MIMESIS: Learning User Simulators as Training Environments for Interactive Agents Paper • 2610.09484 • Published 14 days ago • 30
IAM: Identity-Aware Human Motion and Shape Joint Generation Paper • 2604.25164 • Published Apr 28 • 2
UMO: Unified In-Context Learning Unlocks Motion Foundation Model Priors Paper • 2603.15975 • Published Mar 16 • 3
LLaMo: Scaling Pretrained Language Models for Unified Motion Understanding and Generation with Continuous Autoregressive Tokens Paper • 2602.12370 • Published Feb 12
Memory-efficient Streaming VideoLLMs for Real-time Procedural Video Understanding Paper • 2504.13915 • Published Apr 10, 2025
Two-Level Meta-Rubrics for Evaluating Open-Ended Generation: GAMUT, a Benchmark for Factual Completeness Paper • 2607.19322 • Published Jul 21 • 11
Knowledge Extraction on Semi-Structured Content: Does It Remain Relevant for Question Answering in the Era of LLMs? Paper • 2509.25107 • Published Sep 29, 2025
SCRIBES: Web-Scale Script-Based Semi-Structured Data Extraction with Reinforcement Learning Paper • 2510.01832 • Published Oct 2, 2025
FACTORY: A Challenging Human-Verified Prompt Set for Long-Form Factuality Paper • 2508.00109 • Published Jul 31, 2025 • 4
Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning Paper • 2403.11401 • Published Mar 18, 2024
Post-training an LLM for RAG? Train on Self-Generated Demonstrations Paper • 2502.10596 • Published Feb 14, 2025
Two-Level Meta-Rubrics for Evaluating Open-Ended Generation: GAMUT, a Benchmark for Factual Completeness Paper • 2607.19322 • Published Jul 21 • 11
InvisMark: Invisible and Robust Watermarking for AI-generated Image Provenance Paper • 2411.07795 • Published Nov 19, 2024