1 citations · 1 across the 7 of their papers we have counts for
8 papers
Handoff Curves: Initial Selection, Later Handoff, and Supervision Targets in Multi-turn LLM Routing
Daniel Matos, Lu Liu, Yanfeng Zhang
We study how initial model selection, later handoff, and training targets affect success and cost in LLM tasks that span multiple turns. We compare several router architectures usi…
VideoReloc: Long-Term Indoor Video Relocalization against a Kilobyte-Scale Semantic Scene Graph
Qianru Li, Xuyang Chen, Xuqin Wang +6
Given a compact semantic scene graph, long-term indoor video relocalization estimates a map-frame trajectory after lighting and furniture changes. Visual methods rely on appearance…
CinemaTraj: Composing Atomic Camera Trajectories for 3D Scenes with LLM Agents
Qianru Li, Xuyang Chen, Erkin Türköz +5
Automatically generating cinematically expressive camera trajectories through 3D scenes from natural language descriptions is a challenging task of high practical value, with appli…
GeodesicNVS: Probability Density Geodesic Flow Matching for Novel View Synthesis
Xuqin Wang, Tao Wu, Yanfeng Zhang +5
Recent advances in generative modeling have substantially enhanced novel view synthesis, yet maintaining consistency across viewpoints remains challenging. Diffusion-based models r…
HierLoc: Hyperbolic Entity Embeddings for Hierarchical Visual Geolocation
Hari Krishna Gadi, Daniel Matos, Hongyi Luo +4
Visual geolocalization, the task of predicting where an image was taken, remains challenging due to global scale, visual ambiguity, and the inherently hierarchical structure of geo…
TurnBack: A Geospatial Route Cognition Benchmark for Large Language Models through Reverse Route
Hongyi Luo, Qing Cheng, Daniel Matos +7
Humans can interpret geospatial information through natural language, while the geospatial cognition capabilities of Large Language Models (LLMs) remain underexplored. Prior resear…
LADB: Latent Aligned Diffusion Bridges for Semi-Supervised Domain Translation
Xuqin Wang, Tao Wu, Yanfeng Zhang +6
Diffusion models excel at generating high-quality outputs but face challenges in data-scarce domains, where exhaustive retraining or costly paired data are often required. To addre…
MeSS: City Mesh-Guided Outdoor Scene Generation with Cross-View Consistent Diffusion
Xuyang Chen, Zhijun Zhai, Kaixuan Zhou +11
Mesh models have become increasingly accessible for numerous cities; however, the lack of realistic textures restricts their application in virtual urban navigation and autonomous…