Submitted by xiao45791 22 Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL HKUSTGZ 12 1
Submitted by QiYao-Wang 3 PatRe: A Full-Stage Office Action and Rebuttal Generation Benchmark for Patent Examination IP Intelligence 2 1
Submitted by taesiri 2 SymptomAI: Towards a Conversational AI Agent for Everyday Symptom Assessment · 33 authors
Submitted by xxzcc 2 Reinforcement Learning for LLM-based Multi-Agent Systems through Orchestration Traces · 1 authors 1 1
Submitted by Xrvitd 2 SVGS: Enhancing Gaussian Splatting Using Primitives with Spatially Varying Colors University of Hong Kong 58 1
Submitted by taesiri 1 A Benchmark for Interactive World Models with a Unified Action Generation Framework · 11 authors 1
Submitted by taesiri 1 OpenSeeker-v2: Pushing the Limits of Search Agents with Informative and High-Difficulty Trajectories · 7 authors 622
Submitted by LiXinran1 1 TCDA: Thread-Constrained Discourse-Aware Modeling for Conversational Sentiment Quadruple Analysis · 5 authors 1 1
Submitted by Zli002 1 SplAttN: Bridging 2D and 3D with Gaussian Soft Splatting and Attention for Point Cloud Completion Southwest Jiaotong University 2 1
Submitted by robtacconelli 1 StateSMix: Online Lossless Compression via Mamba State Space Models and Sparse N-gram Context Mixing · 1 authors 1 1
Submitted by taesiri - Workspace-Bench 1.0: Benchmarking AI Agents on Workspace Tasks with Large-Scale File Dependencies · 20 authors
Submitted by PeiyangLiu - Chain of Evidence: Pixel-Level Visual Attribution for Iterative Retrieval-Augmented Generation · 5 authors 0 1
xiao45791 
