Thinking with Map Collection Thinking with Map: Reinforced Parallel Map-Augmented Agent for Geolocalization • 4 items • Updated 1 day ago • 1
DynamicVLA: A Vision-Language-Action Model for Dynamic Object Manipulation Paper • 2601.22153 • Published 12 days ago • 68
Scaling Embeddings Outperforms Scaling Experts in Language Models Paper • 2601.21204 • Published 12 days ago • 98
Everything in Its Place: Benchmarking Spatial Intelligence of Text-to-Image Models Paper • 2601.20354 • Published 13 days ago • 110
Harder Is Better: Boosting Mathematical Reasoning via Difficulty-Aware GRPO and Multi-Aspect Question Reformulation Paper • 2601.20614 • Published 13 days ago • 117
ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Ranking Paper • 2601.06487 • Published Jan 10 • 52
Urban Socio-Semantic Segmentation with Vision-Language Reasoning Paper • 2601.10477 • Published 26 days ago • 155
GeoVista: Web-Augmented Agentic Visual Reasoning for Geolocalization Paper • 2511.15705 • Published Nov 19, 2025 • 97
Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking Paper • 2601.04720 • Published Jan 8 • 55
AgentOCR: Reimagining Agent History via Optical Self-Compression Paper • 2601.04786 • Published Jan 8 • 29
Thinking with Map: Reinforced Parallel Map-Augmented Agent for Geolocalization Paper • 2601.05432 • Published Jan 8 • 166
Taming Hallucinations: Boosting MLLMs' Video Understanding via Counterfactual Video Generation Paper • 2512.24271 • Published Dec 30, 2025 • 63
On GRPO Collapse in Search-R1: The Lazy Likelihood-Displacement Death Spiral Paper • 2512.04220 • Published Dec 3, 2025 • 15