Papers
SpiderFlow: Efficient Topology-Aware Scheduling for LLM Training Across Decentralized GPU Clusters
Zihan Chang, Shuibing He, Bo Zhou et al.
Toward Consistent World Models with Multi-Token Prediction and Latent Semantic Enhancement
Qimin Zhong, Hao Liao, Haiming Qin et al.
Learning While Staying Curious: Entropy-Preserving Supervised Fine-Tuning via Adaptive Self-Distillation for Large Reasoning Models
Hao Wang, Hao Gu, Hongming Piao et al.
From Charts to Code: A Hierarchical Benchmark for Multimodal Models
Jiahao Tang, Henry Hengyuan Zhao, Lijian Wu et al.
FinChart-Bench: Benchmarking Financial Chart Comprehension in Vision-Language Models
Dong Shu, Haoyang Yuan, Yuchen Wang et al.
Inside Out: Evolving User-Centric Core Memory Trees for Long-Term Personalized Dialogue Systems
Jihao Zhao, Ding Chen, Zhaoxin Fan et al.
Android Coach: Improve Online Agentic Training Efficiency with Single State Multiple Actions
Guo Gan, Yuxuan Ding, Cong Chen et al.
Reinforced Informativeness Optimization for Long-Form Retrieval-Augmented Generation
Yuhao Wang, Ruiyang Ren, Yucheng Wang et al.
ALDEN: Reinforcement Learning for Active Navigation and Evidence Gathering in Long Documents
Tianyu Yang, Terry Ruas, Yijun Tian et al.
FinCall-Surprise: A Large Scale Multi-modal Benchmark for Earning Surprise Prediction
Dong Shu, Yanguang Liu, Huopu Zhang et al.
Beyond Single-shot Writing: Deep Research Agents are Unreliable at Multi-turn Report Revision
Bingsen Chen, Boyan Li, Ping Nie et al.
Answering the Wrong Question: Reasoning Trace Inversion for Abstention in LLMs
Abinitha Gourabathina, Inkit Padhi, Manish Nagireddy et al.
CODESTRUCT: Code Agents over Structured Action Spaces
Myeongsoo Kim, Chao-Chun Hsu, Dingmin Wang et al.
IUQ: Interrogative Uncertainty Quantification for Long-Form Large Language Model Generation
Haozhi Fan, Jinhao Duan, Kaidi Xu
DORA: A Dual-Objective Reinforcement Learning Framework for Effective and Efficient Multimodal Agentic Search
Guangming Qin, Yuhao Deng, Yukun Zhao et al.
CrochetBench: Can Vision-Language Models Move from Describing to Doing in Crochet Domain?
Peiyu Li, Xiaobao Huang, Ting Hua et al.
Scaling Law for Multimodal Large Language Model Supervised Fine-Tuning
YiFan Zhang, Tao Yu, Feng Li et al.
RoboFailRing: Retrieval-Augmented and Language Grounding Failure Detection for VLM-enabled Robotic Manipulation
Chenduo Ying, Linkang Du, Yuanchao Shu et al.
Vista-LLM: Decoupled Query-Guided Visual Token Pruning for Efficient Long-Video Large Language Models
Zhenyu Li, Zuchao Li, Ping Wang et al.
GLARE: Agentic Reasoning for Legal Judgment Prediction
Xinyu Yang, Chenlong Deng, Zhicheng Dou
Arguments that Alter Minds: LLM Rationales Sway Human (and LLM) Notions of Plausibility
Shramay Palta, Peter A. Rankel, Sarah Wiegreffe et al.
Stereotype Bias in a Bilingual Setting: A Culturally Grounded Evaluation in Kazakhstan
Nurkhan Laiyk, Daniil Orel, Ayana Mussabayeva et al.
A Goal Without a Plan Is Just a Wish: Efficient and Effective Global Planner Training for Long-Horizon Agent Task
Shuzheng Si, Haozhe Zhao, Kangyang Luo et al.
Bridging Distance and Spectral Positional Encodings via Anchor-Based Diffusion Geometry Approximation
Yan Zimo, Zheng Xie, Runfan Duan et al.
Breaking Down and Building Up: Mixture of Skill-Based Vision-and-Language Navigation Agents
Tianyi Ma, Yue Zhang, Zehao Wang et al.