Gu

Infinitegu

11

AI & ML interests

NLP; LLM

Organizations

None yet

upvoted 5 papers 3 months ago

Beyond Borrowed Histories: Person-Aligned User Simulation for Interactive Role-Playing Evaluation

Paper • 2607.27816 • Published Jul 30 • 35

BM25 Wins at Scale: A Scaling Study of Retrieval-Augmented Generation Paradigms

Paper • 2607.26497 • Published Jul 30 • 53

MPIE-Bench: Benchmarking Anatomically Plausible Multi-Person Interaction Editing

Paper • 2607.27616 • Published Jul 30 • 40

AlayaWorld: Interactive Long-Horizon World Modeling -- Full Technical Report

Paper • 2607.18367 • Published Jul 20 • 64

AlayaWorld: Long-Horizon and Playable Video World Generation

Paper • 2607.06291 • Published Jul 7 • 89

upvoted 2 papers 5 months ago

Stream-T1: Test-Time Scaling for Streaming Video Generation

Paper • 2605.04461 • Published May 6 • 108

Stream-R1: Reliability-Perplexity Aware Reward Distillation for Streaming Video Generation

Paper • 2605.03849 • Published May 5 • 129

upvoted 3 papers 9 months ago

WildGraphBench: Benchmarking GraphRAG with Wild-Source Corpora

Paper • 2602.02053 • Published Feb 2 • 41

Wiki Live Challenge: Challenging Deep Research Agents with Expert-Level Wikipedia Articles

Paper • 2602.01590 • Published Feb 2 • 33

FS-Researcher: Test-Time Scaling for Long-Horizon Research Tasks with File-System-Based Agents

Paper • 2602.01566 • Published Feb 2 • 52

upvoted a paper over 1 year ago

Test-Time Scaling with Reflective Generative Model

Paper • 2507.01951 • Published Jul 2, 2025 • 108