstract: With the widespread application of LLM-based agents across various domains, their complexity has introduced new security threats. Existing red-team methods …

Yanxu Mao, Peipei Liu, Tiehan Cui, Congying Liu, Mingzhe Xing, Datao You

5 views Apr 8

Academic · 1 min

Efficient Inference for Large Vision-Language Models: Bottlenecks, Techniques, and Prospects

arXiv:2604.05546v1 Announce Type: new Abstract: Large Vision-Language Models (LVLMs) enable sophisticated reasoning over images and videos, yet their inference is hindered by a systemic efficiency …

Jun Zhang, Yicheng Ji, Feiyang Ren, Yihang Li, Bowen Zeng, Zonghao Chen, Ke Chen, Lidan Shou, Gang Chen, Huan Li

7 views Apr 8

Academic · 1 min

Learning to Edit Knowledge via Instruction-based Chain-of-Thought Prompting

arXiv:2604.05540v1 Announce Type: new Abstract: Large language models (LLMs) can effectively handle outdated information through knowledge editing. However, current approaches face two key limitations: (I) …

Jinhu Fu, Yan Bai, Longzhu He, Yihang Lou, Yanxiao Zhao, Li Sun, Sen Su

16 views Apr 8

Academic · 1 min

Turbulence-like 5/3 spectral scaling in contextual representations of language as a complex system

arXiv:2604.05536v1 Announce Type: new Abstract: Natural language is a complex system that exhibits robust statistical regularities. Here, we represent text as a trajectory in a …

Zhongxin Yang, Chun Bao, Yuanwei Bin, Xiang I. A. Yang, Shiyi Chen

5 views Apr 8

Academic · 1 min

Cross-Modal Coreference Alignment: Enabling Reliable Information Transfer in Omni-LLMs

arXiv:2604.05522v1 Announce Type: new Abstract: Omni Large Language Models (Omni-LLMs) have demonstrated impressive capabilities in holistic multi-modal perception, yet they consistently falter in complex scenarios …

Hongcheng Liu, Yuhao Wang, Zhe Chen, Pingjie Wang, Zhiyuan Zhu, Yixuan Hou, Yanfeng Wang, Yu Wang

8 views Apr 8

Academic · 1 min

Don't Act Blindly: Robust GUI Automation via Action-Effect Verification and Self-Correction

arXiv:2604.05477v1 Announce Type: new Abstract: Autonomous GUI agents based on vision-language models (VLMs) often assume deterministic environment responses, generating actions without verifying whether previous operations …

Yuzhe Zhang, Xianwei Xue, Xingyong Wu, Mengke Chen, Chen Liu, Xinran He, Run Shao, Feiran Liu, Huanmin Xu, Qiutong Pan, Haiwei Wang

5 views Apr 8

Academic · 1 min

Content Fuzzing for Escaping Information Cocoons on Digital Social Media

arXiv:2604.05461v1 Announce Type: new Abstract: Information cocoons on social media limit users' exposure to posts with diverse viewpoints. Modern platforms use stance detection as an …

Yifeng He, Ziye Tang, Hao Chen

16 views Apr 8

Academic · 1 min

Learning What Matters: Dynamic Dimension Selection and Aggregation for Interpretable Vision-Language Reward Modeling

arXiv:2604.05445v1 Announce Type: new Abstract: Vision-language reward modeling faces a dilemma: generative approaches are interpretable but slow, while discriminative ones are efficient but act as …

Qiyuan Chen, Hongsen Huang, Jiahe Chen, Qian Shao, Jintai Chen, Hongxia Xu, Renjie Hua, Chuan Ren, Jian Wu

10 views Apr 8

EpiBench: Benchmarking Multi-turn Research Workflows for Multimodal Agents

Context-Agent: Dynamic Discourse Trees for Non-Linear Dialogue

FastDiSS: Few-step Match Many-step Diffusion Language Model on Sequence-to-Sequence Generation--Full Version

AutoSOTA: An End-to-End Automated Research System for State-of-the-Art AI Model Discovery

Stop Fixating on Prompts: Reasoning Hijacking and Constraint Tightening for Red-Teaming LLM Agents

Efficient Inference for Large Vision-Language Models: Bottlenecks, Techniques, and Prospects

Learning to Edit Knowledge via Instruction-based Chain-of-Thought Prompting

Turbulence-like 5/3 spectral scaling in contextual representations of language as a complex system

Cross-Modal Coreference Alignment: Enabling Reliable Information Transfer in Omni-LLMs

Don't Act Blindly: Robust GUI Automation via Action-Effect Verification and Self-Correction

Content Fuzzing for Escaping Information Cocoons on Digital Social Media

Learning What Matters: Dynamic Dimension Selection and Aggregation for Interpretable Vision-Language Reward Modeling

JCG, PC

HSOLLC Co., Ltd.