EGGS: Exchangeable 2D/3D Gaussian Splatting for Geometry-Appearance Balanced Novel View Synthesis
arXiv:2512.02932v1 Announce Type: cross Abstract: Novel view synthesis (NVS) is crucial in computer vision and graphics, with wide applications in…
Benchmarking Scientific Understanding and Reasoning for Video Generation using VideoScience-Bench
arXiv:2512.02942v1 Announce Type: cross Abstract: The next frontier for video generation lies in developing models capable of zero-shot reasoning, where…
Forecasting in Offline Reinforcement Learning for Non-stationary Environments
arXiv:2512.01987v2 Announce Type: replace-cross Abstract: Offline Reinforcement Learning (RL) provides a promising avenue for training policies from pre-collected datasets when…
The 4/$delta$ Bound: Designing Predictable LLM-Verifier Systems for Formal Method Guarantee
arXiv:2512.02080v1 Announce Type: new Abstract: The idea of using Formal Verification tools with large language models (LLMs) has enabled scaling…
Aligning Artificial Superintelligence via a Multi-Box Protocol
arXiv:2511.21779v1 Announce Type: new Abstract: We propose a novel protocol for aligning artificial superintelligence (ASI) based on mutual verification among…
Scale-Agnostic Kolmogorov-Arnold Geometry in Neural Networks
arXiv:2511.21626v2 Announce Type: replace-cross Abstract: Recent work by Freedman and Mulligan demonstrated that shallow multilayer perceptrons spontaneously develop Kolmogorov-Arnold geometric…
Serving Heterogeneous LoRA Adapters in Distributed LLM Inference Systems
arXiv:2511.22880v1 Announce Type: cross Abstract: Low-Rank Adaptation (LoRA) has become the de facto method for parameter-efficient fine-tuning of large language…
Adversarial Training for Process Reward Models
arXiv:2511.22888v1 Announce Type: cross Abstract: Process Reward Models (PRMs) enhance reasoning ability of LLMs by providing step-level supervision. However, their…
G$^2$VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning
arXiv:2511.21688v2 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) still lack robustness in spatial intelligence, demonstrating poor performance on spatial understanding…