Submitted by AnitaLeung 70 The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning · 12 authors 1
Submitted by libr6 27 Embodied.cpp: A Portable Inference Runtime of Embodied AI Models on Heterogeneous Robots PhysicalAI System Group @ SAIL Lab, Southeast University 45 1
Submitted by zwq2018 22 VLA-Corrector: Lightweight Detect-and-Correct Inference for Adaptive Action Horizon ZJU-OmniAI 18 2
Submitted by saurabhcantina 12 OrbitQuant: Data-Agnostic Quantization for Image and Video Diffusion Transformers Cantina, Inc. 1
Submitted by selimkuzucu 8 DataComp-VLM: Improved Open Datasets for Vision-Language Models · 36 authors 23 1
Submitted by Zonghao2025 6 Securing the AI Agent: A Unified Framework for Multi-Layer Agent Red Teaming Tencent 1
Submitted by wzy6055 4 Interpretation-Oriented Cloud Removal via Observation-Anchored Residual Flow with Geo-Contextual Alignment Chinese University of Hong Kong, Shenzhen 0 1
Submitted by Franck-Dernoncourt 4 MultAttnAttrib: Training-Free Multimodal Attribution in Long Document Question Answering · 10 authors 1
Submitted by baolongnguyenhuu 3 AGE: Adaptive-masking for Graph Embedding in Graph Retrieval-Augmented Generation OMRON SINIC X Corp. 3
AnitaLeung 
